Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yakefu, Adina, Xie, Bin, Xu, Chongyang, Zhang, Enwen, Zhou, Erjin, Jia, Fan, Yang, Haitao, Fan, Haoqiang, Zhang, Haowei, Peng, Hongyang, Tan, Jing, Huang, Junwen, Liu, Kai, Liu, Kaixin, Gu, Kefan, Zhang, Qinglun, Zhang, Ruitao, Huang, Saike, Cheng, Shen, Liu, Shuaicheng, Wang, Tiancai, Wang, Tiezhen, Sun, Wei, Tang, Wenbin, Wei, Yajun, Chen, Yang, Gui, Youqiang, Zhao, Yucheng, Ma, Yunchao, Wei, Yunfei, Yang, Yunhuan, Guo, Yutong, Chen, Ze, Du, Zhengyuan, Zhang, Ziheng, Liu, Ziming, Yan, Ziwei
Format:	Preprint
Published:	2025
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866909860493262848
author	Yakefu, Adina Xie, Bin Xu, Chongyang Zhang, Enwen Zhou, Erjin Jia, Fan Yang, Haitao Fan, Haoqiang Zhang, Haowei Peng, Hongyang Tan, Jing Huang, Junwen Liu, Kai Liu, Kaixin Gu, Kefan Zhang, Qinglun Zhang, Ruitao Huang, Saike Cheng, Shen Liu, Shuaicheng Wang, Tiancai Wang, Tiezhen Sun, Wei Tang, Wenbin Wei, Yajun Chen, Yang Gui, Youqiang Zhao, Yucheng Ma, Yunchao Wei, Yunfei Yang, Yunhuan Guo, Yutong Chen, Ze Du, Zhengyuan Zhang, Ziheng Liu, Ziming Yan, Ziwei
author_facet	Yakefu, Adina Xie, Bin Xu, Chongyang Zhang, Enwen Zhou, Erjin Jia, Fan Yang, Haitao Fan, Haoqiang Zhang, Haowei Peng, Hongyang Tan, Jing Huang, Junwen Liu, Kai Liu, Kaixin Gu, Kefan Zhang, Qinglun Zhang, Ruitao Huang, Saike Cheng, Shen Liu, Shuaicheng Wang, Tiancai Wang, Tiezhen Sun, Wei Tang, Wenbin Wei, Yajun Chen, Yang Gui, Youqiang Zhao, Yucheng Ma, Yunchao Wei, Yunfei Yang, Yunhuan Guo, Yutong Chen, Ze Du, Zhengyuan Zhang, Ziheng Liu, Ziming Yan, Ziwei
contents	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.
format	Preprint
id	arxiv_https___arxiv_org_abs_2510_17950
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies Yakefu, Adina Xie, Bin Xu, Chongyang Zhang, Enwen Zhou, Erjin Jia, Fan Yang, Haitao Fan, Haoqiang Zhang, Haowei Peng, Hongyang Tan, Jing Huang, Junwen Liu, Kai Liu, Kaixin Gu, Kefan Zhang, Qinglun Zhang, Ruitao Huang, Saike Cheng, Shen Liu, Shuaicheng Wang, Tiancai Wang, Tiezhen Sun, Wei Tang, Wenbin Wei, Yajun Chen, Yang Gui, Youqiang Zhao, Yucheng Ma, Yunchao Wei, Yunfei Yang, Yunhuan Guo, Yutong Chen, Ze Du, Zhengyuan Zhang, Ziheng Liu, Ziming Yan, Ziwei Robotics 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.
title	RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies
topic	Robotics
url	https://arxiv.org/abs/2510.17950