arXiv cs.RO· NVIDIA, :, Anis Ahmad, Jon Allen, Malik Aqeel Anwar, Jesse Archer, Maciej Bala, Piotr Barejko, Aarti Basant, Dan Blick, Taras Bolzhelarskyi, Henry Che, Jin Chen, Yukang Chen, Tae Eun Choe, Yuzhu Dong, Nat Duca, Liang Feng, Francesco Ferroni, Xiao Fu, Mohit Gambhir, Vivek Goel, Rony Goldenthal, Aryaman Gupta, Ali Hassani, Nathan Hayes-Roth, Yong He, Michael Honke, Shengyu Huang, Wei Huang, DeLesley Hutchins, Suneel Indupuru, Pooya Jannaty, Jingyi Jin, Janmesh Kalra, Ashna Khetan, Xin Kong, Aleksandr Korovko, Hui Kuang, Zhengfei Kuang, George Kurian, Jean-Francois Lafleche, Jayjun Lee, Justin Leung, William Lew, Xiang Li, Zhaoshuo Li, Chen-Hsuan Lin, Ming-Yu Liu, Xiangyu Lu, Yuhang Lu, Martin Ding Ma, Qianli Ma, Aditya Mahajan, Miguel Martin, Janarbek Matai, Jonathan McCaffrey, Qing Miao, Ashkan Mirzaei, Mustafa Munir, Sangmin Oh, David Pankratz, Trung Pham, Marilyn Reeb, Gavriel State, Jiaxiang Tang, Shitao Tang, Yue Tang, Tolou Tavakkoli, Alexander Temirov, Hweimi Tsou, Sergei Vasilev, Thomas Volk, Andrew Z. Wang, Hao Wang, Shijie Wang, Zhonghao Wang, David Wehr, Shumian Xin, Mengyao Xu, Yao Xu, Shuai Yang, Sophia Zalewski, Pengcuo Zeren, Cindy Zha, Jing Zhang, Yuliya Zhautouskaya, Kaiwen Zheng, Andrew Zhu, Rick Zhuang·· 5 天前精选AI 评分78
NVIDIA 提出基于 Cosmos 的交互式世界仿真框架
Interactive World Simulation with Cosmos for Physical AI
AI 导读
NVIDIA 提出一个共享框架,将 Cosmos 世界基础模型适配为面向 Physical AI 的实时交互式世界仿真。该框架能根据动作和场景控制流式输出视觉观测,既支持预测动作的视觉后果,也支持从外部仿真器维护的物理状态生成观测。作者在相机导航、机器人操作、可控视频迁移和多视角自动驾驶仿真中做了演示,并公开了代码与模型检查点。
推荐理由
NVIDIA 把 Cosmos 世界基础模型改造成可实时交互的仿真框架,并公开代码与权重,读者可据此判断世界模型在机器人训练中的可用边界。
来源:arXiv cs.RO · arxiv.org