Ramezani, Mahya (University of Luxembourg), Habibi, Hamed (University of Luxembourg), Sanchez-Lopez, Jose-Luis (University of Luxembourg), Voos, Holger (University of Luxembourg)

UAV Path Planning Employing MPC-Reinforcement Learning Method Considering Collision Avoidance

Scheduled for presentation during the Regular Session "Path Planning III" (ThA3), Thursday, June 8, 2023, 09:20−09:40, Room 464

2023 International Conference on Unmanned Aircraft Systems (ICUAS), June 6-9, 2023, Lazarski University, Warsaw, Poland

This information is tentative and subject to change. Compiled on April 19, 2024

Abstract

In this paper, we tackle the problem of Unmanned Aerial (UAV) path planning in complex and uncertain environments by designing a Model Predictive Control (MPC), based on a Long-Short-Term Memory (LSTM) network integrated into the Deep Deterministic Policy Gradient algorithm. In the proposed solution, LSTM-MPC operates as a deterministic policy within the DDPG network, and it leverages a predicting pool to store predicted future states and actions for improved robustness and efficiency. The use of the predicting pool also enables the initialization of the critic network, leading to improved convergence speed and reduced failure rate compared to traditional reinforcement learning and deep reinforcement learning methods. The effectiveness of the proposed solution is evaluated by numerical simulations.