arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.21140cs.RO
收藏

用于接触约束感知阻抗控制的流形生成退火算法(结合强化学习先验)

Manifold Generative Annealing for Contact Constraint-aware Impedance Control with Reinforcement Learning Prior

Carnegie Mellon University(卡内基梅隆大学);Chinese Academy of Sciences(中国科学院)

Zhilin He, Guoquan Qi, Changliu Liu

AI总结:

该研究针对接触丰富机器人任务中接触条件变化导致现有方法失效的问题,提出流形生成退火(MGA)框架,结合无模型与基于模型方法优化运动-阻抗,在三类任务中提升了阻抗控制的安全成功率。

摘要:

接触丰富的机器人任务需要在不确定的交互动力学和物理约束下实现协调运动与阻抗控制。尽管近期基于学习策略的方法能提供有用的交互策略,但当接触条件与训练时不同时,这些方法可能失效。基于模型的生成方法在后退时域轨迹优化上展现出良好结果,但往往缺乏同时考虑约束几何和实际接触响应的结构化行为引导与优化。为此,我们提出流形生成退火(Manifold Generative Annealing,MGA),一种结合无模型与基于模型的生成框架,用于运动-阻抗优化。MGA首先将预训练的强化学习策略组织为结构化序列提案,保留任务特定的交互策略但不强制执行;随后通过基于模型的回滚评估这些提案与探索样本,以优化或单独选择执行方案。关键在于,感知实现的流形优化使优化库的更新与任务约束及局部可实现的物理响应对齐,让学习到的经验能在接触条件变化时指导在线适应。实验涵盖表面扫描、插销插入和人形机器人推搡任务,在标称条件和感知偏移条件下,阻抗控制的安全成功率均得到提升。

英文摘要:

Contact-rich robotic tasks require coordinated motion and impedance under uncertain interaction dynamics and physical constraints. While recent methods on learned policies provide useful interaction strategies, they may fail when contact conditions differ from those encountered during training. Model-based generative methods show promising receding-horizon trajectories optimization results, but often lack structured behavioral guidance and refinement that jointly accounts for constraint geometry and actual contact responses. To this end, we propose Manifold Generative Annealing (MGA), a joint model-free and model-based generative framework for motion--impedance optimization. MGA first organizes pretrained reinforcement learning policies into structured sequence proposals, retaining task-specific interaction strategies without committing to their execution. It then evaluates these proposals alongside exploratory samples through model-based rollouts for refinement or separate execution selection. Crucially, realization-aware manifold refinement aligns updates from the refinement bank with both task constraints and locally achievable physical responses, allowing learned experience to guide online adaptation under changing contact conditions. Experiments cover surface scanning, peg insertion, and humanoid pushing, with improved safety success rate of impedance control under nominal and sensing-shift conditions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