A Conformal Mapping-based Framework for Robot-to-Robot and Sim-to-Real Transfer Learning

被引:1
|
作者
Gao, Shijie [1 ,2 ]
Bezzo, Nicola [1 ,2 ]
机构
[1] Univ Virginia, Dept Elect & Comp Engn, Charlottesville, VA 22904 USA
[2] Univ Virginia, Link Lab, Charlottesville, VA 22904 USA
关键词
ALGORITHM;
D O I
10.1109/IROS51168.2021.9636682
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper presents a novel method for transferring motion planning and control policies between a teacher and a learner robot. With this work, we propose to reduce the sim-to-real gap, transfer knowledge designed for a specific system into a different robot, and compensate for system aging and failures. To solve this problem we introduce a Schwarz-Christoffel mapping-based method to geometrically stretch and fit the control inputs from the teacher into the learner command space. We also propose a method based on primitive motion generation to create motion plans and control inputs compatible with the learner's capabilities. Our approach is validated with simulations and experiments with different robotic systems navigating occluding environments.
引用
收藏
页码:1289 / 1295
页数:7
相关论文
共 50 条
  • [41] Real-Sim-Real Transfer for Real-World Robot Control Policy Learning with Deep Reinforcement Learning
    Liu, Naijun
    Cai, Yinghao
    Lu, Tao
    Wang, Rui
    Wang, Shuo
    APPLIED SCIENCES-BASEL, 2020, 10 (05):
  • [42] Sim-Real Mapping of an Image-Based Robot Arm Controller Using Deep Reinforcement Learning
    Sasaki, Minoru
    Muguro, Joseph
    Kitano, Fumiya
    Njeri, Waweru
    Matsushita, Kojiro
    APPLIED SCIENCES-BASEL, 2022, 12 (20):
  • [43] Efficient Jacobian-Based Inverse Kinematics With Sim-to-Real Transfer of Soft Robots by Learning
    Fang, Guoxin
    Tian, Yingjun
    Yang, Zhi-Xin
    Geraedts, Jo M. P.
    Wang, Charlie C. L.
    IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2022, 27 (06) : 5296 - 5306
  • [44] A Domain Data Pattern Randomization based Deep Reinforcement Learning method for Sim-to-Real transfer
    Gong, Peng
    Shi, Dianxi
    Xue, Chao
    Chen, Xucan
    2021 5TH INTERNATIONAL CONFERENCE ON INNOVATION IN ARTIFICIAL INTELLIGENCE (ICIAI 2021), 2021, : 1 - 7
  • [45] Human-Guided Reinforcement Learning With Sim-to-Real Transfer for Autonomous Navigation
    Wu, Jingda
    Zhou, Yanxin
    Yang, Haohan
    Huang, Zhiyu
    Lv, Chen
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (12) : 14745 - 14759
  • [46] A Survey of Sim-to-Real Transfer Techniques Applied to Reinforcement Learning for Bioinspired Robots
    Zhu, Wei
    Guo, Xian
    Owaki, Dai
    Kutsuzawa, Kyo
    Hayashibe, Mitsuhiro
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (07) : 3444 - 3459
  • [47] Zero-shot sim-to-real transfer of reinforcement learning framework for robotics manipulation with demonstration and force feedback
    Chen, Yuanpei
    Zeng, Chao
    Wang, Zhiping
    Lu, Peng
    Yang, Chenguang
    ROBOTICA, 2023, 41 (03) : 1015 - 1024
  • [48] NeuronsGym: A Hybrid Framework and Benchmark for Robot Navigation With Sim2Real Policy Learning
    Li, Haoran
    Hu, Guangzheng
    Liu, Shasha
    Ma, Mingjun
    Chen, Yaran
    Zhao, Dongbin
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2024,
  • [49] Sim-to-Real Transfer Reinforcement Learning for Position Control of Pneumatic Continuum Manipulator
    Cheng, Qiang
    Liu, Hongshuai
    Gao, Xifeng
    Zhang, Ying
    Hao, Lina
    IEEE ACCESS, 2023, 11 : 126110 - 126118
  • [50] Sim-to-real transfer of active suspension control using deep reinforcement learning
    Wiberg, Viktor
    Wallin, Erik
    Falldin, Arvid
    Semberg, Tobias
    Rossander, Morgan
    Wadbro, Eddie
    Servin, Martin
    ROBOTICS AND AUTONOMOUS SYSTEMS, 2024, 179