TacGooseBumps (TacGB)：为仅法向触觉传感器加装剪切编码以学习接触丰富操作
TacGooseBumps (TacGB): Retrofitting Normal-Only Tactile Sensors with Shear Encoding for Learning Contact-Rich Manipulation
浏览论文内容
中文总结 AI 辅助
针对接触丰富操作中视觉与法向触觉难以区分切向接触状态的问题，提出TacGB被动薄膜，将切向载荷机械编码为压力图变化，在不改变传感器或策略输入格式下，提升插入成功率最高36个百分点，并改善效率与接触质量。
中文摘要 AI 辅助
接触丰富的策略常常失败，因为不同的物理状态看起来相似却需要不同的动作。相机可能无法揭示连接器是否对齐或完全就位，而许多仅法向的触觉传感器可能错过垂直于抓取方向的切向交互，这些交互正是区分这些状态的关键。我们探究学习策略是否需要校准的剪切测量，还是仅需一种可重复的观测来分离依赖剪切的接触状态。我们提出TacGooseBumps (TacGB)，一种被动圆顶薄膜，通过机械方式将切向载荷编码为现有传感器压力图中的模式变化。切向载荷使每个圆顶倾斜并重新分配其足迹上的压力；端到端策略直接消费生成的压力图，无需额外电子元件、力重建或taxel级圆顶对齐。在四个模仿学习任务和两条数据采集流程中，TacGB提升了目标达成率、效率和接触质量：插入成功率最高提升36个百分点，成功插入完成更快，易碎物体放置更轻柔，绘图更连续且更直。信号、分阶段、失败模式和轨迹分析将这些改进归因于视觉和法向压力难以分辨任务相关切向交互的接触状态。这些结果表明，剪切无需以度量方式测量即可惠及机器人学习；它可以通过机械编码实现，而无需改变底层触觉传感器或策略的压力图输入格式。
英文摘要
Contact-rich policies often fail because distinct physical states look alike yet require different actions. Cameras may not reveal whether a connector is aligned or fully seated, while many normal-only tactile sensors can miss the tangential interactions perpendicular to the grasping direction that distinguish these states. We ask whether a learning policy needs calibrated shear measurements, or only a repeatable observation that separates shear-dependent contact states. We introduce TacGooseBumps (TacGB), a passive domed film that mechanically encodes tangential loading as pattern changes in an existing sensor's pressure map. Tangential loading tilts each dome and redistributes pressure across its footprint; an end-to-end policy consumes the resulting maps without added electronics, force reconstruction, or taxel-level dome alignment. Across four imitation-learning tasks and two data-collection pipelines, TacGB improves goal attainment, efficiency, and contact quality: insertion success increases by up to 36 percentage points, and successful insertions are completed faster, while fragile-object placement becomes gentler and drawing becomes more continuous and straight. Signal, stage-wise, failure-mode, and trajectory analyses link these gains to contact regimes in which task-relevant tangential interactions are poorly resolved by vision and normal pressure alone. Together, these results show that shear need not be measured metrically to benefit robot learning; it can instead be mechanically encoded without changing the underlying tactile sensor or the policy's pressure-map input format.
发表机构
- University of California, Berkeley（加州大学伯克利分校）
- Saratoga High School（萨拉托加高中）
机构由 AI 辅助整理，请以论文原文为准。
