Keywords: Electric vehicles and intelligent transportation., Scene analysis, Human-computer interaction
Abstract: Autonomous vehicles have become one of the key solutions to overcome adverse traffic conditions. This upcoming technology is aimed to decrease traffic congestion and road accidents in developing countries, such as Malaysia. Recently, Ministry of Transport in Malaysia has launched Guideline for Public Road Trials of Autonomous Vehicles as a guideline for organizations to conduct physical testing of autonomous vehicles on designated public roads. This guideline will encourage automotive industries to focus more on development and deployment of autonomous vehicles in Malaysia. However, there are several challenges that need to be focused once emphasizing on the scenario-based testing of autonomous vehicle in Malaysian road and traffic environment. Therefore, a safety assessment in virtual platform for autonomous vehicle is required as part of the homologation process to further enhance the deployment of autonomous vehicle in developing countries, such as Malaysia. The purpose of this platform is to design a scenario-based assessment in virtual environment based on Malaysian road and traffic conditions. The platform can be used as the first layer of testing procedure for autonomous vehicle using various type of scenarios and testing standard before focusing on physical testing. The platform will be used to develop scenario-based simulation testing to evaluate the performance of the autonomous vehicles to adapt with Malaysian roads and traffic environments to minimize possible road accidents.

Keywords: Electric vehicles and intelligent transportation., Internet of things, Intelligent automation
Abstract: Smart mobility is a rising technology to provide a safe and efficient transportation system. Connected autonomous vehicles (AVs) are getting tremendous attention while considered smart mobility due to their emerging nature. However, new hybrid and compact technologies are necessary to provide multiple services in less space and low cost and significantly improve the safety of the vehicles. The joint sensing and communication (SensCom) platform is a potential solution for integrated sensing and communication activity for connected AVs. In this paper, we developed a SensCom hardware platform to enable sensing and communication together. We have demonstrated through a working model that the mutual interference of sensing and communication signals can be easily mitigated, and thus both the functionalities can be achieved using the same hardware.

Keywords: Electric vehicles and intelligent transportation., Intelligent automation, Learning and Statistical methods
Abstract: Recently, autonomous vehicles (AVs) have received a lot of attention from the automotive industry as well as the AV research community across the globe. To increase the safety of the flow of traffic, they are anticipated to help or perhaps take the place of human drivers when it comes to vehicle manoeuvring at various levels of autonomy. But before they can be widely used, AVs must first be developed to overcome their inherent security and road safety issues. The adoption of autonomous vehicles depends on the results of the driving test and their safety validation on the roads. This paper examines the associated autonomous vehicle testing and validation methodologies such as autonomous vehicle functional testing, integrated vehicle testing, and system verification across many architectures. In addition, the paper presents some of the state-of-the-art machine learning algorithms used for AV operation on roads. Knowledge of such recent trends in the validation and verification techniques for road safety will be helpful for the development of autonomous vehicles.

Keywords: Man-machine interactions, Human centered systems, Robot control
Abstract: Research on the shared control system for human-in-the-loop cooperative driving has grown steadily in the past decade. However, most proposed methodologies were focused on structural roads such as highway rather than the unstructured environment. This paper presents a novel potential hazard-aware shared steering approach for human-robot cooperative driving in unstructured environment. First, we propose a hierarchical Gaussian risk field (HGRF) to evaluate the potential hazard of the predicted path. Then an adaptive control authority allocation module is developed to engage the control in real-time. The control authority will be fully owned by the human driver when the vehicle drives in a safe manner. However, in the situation where the hazard level is predicted to be high, the authority of the human driver decrease, and the automation actively assists the driver by dynamically sharing the control authority to enhance safety and performance. The proposed methodology is experimentally verified with a steer-by-wire car-like mobile robot. The results show that our proposed approach can effectively engage and cooperatively control the vehicle in hazard cases, ensuring driving safety.

Keywords: Electric vehicles and intelligent transportation., Intelligent systems, Intelligent automation
Abstract: This paper presents a multi-objective strategy for trajectory tracking of intelligent electric vehicles incorporating tracking performance with the energy economy. A model predictive controller is built using the single-track vehicle dynamics model to predict planar motions. The optimization problem is formulated with a cost function involving tracking errors and motor efficiency. The proposed system is verified on a typical road in the co-simulation platform - CarSim/Simulink. Experimental results from the simulation demonstrate the expected performance of the developed system.

Keywords: Electric vehicles and intelligent transportation.
Abstract: The worldwide development of Autonomous Vehicles (AVs) has also encouraged the use of software simulators for virtual testing of AVs. However, the effectiveness of the AV simulators is constrained by numerous challenges, such as their computational cost and lack of fidelity in specific areas. In this paper, we describe the modality of virtual testing and its benefits for AV development and validation. Moreover, we summarize and provide an overview of the state-of-the-art AV simulators, their limitations, and the current directions toward improvement.

Keywords: Image/video analysis, Object recognition, Tracking and surveillance
Abstract: Group re-identification (GReID) is an important yet less-studied task. GReID focuses on associating the group images across non-overlapping cameras. The key challenges of GReID include layout variation, membership changes, and occlusion. Most existing methods focus on group variation but ignore the occlusion that frequently occurs in the group. To this end, we design a novel Transformer-based Siamese Network for GReID (TSN-GReID) for joint learning of classification and correspondence tasks to learn more robust group features for group layout and membership changes. Furthermore, we put forward an original regrouping random patch module(RRPM) which respectively regroups the member patch embedding and member-level local features to generate group features with improved discrimination ability and more diversified coverage to deal with occlusion. Experimental results demonstrate the effectiveness of our approach, which significantly outperforms state-of-the-art methods by 4.6 % Rank-1 on the CUHK-SYSU group (CSG) dataset and by 7.1% Rank-1 on the DukeMTMC group dataset.

Keywords: Image/video analysis, Scene analysis, Object recognition
Abstract: Semi-supervised semantic segmentation aims to maximize the training performance for a limited annotation cost. Existing methods such as cross pseudo supervision have shown excellent performance, yet ignore potential information interactions between labeled and unlabeled data, and suffer from misleading incorrect pseudo labels. This paper takes two ways to improve each of these shortcomings. Firstly, we perform feature-level mixing and cross-decoupling using labeled and unlabeled data to establish potential interactions between the two types of data. Secondly, an uncertainty-aware loss re-weighting method based on information entropy is used to mitigate the negative effects of incorrect pseudo labels. Experimentally, our method further improves the previous cross pseudo supervision method with competitive performance on PASCAL VOC 2012 dataset under various data partition protocols.

Keywords: Vision for robots, Localization, navigation and mapping, Electric vehicles and intelligent transportation.
Abstract: This paper describes a method of environment mapping for autonomous vehicles that takes the advantages of the high-definition dense local map and sparse global map at the same time. The proposed system consists of two estimators, occupancy grid map estimator that is suitable for online local navigation and the new sparse road boundary map estimator for long-term global mapping. The occupancy grid map is estimated with a common Bayesian inference method. On the other hand, the road boundary map estimator is built based on a simple particle filter algorithm which, compared to grid-based map, is memory efficient as it does not require the algorithm to maintain the occupancy state of each point in space. Both estimations are performed by fusing the information from both LiDAR and camera sensors. Our tests in Carla Simulator have shown that the proposed global road boundary mapping system can construct the global map of the test environment well. The particle filter in the proposed algorithm can also reduce the error of road boundary estimation. Moreover, this paper provides the method to fuse the road boundary map into the grid map, which can improve the accuracy of the grid mapping.

Keywords: Vision for robots
Abstract: In order to insert a fork into a hole of a pallet by a forklift located in front of a pallet, it is necessary to control the height position, reach position, and tilt angle of the fork to match the position and orientation of the hole of the pallet. In order to make AGF (Autonomous Guided Forklift) do this automatically, we propose an image measurement method to measure the pitch inclination of the pallet in the camera coordinate system from an image obtained by using a wide-angle camera. In addition, we propose an image measurement method to easily acquire the calibration information between the camera coordinate system and the fork coordinate system necessary to apply the measurements in the camera coordinate system to the fork control. In the experiment space, a wide-angle camera was fixed at the backrest of a reach type forklift. The wide-angle images taken by placing a pallet in front of the camera were processed. As a result of evaluating the error by comparing the image measurement value with the hand measurement value when changing the pitch inclination angle of the pallet, the relative height of the pallet and the fork, and whether the pallet is loaded or not, it was confirmed that the error was within the allowable range for safely inserting the fork.

Keywords: Adaptive control, Identification and estimation, Sensor networks
Abstract: The purpose of this study is to develop an effective computational scheme to solve the optimal tracking control problem for repeated trials in distributed parameter system where quantity under control cannot be observed directly. In such situations, the reliability of model predictions is of crucial importance as the ultimate objective in model-based control becomes the accurate forecast of the system states. Particularly, given a finite number of possible spatial locations at which sensors may reside, we select gaged sites so as to maximize the prediction accuracy. For that purpose, a suitable output criterion is proposed as a measure of the prediction quality, then the sensor selection problem is formulated in terms of optimization task and effectively solved with dedicated algorithm. The optimal measurement schedule is further incorporated into the iterative learning control scheme for effective solution of the underlying tracking control problem for the friction welding process.

Keywords: Discrete event systems, Distributed optimization and MPC
Abstract: In this paper, we introduce a new conservation-based approach to model traffic dynamics, and apply the model predictive control (MPC) approach to manage the boundary traffic inflow and outflow, so that the traffic congestion is reduced. We establish an interface between the Simulation of Urban Mobility (SUMO) software and MATLAB to define a network of interconnected roads (NOIR) as a directed graph, and present traffic congestion management as a network control problem. By formally specifying the traffic feasibility conditions, and using the linear temporal logic, we present the proposed MPC-based boundary control problem as a quadratic programming with linear equality and inequality constraints. The success of the proposed traffic boundary control is demonstrated by simulation of traffic congestion control in Center City Philadelphia.

