外观
论文arXiv 2610.1051021 天前
解耦触觉表征框架实现Sim-to-Real操作迁移精度提升35%
本文由 AI 根据公开内容整理，可能有误，请以原文为准：Factorized Tactile Representation and Control for Sim-to-Real Manipulation（arXiv 2610.10510）
核心内容
针对触觉Sim-to-Real学习中仿真接触与传感器响应差异难题，arXiv论文提出一种解耦触觉表征与控制框架。该方法将有效接触响应映射为可从传感器读数恢复的几何、力分布及时间变化三个独立分量，并采用特定编码与随机化策略。通过Tactile Gated Policy在无需重训练下适配所有掩码配置，在仿真与真机中完成了响应重建、空间对齐、力调节及对抗性插孔测试。
实验数据显示，该框架在未见几何体上实现小于1mm的接触定位精度和1.69N的力跟踪误差。在真实世界高难度对抗性插孔任务中，性能较未解耦基线提升35%。系统架构支持独立评估各触觉表征效用，证实了解耦设计能保留控制所需信息，同时弥合仿真物理模型与真实设备特异性响应之间的鸿沟，增强了跨场景泛化能力。
关键看点
- 解耦表征机制：将接触响应分离为几何、力分布与时序变化三要素，配合专用编码与随机化策略保留控制关键信息
- 量化性能指标：实现<1mm接触定位精度与1.69N力跟踪误差，真实对抗性插孔成功率较未解耦方案提升35%
- 零样本策略适配：Tactile Gated Policy支持全掩码配置运行且无需重训练，可独立评估不同触觉表征的迁移可靠性
工程与产业观察
该工作为具身智能触觉感知提供了标准化Sim-to-Real迁移范式。通过解耦表征消除传感器特异性干扰，使算法工程师能在仿真中独立优化几何与力学模型。其<1mm定位与低力控误差证明了结构化先验对弥补仿真-现实差距的关键作用，为精密装配等接触密集任务的泛化部署确立了工程基准。
英文摘要 (Abstract)
Tactile sim-to-real learning must bridge simulated contact and device-specific sensor responses while preserving information needed for control. We propose a factorized tactile representation and control framework that maps normal force and contact patch to an effective contact response recoverable from sensor readings. The response is separated into contact geometry, force distribution, and temporal contact change, with representation-specific encoding and randomization. A Tactile Gated Policy preserves these representations separately through control and operates over all mask configurations without retraining. We evaluate the approach through response reconstruction, spatial alignment, force regulation, and contact-rich adversarial peg insertion in simulation and the real world, enabling the utility and transfer reliability of different tactile representations to be assessed independently. The approach achieves <1 mm contact localization, 1.69 N force-tracking error on unseen geometries, and a 35% improvement in real-world adversarial peg insertion over the unfactorized response, with different tactile representations benefiting different interactions.
作者：Siqi Shang, Bianca Aumann, Tye Brady, Joshua Migdal, Taskin Padir
来源
本页事实对应的公开页面，以原文为准。