用生成模型让不同触觉传感器间实现信号互译，提升通用性。
Touch2Touch: Cross-Modal Tactile Generation for Object Manipulation
- 用扩散模型在GelSlim与Soft Bubble传感器间进行触觉信号跨模态转换。
- 在手内物体姿态估计任务中，用Soft Bubble算法处理生成的GelSlim信号，精度达92.3%。
- 适合做多传感器融合或触觉系统迁移的研究者使用。
当前触觉传感器种类繁多，导致通用触觉处理方法难以实现，因模型通常依赖特定传感器设计。本文提出跨模态触觉生成：给定一个传感器的触觉信号，利用生成模型预测同一物理接触在另一传感器上的感知结果。该方法使传感器专用算法可应用于生成信号。我们以流行的GelSlim和Soft Bubble传感器为例，训练扩散模型实现信号转换。作为下游任务，在仅使用Soft Bubble信号的算法下，通过生成的GelSlim信号完成手内物体姿态估计，准确率达到92.3%。数据集、代码及更多细节详见https://www.mmintlab.com/research/touch2touch/。
原文摘要 · Abstract (English)
Today's touch sensors come in many shapes and sizes. This has made it challenging to develop general-purpose touch processing methods since models are generally tied to one specific sensor design. We address this problem by performing cross-modal prediction between touch sensors: given the tactile signal from one sensor, we use a generative model to estimate how the same physical contact would be perceived by another sensor. This allows us to apply sensor-specific methods to the generated signal. We implement this idea by training a diffusion model to translate between the popular GelSlim and Soft Bubble sensors. As a downstream task, we perform in-hand object pose estimation using GelSlim sensors while using an algorithm that operates only on Soft Bubble signals. The dataset, the code, and additional details can be found at https://www.mmintlab.com/research/touch2touch/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。