用生成式动作采样动态调节机器人柔顺性，提升人机协作稳定性。
Generative Action-Chunk Sampling for Adaptive Stiffness Control in Physical Human-Robot Collaboration
- 基于视觉与力矩输入，生成多个未来动作片段以评估不确定性。
- 动作片段差异越大，机器人越柔顺；差异小则提供稳固辅助，成功率95%。
- 适合需要自适应交互的工业协作场景，如搬运、装配等任务。
物理人机协作中，机器人需在人类意图明确时提供协助，而在多种未来动作可能时保持柔顺。本文提出一种基于生成式动作片段采样的自适应刚度控制框架。该策略在RGB图像和外部关节力矩估计条件下，从观测条件先验中采样多个未来动作片段。通过分析采样动作间的差异，实时调整关节刚度与阻尼：差异越大，机器人越柔顺以支持人类引导；差异越小，则提供更稳固的协助。在包含四个可能方向的真实协作搬运任务中，该方法平均成功率达0.95，优于固定刚度方案（0.83）和确定性基线（0.69）。当接近方向判断时刻，动作差异上升，控制器相应降低刚度。结果表明，生成式策略采样动作的差异可作为在线控制信号，有效平衡人机交互中的协助与柔顺性。
原文摘要 · Abstract (English)
Physical human-robot collaboration requires a robot to provide assistance when human intention is clear while remaining compliant when several future motions are plausible. We present an adaptive stiffness framework based on generative action-chunk sampling. Conditioned on an RGB image and external joint-torque estimates, the policy samples multiple future action chunks from an observation-conditioned prior. Variation among the sampled action chunks is used to continuously adapt joint stiffness and damping. Greater variation makes the robot more compliant to facilitate human guidance, whereas lower variation provides firmer assistance. In a real-world collaborative transport task with four possible directions, the proposed method achieved an average success rate of 0.95, compared with 0.83 for a fixed-stiffness ablation and 0.69 for a deterministic baseline. Near direction determination, variation among the sampled action chunks increased and the controller accordingly reduced stiffness. These results suggest that variation among actions sampled by a generative policy can serve as an online control signal for balancing assistance and compliance in physical human-robot interaction.
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。