arXiv 2510.179502025-10-20cs.RO

RoboChallenge：具身策略的大规模真实机器人评估

RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies

Dexmal；Hugging Face Project（Hugging Face项目）

Adina Yakefu, Bin Xie, Chongyang Xu, Enwen Zhang, Erjin Zhou, Fan Jia, Haitao Yang, Haoqiang Fan, Haowei Zhang, Hongyang Peng, Jing Tan, Junwen Huang, Kai Liu, … 展开作者

Adina Yakefu, Bin Xie, Chongyang Xu, Enwen Zhang, Erjin Zhou, Fan Jia, Haitao Yang, Haoqiang Fan, Haowei Zhang, Hongyang Peng, Jing Tan, Junwen Huang, Kai Liu, Kaixin Liu, Kefan Gu, Qinglun Zhang, Ruitao Zhang, Saike Huang, Shen Cheng, Shuaicheng Liu, Tiancai Wang, Tiezhen Wang, Wei Sun, Wenbin Tang, Yajun Wei, Yang Chen, Youqiang Gui, Yucheng Zhao, Yunchao Ma, Yunfei Wei, Yunhuan Yang, Yutong Guo, Ze Chen, Zhengyuan Du, Ziheng Zhang, Ziming Liu, Ziwei Yan

备注：: Authors are listed in alphabetical order. The official website is located at https://robochallenge.ai

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 RoboChallenge 在线真实机器人评估系统，并以 Table30 基准调研多种最新 VLA 模型，以支持具身策略的大规模、可扩展且可复现评测。

摘要：

在真实机器上进行测试对于机器人控制算法不可或缺。在基于学习的算法（尤其是 VLA 模型）背景下，对大规模评估（即在大量任务上测试大量模型）的需求正变得日益迫切。然而，妥善完成这项工作绝非易事，尤其是在考虑可扩展性和可复现性时。在本报告中，我们描述了构建 RoboChallenge 的方法，这是一个用于测试机器人控制算法的在线评估系统；同时介绍了我们利用初始基准 Table30 对近期最先进 VLA 模型开展的调研。

英文摘要：

Testing on real machines is indispensable for robotic control algorithms. In the context of learning-based algorithms, especially VLA models, demand for large-scale evaluation, i.e. testing a large number of models on a large number of tasks, is becoming increasingly urgent. However, doing this right is highly non-trivial, especially when scalability and reproducibility is taken into account. In this report, we describe our methodology for constructing RoboChallenge, an online evaluation system to test robotic control algorithms, and our survey of recent state-of-the-art VLA models using our initial benchmark Table30.

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。