让机器人在复杂交互中自适应切换控制模式，提升操作稳定性。
HMC: Learning Heterogeneous Meta-Control for Contact-Rich Loco-Manipulation
- 通过扭矩空间融合位置、阻抗和力位混合控制，实现平滑切换。
- 在真实人形机器人上完成擦桌、开抽屉等任务，性能提升超50%。
- 适合需要精准力控的复杂操作场景，如工业装配与服务机器人。
从真实世界机器人示范中学习，有望实现对复杂环境的有效交互。然而，交互动力学的复杂性和变异性常导致纯位置控制器在接触或负载变化时表现不佳。为此，我们提出一种用于运动-操作任务的异质元控制（HMC）框架，可自适应地组合位置、阻抗和力-位混合等多种控制模式。首先引入一个名为 HMC-Controller 的接口，在扭矩空间中连续融合不同控制策略的动作，支持远程操控与策略部署。其次，为学习鲁棒的力感知策略，我们提出 HMC-Policy，将多种控制器统一为异质架构，采用专家混合式路由机制，结合大规模仅位置数据与精细力感知示范数据进行训练。在真实人形机器人上的实验表明，该方法在擦桌、开抽屉等挑战性任务中相比基线性能提升超过50%，验证了HMC的有效性。
原文摘要 · Abstract (English)
Learning from real-world robot demonstrations holds promise for interacting with complex real-world environments. However, the complexity and variability of interaction dynamics often cause purely positional controllers to struggle with contacts or varying payloads. To address this, we propose a Heterogeneous Meta-Control (HMC) framework for Loco-Manipulation that adaptively stitches multiple control modalities: position, impedance, and hybrid force-position. We first introduce an interface, HMC-Controller, for blending actions from different control profiles continuously in the torque space. HMC-Controller facilitates both teleoperation and policy deployment. Then, to learn a robust force-aware policy, we propose HMC-Policy to unify different controllers into a heterogeneous architecture. We adopt a mixture-of-experts style routing to learn from large-scale position-only data and fine-grained force-aware demonstrations. Experiments on a real humanoid robot show over 50% relative improvement vs. baselines on challenging tasks such as compliant table wiping and drawer opening, demonstrating the efficacy of HMC.
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。