让机器人学会利用复杂机械结构，提升真实行走表现。
Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation
- 基于真实机械结构建模，用GPU加速仿真闭环运动链。
- 在真实机器人上零样本部署，比传统控制方法更稳定。
- 适合研究复杂人形机器人运动控制的开发者。
强化学习（RL）推动了人形机器人行走的进步，但多数框架未考虑并联驱动机构中嵌入的机械智能，主要受限于模拟器对闭链结构的支持不足。这种忽略会导致运动建模失准和策略性能下降，尤其在高复杂度驱动系统中更为明显。本文提出三种并联机构（差动滑轮、五杆连杆、四杆连杆）的通用建模与仿真方法，并通过端到端课程强化学习框架，为一个儿童尺寸的人形机器人BRUCE训练出具备并联机制感知能力的策略。不同于依赖串行近似的传统方法，我们采用GPU加速的MuJoCo（MJX）原生模拟所有闭链约束，完整保留硬件的非线性力学特性。在基准测试中，该方法相较模型预测控制器（MPC）展现出更强的表面泛化能力和真实世界零样本部署表现。本工作凸显了在端到端学习流程中完整仿真并联机构的计算优势与性能收益。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。