Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tanaka, Yusuke, Zhu, Alvin, Wang, Quanyou, Liu, Yeting, Hong, Dennis
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911242073931776
author Tanaka, Yusuke
Zhu, Alvin
Wang, Quanyou
Liu, Yeting
Hong, Dennis
author_facet Tanaka, Yusuke
Zhu, Alvin
Wang, Quanyou
Liu, Yeting
Hong, Dennis
contents Reinforcement learning (RL) has enabled advances in humanoid robot locomotion, yet most learning frameworks do not account for mechanical intelligence embedded in parallel actuation mechanisms due to limitations in simulator support for closed kinematic chains. This omission can lead to inaccurate motion modeling and suboptimal policies, particularly for robots with high actuation complexity. This paper presents general formulations and simulation methods for three types of parallel mechanisms: a differential pulley, a five-bar linkage, and a four-bar linkage, and trains a parallel-mechanism aware policy through an end-to-end curriculum RL framework for BRUCE, a kid-sized humanoid robot. Unlike prior approaches that rely on simplified serial approximations, we simulate all closed-chain constraints natively using GPU-accelerated MuJoCo (MJX), preserving the hardware's mechanical nonlinear properties during training. We benchmark our RL approach against a model predictive controller (MPC), demonstrating better surface generalization and performance in real-world zero-shot deployment. This work highlights the computational approaches and performance benefits of fully simulating parallel mechanisms in end-to-end learning pipelines for legged humanoids. Project codes with parallel mechanisms: https://github.com/alvister88/og_bruce
format Preprint
id arxiv_https___arxiv_org_abs_2507_00273
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation
Tanaka, Yusuke
Zhu, Alvin
Wang, Quanyou
Liu, Yeting
Hong, Dennis
Robotics
Reinforcement learning (RL) has enabled advances in humanoid robot locomotion, yet most learning frameworks do not account for mechanical intelligence embedded in parallel actuation mechanisms due to limitations in simulator support for closed kinematic chains. This omission can lead to inaccurate motion modeling and suboptimal policies, particularly for robots with high actuation complexity. This paper presents general formulations and simulation methods for three types of parallel mechanisms: a differential pulley, a five-bar linkage, and a four-bar linkage, and trains a parallel-mechanism aware policy through an end-to-end curriculum RL framework for BRUCE, a kid-sized humanoid robot. Unlike prior approaches that rely on simplified serial approximations, we simulate all closed-chain constraints natively using GPU-accelerated MuJoCo (MJX), preserving the hardware's mechanical nonlinear properties during training. We benchmark our RL approach against a model predictive controller (MPC), demonstrating better surface generalization and performance in real-world zero-shot deployment. This work highlights the computational approaches and performance benefits of fully simulating parallel mechanisms in end-to-end learning pipelines for legged humanoids. Project codes with parallel mechanisms: https://github.com/alvister88/og_bruce
title Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation
topic Robotics
url https://arxiv.org/abs/2507.00273