发表机构
Saitama University（埼玉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出阻抗克隆方法，通过模仿刚度和平衡点参数而非轨迹，实现接触丰富操作对表面几何变化的鲁棒性，在擦拭和拾放任务中优于轨迹基线和固定阻抗基线。
AI 中文摘要
接触丰富的操作要求机器人调节与表面的接触力，而表面的几何形状可能偏离训练条件，产生不可预测的变化。基于轨迹的模仿学习通过重现可观测输出来进行学习，在这种偏移下会失效。我们提出阻抗克隆方法，该方法转而模仿生成运动的生物力学先验——即刚度和平衡点——从而被动地吸收接触不确定性。由于这些参数编码的是意图而非结果，它们能够泛化到轨迹重现无法泛化的表面几何形状。我们通过粒子滤波器从双边遥操作演示中提取这些参数，无需力/力矩传感器，并在两个CRANE-X7机械臂上评估该框架。在关节空间动作的擦拭任务中，基于轨迹的基线在低于-6厘米时失去接触，而所提方法在高于-6厘米时保持一致的4-5牛接触力，低于-6厘米时逐渐减小；在笛卡尔空间动作下，其0至+8厘米的力-高度斜率为0.13±0.03牛/厘米，而固定阻抗基线为0.34-0.83牛/厘米。在包含10个不同杯子的拾放任务（100次试验）中，所提方法成功84次，优于固定阻抗基线（74/100），并与使用一次演示而非十次的变阻抗控制基线（82/100）表现相当。在抓取任务中，该表示降低了ILBiT和Mamba两种骨干网络的扭矩跟踪误差，证实了其跨架构的通用性。
英文摘要
Contact-rich manipulation requires robots to regulate force against surfaces whose geometry deviates unpredictably from training conditions. Trajectory-based imitation learning, which reproduces observable outputs, breaks down under such shifts. We propose Impedance Cloning, which instead imitates the biomechanical priors that generate motion -- the stiffness and equilibrium point -- and thereby passively absorbs contact uncertainty. Because these parameters encode intent rather than outcome, they generalize across surface geometries where trajectory reproduction does not. We extract them from bilateral teleoperation demonstrations via a particle filter without force/torque sensors and evaluate the framework on two CRANE-X7 manipulators. In a wiping task with joint-space actions, the trajectory-based baseline loses contact below -6 cm, whereas the proposed method maintains a consistent 4-5 N contact force above -6 cm, with a gradual decrease below; with Cartesian-space actions, its force-height slope over 0 to +8 cm is 0.13 +/- 0.03 N/cm, versus 0.34-0.83 N/cm for fixed-impedance baselines. In a pick-and-place task with 10 diverse cups (100 trials), the proposed method succeeds in 84 trials, outperforming the fixed-impedance baseline (74/100) and performing comparably to a variable impedance control baseline (82/100) with one demonstration instead of ten. In a grasping task, the representation reduces torque tracking error with both ILBiT and Mamba backbones, confirming its generality across architectures.
Comments8 pages, 7 figures, 3 tables. Submitted to IEEE Robotics and Automation Letters (RA-L)