Keywords: Modeling and identification, Identification and estimation
Abstract: Traditional identification approaches for robotic systems based on the inverse dynamic model and the least squares method are the most used to identify dynamic parameters of robots. However these methods often require a well-tuned filtering or estimation of the position, velocity, acceleration and torque to avoid bias in identification results. The cutoff frequency of the low-pass filter that is usually used must be well chosen, which is not always a trivial task. In this paper, we propose to use an extended Kalman filter to reduce the noise on the measured position and to estimate the velocity and acceleration. These estimates can then be fed to the controller to further reduce the noise in the control torque. The effect of the tuning of this filter is examined and the presented approach is validated through simulations and experiments on a one degree of freedom system.

Keywords: Modeling and identification, Identification and estimation
Abstract: This paper deals with the dynamic parameter identification of the KUKA LBR iiwa R820, a robotic manipulator with flexible joints intended for collaborative applications. The control software interface of this robot provides different signals that allow the parameter identification of not only the real robot, but also of the model integrated in the robot’s controller, in a reverse engineering process. By analyzing the successive positions and torques computed by the controller, an accurate set of inertial parameters referring to the robot’s model integrated in the controller is obtained. A percent error in the torque reconstruction of less than 1% for every joint, validates the process. Then, this set of parameters is useful to complete and compare the set of parameters that is obtained with real physical measurements which is more prone to errors due to noise and uncertainties. Finally, the torque reconstruction using the measured signals is compared with models present in bibliography, showing a better performance.

Keywords: Multi-agent systems, Networked control systems, Neural networks
Abstract: Abstract— In this paper, we consider a discrete private and expressed (synchronous and asynchronous) opinion dynamics model with competitive relationships. Unlike the usual agent-based opinion dynamics models, competition between individuals is investigated in a social media network. The expressed opinions or states of the individuals in the network are represented by asynchronous dynamics where each individual has a choice to express their opinion at each time step. Each agent uses a Q-learning algorithm to decide when to express its opinion with the purpose of swaying the opinions of other connected agents to a desired outcome. The private opinions or states of the individuals are derived from a combination of their own private opinion and the expressed opinions of connected agents. The communication between agents is dictated by an underlying network topology. The dynamics of the social media environment are modeled by private and expressed, both asynchronous and synchronous, opinion dynamics model. The system is investigated for polarization or consensus under different conditions. To illustrate the results simulations of the system dynamics are provided.

Keywords: Data analytics., Object recognition
Abstract: Traditional pattern classification methods can handle the objects whose categories are contained in the given (known) categories of training data. In open-set scenarios, objects to classify may belong to the ignorant (unknown) classes that is not included in training data set. Open-Set Recognition (OSR) tries to detect these unknown class objects and classify known class objects. In this paper, we propose a NEW OSR method based on k-Nearest Neighbors (k-NNs). The test data (objects to classify) is put together with the labeled training data, so that the labeled training instances and the unlabeled objects to classify can appear in the k-NNs of other objects. Then, the probability of object lying in the given classes can be determined according to the k-NNs of this object. If the labeled training data is the majority of k-NNs, this object most likely belongs to one of the given classes, and the distances between the object and its neighbors are taken into account here. Then the objects with high probability are marked with the estimated probability. However, if most of k-NNs are the unlabeled test objects, the class of object cannot be classified in this step because the k-NNs of the object is uncertain. In this paper, the probability of the other uncertain objects belonging to known classes is re-calculated based on the labeled training instances and the objects marked with the estimated probability. Such iteration will not stop until all the probabilities of objects belonging to known classes are not changed. Then, the Otsu's method is employed to obtain the optimal threshold for the final recognition. If the probability of object belonging to known classes is smaller than this threshold, it will be assigned to the unknown class. The other objects will be considered as known classes and then committed to a specific class by a pre-trained classifier. The effectiveness of the proposed method has been validated using some experiments.

Keywords: Object recognition, Image-based modeling, Neural networks
Abstract: In target recognition, the information about the target usually exists in several domains captured by different sources (sensors). However, it is difficult for us to obtain the perfect target information as the source domain data due to the sensors' limitations sometimes. For the target classification of visible and infrared paired images, we assume that some classes of visible and infrared paired images and other classes of visible images can be obtained, whereas other classes of unseen infrared images need to be classified. This problem is actually a zero-shot deep domain adaptation (ZDDA) problem which divides the data into task-relevant (T-R) data and task-irrelevant (T-I) data. Moreover, the classes of T-R data require recognition, while the classes of T-I data do not need. The traditional ZDDA method sacrifices the classification accuracy of T-R data in the target domain for the generalization ability of T-I data in the source domain. So we propose a method to solve the problem in another way. More precisely, we first use the image-to-image translation network to learn the mapping between the source domain (visible images) T-I data and the target domain (infrared images) T-I data, and convert the visible T-R images to pseudo-infrared images. Then the pseudo-infrared images and the inverted grayscale T-R images are combined to construct a new hybrid domain (source domain I). Meanwhile, we also construct a hybrid domain (source domain II) of T-I images similarly. Besides, we use the infrared T-I images to construct the third domain (source domain III). Finally, we design a deep domain generalization method for cross-domain infrared image classification. And the total loss consists of the classification loss of the source domain I and the distribution alignment loss between the source domains II and III. We evaluate our method using VAIS ship and RGB-NIR scene datasets. The experimental results demonstrate the effectiveness of the proposed method.

Keywords: Image/video analysis, Scene analysis
Abstract: We propose a dense mapping algorithm based on surfel with line constraint, called SLD-MAP for room-scale and urban-size environment, which aims to improve reconstruction accuracy and reduce void space on the reconstruction surface. We apply visual odometry to estimate camera poses, and reconstruct the 3D environment according to the input depth image and RGB image. The first step is to optimize the pose with line constraints. The second step is to extract the superpixel and resize the radius and position of the superpixel with line constraints. The third step is to generate surfels and fuse them with local maps. The fourth step is plane fitting of local map. The last step is to update the local map and deform the global map. Finally, the reconstruction accuracy is evaluated on public datasets, compare with the state-of-the-art methods. Index Terms—Image reconstruction, dense mapping, surfel feature, line constraint

Keywords: Image/video analysis, Visual servoing
Abstract: Abstract— Feature matching is an important step for SLAM with high real-time requirements. Currently, most feature matching methods only rely on visual information, even in visual-inertial SLAM. In this paper, we propose an efficient feature matching method for point and line features by fusing IMU information with visual information. The key ideas are utilizing IMU pre-integration to estimate the relative pose change of two consecutive frames and narrow the feature search area to accelerate feature matching. Experiment results show that our method shortens the feature matching time significantly compared with other feature matching methods while ensuring high matching accuracy. Keywords—Visual-Inertial SLAM, Point and line features, Feature Matching, IMU Pre-integration

Keywords: Localization, navigation and mapping, Visual servoing, Image/video analysis
Abstract: — Simultaneous localization and mapping (SLAM) is an attractive and hot research topic in computer vision, robotics, and artificial intelligence. Autonomous vehicles driving in unknown environments try to perceive and map the surrounding environment while recognizing their location and trajectory. In this paper, five state-of-the-art open-source 3D lidar-only SLAM algorithms are reviewed: LOAM, LeGO-LOAM, F-LOAM, BALM, and MULLS. We briefly introduce the characteristics of these algorithms. Finally, the experimental comparison is carried out to compare the absolute pose error (APE), efficiency, and operation memory occupation of each algorithm.

Keywords: Adaptive control, Perception systems
Abstract: We present an efficient two-phase approach to motion planning for fixed-wing Unmanned Aerial Vehicles (UAV) navigating in complex 3D air slalom environments. Firstly, in discrete 3D workspace, a global planner computer a obstacle-free path roughly which satisfies the kinematic constraints of the UAV. Given a coarse global path, a local planner generate a Dubins curve with collision avoidance based on the UAS's perception constraints, dynamic constraints and the collision perception information received. We also introduce a method of decoupling the horizontal and vertical motion directions of the fixed-wing UAV, realizing the 2D Dubins curve planning in 3D workspace, along with precomputed sets of motion primitives derived from the vehicle dynamics model in order to achieve high efficiency. Finally, the feasibility of two-phase 3D motion planning in appropriate FOV is experimentally demonstrated.

Keywords: Smart grid
Abstract: To enhance the resilience of transmission networks with offshore wind farms (OWFs) and pump hydro energy storage systems (PHESSs) towards typhoons, a resilient unit commitment scheme is proposed. This problem is formulated as a two-stage robust optimization problem, where the uncertain impacts of typhoons on OWF output, transmission line failures, and demands are captured by a robust uncertain set with chance constraints. This uncertainty set is embedded into a two-stage robust unit commitment model, where the commitment of thermal units is optimized in the first-stage and PHESSs are scheduled in the second-stage optimization as the emergency resources. The two-stage robust optimization problem is solved using the column and constraint generation (C&CG) algorithm. Simulations are performed on the modified IEEE-RTS test systems with real OWF output during Typhoon Higos, and the effectiveness of proposed scheme is verified regarding the reduction of worst case load shedding.

Keywords: Hybrid systems
Abstract: The development and utilization of renewable energy is an essential development strategy to cope with the energy crisis. Based on the wind power prediction information, wind power can be integrated into the system reserve to balance the operating economy of thermal power units and renewable energy consumption. Thus, the reserve dispatching model on the basis of the two-stage stochastic optimization model is established in this paper to deal with the uncertainty of wind output. Thus, the reserve dispatching model on the basis of the two-stage stochastic optimization model is established in this paper to deal with the uncertainty of wind power. Numerical results on an advanced IEEE 24-bus system demonstrate the effectiveness of the proposed model. The results show that the operating schedule of wind power incorporated into the reserve can alleviate the anti-peaking shaving characteristics and improve wind power utilization.

