Arm-Constrained Curriculum Learning for Loco-Manipulation of the Wheel-Legged Robot

Zifan Wang*1,2, Yufei Jia*2, Lu Shi*2, Haoyu Wang2, Haizhou Zhao2, Xueyang Li3,
Jinni Zhou1, Jun Ma1, Guyue Zhou2
1The Hong Kong University of Science and Technology (Guangzhou), 2Institute for AI Industry Research (AIR), Tsinghua University, 3DISCOVER Robotics
Interpolate start reference image.

Tasks accomplished by the proposed architecture.

Top-Left: door-opening-and-pulling task, Top-Right: fan-knob-twitching task, Bottom-Left: relay-baton-chasing task, Bottom-Right: door-opening-and-pushing task.

Abstract

Incorporating a robotic manipulator into a wheel- legged robot enhances its agility and expands its potential for practical applications. However, the presence of potential instability and uncertainties presents additional challenges for control objectives. In this paper, we introduce an arm- constrained curriculum learning architecture to tackle the issues introduced by adding the manipulator.

Firstly, we develop an arm-constrained reinforcement learning algorithm to ensure safety and stability in control performance.

Additionally, to address discrepancies in reward settings between the arm and the base, we propose a reward-aware curriculum learning method. The policy is first trained in Isaac gym and transferred to the physical robot to do dynamic grasping tasks, including the door-opening task, fan-twitching task and the relay-baton- picking and following task. The results demonstrate that our proposed approach effectively controls the arm-equipped wheel- legged robot to master dynamic grasping skills, allowing it to chase and catch a moving object while in motion.

Interpolate start reference image.

The overall illustration of the proposed framework. Top: two-phase learning procedure; Bottom: the detailed representation of the network.

Video

BibTeX

 
      @misc{wang2024armconstrained,
        title={Arm-Constrained Curriculum Learning for Loco-Manipulation of the Wheel-Legged Robot}, 
        author={Zifan Wang, Yufei Jia, Lu Shi, Haoyu Wang, Haizhou Zhao, Xueyang Li, Jinni Zhou, Jun Ma and Guyue Zhou},
        year={2024},
        eprint={2403.16535},
        archivePrefix={arXiv},
        primaryClass={cs.RO}
  }