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
  • [1] Model-free Data-driven Predictive Control Using Reinforcement Learning
    Sawant, Shambhuraj
    Reinhardt, Dirk
    Kordabad, Arash Bahari
    Gros, Sebastien
    [J]. 2023 62ND IEEE CONFERENCE ON DECISION AND CONTROL, CDC, 2023, : 4046 - 4052
  • [2] Data-Driven Robust Control Using Reinforcement Learning
    Ngo, Phuong D.
    Tejedor, Miguel
    Godtliebsen, Fred
    [J]. APPLIED SCIENCES-BASEL, 2022, 12 (04):
  • [3] Data-Driven Control of Hydraulic Manipulators by Reinforcement Learning
    Yao, Zhikai
    Xu, Fengyu
    Jiang, Guo-Ping
    Yao, Jianyong
    [J]. IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2024, 29 (04) : 2673 - 2684
  • [4] DATA-DRIVEN MODEL-FREE ITERATIVE LEARNING CONTROL USING REINFORCEMENT LEARNING
    Song, Bing
    Phan, Minh Q.
    Longman, Richard W.
    [J]. ASTRODYNAMICS 2018, PTS I-IV, 2019, 167 : 2579 - 2597
  • [5] Learning Based Stochastic Data-Driven Predictive Control
    Hiremath, Sandesh Athni
    Mishra, Vikas Kumar
    Bajcinca, Naim
    [J]. 2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC), 2022, : 1684 - 1691
  • [6] Data-driven Adaptive Iterative Learning Predictive Control
    Lv, Yunkai
    Chi, Ronghu
    [J]. 2017 6TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS (DDCLS), 2017, : 374 - 377
  • [7] Quantitative comparison of reinforcement learning and data-driven model predictive control for chemical and biological processes
    Oh, Tae Hoon
    [J]. COMPUTERS & CHEMICAL ENGINEERING, 2024, 181
  • [8] Data-Driven Economic NMPC Using Reinforcement Learning
    Gros, Sebastien
    Zanon, Mario
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2020, 65 (02) : 636 - 648
  • [9] Safe Data-Driven Model Predictive Control of Systems With Complex Dynamics
    Mitsioni, Ioanna
    Tajvar, Pouria
    Kragic, Danica
    Tumova, Jana
    Pek, Christian
    [J]. IEEE TRANSACTIONS ON ROBOTICS, 2023, 39 (04) : 3242 - 3258
  • [10] On the Performance of Data-Driven Reinforcement Learning for Commercial HVAC Control
    Faddel, Samy
    Tian, Guanyu
    Zhou, Qun
    Aburub, Haneen
    [J]. 2020 IEEE INDUSTRY APPLICATIONS SOCIETY ANNUAL MEETING, 2020,