Keywords: Neural networks, Smart grid
Abstract: Owing to the increasing penetration of offshore wind energy in smart grids, accurate forecasting plays a significant role in energy improvement and economic dispatch. However, owing to the intermittent and uncertain nature of wind power, traditional numerical weather prediction methods can hardly capture the fluctuation caused by wind power. This paper proposes a deep-learning based forecasting algorithm to predict offshore wind power under consideration of various environmental factors. In order to reduce forecasting error, an ensemble strategy is utilized to improve the prediction performance. The developed model has been practically tested on an offshore wind farm in Nantong, China. The forecasting results demonstrate the high accuracy and quality of the proposed method for wind power prediction, which provides an efficient reference to optimal power system operation.

Keywords: Smart grid
Abstract: The fatigue analysis is important in the operation of the wind turbine. However, integrating the fatigue index of each substructure to construct the overall fatigue index of the wind turbine is difficult. Different from the existing research that only uses the weighted summation method to design the overall fatigue index, an index construction method that relates the operating fatigue to the economic loss is proposed. The cumulative damage of the structure is derived by using the damage equivalent load in the fatigue evaluation of each substructure of the wind turbine, and then the maintenance cost of each structure is analyzed in depth, and the maintenance cost function of each substructure is constructed to determine the economic loss equivalent to the cumulative damage of the structure. Since the proposed method converts fatigue damage into economic loss, the economic loss of each structure can be directly added to construct the overall equivalent economic loss index, which avoids the problem of custom weighting of the comprehensive index structure. Finally, simulation experiments verify the scientificity and superiority of the proposed indicator.

Keywords: Energy management systems, Smart grid, Planning, scheduling and coordination
Abstract: This paper presents a novel multi-stage stochastic sequential black-start restoration model for the power transmission system with high penetration of renewable energy sources (RESs) after large-scale blackouts. Considering the uncertainties of RESs and the sequential restoration of the network, a two-stage generator model is designed to collaboratively dispatch the black-start units, RESs, and other thermal units during the restoration process. Finally, a modified New England 10-unit-39-bus test power system is employed to verify the effectiveness of the proposed model. Case studies indicate that the proposed model can coordinate the restoration of thermal units, RESs, and power loads. And RESs can effectively support the load restoration during the black-start process.

Keywords: Discrete event systems, Process control, Networked control systems
Abstract: This paper proposes a deadlock recovery method for flexible manufacturing systems modeled with Petri nets. Recovery transitions are added to the net allowing to return from all the deadlock markings to the legal ones. Unlike similar methods based on recovery transitions, the proposed recovery policy focuses on process instances of the system. Its aim is to reset the lowest number of them, with minimal executed number of steps in a process instance. The proposed approach is formally analysed regarding the correctness and complexity, as well as illustrated with some widely used examples and compared with the similar known methods. The comparison shows that the presented method is efficient, despite the slightly different optimization criteria than in other similar methods.

Keywords: Control applications, Network-based systems
Abstract: Efficient transfer of time-sensitive data plays an essential role in entertainment, personal and business communication, and in industry, especially in the systems of monitoring and robotic automation. In those application areas high network throughput together with short latency, and resiliency from network problems are expected. One of the most promising methods of answering those challenges is to simultaneously engage multiple paths of communication. Currently, only two protocols provide such a possibility in public networks – the multipath version of TCP (MPTCP) and the multipath version of QUIC (MPQUIC). Both protocols split data units over available paths via a component named scheduler. The default scheduler favors throughput over protocol delay, which is unsuitable in industrial applications. In the paper, a balanced solution – a synchronizing scheduler – that reduces the protocol delay is proposed. Its properties are analyzed formally and tested experimentally in the framework of both MPTCP and MPQUIC in the open Internet.

Keywords: Process control, Delay systems, Networked control systems
Abstract: In order to improve supply system robustness, or gain cost advantage, multiple delivery modes may be used. In this work, the (r, Q) inventory policy is formally investigated as a tool to control the resupply process of a remote depot that answers uncertain market demand. In the considered scenario, the goods are relocated using multiple channels with diverse properties concerning transportation delay, lot size, and quality, e.g., trucks, or trains. The lot partitioning strategy is adapted on the fly to the current channel characteristics. A dynamic model of the supplier-depot interaction is built and used to evaluate the policy properties in a robust control framework. Using the constructed framework, it is explicitly shown how to select the policy parameters to obtain full demand realization, thus eliminating backorders, irrespective of the pattern of delay and demand fluctuations. It is also discussed how to assign the warehouse space at the depot so that emergency storage will not be required even though, as a result of channel disruptions, deliveries from a few periods arrive simultaneously, or out of order.

Keywords: Networked control systems, Control applications
Abstract: This paper concerns the finite-time (FT) proportional-integral-derivative (PID) predictive control for networked control systems (NCSs) with time-varying delays. A PID networked predictive control (PID-NPC) method is first proposed. This method makes use of historical information and its error of prediction state. Furthermore, an augmented switched control system is established in which the switching signal is determined by the time delay. Sufficient conditions are derived so that the resulting systems are finite-time boundedness (FTB). Then novel FT-PID controllers and the corresponding FT observers are given to compensate for the time-varying delays actively. Simulation example illustrates the effectiveness of the proposed method.

Keywords: Networked games, Control applications
Abstract: A new asymptotic Nash equilibrium for a class of linear quadratic mean-field game problem with a finite number of agents is found by using the cost function decomposition method. The cost function value corresponding with this equilibrium is also computed. This value turns out to be smaller than the one obtained by the state average approximation method. The difference is prominent when the number of agents is small, but vanishes as the number of agents tends to infinity.

Keywords: Localization, navigation and mapping, Electric vehicles and intelligent transportation., Robot sensing and data fusion
Abstract: Place recognition plays a crucial role in re-localization and loop closure detection tasks for robots and vehicles. This paper seeks a well-defined global descriptor for LiDAR-based place recognition. Compared to local descriptors, global descriptors show remarkable performance in urban road scenes but are usually viewpoint-dependent. To this end, we propose a simple yet robust global descriptor dubbed FreSCo that decomposes the viewpoint difference during revisit and achieves both translation and rotation invariance by leveraging Fourier Transform and circular shift technique. Besides, a fast two-stage pose estimation method is proposed to estimate the relative pose after place retrieval by utilizing the compact 2D point clouds extracted from the original data. Experiments show that FreSCo exhibited superior performance than contemporaneous methods on sequences of different scenes from multiple datasets. Code will be publicly available at https://github.com/soytony/FreSCo.

Keywords: Modeling and identification, Electric vehicles and intelligent transportation., Nonlinear systems
Abstract: This paper proposes a method to efficiently compute the voltage and current along a transmission line which can be “damaged”; that is its electrical properties can be unevenly distributed. The method approximates a transmission line by a self-similar circuit network and leverages our previous work regarding the frequency response for that class of networks. The main motivation arises from research for railway track circuit systems where transmission line models are often employed. Determining deviations from baseline properties of the railway circuit is important for health monitoring of the system and furthermore, changes in circuit properties due to a train occupying a segment of the track also is of great interest as a means to ensure safety. Thus, in addition to monitoring the integrity of the railway circuit, our approach also could provide a means for safe operation in that it can be used to detect segments of the rail system that are occupied by trains.

Keywords: Electric vehicles and intelligent transportation., Energy management systems, Neural networks
Abstract: Li-ion battery State of Health (SOH) estimation is a crucial function of the Electric Vehicle (EV) Battery Management System. This is because of the unpredictable performance of Li-ion battery cells once the nominal capacity drops below 70% (due to exposure to numerous cycles). Artificial Neural Networks (ANNs) have gained popularity for SOH estimation in recent years due to their high flexibility and low complexity. The possibility of using parallel recurrent architectures in ANNs for SoH estimation is investigated in this paper. Gated Recurrent Unit (GRU-RNN) architecture was used for the parallel recurrent layers, due to its simplicity and good SoH prediction capability as seen in recent literature. The charging profile of B0005, B0006, B0007 and B0018 batteries from the NASA Ames Prognostics Center of Excellence (PCoE) dataset were used for training and testing the ANNs. The time intervals between certain points in the charging voltage profile (3.8 to 3.9V, 3.9 to 4.0V and 4.0 to 4.1V) and the time interval between 0.1 to 0.05A of the charging current profile were used as input features. The obtained results show that the proposed model has low testing dataset Mean Squared Error (MSE) (0.0299%) and good generalization when compared to the conventional GRU-RNN (0.352% MSE), parallel Bidirectional GRU-RNN (0.0360% MSE), parallel Long Short Term Memory configuration (0.0549% MSE), Bidirectional GRU-RNN (0.035% MSE) and GRU-RNN with attention (0.0448% MSE). Overall, the proposed model can accurately predict the SoH of the Li-ion batteries upon successful implementation on an EV, resulting in better consumer safety.

Keywords: Electric vehicles and intelligent transportation., Cyber security in networked control systems, Robot sensing and data fusion
Abstract: Collective Perception Messages (CPM) enable vehicles to share their perceived objects with their neighbors in V2X network. These perception data extend local vehicles' perception and consequently improve road safety awareness. However, attacks on perception data are challenging and require advanced and efficient misbehavior detection mechanism especially in specific road scenarios where contradictory information need to be analysed. In this work, we introduce a trust management framework to detect misbehaving nodes through transmitted CPM messages. Our framework is based on trust assessment built through several processing steps. It addresses conflict situation when contradictory data are received using the Subjective Logic mechanism. The results show that our solution is effective in detecting misbehaving nodes based on their attributed trust scores. In addition, we show the impact of our solution and some CPM configuration parameters on safety services and especially on risk anticipation in intersection scenarios.

