SlipSense：用于低延迟和泛化滑动检测的多模态触觉学习
SlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip Detection
查看机构详情
- Analog Devices, Inc.（亚德诺半导体公司）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对滑动检测延迟与泛化不足，提出基于TacV5的多模态触觉框架SlipSense，融合压阻阵列与加速度计，实现240Hz预测，宏F1达96.7%，并零样本迁移至新平台。
中文摘要 AI 辅助
滑动检测是灵巧操作的基础，然而现有系统往往缺乏对检测延迟和跨平台泛化能力的精确刻画。我们提出了SlipSense，一个基于TacV5的多模态触觉滑动检测框架。TacV5是一种紧凑型传感器，集成了一个以240 Hz运行的32×32压阻阵列和一个以8 kHz运行的三轴MEMS加速度计。压阻阵列捕获空间压力分布，而加速度计捕获摩擦引起的振动，提供互补的滑动线索。该框架执行模态特定编码、传感器内融合以及带有因果时间预测的跨模态注意力，预测频率为240 Hz。在涵盖37个物体的140万帧数据集上的实验证明了两种模态的互补性。SlipSense实现了96.7%的宏F1分数，假阳性率低于1.6%，在23.1毫秒内检测到76%的滑动事件。当仅使用UMI数据训练时，SlipSense零样本泛化到Tesollo灵巧手，无需重新训练即可跨未见物体、不同传感器单元和机器人平台进行迁移。
英文摘要
Slip detection is fundamental to dexterous manipulation, yet existing systems often lack precise characterization of detection latency and cross-platform generalization. We present SlipSense, a multimodal tactile slip-detection framework built on TacV5, a compact sensor integrating a $32 \times 32$ piezoresistive array operating at 240 Hz and a 3-axis MEMS accelerometer operating at 8 kHz. The piezoresistive array captures spatial pressure distributions, while the accelerometer captures friction-induced vibrations, providing complementary slip cues. The framework performs modality-specific encoding, intra-sensor fusion, and cross-modal attention with causal temporal prediction at 240 Hz. Experiments on a dataset of 1.4 million frames spanning 37 objects demonstrate the complementarity of the two modalities. SlipSense achieves 96.7% Macro F1 with a false-positive rate below 1.6%, detecting 76% of slip events within 23.1 ms. When trained solely on UMI data, SlipSense generalizes zero-shot to a Tesollo dexterous hand, transferring across unseen objects, distinct sensor units, and robotic platforms without retraining.
