发表机构
Amazon Fulfillment Technologies & Robotics; The University of Texas at Austin; Northeastern University（亚马逊履约技术与机器人; 德克萨斯大学奥斯汀分校; 东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出因子化触觉表征与控制框架，将接触响应分解为几何、力分布和时间变化，通过触觉门控策略实现仿真到现实迁移，在插销插入等任务中显著提升性能。
AI 中文摘要
触觉仿真到现实学习必须在保留控制所需信息的同时，弥合仿真接触与设备特定传感器响应之间的差距。我们提出了一种因子化触觉表征与控制框架，将法向力和接触斑映射为可从传感器读数中恢复的有效接触响应。该响应被分离为接触几何、力分布和时间接触变化，并采用表征特定的编码和随机化。一种触觉门控策略在控制过程中分别保留这些表征，并在所有掩码配置上无需重新训练即可运行。我们通过响应重建、空间对齐、力调节以及仿真和现实中的接触丰富对抗性插销插入来评估该方法，使得不同触觉表征的效用和迁移可靠性能够被独立评估。该方法在未见几何体上实现了小于1毫米的接触定位、1.69牛的力跟踪误差，并在现实对抗性插销插入中相比未因子化响应提升了35%，且不同触觉表征有利于不同的交互任务。
英文摘要
Tactile sim-to-real learning must bridge simulated contact and device-specific sensor responses while preserving information needed for control. We propose a factorized tactile representation and control framework that maps normal force and contact patch to an effective contact response recoverable from sensor readings. The response is separated into contact geometry, force distribution, and temporal contact change, with representation-specific encoding and randomization. A Tactile Gated Policy preserves these representations separately through control and operates over all mask configurations without retraining. We evaluate the approach through response reconstruction, spatial alignment, force regulation, and contact-rich adversarial peg insertion in simulation and the real world, enabling the utility and transfer reliability of different tactile representations to be assessed independently. The approach achieves <1 mm contact localization, 1.69 N force-tracking error on unseen geometries, and a 35% improvement in real-world adversarial peg insertion over the unfactorized response, with different tactile representations benefiting different interactions.
Comments8 pages, 7 figures
