注意间隙:通过意图-执行不匹配学习隐式阻抗
Mind the Gap: Rethinking I/O Design for Contact-Rich Visuomotor Policy Learning
AI总结:
通过意图-执行不匹配学习隐式阻抗,实现低成本硬件的鲁棒力感知与动态补偿。
摘要:
远程操作本质上依赖于人类操作员作为闭环控制器主动补偿硬件缺陷,包括延迟、机械摩擦和缺乏显式力反馈。标准行为克隆(BC)通过模仿机器人的执行轨迹,根本上忽略了这种补偿机制。在本工作中,我们提出了一种双状态条件框架,将学习目标转向“意图克隆”(主命令)。我们提出意图-执行不匹配,即主命令与从动响应之间的差异,不是噪声,而是一个关键信号,它物理上编码隐式相互作用力,并算法上揭示操作员克服系统动力学的策略。通过预测主意图,我们的策略学习生成一个“虚拟平衡点”,有效地实现了隐式阻抗控制。此外,通过显式地对这种不匹配的历史进行条件,模型执行隐式系统识别,将跟踪误差视为外部力以闭合控制回路。为弥补由于推理延迟引起的时间间隙,我们进一步将策略公式化为轨迹修补器,以确保连续控制。我们在无传感器、低成本的双臂设置上验证了我们的方法。在需要接触丰富操作和动态跟踪的任务中,经验结果揭示了一个决定性的差距:虽然标准执行克隆因无法克服接触刚度和跟踪滞后而失败,我们的不匹配意识方法实现了稳健的成功。这提供了一个最小化的行为克隆框架,适用于低成本硬件,使力感知和动态补偿无需依赖显式力传感。视频可在项目页面上获得。
英文摘要:
Contact-rich teleoperation logs expose a policy I/O design choice: demonstrations may contain the robot execution (E), leader command (C), or both. These signals are not interchangeable: E2E may discard contact-generating command offsets, whereas E2C preserves these offsets but omits the robot's execution response. We propose Dual-State Conditioning (EC2C), which conditions on both E and C while predicting future C, exposing command-execution mismatch as a cue for contact, latency, payload, and operator compensation; in quasi-static contact, this cue is often force-correlated. On a low-cost setup without force, tactile, or motor-current policy input, EC2C outperforms E2E and a strong E2C baseline across several real-world contact-rich, force-sensitive, and dynamic tasks. These results support EC2C as a practical default I/O setting for contact-rich imitation learning. We further formulate latency-adaptive inpainting as a temporal extension of this I/O choice for action-chunking policies, and discuss when long histories help dynamic inference or introduce causal confounding.
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。