发表机构
The University of Hong Kong; INFIFORCE; The Chinese University of Hong Kong (Shenzhen); Wuhan Textile University; Ocean University of China; Wuhan University（香港大学; INFIFORCE; 香港中文大学（深圳）; 武汉纺织大学; 中国海洋大学; 武汉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TACROSS是一款跨异构触觉传感器的系统，通过接触事件对齐实现人类触觉到机器人的迁移，在四个接触操作任务上效率提升3.5倍、设备成本降低95.7%，将开源软硬件及超150小时触觉数据集。
AI 中文摘要
在机器人上收集触觉演示数据成本高且速度慢，这促使人们使用低成本的人类触觉手套来实现可扩展的数据收集。然而，人类电容式/压阻式手套与机器人触觉传感器在 transduction（换能）原理、传感器布局、空间分辨率和动态响应方面存在根本差异，这使得原始传感器通道的对齐问题难以解决。为解决该问题，我们提出了TACROSS，这是一种可扩展的系统，用于从人类触觉中学习并将其迁移到机器人，该系统通过在接触事件层面而非原始传感器值层面对齐触觉流来弥合这种异构性。TACROSS的硬件组件集成了一款五层结构、成本为10.86美元、拥有285个传感点的压阻式手套。为对齐接触语义，我们设计了规范化器（canonicalizers）和残差适配器（residual adapters），通过一款跨手指注意力的时间Transformer将异构信号映射到256维的共享触觉潜空间。我们进一步引入了基于机器人的策略学习方案，其中机器人演示是真实动作监督的唯一来源，而人类演示则支持触觉表示学习，并通过有效的重定向手部目标提供置信度加权的辅助监督。我们在四个接触丰富的操作任务上评估了我们的系统。与传统遥操作相比，我们提出的系统实现了3.5倍的效率提升，同时将演示采集设备成本降低了95.7%。我们将开源TACROSS的硬件和软件系统，并公开发布包含超过150小时记录的触觉数据集。项目页面：this https URL。
英文摘要
Collecting tactile demonstrations on robots is costly and slow, motivating the use of lower-cost human tactile gloves for scalable data collection. However, human capacitive/piezoresistive gloves and robotic tactile sensors differ fundamentally in transduction principle, sensor layout, spatial resolution, and dynamic response, making alignment of raw sensor channels ill-posed. To address this problem, we present TACROSS, a scalable system for learning from human touch and transferring it to robots that bridges this heterogeneity by aligning tactile streams at the level of contact events rather than raw sensor values. The hardware component of TACROSS integrates a piezoresistive glove with five layers and a cost of USD 10.86 with 285 sensing points. To align contact semantics, we design canonicalizers and residual adapters that map heterogeneous signals into a shared tactile latent with 256 dimensions via a temporal Transformer with attention across fingers. We further introduce a robot-grounded policy learning scheme in which robot demonstrations provide the sole source of ground-truth action supervision, while human demonstrations support tactile representation learning and provide confidence-weighted auxiliary supervision through valid retargeted hand targets. We evaluate our system on four contact-rich manipulation tasks. Compared to conventional teleoperation, our proposed system achieves a 3.5-fold efficiency improvement while reducing demonstration acquisition equipment cost by 95.7%. We will open-source the TACROSS hardware and software system and publicly release a tactile dataset comprising over 150 hours of recordings. Project page: https://tacross-touch-project.github.io/.