Keywords: Mobile robotics, Mechanism design and applications.
Abstract: Mobile robots that can carry heavy loads play an important role in transporting and exploring in unstructured environment. However, there are some problems existing in conventional motor direct-drive robots such as excessive joint torque and unfoldable legs when they are under heavy loads. This paper proposes a tendon-actuated foldable wheeled-legged robot with high load-bearing capacity. A spreader is attached to the knee joint so that the output torque of the motor can be amplified by pulling the end of the spreader with a cable. The single and double fixed pulleys are used to reduce the required cable tension and avoid the interference of different cables, which can better achieve the folding of legs. In addition, the statics and kinematics of the tendon-actuated leg and the formulas for calculating the required tension and motor torque, as well as the relationship between foot velocity, joint speed, and motor speed are given. Finally, Matlab is used for simulation analysis, and it is found that the joint torques required for the tendon actuation are lower than for the direct actuation at the same joint angles.

Keywords: Human centered systems, Modeling and identification, Man-machine interactions
Abstract: Physical Human-Robot Interaction (pHRI) is an important field that has grown considerably over the last years. Nowadays, new possible applications are being evaluated. In order to tackle the new issues that might arise, novel methods for robot control have to be used. To ease the comparison and evaluation of those methods, this work proposes a simulated framework to study the collaboration between a robot manipulator and a person while moving payloads. The way of conceiving the simulated framework done in Matlab is presented, detailing how the robot, the object, and the person can be described. Experiments are done on a real robot KUKA LBR iiwa 14 R820 to compare and validate the interaction forces predicted by the proposed framework. Results showed that this method allows to simulate the co-manipulation of objects, even with unknown load, showing forces that are close to the real ones applied by the person. The Matlab code is publicly available at https://gitlab.com/MMujica/simulated_framework_phrc.

Keywords: Intelligent systems, Man-machine interactions, Intelligent automation
Abstract: In real-world applications, the effective integration of learning and reasoning in a cognitive agent model is a challenging mission. However, such integration may lead to a better understanding, practice, and construction of more realistic models, especially for mathematical learning. Unfortunately, existing models are either oversimplified or require much processing time, which is unsuitable for online learning and education. Therefore, we propose a novel cognitive learning model, called Mathematical Cognitive Learning Model (MathCLM) based on the evolution of knowledge graph, for online mathematical learning that seeks to effectively represent, learn, and reason in online learning environments. The model's architecture combines cognitive learning with symbolic knowledge representation based on natural language processing (NLP). We introduce the mathematical instance concept to build the strategies by mathematical knowledge, such as theorems, axioms, etc., and infer new custom instances based on the learning knowledge. Furthermore, it can deal with uncertainty and errors from instances recommendation using a graph matching model and displays the inference progressing with different combinations of instances. We build a platform to promote and validate our model. The validation of the model on the real-world platform and the results presented here indicate the promise of the approach when performing online learning and reasoning in real-world scenarios, with possible applications in various areas.

Keywords: Human-computer interaction
Abstract: At present, many projects are being developed with human-computer interfaces in different areas but few are related to music. In this work we present a scorewriter application that uses electrooculography as input interface. For one side, the hardware used to record the electrooculogram consists mainly of a low-cost Arduino based microcontroller board that will receive the signal from the electrodes, collect it and send it via USB to the computer. On the other hand, we use free software to implement the application running on the computer. This application is in charge of processing, classifying (using a neural network) and translating the signal into commands to finally build the song and play it. The modularity of the application allows it to be easily modified for other tasks using the same interface. Due to the nature of the application it is very suitable for entertainment. Furthermore, due to the characteristics of its interface it is also suitable for people with reduced mobility who want to easily perform simple music composition tasks.

Keywords: Control engineering education, Control applications, Process control
Abstract: In the paper, there is presented a MATLAB Toolbox that allows simulation and parameter tuning of closed-loop systems with fractional-variable-order digital PID (FVOPID) controllers. The proposed toolbox provides MATLAB Simulink blocks of FVOPID based on two different implementations of Grünwald-Letnikov fractional-variable-order operator. An additional part of the toolbox is an application with a GUI interface which primary purpose is to simulate and find the optimal tuning parameters of FVOPID for a given closed-loop system. The tuning process, in this case, can be performed employing different optimization methods set to minimize an objective function according to the selected integral criterion. The paper describes the internal architecture (design) of the toolbox and its functionalities.

Keywords: Event-triggered and self-triggered control, Image/video analysis, Robot control
Abstract: Blockchain is a disruptive technology, normally used within financial applications, however, it can be very beneficial in certain robotic contexts, such as when an immutable register of events is required. Among the several properties of Blockchain that can be useful within robotic environments, we find not just immutability but also data decentralization, irreversibility, accessibility and non-repudiation. In this paper, we propose an architecture that uses blockchain as a ledger, and smart-contracts for robotic control by using oracles to process data. We show how to register events in a secure way, how it is possible to use smart-contracts to control robots and how to interface with external algorithms for image analysis. The proposed architecture is modular and can be used in multiple contexts such as in manufacturing, network control, robot control, and others, since it is easy to integrate, adapt, maintain and extend to new domains, only requiring new tailored smart-contracts.

Keywords: Adaptive control, Multi-agent systems
Abstract: In this paper, we propose a control for a class of multi-agent systems described by diffusion partial differential equations to solve the leader-follower consensus problem. Each group of follower agents changes according to the leader group's formation, obtaining the desired formation by applying boundary control. We use the Lyapunov direct method to prove the system is uniformly ultimately bounded. Numerical simulation results finally show the validity of the proposed control.

Keywords: Human-computer interaction, Robot control, Intelligent automation
Abstract: The remote control of Unmanned Aerial Vehicles (UAVs) in emergency rescues, large-scale search, e-commerce and other fields is still a hot topic. The majority of current remote human-computer interaction techniques, such as joy- sticks, monitoring interfaces, or gesture control, lack flexibility, have weak immersion, and have poor interaction. The study proposes the development of a novel system for controlling multiple UAVs using virtual reality (VR). A virtual system and a physical system make up the control system. A VR application uses a head-mounted display (HMD) to show the user a digital twin environment of a drone and a faraway location. The operators pilot the quadcopters with a set of virtual reality handles. Control data is translated directly from VR to the real UAV in realtime. The experimental results showed a stable and convenient method of manipulation by the VR scene. With the support of the proposed system, ultra-remote control is possible, and immersive maneuvering makes controlling multiple drones easier.

Keywords: Adaptive control, Robust control, Nonlinear systems
Abstract: This paper investigates the attitude trajectory tracking control problem for quadrotor UAVs. An uncertain nonlinear affine state system is modeled from the quadrotor with unknown external disturbances. By checking the existence of certain auxiliary matrix, a milder controllability condition for the quadrotor model is introduced building upon which a robust adaptive attitude trajectory tracking controller is proposed, which guarantees that all signals in the closed loop quadrotor system are globally ultimately uniformly bounded (GUUB) and the trajectory tracking errors converge to zero asymptotically. Finally, the effectiveness of our method is verified by simulations.

Keywords: Activity/behavior recognition, Perception systems, Object recognition
Abstract: Radar is widely used in human activity recognition because of its powerful micro-doppler feature capture capability and environmental adaptability. In this work, we propose a novel radar-based potential drowning detection system. To enhance the cross-domain fusion efficiency and intra-domain feature learning, we design a two-stage fusion network for the drowning detection system. In the first-stage fusion, we integrate the encoded features of three-domain radar maps along either the temporal or spatial dimension. In the second-stage fusion, we use Attention-LSTM and 1D-CNN to extract deep information from temporal-fused and spatial-fused features, and further combine these features using a trainable weighted average strategy. Based on our proposed novel fusion architecture, fine-grained aquatic human activity recognition is achieved. In the experiments, we collect a nine-class aquatic human activity dataset. The experimental results demonstrate the superiority of the proposed TSFNet over the conventional ones. The dataset and the associated codes are available at: https: //github.com/DingdongD/aquatic-activity-dataset.

Keywords: Localization, navigation and mapping, Vision for robots, Mobile robotics
Abstract: Vision-based SLAM has played an important role in many robotic applications. However, most existing visual SLAM methods are developed under a static world assumption and the robustness in dynamic environments remains a challenging problem. In this paper, we propose a robust RGB-D SLAM system for autonomous vehicles in dynamic scenarios which uses geometry-only information to reduce the impact of moving objects. To achieve this, we introduce an effective and efficient dynamic points detection module in a feature-based SLAM system. Specifically, for each new RGB-D image pair, we first segment the depth image into a few regions using the KMeans algorithm, and then identify the dynamic regions via their reprojection errors. The feature points located in these dynamic regions are then removed and only static ones are used for pose estimation. A dense map that contains only static parts of the environment is also produced by removing dynamic regions in the keyframes. Extensive experiments on public dataset and in real-world scenarios demonstrate that our method provides significant improvement in localization accuracy and mapping quality in dynamic environments.

Keywords: Distributed optimization and MPC, Network-based systems, Sensor networks
Abstract: In this paper, we propose a gradient-free penalty ADMM to distributedly solve constrained convex optimization problems over network systems. All agents only communicate with their neighbors and local decision variables constrained in feasible set constraints. We design a pseudo-gradient to obtain an approximate gradient. Then we update decision variables based on the approximate gradient and penalty ADMM method. Moreover, we analyze the convergent performance of the proposed algorithm and summarize some conclusions.

