Skip to content

论文HF Daily Papers · arXiv 2611.1280613 天前

LingBot-Touch触觉基础模型实现异构传感器统一表征与灵巧操作增强 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:Learning Heterogeneous Tactile Representation for General Dexterous Manipulation(HF Daily Papers · arXiv 2611.12806)

核心内容 ​

针对商用触觉传感器物理特性差异大、数据难以复用的痛点,研究团队发布LingBot-Touch触觉基础模型。该工作旨在解耦触觉理解与特定传感器物理属性,使具身模型能有效利用异构触觉数据。实验覆盖仿真与真机多硬件平台部署,证实该统一表征在复杂灵巧操作任务中具备显著性能增益与计算效率优势,为跨传感器触觉学习规模化提供了可行路径。

技术上,LingBot-Touch实现了压阻、磁性和视触觉传感器的统一表征空间,且架构支持新传感器类型扩展。其输出的触觉Token具备即插即用特性,可无缝接入Diffusion Policy及π0.5、LingBot-VLA等视觉-语言-动作模型。这种模块化设计允许算法工程师在不更改策略主干的前提下引入触觉反馈,有效解决了多模态融合中触觉数据格式碎片化的问题,降低了异构硬件适配门槛。

关键看点 ​

  • 异构统一表征:支持压阻、磁性及视触觉三类传感器统一编码,架构可扩展适配新型触觉硬件
  • 策略即插即用:触觉Token兼容Diffusion Policy与π0.5等VLA模型,无需重构策略即可增强灵巧性
  • 多平台实证:经仿真与真机多硬件验证,在复杂操作任务中提升性能同时保持高计算效率
  • 解耦传感器物理:将触觉理解从特定物理原理中剥离,解决异构数据复用难题以支持规模化训练

工程与产业观察 ​

该工作通过基础模型范式解决了触觉传感碎片化难题,将异构硬件数据转化为标准化Token,大幅降低灵巧操作算法对特定传感器的依赖。对于具身智能研发而言,这意味着可构建跨硬件通用触觉数据集,加速Sim-to-Real迁移;产业侧则获得了解耦算法与硬件绑定的技术底座,利于多源触觉供应链整合与通用灵巧手生态建设。

英文摘要 (Abstract) ​

Tactile sensing is an indispensable modality for contact-rich dexterous manipulation, a capability that hints at the ultimate frontiers of embodied intelligence. However, commercially available tactile sensors are still at a relatively early stage of development, with each type of sensor offering irreplaceable strengths alongside its own drawbacks. A key challenge is thus to free tactile understanding from sensor-specific physics, so that embodied models can effectively leverage heterogeneous tactile data. To this end, we develop LingBot-Touch, a tactile foundation model characterized by the following properties. (i) Our model yields a unified representation across different tactile sensors (i.e., piezoresistive, magnetic, and visuotactile sensors), and is easily extensible to new sensor types. (ii) The resulting tactile tokens are plug-and-play: they can be seamlessly integrated into policy models across paradigms, from diffusion policy to vision-language-action (VLA) models such as π_{0.5} and LingBot-VLA, consistently enhancing manipulation dexterity. (iii) Extensive experiments, spanning simulation and real-robot deployments across multiple hardware platforms, demonstrate that our tactile representation substantially benefits complex manipulation tasks while maintaining strong computational efficiency. We believe the findings in this work demonstrate the potential of leveraging cross-sensor data to scale tactile learning, and offer encouraging insights for the design of future hardware and embodied models.

Hugging Face Daily Papers 热度:90 upvotes 作者:Bing Han, Yichuan Peng, Haoyu Dong, Yuanmeng Hu, Yongyi Jia, Fangjing Wang, Kecheng Zheng, Yiming Zhang, Yanhong Zeng, Xiaoqing Zhang, Chen Song, Rundong Zou, Anqi Dong, Yuan Guan, Ka Leong Cheng, Xin…

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. HF Daily Papers · arXiv 2611.12806:Learning Heterogeneous Tactile Representation for General Dexterous Manipulation ↗访问 2026-11-10