首页|Robust reinforcement learning with UUB guarantee for safe motion control of autonomous robots

Robust reinforcement learning with UUB guarantee for safe motion control of autonomous robots

扫码查看
原文链接
  • 万方数据
  • 维普
This paper addresses the issue of safety in reinforcement learning(RL)with disturbances and its application in the safety-constrained motion control of autonomous robots.To tackle this problem,a robust Lyapunov value function(rLVF)is proposed.The rLVF is obtained by introducing a data-based LVF under the worst-case disturbance of the observed state.Using the rLVF,a uniformly ultimate boundedness criterion is established.This criterion is desired to ensure that the cost function,which serves as a safety criterion,ultimately converges to a range via the policy to be designed.Moreover,to mitigate the drastic variation of the rLVF caused by differences in states,a smoothing regularization of the rLVF is introduced.To train policies with safety guarantees under the worst disturbances of the observed states,an off-policy robust RL algorithm is proposed.The proposed algorithm is applied to motion control tasks of an autonomous vehicle and a cartpole,which involve external disturbances and variations of the model parameters,respectively.The experimental results demonstrate the effectiveness of the theoretical findings and the advantages of the proposed algorithm in terms of robustness and safety.

motion controlreinforcement learningrobustnessstability

ZHANG RuiXian、HAN YiNing、SU Man、LIN ZeFeng、LI HaoWei、ZHANG LiXian

展开 >

School of Astronautics,Harbin Institute of Technology,Harbin 150001,China

School of Management,Harbin Institute of Technology,Harbin 150001,China

Beijing Institute of Tracking and Telecommunication Technology,Beijing 100094,China

National Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaFundamental Research Funds for the Central Universities,ChinaFundamental Research Funds for the Central Universities,ChinaFundamental Research Funds for the Central Universities,ChinaState Key Laboratory of Robotics and System(HIT)Heilongjiang Touyan Team

6222530512072088HIT.BRET.2022004HIT.OCEF.2022047HIT.DZIJ.2023049JCKY2022603C016

2024

10.1007/s11431-023-2435-3

中国科学:技术科学(英文版)
中国科学院

中国科学:技术科学(英文版)

CSTPCDEI
影响因子：1.056
ISSN：1674-7321
年,卷(期)：2024.67(1)
  • 31