arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.21625cs.RO
收藏

Tacmap: 通过几何一致的穿透深度图弥合触觉仿真到现实的差距

Tacmap: Bridging the Tactile Sim-to-Real Gap via Geometry-Consistent Penetration Depth Map

Sharpa;HKUST(香港科技大学);NVIDIA(英伟达)

Lei Su, Zhijie Peng, Renyuan Ren, Shengping Mao, Juan Du, Kaifeng Zhang, Xuezhou Zhu

AI总结:

Tacmap通过统一的变形地图表示弥合触觉仿真与现实的差距,利用体积穿透深度实现高保真且高效的触觉仿真,验证了在抓取任务中仿真政策的零样本迁移能力。

摘要:

基于视觉的触觉传感器(VBTS)对于实现灵活的机器人操作至关重要,但触觉仿真到现实的差距仍然是一个根本性瓶颈。当前触觉仿真面临持续性的困境:简化几何投影缺乏物理真实性,而高保真的有限元方法(FEM)在大规模强化学习中计算成本过高。本文提出Tacmap,一种高保真且计算高效的触觉仿真框架,其核心思想是通过共享的变形地图表示统一仿真与现实领域。具体来说,在仿真中计算3D交集体积作为深度图,在现实世界中使用自动化数据采集装置学习从原始触觉图像到真实深度图的鲁棒映射。通过在统一的几何空间中对齐仿真与现实,Tacmap在保持物理一致性的同时最小化领域偏移。在多样化的接触场景中定量评估显示,Tacmap的变形地图与现实测量高度吻合。此外,我们通过手持旋转任务验证了Tacmap的实用性,其中在仿真中训练的策略能够零样本迁移至物理机器人。

英文摘要:

Vision-Based Tactile Sensors (VBTS) are essential for achieving dexterous robotic manipulation, yet the tactile sim-to-real gap remains a fundamental bottleneck. Current tactile simulations suffer from a persistent dilemma: simplified geometric projections lack physical authenticity, while high-fidelity Finite Element Methods (FEM) are too computationally prohibitive for large-scale reinforcement learning. In this work, we present Tacmap, a high-fidelity, computationally efficient tactile simulation framework anchored in volumetric penetration depth. Our key insight is to bridge the tactile sim-to-real gap by unifying both domains through a shared deform map representation. Specifically, we compute 3D intersection volumes as depth maps in simulation, while in the real world, we employ an automated data-collection rig to learn a robust mapping from raw tactile images to ground-truth depth maps. By aligning simulation and real-world in this unified geometric space, Tacmap minimizes domain shift while maintaining physical consistency. Quantitative evaluations across diverse contact scenarios demonstrate that Tacmap's deform maps closely mirror real-world measurements. Moreover, we validate the utility of Tacmap through an in-hand rotation task, where a policy trained exclusively in simulation achieves zero-shot transfer to a physical robot.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