Safe Reinforcement Learning using Data-Driven Predictive Control

被引:1
|
作者
Selim, Mahmoud [1 ]
Alanwar, Amr [2 ]
El-Kharashi, M. Watheq [1 ]
Abbas, Hazem M. [1 ]
Johansson, Karl H. [3 ]
机构
[1] Ain Shams Univ, Cairo, Egypt
[2] Jacobs Univ, Bremen, Germany
[3] KTH Royal Inst Technol, Stockholm, Sweden
关键词
Reinforcement learning; robot safety; task and motion planning;
D O I
10.1109/ICCSPA55860.2022.10018994
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical systems still needs to be well justified due to the exploration nature of many RL algorithms, especially when the model of the robot and the environment are unknown. To address this challenge, we propose a data-driven safety layer that acts as a filter for unsafe actions. The safety layer uses a data-driven predictive controller to enforce safety guarantees for RL policies during training and after deployment. The RL agent proposes an action that is verified by computing the data-driven reachability analysis. If there is an intersection between the reachable set of the robot using the proposed action, we call the data-driven predictive controller to find the closest safe action to the proposed unsafe action. The safety layer penalizes the RL agent if the proposed action is unsafe and replaces it with the closest safe one. In the simulation, we show that our method outperforms state-of-the-art safe RL methods on the robotics navigation problem for a Turtlebot 3 in Gazebo and a quadrotor in Unreal Engine 4 (UE4).
引用
收藏
页数:6
相关论文
共 50 条
  • [31] Data-driven torque and pitch control of wind turbines via reinforcement learning
    Xie, Jingjie
    Dong, Hongyang
    Zhao, Xiaowei
    [J]. RENEWABLE ENERGY, 2023, 215
  • [32] Data-driven constrained reinforcement learning for optimal control of a multistage evaporation process
    Yao, Yao
    Ding, Jinliang
    Zhao, Chunhui
    Wang, Yonggang
    Chai, Tianyou
    [J]. CONTROL ENGINEERING PRACTICE, 2022, 129
  • [33] Data-Driven Wind Farm Control via Multiplayer Deep Reinforcement Learning
    Dong, Hongyang
    Zhao, Xiaowei
    [J]. IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2023, 31 (03) : 1468 - 1475
  • [34] Reinforcement Learning based Data-driven Optimal Control Strategy for Systems with Disturbance
    Fan, Zhong-Xin
    Li, Shihua
    Liu, Rongjie
    [J]. 2023 IEEE 12TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE, DDCLS, 2023, : 567 - 572
  • [35] Data-driven predictive control for networked control systems
    Xia, Yuanqing
    Xie, Wen
    Liu, Bo
    Wang, Xiaoyun
    [J]. INFORMATION SCIENCES, 2013, 235 : 45 - 54
  • [36] Learning for Depth Control of a Robotic Penguin: A Data-Driven Model Predictive Control Approach
    Pan, Jie
    Zhang, Pengfei
    Wang, Jian
    Liu, Mingxin
    Yu, Junzhi
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2023, 70 (11) : 11422 - 11432
  • [37] Learning Model Predictive Control for Iterative Tasks. A Data-Driven Control Framework
    Rosolia, Ugo
    Borrelli, Francesco
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2018, 63 (07) : 1883 - 1896
  • [38] Data-Driven Lateral Fault-tolerance Control of Autonomous Vehicle System Using Reinforcement Learning
    Li, Yan
    Zhang, Hao
    Wang, Zhuping
    [J]. 2020 IEEE 16TH INTERNATIONAL CONFERENCE ON CONTROL & AUTOMATION (ICCA), 2020, : 1410 - 1415
  • [39] Data-Driven Predictive Control for Autonomous Systems
    Rosolia, Ugo
    Zhang, Xiaojing
    Borrelli, Francesco
    [J]. ANNUAL REVIEW OF CONTROL, ROBOTICS, AND AUTONOMOUS SYSTEMS, VOL 1, 2018, 1 : 259 - 286
  • [40] A Data-Driven Multi-Agent Autonomous Voltage Control Framework Using Deep Reinforcement Learning
    Wang, Shengyi
    Duan, Jiajun
    Shi, Di
    Xu, Chunlei
    Li, Haifeng
    Diao, Ruisheng
    Wang, Zhiwei
    [J]. IEEE TRANSACTIONS ON POWER SYSTEMS, 2020, 35 (06) : 4644 - 4654