Keywords: Fuzzy systems, Network-based systems
Abstract: Multi-sensor information acquisition system can reflect the operation status of machinery more comprehensively and reliably, but also demands higher requirements on data analysis algorithms. Unlike previous deep learning models, the emerging graph neural network (GNN) has a remarkable performance in mining graph structure and patterns, effectively integrating multiple node relationships and features. This paper presents a fault diagnosis algorithm for rotating machinery based on multi-sensor information fusion using the modified Graph Attention Network— GATv2. Firstly, the dependencies between multi-sensor signals are explicitly extracted by the Grow-Shrink (GS) algorithm, where the topology of the constructed graph can characterize different failure states of the equipment. During the aggregation process, the attention mechanism in the GATv2 assigns higher weights to informative nodes for the effective fusion of multi-sensor information. Experiments on bearing and gearbox datasets show that the proposed diagnosis framework can yield more expressive multi-sensor representations, and diagnostic accuracy is improved significantly compared to the single-sensor graph.

Keywords: Neural networks, Localization, navigation and mapping, Learning and Statistical methods
Abstract: The method described in this paper proposes a supervised Deep Neural Network (DNN) approach for the prediction of anomalies in camera-based navigation. The method is inspired by the unsolved issues of Integrity Monitors (IMs) when some of the sensor measurement covariances are unknown or inconsistent. Especially, the focus is on predicting when the estimation error distribution would require fatter tails to include outliers. The developed method takes into account single-frame image features as well as transient changes in the error. In the best of our knowledge, this is the first work that predicts anomalies in the error covariance of SLAM estimates and associates them with low-level image features. Finally, the prediction method can be used with other sensors as well, allowing the future development of navigation algorithm- and sensor-agnostic safety monitoring frameworks.

Keywords: Localization, navigation and mapping, Feature extraction, grouping and segmentation, Tracking and surveillance
Abstract: This paper presents the results of initial evaluation of the usage of onboard down-looking electro-optical sensors to assist in GPS-free navigation of aerial platforms. The paper starts with presenting a general idea behind the image-matching navigation concept, followed by discussing the key results of the three experimentation campaigns utilizing different sets of sensors used to collect imagery data. The paper discusses sensor setups, assesses different image processing methods, looks at different operating environments, and reveals limitations related to the image-matching aid to navigation. The paper ends with conclusions and recommendations for future research in developing an integrated navigation system relying on inertial measurement unit data complemented with the relative position fixes provided by the image-matching algorithm.

Keywords: Localization, navigation and mapping, Robot sensing and data fusion, Mobile robotics
Abstract: Although accurate and reliable localization is a prerequisite for autonomous driving, in urban environments neither the Global Navigation Satellite System (GNSS) nor the Simultaneous Localization and Mapping (SLAM) ensure satisfying results in terms of both local accuracy and global consistency. Hence, we contribute in this paper a method to augment the existing LiDAR-based SLAM systems with GNSS measurements, applying the factor graph formulation of the problem. We contribute a tightly coupled GNSS/LiDAR SLAM considering constraints from LiDAR and GNSS mea- surements, and propose a filtering procedure to cope with GNSS measurements that introduce non-Gaussian noise. We evaluate our approach on the challenging UrbanNav dataset, considering different LiDAR SLAM algorithms and different GNSS receivers, and showing that our solution outperforms previous approaches to GNSS/LiDAR integration.

Keywords: Localization, navigation and mapping, Mobile robotics, Robot control
Abstract: In this paper, we deal with the problem of full-body path planning for walking robots. The state of walking robots is defined in multi-dimensional space. Path planning requires defining the path of the feet and the robot's body. Moreover, the planner should check multiple constraints like static stability, self-collisions, collisions with the terrain, and the legs' workspace. As a result, checking the feasibility of the potential path is time-consuming and influences the performance of a planning method. In this paper, we verify the feasibility of sampling-based planners in the path planning task of walking robots. We identify the strengths and weaknesses of the existing planners. Finally, we propose a new planning method that improves the performance of path planning of legged robots.

Keywords: Vision for robots, Neural networks, Perception systems
Abstract: In this research, we deal with the problem of estimating 3D object positions based on 2D localization data and 2D object bounding boxes determined on the RGB images by a CNN object detector. We use a mobile-manipulating robot equipped with an RGB-D camera and a 2D laser scanner. In contrast to other methods, which are based either on end-to-end neural networks or machine learning solutions, we propose an approach that allows estimating 3D object positions from a sequence of images and 2D robot poses obtained from an onboard 2D localization system. We determine a set of lines from the robot localization data and the object detections, which define the observation directions. The closest point to a set of lines determines an approximate object location. We define the 3D object position estimation as an optimization problem and solve using efficient GPU implementation. Finally, we present results based on data collected on the real robot in an unstructured environment.

Keywords: Image/video analysis, Object recognition, Vision for robots
Abstract: In this paper, we focus on the detection of tiny objects. The goal is to improve the performance of tiny object detection while preserving the average precision and recall metrics compared to a brute-force, sliding-window approach. We extend the object categories in COCO detection metrics from small, medium, and large by defining tiny, very tiny, and micro-objects. We propose an evaluation protocol for all six object sizes. To detect tiny objects, we offer a novel ROI proposal method based on a two-level nested U-structure architecture U2Net. For this purpose, we experiment with multiple dilation techniques as well as Region of Interest (ROI) aggregation methods. We evaluate our method using the Mapillary Traffic Sign Dataset. The obtained detection strategy outperforms the single-step prediction approach and is comparable to the quality obtained with the use of the sliding-window, being nearly 7 times faster.

Keywords: Search, rescue and field robotics, Control applications, Process automation
Abstract: A sensor-equipped Unmanned Aerial Vehicle (UAV) can be used to gather surface information of a structure, performing an autonomous inspection. It can significantly improve the efficiency of the visual inspection tasks and reduce the operating cost and the human risks involved in the tasks. A complete inspection coverage path generating method comprising two sets of viewpoints is presented in this research. The first set of viewpoints, revolving viewpoints, is generated based on the geometry of the inspection target and revolving around the target. The second set of viewpoints, gap-filling viewpoints, is generated to compensate for the insufficiency of the revolving viewpoints, filling all the unseen surface patches and guaranteeing full coverage. The system's scalability was proven by the planning outcomes for two different structures on different scales, which met both requirements of close-up inspection and photogrammetry.

Keywords: Distributed optimization and MPC, Multi-agent systems, Networked control systems
Abstract: This paper considers a distributed linearquadratic regulator (LQR) method for a multiagent system when the main objective is to guarantee the final states of all agents to satisfy some predetermined constraints. The the asymptotic convergence of the proposed approach is ensured via finite horizon-time linear-quadratic (LQ) performance for discrete-time linear subsystems. The cost function consists of the control input energy consumption and the distance to a desired free-endpoint. By applying a modified Nesterov-accelerated gradient algorithm, each agent determines its optimal control inputs using only information of its own and its neighbors. Then the proposed method is applied to a displacement-based formation control problem. Simulation results are used to verify the effectiveness of the designed formation control method.

Keywords: Cooperative control, Cyber security in networked control systems, Multi-agent systems
Abstract: This paper investigates practical time-varying formation tracking problems for high-order multiagent systems in an adversarial environment, where the leader's control input is unknown and the followers are prone to agent-attacks. To guarantee the remaining benign followers not suffering attacks still can track the leader's trajectory with an expected formation configuration, the resilient practical time-varying formation (RPTVF) tracking is examined in this work. Firstly, to avoid the influence of attacked follower agents, a security strategy is proposed, which is an enhanced version of weighted mean-subsequence-reduced algorithm. Secondly, using relative information of neighbors, a resilient tracking protocol is designed for each benign follower to track the leader. Then, it is proved that according to the above strategy and protocol, the multiagent systems with a leader of unknown input can reach convergence in a finite time. Finally, simulation examples are given to verify the theoretical results.

Keywords: Cooperative control, Adaptive control, Multi-agent systems
Abstract: This paper studies the distance-based formation control problem where agents in the system are modeled with single-integrators with parametric uncertainties. We propose to use adaptive control as the main tool to approach the problem. Under the assumption that only local displacements are available, an adaptive distance-based control law is proposed and analysed. If additionally, each agent can sense its local position, we propose using an additional observer to estimate the uncertain parameters and stabilize the desired formation. Simulation results are also given to support the theoretical results.

Keywords: Multi-agent systems, Delay systems, Networked control systems
Abstract: The paper analyzes the decentralized deployment policies for scalar multi-agent systems subject to delays. As a main contribution we obtain explicit conditions on the local feedback gains at the level of subsystems, which ensure safe deployment independent of the delays on the measurement of the positions of the neighboring agents. From the theoretic point of view, positive invariance of sets is used as a main concept for the proofs of the results.

Keywords: Multi-agent systems, Learning and Statistical methods, Neural networks
Abstract: This paper investigates the data transmission resilience between agents of a cluster-based, heterogeneous, multi-agent deep reinforcement learning (MADRL) system under gradient-based adversarial attacks. We propose an algorithm using a deep Q-network (DQN) approach and a proportional feedback controller to defend against the fast gradient sign method (FGSM) attack and improve the DQN agent performance. The feedback control system is an auxiliary tool that helps the DQN algorithm reduce system deficiencies. In accordance with the achieved results and under FGSM adversarial attack, the resilience of the developed system is evaluated in three different ways termed robust, semi-robust, and non-robust based on average reward and DQN loss. The data transfer is carried out between agents of a MADRL system in timely and time-delayed manners, for both leaderless and leader-follower scenarios. Simulation results are included to verify the presented results.

