Saved in:
Bibliographic Details
Main Authors: Zhang, Xinglong, Peng, Yaoqian, Luo, Biao, Pan, Wei, Xu, Xin, Xie, Haibin
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2112.11217
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914664753922048
author Zhang, Xinglong
Peng, Yaoqian
Luo, Biao
Pan, Wei
Xu, Xin
Xie, Haibin
author_facet Zhang, Xinglong
Peng, Yaoqian
Luo, Biao
Pan, Wei
Xu, Xin
Xie, Haibin
contents Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence guarantees. Also, few works have addressed the safe RL algorithm design under time-varying safety constraints. This paper proposes a safe RL algorithm for optimal control of nonlinear systems with time-varying state and control constraints. In the proposed approach, we construct a novel barrier force-based control policy structure to guarantee control safety. A multi-step policy evaluation mechanism is proposed to predict the policy's safety risk under time-varying safety constraints and guide the policy to update safely. Theoretical results on stability and robustness are proven. Also, the convergence of the actor-critic implementation is analyzed. The performance of the proposed algorithm outperforms several state-of-the-art RL algorithms in the simulated Safety Gym environment. Furthermore, the approach is applied to the integrated path following and collision avoidance problem for two real-world intelligent vehicles. A differential-drive vehicle and an Ackermann-drive one are used to verify offline deployment and online learning performance, respectively. Our approach shows an impressive sim-to-real transfer capability and a satisfactory online control performance in the experiment.
format Preprint
id arxiv_https___arxiv_org_abs_2112_11217
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles
Zhang, Xinglong
Peng, Yaoqian
Luo, Biao
Pan, Wei
Xu, Xin
Xie, Haibin
Machine Learning
Artificial Intelligence
Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence guarantees. Also, few works have addressed the safe RL algorithm design under time-varying safety constraints. This paper proposes a safe RL algorithm for optimal control of nonlinear systems with time-varying state and control constraints. In the proposed approach, we construct a novel barrier force-based control policy structure to guarantee control safety. A multi-step policy evaluation mechanism is proposed to predict the policy's safety risk under time-varying safety constraints and guide the policy to update safely. Theoretical results on stability and robustness are proven. Also, the convergence of the actor-critic implementation is analyzed. The performance of the proposed algorithm outperforms several state-of-the-art RL algorithms in the simulated Safety Gym environment. Furthermore, the approach is applied to the integrated path following and collision avoidance problem for two real-world intelligent vehicles. A differential-drive vehicle and an Ackermann-drive one are used to verify offline deployment and online learning performance, respectively. Our approach shows an impressive sim-to-real transfer capability and a satisfactory online control performance in the experiment.
title Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2112.11217