arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.25459cs.ROcs.CVcs.LG
收藏

BiDex-100:覆盖100+仿真任务的双手灵巧操作综合基准

BiDex-100: A Comprehensive Benchmark for Bimanual Dexterous Manipulation Across 100+ Simulation Tasks

Zhejiang University(浙江大学);Ant Group(蚂蚁集团)

Yong Wang, Kecheng Zheng, Xing Zhu, Chao Xu, Yujun Shen, Shengze Cai

AI总结:

本文提出BiDex-100双手灵巧操作仿真基准,含106个任务等,评估7个视觉-语言-动作模型并建立相关基线。

摘要:

双手灵巧操作在机器人动作模型研究中日益受到关注。然而,鲜有研究开发专门针对灵巧操作的基准,导致现有模型的灵巧操作能力未得到充分表征。本文提出BiDex-100,这是一个双手灵巧操作仿真基准,兼具广泛的任务覆盖、多维度评估和高自由度手型体。具体而言,该基准包含106个任务,沿泛化性、指令遵循、有限演示、长时序和记忆五大能力轴组织;每个任务配有域外变体,具备可控的视觉与空间变化,可系统评估鲁棒性。此外,该基准支持两种体,提供8080个经成功验证的遥操作演示,总计625万帧。我们在统一协议下评估了7个最新的视觉-语言-动作模型,建立了能力特定性能、鲁棒性和数据效率的基线。该基准网站可通过此URL访问。

英文摘要:

Bimanual manipulation with dexterous hands has attracted growing attention in research on robotic action models. However, few studies have developed benchmarks specifically tailored for dexterous manipulation, leaving the dexterous manipulation capabilities of existing models insufficiently characterized. In this paper, we present BiDex-100, a simulation benchmark for bimanual dexterous manipulation that combines broad task coverage, multi-dimensional evaluation, and high-DoF hand embodiments. Concretely, the benchmark comprises 106 tasks organized along five capability axes: generalization, instruction following, limited demonstrations, long horizon, and memory. Each task is paired with an out-of-domain variant featuring controlled visual and spatial changes, allowing systematic assessment of robustness. In addition, the benchmark supports two embodiments and provides 8,080 success-validated teleoperated demonstrations, totaling 6.25 million frames. We evaluate seven recent Vision-Language-Action models under a unified protocol, establishing baselines for capability-specific performance, robustness, and data efficiency. The website is available at https://robbyant-research.github.io/BiDex-100/.

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。

↑