Bench2Dex：跨灵巧手的视觉-触觉双臂灵巧操作基准
Bench2Dex: Benchmarking Visuo-Tactile Bimanual Dexterous Manipulation Across Dexterous Hands
浏览论文内容
中文总结 AI 辅助
提出Bench2Dex仿真基准，统一12种灵巧手的触觉观测格式，含26个双臂任务和1300演示，评估四种策略，为跨手视觉-触觉学习提供平台。
中文摘要 AI 辅助
触觉传感提供了仅凭视觉难以推断的接触信息，但灵巧手的触觉硬件尚未收敛到通用设计。灵巧手在手指结构、接触表面和传感器布局上各不相同，而模拟触觉信号与物理传感器产生的测量值仍存在差异。这些因素使得在一致的实验环境中研究跨多种灵巧手的视觉-触觉操作变得困难。我们提出了Bench2Dex，一个涵盖12种灵巧手的视觉-触觉双臂操作仿真基准。我们通过共享的模拟触觉接口适配现有机器人模型，该接口将局部接触几何转换为类似图像的触觉观测。该接口在不同手部形态间提供一致的观测格式，而不试图复现特定物理触觉传感器的输出。Bench2Dex包含26个双臂操作任务，涉及工具使用、铰接物体交互和多阶段操作，并配有约1300个人类遥操作演示。该基准提供同步的视觉、触觉、本体感觉、动作和物体状态观测，以及可执行的任务指标。为增强鲁棒性，我们将七种扰动类型分为不变轴（正确动作不变）和等变轴（正确动作随扰动变化）。我们在Bench2Dex上评估了ACT、Diffusion Policy、pi0.5和GR00T N1.5，并报告了它们的性能和失败模式。Bench2Dex旨在作为跨灵巧手研究视觉-触觉学习的平台。它不假设模拟触觉观测能替代真实触觉传感；在触觉硬件和仿真模型仍在发展之际，它为算法开发提供了一个共享环境。
英文摘要
Tactile sensing provides contact information that can be difficult to infer from vision alone, but tactile hardware for dexterous hands has not converged to a common design. Dexterous hands differ in finger structure, contact surfaces, and sensor layouts, while simulated tactile signals still differ from measurements produced by physical sensors. These factors make it difficult to study visuo-tactile manipulation across diverse dexterous hands within a consistent experimental setting. We present Bench2Dex, a simulation benchmark for visuo-tactile bimanual manipulation across 12 dexterous hands. We adapt existing robot models with a shared simulated tactile interface that converts local contact geometry into image-like tactile observations. The interface provides a consistent observation format across different hand morphologies without attempting to reproduce the output of a specific physical tactile sensor. Bench2Dex includes 26 bimanual manipulation tasks that involve tool use, articulated-object interaction, and multi-stage manipulation, together with about 1.3K human-teleoperated demonstrations. The benchmark provides synchronized visual, tactile, proprioceptive, action, and object-state observations, together with executable task metrics. For robustness, we group seven perturbation types into invariance axis, where the correct action does not change, and equivariance axis, where the correct action changes together with the perturbation. We evaluate ACT, Diffusion Policy, pi0.5, and GR00T N1.5 on Bench2Dex and report their performance and failure modes. Bench2Dex is meant as a platform for studying visuo-tactile learning across dexterous hands. It does not assume that simulated tactile observations can replace real tactile sensing; it offers a shared setting for algorithm development while tactile hardware and simulation models are still evolving.
