Decentralized Motor Skill Learning for Complex Robotic Systems

2023-06-30 · Yanjiang Guo, Zheyuan Jiang, Yen-Jen Wang, Jingyue Gao, Jianyu Chen

Reinforcement learning (RL) has achieved remarkable success in complex robotic systems (eg. quadruped locomotion). In previous works, the RL-based controller was typically implemented as a single neural network with concatenated observation input. However, the corresponding learned policy is highly task-specific. Since all motors are controlled in a centralized way, out-of-distribution local observations can impact global motors through the single coupled neural network policy. In contrast, animals and humans can control their limbs separately. Inspired by this biological phenomenon, we propose a Decentralized motor skill (DEMOS) learning algorithm to automatically discover motor groups that can be decoupled from each other while preserving essential connections and then learn a decentralized motor control policy. Our method improves the robustness and generalization of the policy without sacrificing performance. Experiments on quadruped and humanoid robots demonstrate that the learned policy is robust against local motor malfunctions and can be transferred to new tasks.

📄 PDF Abstract BibTeX arXiv:2306.17411

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Control

2023-11-14 · Pei Zhang, Zhaobo Hua, Jinliang Ding

The development of intelligent robots requires control policies that can handle dynamic environments and evolving tasks. Pre-training reinforcement learning has emerged as an effective approach to address these demands b…

Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning

Policy Search for Motor Primitives in Robotics

2008-12-01 · NeurIPS 2008 12 · Jens Kober, Jan R. Peters

Many motor skills in humanoid robotics can be learned using parametrized motor primitives as done in imitation learning. However, most interesting motor learning problems are high-dimensional reinforcement learning probl…

Imitation Learning Policy Gradient Methods reinforcement-learning Reinforcement Learning+1

MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control

2022-05-26 · Vittorio Caggiano, Huawei Wang, Guillaume Durandau, Massimo Sartori 외

Embodied agents in continuous control domains have had limited exposure to tasks allowing to explore musculoskeletal properties that enable agile and nimble behaviors in biological beings. The sophistication behind neuro…

continuous-control Continuous Control

Mimicking the Maestro: Exploring the Efficacy of a Virtual AI Teacher in Fine Motor Skill Acquisition

2023-10-16 · Hadar Mulian, Segev Shlomov, Lior Limonad, Alessia Noccaro 외

Motor skills, especially fine motor skills like handwriting, play an essential role in academic pursuits and everyday life. Traditional methods to teach these skills, although effective, can be time-consuming and inconsi…

Imitation Learning reinforcement-learning Reinforcement Learning

Exploring AI-enhanced Shared Control for an Assistive Robotic Arm

2023-06-23 · Max Pascher, Kirill Kronhardt, Jan Freienstein, Jens Gerken

Assistive technologies and in particular assistive robotic arms have the potential to enable people with motor impairments to live a self-determined life. More and more of these systems have become available for end user…