Learning to Hop for a Single-Legged Robot with Parallel Mechanism

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Hongbo, Chu, Xiangyu, Chen, Yanlin, Tang, Yunxi, Yue, Linzhu, Liu, Yun-Hui, Au, Kwok Wai Samuel
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912197137924096
author Zhang, Hongbo
Chu, Xiangyu
Chen, Yanlin
Tang, Yunxi
Yue, Linzhu
Liu, Yun-Hui
Au, Kwok Wai Samuel
author_facet Zhang, Hongbo
Chu, Xiangyu
Chen, Yanlin
Tang, Yunxi
Yue, Linzhu
Liu, Yun-Hui
Au, Kwok Wai Samuel
contents This work presents the application of reinforcement learning to improve the performance of a highly dynamic hopping system with a parallel mechanism. Unlike serial mechanisms, parallel mechanisms can not be accurately simulated due to the complexity of their kinematic constraints and closed-loop structures. Besides, learning to hop suffers from prolonged aerial phase and the sparse nature of the rewards. To address them, we propose a learning framework to encode long-history feedback to account for the under-actuation brought by the prolonged aerial phase. In the proposed framework, we also introduce a simplified serial configuration for the parallel design to avoid directly simulating parallel structure during the training. A torque-level conversion is designed to deal with the parallel-serial conversion to handle the sim-to-real issue. Simulation and hardware experiments have been conducted to validate this framework.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11945
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Hop for a Single-Legged Robot with Parallel Mechanism
Zhang, Hongbo
Chu, Xiangyu
Chen, Yanlin
Tang, Yunxi
Yue, Linzhu
Liu, Yun-Hui
Au, Kwok Wai Samuel
Robotics
This work presents the application of reinforcement learning to improve the performance of a highly dynamic hopping system with a parallel mechanism. Unlike serial mechanisms, parallel mechanisms can not be accurately simulated due to the complexity of their kinematic constraints and closed-loop structures. Besides, learning to hop suffers from prolonged aerial phase and the sparse nature of the rewards. To address them, we propose a learning framework to encode long-history feedback to account for the under-actuation brought by the prolonged aerial phase. In the proposed framework, we also introduce a simplified serial configuration for the parallel design to avoid directly simulating parallel structure during the training. A torque-level conversion is designed to deal with the parallel-serial conversion to handle the sim-to-real issue. Simulation and hardware experiments have been conducted to validate this framework.
title Learning to Hop for a Single-Legged Robot with Parallel Mechanism
topic Robotics
url https://arxiv.org/abs/2501.11945