Keywords: multi-robot systems, Localization, navigation and mapping
Abstract: Deadlock is always a challenging problem for multi-agent pathfinding, especially when the system is in high scales in terms of number of agents and map size. Some recent studies showed that the agents can learn to resolve the deadlock problem through reinforcement learning. However, most of them are not designed for non-holonomic robots, which are commonly applied in warehouses. In particular, the rotation movement may cause the agents staying at the same locations for a long time, and the deadlock happens more frequently especially in dense environment. In this paper, an algorithm called MAPF-rot with a deadlock breaking scheme is proposed to tackle the deadlock problem arising from the rotation movement in the multi-agent pathfinding problem. Experiments are performed to demonstrate the efficiency of the proposed algorithm.

Keywords: Multi-agent systems, Consensus algorithms
Abstract: The paper is devoted to multi-agent systems with memories under denial-of-service (DoS) attacks. The memory is represented by the fractional derivative that appears in the dynamics of the considered systems. The problem that we aim to address is, under which conditions the system continues to be stable or is in consensus mode, despite DoS attacks. Solutions to these problems are proposed in the presented theorems. We strengthen the theoretical considerations with numerical simulations.

Keywords: Cyber security in networked control systems, Identification and estimation, Adaptive control
Abstract: In this study, an adaptive controller for CyberPhysical Systems(CPSs) subjected to cyberattacks is proposed to track a class of target system with unknown inputs and states. Firstly, an estimation strategy is proposed to adaptively estimate the unknown inputs and states of target on the basis of finite impulse response (FIR) filter. Secondly, due to the existence of cyberattacks in CPSs, an adaptive tracking control scheme with designed compensation signal is constructed to stabilize the system performance which might be damaged by attacks, where Lyapunov function related to adaptive estimated factor is adopted to prove that the CPSs are able to track the target under attacks. In the last part, a numerical experiment is implemented to demonstrate the validity of the theoretical results.

Keywords: Cyber security in networked control systems, Event-triggered and self-triggered control, Nonlinear systems
Abstract: This note studies the issue of decentralized event-triggered control (ETC) for nonlinear cyber-physical systems (CPSs) under denial-of-service (DoS) attack by output feedback. Due to the existence of DoS attack, an attack signal dependent observer is designed to reconstruct the unknown system states. To save the communication resources, an ETC strategy is introduced. Since the triggering controller is only updated at triggering instants, it may not switch from normal (attack) mode to attack (normal) mode when the system works well or subjects to attack. This feature may lead to the mismatch behavior between triggering controller and corresponding subsystem and destroyed system performance. To solve this issue for nonlinear CPSs, a decentralized ETC scheme is given based on the feature of DoS attack. With the presented control scheme, a new decentralized event-triggered controller is designed through the idea of average dwell time, under which all closed-loop signals are bounded and the system states can converge to a bounded close set around the origin. Meantime, it is proved that the Zeno behavior is avoided successfully. Finally, as the effectiveness verification of the proposed control strategy, a practical example is provided.

Keywords: Distributed estimation, Neural networks, Identification and estimation
Abstract: This paper studies the distributed estimation problem of sensor networks where the noise parameters are unknown and some sensors cannot obtain the measurements. The expectation maximization (EM) algorithm integrating Kalman filtering algorithm, which is called the EM-KF algorithm, is adopted to sensor networks. Simulation examples are given to illustrate the effectiveness of the algorithm. By using LSTM network, and LSTM-KF algorithm is further proposed to improve the accuracy of EM-KF algorithm.

Keywords: Nonlinear systems, Event-triggered and self-triggered control, Adaptive control
Abstract: This paper studies the problem of dynamic event-triggered (ET) output feedback (OF) control for switched nonlinear systems (SNSs) with uncertain output function. The considered system allows more general growth restriction. Firstly, to deal with the system uncertainties, a homogeneous observer embedded with a dynamic gain is put forward. Then, an adaptive control scheme under arbitrary switching is presented. It is worth emphasizing that the threshold parameters of the used ET mechanism can be dynamically adjusted. Besides, it is proven that all signals of the closed-loop system are bounded. The effectiveness of the presented method is verified by an illustrative example.

Keywords: Distributed optimization and MPC, Networked control systems, Nonlinear systems
Abstract: In this paper we proposed a data-driven distributed model predictive control (MPC) for the load frequency control of the multi-area interconnection nonlinear power system. The data-driven Koopman operator method is used to deal with the nonlinear wind power generation system in each area. The distributed Koopman operator algorithm is proposed to deal with the huge amount of data in the large-scale distributed system. Based on the distributed linear model obtained by the distributed Koopman operator algorithm, the distributed MPC is applied to realize the load frequency control (LFC) of the multi-area power system. The cooperation-based cost function is optimized by the MPC controller in each area, and the global optimal solution can be achieved by the proposed method. The effectiveness and practicability of the proposed algorithm are demonstrated by the simulation.

Keywords: Multi-agent systems, Consensus algorithms, Cooperative control
Abstract: In this article, the fixed-time distributed average tracking (DAT) problem of second-order multiagent systems (MASs) under the undirected topology is discussed. The DAT algorithm is composed of a distributed average estimator and an estimator-based decentralized tracking controller. The distributed average estimator guarantees that the agents estimate the average value of multiple time-varying reference signals (TVRSs) with bounded derivatives within a fixed time. Then, through the back-stepping method, the estimator-based decentralized tracking controller is proposed to ensure that each agent reaches the average value of the multiple TVRSs within a fixed time. Finally, numerical simulation results verify the effectiveness of the proposed protocol.

Keywords: Cooperative control, Adaptive control, Networked control systems
Abstract: This paper investigates a prescribed performance control (PPC) problem for a formation of unmanned aerial vehicles (UAVs) under anti-collision constraints. By means of artificial potential field (APF) and adaptive backstepping techniques, a new performance guaranteed formation control scheme is developed for UAVs. In this scheme, two APF functions are constructed to obtain collision-free flight paths while eliminating local oscillation and forced collision to barriers. And an adaptive performance guaranteed strategy is incorporated into a distributed formation controller which is compatible to the designed APF functions. It is shown that using the developed scheme, desired formation configurations can be achieved with both performance and anti-collision requirements satisfied during the flight. Simulation results verify the effectiveness of the proposed formation flight scheme.

Keywords: Localization, navigation and mapping, Electric vehicles and intelligent transportation.
Abstract: The increasing number of vehicles and dynamic changes in traffic situations make real-time route planning strongly necessary. The route-guiding method is supposed to cope with dynamic traffic situations. In addition, the ability to adapt to the second fastest route is very important when traffic congestion suddenly occurs on the fastest path. This paper proposes a method of using reinforcement learning to solve dynamic route planning problems, and the adaptation from a static learning rate to a dynamic learning rate enhances the capability to deal with emergent congestion. Meanwhile, the waiting time before each traffic light also is considered as a reward factor in the proposed algorithm. Contrast experiments have been conducted on the simulation network by SUMO, which have demonstrated well that our proposed method has better performance than other methods.

Keywords: Image/video analysis, Activity/behavior recognition
Abstract: In this paper, we propose a conditional early exiting framework with Ulam’s Game for traffic sign recognition. Since the traffic sign recognition system has extremely high requirements on dynamic performance, we pays more attention to improving the detection efficiency, hoping to obtain results in a shorter time. In our system, we use a modified ResNet-50 as backbone network to do feature extraction and use a Pooling module to accumulate feature. Then, we have a Gate module to determine whether the feature have accumulated enough to begin Ulam’s Game. A classifier is used to get candidate results, which are used to run Ulam’s Game and get the final prediction. The model shows good detection accuracy and dynamic performance in multiple data sets (Mini-Kinetics, ActivityNet, Lisa).

Keywords: Electric vehicles and intelligent transportation., Data analytics., Neural networks
Abstract: There is no doubt that in the near future, machines will share roads with human drivers. Therefore, the prediction of human drivers’ lane changing behavior is imperative. Lane- change prediction is one of the most important ones. Human drivers and the self-driving vehicles need to ensure that no other vehicle will change lanes and move to the same range of the target lane where the ego vehicle is going. The existing short-term prediction algorithms can only provide a prediction horizon of 3 ∼ 5s, leaving only a limited reaction time for drivers and autonomous path planning modules. Moreover, most of the previous studies only studied the inference of lane change in expressway environment, without lane segmentation and merging. Compared with the more common urban environment, most previous studies only studied the inference of lane-change in expressway environment. Among these studies, there are few studies that can deal with multi-scenario and scenario switching. In this paper, a Scenario Encoding Model (SEM) is proposed to help solve the problem of long-term lane-change prediction and the scenario switching problem in the existing short-term lane- change prediction. Even in the absence of road history data, the SEM can model the road scenario and encode the real-time road scene by using Self-Organizing Map (SOM) In the mean time, the established initial model has the ability to be further evolved into a historical bias model in the background of a large amount of road historical data. The evaluation test of this SEM has been done through the NGSIM dataset.

Keywords: Electric vehicles and intelligent transportation., Big data, Neural networks
Abstract: Abstract— Traffic speed prediction is a significant branch of the intelligent transportation system (ITS). A good prediction could alleviate the non-recurring congestion on the road and provide a strong decision-making basis for traffic management and control. However, it is always a challenging research problem due to the complexity of the road network and the dynamics of traffic conditions. Many deep learning-based methods have been applied to the traffic prediction problem, which could extract both spatial and temporal information efficiently. However, for some dataset that suffers from data paucity problem, the generalization ability of the model is not good and the performance degrades. To tackle this problem, we proposed a novel graph-based generative adversarial network for the traffic speed prediction problem. We design a generative network to generate some fake traffic data and use a discriminative network to distinguish between real and fake targets. The generator consists of a GraphSAGE and LSTM model to learn the representation of spatial-temporal traffic data. Several experiments have been conducted on several real-world traffic datasets, demonstrating that our proposed model outperforms other baseline models. The experiment results illustrate the importance of utilizing GAN in the training process, which improves the generalization ability of the prediction model.

