用被动肢体设计让双足机器人更高效稳定地行走跑步
Model-Based Reinforcement Learning Exploits Passive Body Dynamics for High-Performance Biped Robot Locomotion
- 引入弹簧等被动元件构建动力学模型
- 利用极限环实现节能且鲁棒的步态，训练收敛慢但性能高
- 适合研究具身智能与仿人机器人控制的学者
身体具身性是近期机器学习领域的重要概念。本研究聚焦双足机器人的被动身体特性，通过基于模型的深度强化学习实现行走与跑步运动。我们在仿真环境中构建了两种模型：一种包含被动元件（如弹簧），另一种为常规类人模型，无被动元件。带有被动元件的模型训练受系统吸引子影响显著，虽然轨迹快速收敛至极限环，但获得高奖励所需时间较长。然而，得益于吸引子驱动的学习机制，所获步态具备鲁棒性和能效优势。结果表明，通过身体与地面动态交互产生的稳定极限环，配备被动元件的机器人能够高效获取高性能运动能力。该研究凸显了在未来的具身人工智能中引入被动属性的重要性。
原文摘要 · Abstract (English)
Embodiment is a significant keyword in recent machine learning fields. This study focused on the passive nature of the body of a biped robot to generate walking and running locomotion using model-based deep reinforcement learning. We constructed two models in a simulator, one with passive elements (e.g., springs) and the other, which is similar to general humanoids, without passive elements. The training of the model with passive elements was highly affected by the attractor of the system. This lead that although the trajectories quickly converged to limit cycles, it took a long time to obtain large rewards. However, thanks to the attractor-driven learning, the acquired locomotion was robust and energy-efficient. The results revealed that robots with passive elements could efficiently acquire high-performance locomotion by utilizing stable limit cycles generated through dynamic interaction between the body and ground. This study demonstrates the importance of implementing passive properties in the body for future embodied AI.
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。