HydroShear：面向触觉模拟到真实强化学习的水弹性剪切仿真

HydroShear: Hydroelastic Shear Simulation for Tactile Sim-to-Real Reinforcement Learning

February 28, 2026

作者: An Dang, Jayjun Lee, Mustafa Mukadam, X. Alice Wu, Bernadette Bucher, Manikantan Nambi, Nima Fazeli

cs.AI

摘要

本文针对接触密集型任务中的触觉仿真到现实策略迁移问题展开研究。现有方法主要关注基于视觉的传感器，强调图像渲染质量却采用过于简化的力和剪切力模型，导致这些模型在诸多精细操作任务中存在显著的仿真与现实差异。我们提出HydroShear——一种非完整流体弹性触觉模拟器，通过建立以下模型推动技术发展：a) 静动摩擦转换机制，b) 路径依赖的力与剪切力累积模型，c) 完整SE(3)空间下的物体-传感器交互。该模拟器基于符号距离函数扩展流体弹性接触模型，实时追踪压头与传感器膜物理交互过程中表面点的位移。我们的方法能从任意水密几何体生成基于物理原理且计算高效的力量场，同时保持对底层物理引擎的无关性。在GelSight Mini传感器实验中，相较于现有方法，HydroShear能更精确地复现实物触觉剪切力。这种高保真特性实现了强化学习策略在四个任务中的零样本仿真到现实迁移：轴孔装配、料箱堆叠、书架插书以及基于滑动检测的抽屉拉取精细抓握控制。本方法平均成功率高达93%，显著优于基于触觉图像训练的策略（34%）及其他剪切力模拟方法（58%-61%）。

English

In this paper, we address the problem of tactile sim-to-real policy transfer for contact-rich tasks. Existing methods primarily focus on vision-based sensors and emphasize image rendering quality while providing overly simplistic models of force and shear. Consequently, these models exhibit a large sim-to-real gap for many dexterous tasks. Here, we present HydroShear, a non-holonomic hydroelastic tactile simulator that advances the state-of-the-art by modeling: a) stick-slip transitions, b) path-dependent force and shear build up, and c) full SE(3) object-sensor interactions. HydroShear extends hydroelastic contact models using Signed Distance Functions (SDFs) to track the displacements of the on-surface points of an indenter during physical interaction with the sensor membrane. Our approach generates physics-based, computationally efficient force fields from arbitrary watertight geometries while remaining agnostic to the underlying physics engine. In experiments with GelSight Minis, HydroShear more faithfully reproduces real tactile shear compared to existing methods. This fidelity enables zero-shot sim-to-real transfer of reinforcement learning policies across four tasks: peg insertion, bin packing, book shelving for insertion, and drawer pulling for fine gripper control under slip. Our method achieves a 93% average success rate, outperforming policies trained on tactile images (34%) and alternative shear simulation methods (58%-61%).