A Contact-Safe Reinforcement Learning Framework for Contact-Rich Robot Manipulation

被引:1
|
作者
Zhu, Xiang [1 ]
Kang, Shucheng [1 ]
Chen, Jianyu [1 ,2 ]
机构
[1] Tsinghua Univ, Inst Interdisciplinary Informat Sci, Beijing, Peoples R China
[2] Shanghai Qizhi Insitute, Shanghai, Peoples R China
关键词
SPACE;
D O I
10.1109/IROS47612.2022.9981185
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Reinforcement learning shows great potential to solve complex contact-rich robot manipulation tasks. However, the safety of using RL in the real world is a crucial problem, since unexpected dangerous collisions might happen when the RL policy is imperfect during training or in unseen scenarios. In this paper, we propose a contact-safe reinforcement learning framework for contact-rich robot manipulation, which maintains safety in both the task space and joint space. When the RL policy causes unexpected collisions between the robot arm and the environment, our framework is able to immediately detect the collision and ensure the contact force to be small. Furthermore, the end-effector is enforced to perform contact-rich tasks compliantly, while keeping robust to external disturbances. We train the RL policy in simulation and transfer it to the real robot. Real world experiments on robot wiping tasks show that our method is able to keep the contact force small both in task space and joint space even when the policy is under unseen scenario with unexpected collision, while rejecting the disturbances on the main task.
引用
收藏
页码:2476 / 2482
页数:7
相关论文
共 50 条
  • [1] Stability-Guaranteed Reinforcement Learning for Contact-Rich Manipulation
    Khader, Shahbaz Abdul
    Yin, Hang
    Falco, Pietro
    Kragic, Danica
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (01) : 1 - 8
  • [2] A review on reinforcement learning for contact-rich robotic manipulation tasks
    Elguea-Aguinaco, Inigo
    Serrano-Munoz, Antonio
    Chrysostomou, Dimitrios
    Inziarte-Hidalgo, Ibai
    Bogh, Simon
    Arana-Arexolaleiba, Nestor
    ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, 2023, 81
  • [3] Safe Data-Driven Contact-Rich Manipulation
    Mitsioni, Ioanna
    Tajvar, Pomia
    Kragic, Danica
    Tumova, Jana
    Pek, Christian
    PROCEEDINGS OF THE 2020 IEEE-RAS 20TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS 2020), 2021, : 120 - 127
  • [4] RMPs for Safe Impedance Control in Contact-Rich Manipulation
    Shaw, Seiji
    Abbatematteo, Ben
    Konidaris, George
    2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022), 2022, : 2707 - 2713
  • [5] Variable Impedance Skill Learning for Contact-Rich Manipulation
    Yang, Quantao
    Durr, Alexander
    Topp, Elin Anna
    Stork, Johannes A.
    Stoyanov, Todor
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (03): : 8391 - 8398
  • [6] Learning Dense Rewards for Contact-Rich Manipulation Tasks
    Wu, Zheng
    Lian, Wenzhao
    Unhelkar, Vaibhav
    Tomizuka, Masayoshi
    Schaal, Stefan
    2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 6214 - 6221
  • [7] State Estimation in Contact-Rich Manipulation
    Wirnshofer, Florian
    Schmidt, Philipp S.
    Meister, Philine
    von Wichert, Georg
    Burgard, Wolfram
    2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2019, : 3790 - 3796
  • [8] A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies
    Stepputtis, Simon
    Bandari, Maryam
    Schaal, Stefan
    Ben Amor, Heni
    2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 11810 - 11817
  • [9] Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty
    Ranjbar, Alireza
    Vien, Ngo Anh
    Ziesche, Hanna
    Boedecker, Joschka
    Neumann, Gerhard
    2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2021, : 2383 - 2390
  • [10] Learning Contact-Rich Manipulation Skills with Guided Policy Search
    Levine, Sergey
    Wagener, Nolan
    Abbeel, Pieter
    2015 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2015, : 156 - 163