arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.04434cs.ROcs.AIcs.CVcs.GR
收藏

RoboDojo:用于综合评估通用机器人操作策略的统一模拟与现实基准测试

RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies

UC Berkeley(加州大学伯克利分校);THU(清华大学);PKU(北京大学);Stanford(斯坦福大学);MIT(麻省理工学院);UNC(北卡罗来纳大学);Princeton(普林斯顿大学);CMU(卡内基梅隆大学);NUS(新加坡国立大学);NTU(南洋理工大学);CUHK(香港中文大学);SJTU(上海交通大学);HKUST (GZ)(香港科技大学(广州));ZJU(浙江大学);Yale(耶鲁大学)
Tianxing Chen, Yue Chen, Zixuan Li, Junyuan Tang, Kailun Su, Haoran Lu, Weijie Wan, Baijun Chen, Songling Liu, Haowen Yan, Honghao Su, Zhiyang Dou, Kaixuan Wang… 展开作者

Tianxing Chen, Yue Chen, Zixuan Li, Junyuan Tang, Kailun Su, Haoran Lu, Weijie Wan, Baijun Chen, Songling Liu, Haowen Yan, Honghao Su, Zhiyang Dou, Kaixuan Wang, Dandan Zhang, Yunze Liu, Yan Qin, Qiwei Liang, Qiwei Wu, Zijian Lin, Wenwei Lin, Yuran Wang, Minghua He, Tianshu Wu, Ruihai Wu, Jingquan Zhou, Kai-Chong Lei, Haibao Yu, Yuanfeng Ji, Weiyang Jin, Guanyu Lin, Xiaofan Li, Qi Xiong, Renjing Xu, Zhongyu Li, Wenhao Chai, Enze Xie, Ziwei Wang, Yao Mu, Hao Dong, Wojciech Matusik, Mingyu Ding, Wenbo Ding, Ping Luo, Masayoshi Tomizuka

AI总结:

现有基准测试在系统评估通用机器人操作策略能力方面有限,本文引入RoboDojo统一基准测试,含模拟与现实任务,支持多维度评估及可扩展评估,还建立了公共排行榜与系统分析。

摘要:

通用机器人操作策略发展迅速,但现有基准测试在系统评估其能力方面存在局限。许多基准测试依赖简单、短期或技能狭窄的任务,且能力覆盖有限,通常仅在模拟或现实世界中进行。模拟能提供可扩展反馈,但忽略物理部署挑战,而现实世界评估成本高、耗时且难以重现。我们引入了RoboDojo,这是一个用于综合评估通用机器人操作策略的统一模拟与现实基准测试。RoboDojo包括42个模拟任务和18个现实世界任务,涵盖了多样且互补的操作能力。模拟基准测试评估五个维度:泛化、记忆、精度、长期执行和开放词汇指令跟随,而现实世界基准测试则使策略面临具有挑战性的物理世界部署条件。RoboDojo通过在Isaac Sim中进行异构并行模拟支持可扩展评估,并提供RoboDojo-RealEval,这是一个具有远程云访问、标准化硬件、场景重置、评估协议和部署接口的可重现现实世界评估系统。与XPolicyLab一起,策略可以一次性集成并在模拟和现实世界设置中进行评估,只需进行最小的调整。我们将30个策略集成到XPolicyLab中,并在RoboDojo上对它们进行评估,建立了一个公共排行榜并对当前策略性能进行了系统分析。网站可通过此http URL访问。

英文摘要:

Generalist robot manipulation policies have advanced rapidly, yet existing benchmarks remain limited in systematically evaluating their capabilities. Many rely on simple, short-horizon, or skill-narrow tasks with limited capability coverage, and are often conducted only in simulation or only in the real world. Simulation enables scalable feedback but misses physical deployment challenges, while real-world evaluation is costly, time-consuming, and difficult to reproduce. We introduce RoboDojo, a unified sim-and-real benchmark for comprehensive evaluation of generalist robot manipulation policies. RoboDojo includes 42 simulation tasks and 18 real-world tasks covering diverse and complementary manipulation capabilities. The simulation benchmark evaluates five dimensions: generalization, memory, precision, long-horizon execution, and open-vocabulary instruction following, while the real-world benchmark exposes policies to challenging physical-world deployment conditions. RoboDojo supports scalable evaluation through heterogeneous parallel simulation in Isaac Sim and provides RoboDojo-RealEval, a reproducible real-world evaluation system with remote cloud access, standardized hardware, scene reset, evaluation protocol, and deployment interface. Together with XPolicyLab, policies can be integrated once and evaluated across simulation and real-world settings with minimal adaptation. We integrate 30 policies into XPolicyLab and evaluate them on RoboDojo, establishing a public leaderboard and systematic analysis of current policy performance. The website is available at http://robodojo-benchmark.com/.

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。

↑