Keywords: Electric vehicles and intelligent transportation., Object recognition, Image/video analysis
Abstract: Recently, with the advancement of vehicle electronics hardware and the rapid development of artificial intelligence technology, intelligent transportation technology has begun to play a very significant role in the development of vehicle technology. Vehicle tracking technology based on deep learning has also received more and more attention, especially since the rapid development of deep neural networks. A significant contribution of this paper is an evaluation of the performance of neural networks in relation to the type of input data, and an exploration of future development possibilities. Based on YOLOv5 and DeepSort, a vehicle detection and tracking algorithm was chosen to test the algorithm's performance on the Bayer data. The results are discussed and analyzed.

Keywords: Feature extraction, grouping and segmentation, Intelligent automation, Image/video analysis
Abstract: 3D semantic segmentation is a vital problem in autonomous driving. Vehicles rely on semantic segmentation to sense the surrounding environment and identify pedestrians, roads, and other vehicles. Though many datasets are publicly available, there exists a gap between public data and real-world scenarios due to the different weathers and environments, which is formulated as the domain shift. These days, the research for Unsupervised Domain Adaptation (UDA) rises for solving the problem of domain shift and the lack of annotated datasets. This paper aims to introduce adversarial learning and cross-modal networks (2D and 3D) to boost the performance of UDA for semantic segmentation across different datasets. With this goal, we design an adversarial training scheme with a domain discriminator and render the domain-invariant feature learning. Furthermore, we demonstrate that introducing 2D modalities can contribute to the improvement of 3D modalities by our method. Experimental results show that the proposed approach improves the mIoU by 7.53% compared to the baseline and has an improvement of 3.68% for the multi-modal performance.

Keywords: Neural networks, Localization, navigation and mapping, Vision for robots
Abstract: Hand-eye calibration methods for surgical robots are employed to derive a transformation between the robot's base motor and visual coordinate systems. Accurately completing hand-eye calibration procedures provides an important guarantee that a surgical robot will exhibit positioning and execution accuracy sufficient for assisting surgeons in successfully completing surgical procedures. To improve the accuracy of robot hand-eye calibration methods based on backpropagation neural network (BPNN) models, we propose a modified BP neural network optimized using the sparrow search algorithm for hand-eye calibration model (TSSABPNN), which can enhance population initialization by applying tent mapping. Furthermore, we also design a new sliding 3D calibration tool. The sparrow search algorithm exhibits good local exploration ability, and we introduce a tent map with ergodic characteristics to initialize the sparrow population information, which further improves the network’s global search ability and convergence rate. Finally, we experimentally analyze four calibration models: TSSABP NN model, a BP NN model optimized using a genetic algorithm of simulated annealing (GASABPNN), an unoptimized BP NN model, and the traditional singular value decomposition method. The results indicate that the proposed TSSABP NN model exhibits the maximum calibration precision and best robustness and iteratively converges faster.

Keywords: Feature extraction, grouping and segmentation, Face and Gesture., Human-computer interaction
Abstract: In this paper, the problem of movement epenthesis in continuous sign language sentences is considered. Movement epenthesis caused due to unwanted but unavoidable hand movement in between two sign gestures in continuous signing has emerged as one of the most challenging problems in automatic sign language recognition. To handle this problem, a novel method based on unsupervised learning approach has been proposed in this paper to separate out video frames corresponding to meaningful sign gestures from meaningless movement epenthesis segments in a continuous signing gesture video clip. Our proposed method is based on K-means clustering of the norm values of the absolute difference between current frames and the reference frame to detect the movement epenthesis frame and then classify the frames of the video as movement epenthesis frames and sign frames. Exhaustive experimentation on the publicly available standard ChaLearn LAP ConGD gesture video dataset was carried out to test our algorithm. Experimental results demonstrate that the proposed method is good enough to detect and separate out the movement epenthesis frames in sentence level sign language videos. Our proposed approach performs the movement epenthesis detection task accurately in 91% of the videos of the ChaLearn LAP ConGD dataset.

Keywords: Factory modeling and simulation, Visual servoing, Robot control
Abstract: We present in this paper a new open-source simulator based on CoppeliaSim and ROS for the popular Franka Emika Robot (FER) fully integrated in the ViSP ecosystem, a powerful library for Visual-Servoing. The simulator features a dynamic model that has been accurately identified from a real robot, leading to more realistic simulations. The C++ API closely follows the ViSP class of the real robot allowing to narrow the gap between simulation code and real control software deployment. Conceived as a multipurpose research simulation platform, it is well suited for visual servoing applications as well as, in general, for any pedagogical purpose in robotics. All the software, models and CoppeliaSim scenes presented in this work are publicly available under free GPL-2.0 license.

Keywords: Man-machine interactions, Perception systems
Abstract: As technology advances, robots are becoming more and more a part of our daily lives. While industrial robots have already been in use for a several years, an increasing number of robots are also employed in the private environment. Human-robot cooperation requires ways to detect interactions in order to prevent possible harms. This paper presents a novel artificial skin made of conductive rubber for robot end-effectors. Integrated electrodes enable proximity, touch and force detection by combining impedance and capacitance tomography techniques. The results of measurements carried out on a prototype are presented in order to show how the tomographic methods provide a local resolution of the detection of close objects and of the force measurement.

Keywords: Feature extraction, grouping and segmentation, Image/video analysis, Tracking and surveillance
Abstract: The matching of incorrect pairs affects the pre- cision of the SLAM/VO system. Because the calculation is complex and time-consuming, the various limitation methods struggle to meet the system’s real-time requirements. FMS is a novel approach that adapts well to both sparse and dense mapping processes, allowing for the verification of matched pairs of features. By displacing features between two consec- utive frames, the projection formula contacts motion patterns. This classifier’s overall characteristics demonstrated that it was extremely effective at applying suitable matched pairings from mismatched features. The proposed algorithm outperformed the raw technique in terms of accuracy and stability when compared to the ORB-SLAM technique.

Keywords: Intelligent automation, Image/video analysis
Abstract: Anomaly detection has been an active artificial intelligence area in research and industrial communities with many unique problem complexities and challenges that require advanced approaches. In this research we concentrate on the analysis of anomalies occurring in big research infrastructures including signal measurement analysis as well as X-ray radiation images classification. The proposed hybrid end-toend anomaly score learning framework consists of two deep learning based approached for anomaly detection dedicated for two different sources of high-dimensional data. The aim of the system is to identify abnormal status of sensors in certain time steps. In this study, we deploy two transfer learning architectures by examining pre-trained VGG-16, VGG-19, InceptionV3, Xception, as well as EfficientNet CNN models with an adjusted densely-connected classifiers. Our database contains 114 h of vacuum signals in total which have been divided into 2700 time windows of 3 min length and 114h of Pinhole images (almost 137000 images). The first model dedicated for signal analysis based on the VGG-16 architecture detects anomalies in diagnostics signals with 92% accuracy and 85.5% precision while the second module for X-ray image classification based on EfficientNet- B4 achieved 91% accuracy and 96% precision. The system achieved overall accuracy of 94%, what is a stateof- the-art result in such research infrastructures.

Keywords: Stereo and Structure from motion
Abstract: We propose a binocular stereo matching algorithm CS-ELAS. This is a cross-scale ELAS algorithm that improves the accuracy and robustness of parallax in weakly textured regions and edge regions. Our approach focuses on improving the accuracy and number of support point sets. We uniformly sample the stereo images to obtain candidate support point sets and determine robustly matched support point sets based on an adaptive cross skeleton. In this way a richer and more accurate set of support points can be obtained in the weakly textured areas near the edges. In addition, our method uses the parallax and confidence maps of low-resolution images as a priori for high-resolution images and adds high-confidence pixel information to the set of high-resolution support points. In this way, it not only increases the number of support points in weak texture regions, but also narrows the search range of candidate support points and reduces the computational cost.

Keywords: Mechanism design and applications., Dexterous manipulation, Medical robots and bio-robotics
Abstract: This paper reports a new modular phalanx which possesses the capabilities of suction adhesion and adjustable stiffness for grasping tasks. The presented membrane-suction hole patterned layer can generate sufficient suction force to grasp objects with large radius of curvature and weight. Variable-stiffness of the phalanx tuned by granular jamming structure considerably enhances the grasping robustness and lifting force. Suction-lift capability and adjustable constrained stiffness are analytically modeled and experimentally validated by suction and constraint force tests on the fabricated prototype. Through various grasping demonstrations, the objects with a radius of 5 cm and thin plates are successfully suction-picked. The proposed soft phalanges are further integrated in articulated and parallel grippers to show their augmentation in motion sequence (picking thin object) and grasping stability (improving 1.35 times in lifting and preventing slip) over conventional grippers.

Keywords: Control applications, Intelligent systems
Abstract: This paper proposes a simple, model-independent method to estimate the sideslip angle of Powered Two-Wheeled Vehicles (P2WV) using knowledge about the road model and an Inertial Measurement Unit (IMU). This proposed model is then tested using simulator software (BikeSim) on different scenarios with different tracks, velocities, and sample rates. Our results indicate the validation of the model. With these promising results, we propose some future applications where this work can be utilized.

Keywords: Control applications, Robot control
Abstract: Solving Direct Shooting Model Predictive Control (MPC) optimization problems online can be computationally expensive if a large horizon is used while also maintaining a dense time sampling. In these cases, it is accepted that trade-offs between computational load and performances should be sought in order to meet real-time feasibility requirements. However, making the problem more tractable for the hardware should not necessarily imply a decrease in performances. One technique that has been proposed in the literature makes use of control input parameterizations to decrease the numerical complexity of nonlinear MPC problems without necessarily affecting the performances significantly. In this paper, we review the use of parameterizations and propose a simple Sequential Quadratic Programming algorithm for nonlinear MPC. We then benchmark the performances of the solver in simulation, showing that parameterizations allow to attain good performances with (significantly) lower computation times than state-of-the-art solvers.

