arXiv · cs.AI · Tan Sang Nguyen, Yi Ru Wang, Shailesh Shailesh, Gang Yang, Jiamo Hu, Jianuo Jiang, Haoquan Fang, Zhongzheng Ren, Zhongyi Luo, Ian Chong, Aaron Tung, Santiago Pravisani, Minghui Lin, Yao Mo, Ishneet Singh, Benjamin Tee, Harold Soh, Siddhartha Srinivasa, Dieter Fox, David Hsu, Haoming Song, Maxime Ellerbach, Thomas Wolf, Pepijn Kooijmans, Ruijie He, Michael Cho, Jiafei Duan · 10 小时前模型评分59
RoboColosseum 提出分布式机器人策略评测框架，在 124 个站点完成 5699 次配对试验
RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild
导读
研究团队提出 RoboColosseum 分布式评测框架，把统一策略服务与标准化协议接入多个本地运行的机器人，在 124 个站点完成 5,699 次配对比较。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “We introduce RoboColosseum, a distributed evaluation framework that combines unified policy serving and standardized protocols across a network of locally operated robots in diverse environments.”
- “The Open Track compares models without task-specific adaptation in blinded, pairwise trials under matched local conditions.”
- “The Fine-tune Track measures how well VLA policies adapt to 20 tasks across all four embodiments when each policy receives the same 100 demonstrations per task.”
来源：arXiv · cs.AI · arxiv.org