Safe Reinforcement Learning for Model-Reference Trajectory Tracking of Uncertain Autonomous Vehicles With Model-Based Acceleration
Applying reinforcement learning (RL) algorithms to control systems design remains a challenging task due to the potential unsafe exploration and the low sample efficiency. In this paper, we propose a novel safe model-based RL algorithm to solve the collision-free model-reference trajectory tracking problem of uncertain autonomous vehicles (AVs). Firstly, a new type of robust control barrier function (CBF) condition for collision-avoidance is derived for the uncertain AVs by incorporating the estimation of the system uncertainty with Gaussian process (GP) regression. Then, a robust CBF-based RL control structure is proposed, where the nominal control input is composed of the RL policy and a model-based reference control policy. The actual control input obtained from the quadratic programming problem can satisfy the constraints of collision-avoidance, input saturation and velocity boundedness simultaneously with a relatively high probability. Finally, within this control structure, a Dyna-style safe model-based RL algorithm is proposed, where the safe exploration is achieved through executing the robust CBF-based actions and the sample efficiency is improved by leveraging the GP models. The superior learning performance of the proposed RL control structure is demonstrated through simulation experiments.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/23798858
-
Supplemental Notes:
- Copyright © 2023, IEEE.
-
Authors:
- Hu, Yifan
- Fu, Junjie
- Wen, Guanghui
- Publication Date: 2023-3
Language
- English
Media Info
- Media Type: Web
- Features: Figures; References;
- Pagination: pp 2332-2344
-
Serial:
- IEEE Transactions on Intelligent Vehicles
- Volume: 8
- Issue Number: 3
- Publisher: Institute of Electrical and Electronics Engineers (IEEE)
- ISSN: 2379-8858
- Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7274857
Subject/Index Terms
- TRT Terms: Crash avoidance systems; Machine learning; Safety; Trajectory control; Uncertainty
- Subject Areas: Data and Information Technology; Highways; Safety and Human Factors; Vehicles and Equipment;
Filing Info
- Accession Number: 01900085
- Record Type: Publication
- Files: TRIS
- Created Date: Nov 20 2023 9:12AM