Keywords: Control applications, Marine systems, Robust control
Abstract: This paper presents a comparative study of nonlinear motion control of the BB2 underwater vehicle operating under the influence of external ocean disturbances. Underwater vehicles are affected by ocean disturbances such as waves and currents, which may deteriorate their tracking performance. Hence, it is essential to design a controller such that it can withstand the effect of ocean disturbances. In this paper, three different nonlinear controllers, namely Computed Torque Control (CTC), Nonlinear Model Predictive Control (NMPC), and Sliding Mode Control (SMC), are developed to track the trajectory of the BB2 vehicle both in the absence and in the presence of periodic disturbances. The effectiveness of the proposed control methods is demonstrated by numerical simulations and their performance is compared.

Keywords: Search, rescue and field robotics, Energy management systems
Abstract: Water activities are common in New Zealand, both recreationally and commercially. The fourth most common cause of accidental death in New Zealand is drowning. One of the most common devices for preventing drowning is a life jacket, which keeps the wearer afloat in an accident, however, until rescue arrives the wearer is still at risk of drowning. Reducing the waiting time for search and rescue and extending the survival time for the victim in the water are two areas that can be improved. It is well known that Internet of Things (IoT) lifejackets can assist with this by providing more functionality, but little progress has been made on energy harvesting to support those functions. In this paper, a review on the potential and feasibility of using life jacket as a medium to harvest energy from the movement of humans during drowning events is presented. A review of life jacket design with IoT and energy source identification is included in the paper. Although the design of the harvesting devices for life jackets will differ from that of typical wearable devices because of the unpredictable ambient environment and safety consideration, a variety of common wearable energy harvesters are reviewed. There is potential for adjusting or scaling up these methods for life jackets. The methods for dynamic modelling of the drowning person’s movement and deformation of the life jacket which can be the source of energy to be harvested necessary for the analysis and design of energy harvesting systems. The research gaps and questions are presented.

Keywords: Robot control, Man-machine interactions, Control applications
Abstract: This paper presents a path following control suitable for human robot collaborative tasks. The path following strategy allows the task description and human-robot interaction to be defined according to components tangent and transversal to a nominal path. With this formulation, the control objectives for each task can be customized to generate motions towards task completion and getting on the nominal path when switching between tasks. Simulation examples of the path following control is presented, demonstrating the ability for the proposed controllers to be customized according to objectives of the human-robot collaboration.

Keywords: Smart grid, Control applications
Abstract: A novel droop control method based on slide mode control for microgrids is proposed to enhance the power sharing performance and suppress disturbances from power components' parameters deviation and loads. The output voltage is controlled to be close to the reference voltage by a sliding mode control loop, which can maintain a good power sharing effect under the variation of system parameters or power loads' sudden fluctuation, i.e. being robust. The controller has high reliability in islanded small and medium-sized microgrids, for it merely requires voltage and current as input, and no additional communication for the proposed controller are required. Finally, by using MATLAB / Simulink, a simulation control model of two parallelled inverters is established to verify the feasibility and effectiveness of the presented controller in this paper.

Keywords: Mechanism design and applications., Mobile robotics, Modeling and identification
Abstract: A robotic head has a key role in exchanging information to indicate its emotional state or communicate during an interaction. Therefore, the main target of this paper is to present the open-source and low-cost robot head, known as Two-Ts, which is developed using 3D printing technology. Its main feature is to reproduce, even with mechanical limitations, the six basic and universal emotions created according to the Facial Action Coding System (FACS). Two steps are necessary for its development. In the first step, as the objective of the Two-Ts is to have characteristics closer to a human head, a Computer Tomography (CT) is performed to scan images of the bones of the skull and jaw of Tamires, author of this paper. In the second step, using the generated images, the structural/mechanical design of the Virtual Two-Ts is modeled and simulated in Autodesk Fusion 360. Before developing the Real Two-Ts, the electronic project is also defined, considering the vision, hearing, and speech systems. In the simulation and real experiment, the Virtual and Real Two-Ts perform basic movements, such as moving the eyes, eyebrows, head, among others. In addition, the emotions of happiness, fear, disgust, anger, surprise, and sadness are implemented, and the results are analyzed. For this, a system is developed to identify and compare the emotions generated on the face of Tamires with those of Virtual and Real Two-Ts.

Keywords: Electric vehicles and intelligent transportation.
Abstract: The potential ability to increase the capacity and safety on roads, as well as fuel economy gains has made vehicle platooning an appealing prospect. However, its use is yet to be widespread, partially due to the security concerns on it. One particular concern is the admission of fake virtual vehicles into the platoons, allowing them to wreak havoc on the platoon, which is known as a Sybil attack. In this paper, we propose a secure vehicular authentication scheme for platoon admission which is resistant to the threats of Sybil attacks. The proposed scheme offers a mutual authentication on both vehicle identity and message through a combination of a key exchange, a digital signature and an encryption scheme based on Elliptic Curve Cryptography (ECC). The scheme holds its outstanding feature to provide both perfect forward secrecy and group backward secrecy to ensure the protection of anonymity of vehicles and platoons while typical malicious attacks such as replay, and man-in-the-middle attacks can also be resisted. A formal evaluation of the security of the scheme by Canetti-Krawczyk (CK) adversary and random oracle model has been conducted to demonstrate its security functionality. Finally, the performance of the proposed scheme has been evaluated to show its efficiency.

Keywords: Electric vehicles and intelligent transportation., Intelligent systems
Abstract: In an Internet of Vehicles (IoV) network, vehicles periodically broadcast Basic Safety Messages (BSMs) that contain the vehicle’s current position, speed, and acceleration. Safety-critical applications like blind-spot warning and lane change warning systems use these BSMs to ensure the safety of road users. However, an attacker can affect the efficacy of such applications by injecting false information into the messages. One such attack is the position falsification attack, where the attacker inserts incorrect information regarding the vehicle’s position in the BSMs. The literature has explored the use of Misbehavior Detection Systems (MDSs) to detect position falsification attacks. But the limitation of the existing MDSs is that they are signature-based and require prior knowledge about the attacks for effective detection. To overcome this shortcoming, we propose a Novel Position Falsification Attack Detection System for the Internet of Vehicles (NPFADS for the IoV) that learns and detects new position falsification attacks emerging in IoV networks. The performance of NPFADS is quantitatively measured using the metrics precision, recall, F1 score, and ROC. The Vehicular Reference Misbehavior (VeReMi) dataset is used as the benchmark to analyze the performance of NPFADS. The performance of NPFADS is compared to existing MDSs in the literature, and the analysis shows that NPFADS performs on par with the existing signature-based detection models even when initialized with zero initial knowledge.

Keywords: Smart grid, Electric vehicles and intelligent transportation., Hybrid systems
Abstract: In this research the instability of voltage in microgrid is still the focus of study and determination. Specifically, First-Swing Instability is experienced in the system in noted changes with characteristics of making the system unstable or returning to a state of stability. The latter calls itself as a phenomenon of re-synchronization. Oblivious to system instability aspects, it is believed that when connecting fast electric vehicle chargers to the electricity distribution system coming from microgrids, they increase basic electrical loads and reduce the stability of the power system. Transitional currents have the characteristic of severely impacting microgrids not prepared in connected or islanded states. The influences of electromagnetic incompatibility of the inrush current, due to their condition of unpredictability and intermittent, have complex identification studies. With increasing electricity demand for electric vehicle chargers, concerns about the effects of network integration increase proportionally. This article emphasizes the influence of initialization of fast chargers on the power variation related to the re-synchronization phenomenon and its mitigating to the stability of microgrid.

Keywords: Electric vehicles and intelligent transportation., Distributed estimation
Abstract: Based on information of the real-time OD matrix estimation and prediction, according to the distributed and hierarchy idea, a novel optimal control strategy on urban expressway is proposed. Firstly, the total traffic demands in a long time was predicted in advance , and the upper bound of the future queue length was made; Secondly, the future traffic state was predicted and the harmonious restrictions for each ramp were built based on global optimum in order to supply a criterion for ramp rate. The simulation results show that the control system is of good dynamic performance. It harmonizes the benefits of every ramp and optimizes the whole performance of the urban expressway network.

Keywords: Electric vehicles and intelligent transportation., Neural networks, Sensor networks
Abstract: The increasing vehicle volume every year affects the prediction of the traffic system. The purpose of predicting traffic flow is to estimate the lost data caused by sensor malfunctions due to connection disruptions or ages. In estimating traffic flow, obtaining and explaining the historical data from the nearest segment sensor is necessary. The graph model can describe the spatial relationship between segments by connecting nodes with edges. Graph Neural Network (GNN) has been used as a learning method to predict the traffic flow in the segment sensor. GNN gets input in the form of spatial data built through a graph model, and the features are traffic density, average vehicle speed, and delay time on the road network. This paper shows that GNN's capability performs better in extracting spatial features and predicting the traffic flow by aggregating the features through connectivity nodes and edges

Keywords: Localization, navigation and mapping, Intelligent automation, Internet of things
Abstract: Indoor Positioning Systems (IPSs) can increase productivity in both office and industrial settings. They continue to become more accurate and robust as the advent of machine learning enables them to overcome the limitations of traditional positioning techniques. Despite this, the mainstream incorporation of IPS is currently hindered by significant infrastructure cost, especially for areas that cannot attain sufficient wireless coverage due to budget or environmental constraints. This paper therefore explores the use of machine learning for infrastructure-limited smartphone-based localization while adhering to practical constraints. The performance of the trained models was compared to that of conventional multilateration while also considering the effect of phone placement on positioning accuracy. Experimental results showed that the model trained under harsher conditions proved to be the most robust for both handheld and pocket mobile tests.