从单张图片重建可触觉感知的3D空间，让机器人学会识别软硬区域。
Monocular Reconstruction of Neural Tactile Fields
- 从单目图像预测接触时的触觉响应分布。
- 相比顶尖方法，体积重建提升85.8%，表面重建提升26.7%。
- 适合需要感知柔性物体的机器人路径规划场景。
机器人在真实环境中操作时需应对形变、柔性和可重构的交互环境，要求具备超越静态几何占据的交互感知3D表示。为此，我们提出神经触觉场（neural tactile fields），一种将空间位置映射到接触预期触觉响应的新3D表征。我们的模型首次实现了从单张单目RGB图像预测神经触觉场。当与现成路径规划器结合时，神经触觉场使机器人能避开高阻力物体，主动选择低阻力区域（如树叶）通过，而非将所有占位空间视为同等不可通行。实验证明，该学习框架在体素3D重建上比当前最优单目方法（LRM 和 Direct3D）提升85.8%，表面重建提升26.7%。
原文摘要 · Abstract (English)
Robots operating in the real world must plan through environments that deform, yield, and reconfigure under contact, requiring interaction-aware 3D representations that extend beyond static geometric occupancy. To address this, we introduce neural tactile fields, a novel 3D representation that maps spatial locations to the expected tactile response upon contact. Our model predicts these neural tactile fields from a single monocular RGB image -- the first method to do so. When integrated with off-the-shelf path planners, neural tactile fields enable robots to generate paths that avoid high-resistance objects while deliberately routing through low-resistance regions (e.g. foliage), rather than treating all occupied space as equally impassable. Empirically, our learning framework improves volumetric 3D reconstruction by $85.8\%$ and surface reconstruction by $26.7\%$ compared to state-of-the-art monocular 3D reconstruction methods (LRM and Direct3D).
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。