Design and Experimental Validation of Deep Reinforcement Learning-Based Fast Trajectory Planning and Control for Mobile Robot in Unknown Environment

• Published in: IEEE transaction on neural networks and learning systems Vol. 35; no. 4; pp. 1 - 15
• Main Authors: Chai, Runqi, Niu, Hanlin, Carrasco, Joaquin, Arvin, Farshad, Yin, Hujun, Lennox, Barry
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Approximation; Artificial neural networks; Collision avoidance; Computer simulation; Control algorithms; Control theory; Deep learning; Deep reinforcement learning (DRL); Exploration; Machine learning; Maneuvers; mobile robot; Mobile robots; motion control; Motion planning; Movement; Neural networks; Noise measurement; noisy prioritized experience replay (PER); optimal motion planning; Planning; recurrent neural network; Reinforcement; Robot control; Robot dynamics; Robot sensing systems; Robots; Tracking; Training; Trajectory; Trajectory control; Trajectory optimization; Trajectory planning; unexpected obstacles; Unknown environments; Waypoints

This article is concerned with the problem of planning optimal maneuver trajectories and guiding the mobile robot toward target positions in uncertain environments for exploration purposes. A hierarchical deep learning-based control framework is proposed which consists of an upper level motion plann...