机器人 / 具身智能

Cosmos 3: Omnimodal World Models for Physical AI

Cosmos 3：面向物理AI的全模态世界模型

NVIDIA, :, Aditi, Niket Agarwal, Arslan Ali, Jon Allen, Martin Antolini, Adeline Aubame, Alisson Azzolini, Junjie Bai, Maciej Bala, Yogesh Balaji, Josh Bapst, Aarti Basant, Mukesh Beladiya, Mohammad Qazim Bhat, Zaid Pervaiz Bhat, Dan Blick, Vanni Brighella, Han Cai, Tiffany Cai, Eric Cameracci, Jiaxin Cao, Yulong Cao, Mark Carlson, Carlos Casanova, Ting-Yun Chang, Yan Chang, Yu-Wei Chao, Prithvijit Chattopadhyay, Roshan Chaudhari, Chieh-Yun Chen, Junyu Chen, Ke Chen, Qizhi Chen, Wenkai Chen, Xiaotong Chen, Yu Chen, An-Chieh Cheng, Click Cheng, Xiu Chia, Jeana Choi, Chaeyeon Chung, Wenyan Cong, Yin Cui, Magdalena Dadela, Nalin Dadhich, Wenliang Dai, Joyjit Daw, Alperen Degirmenci, Rodrigo Vieira Del Monte, Robert Denomme, Sameer Dharur, Marco Di Lucca, Ke Ding, Wenhao Ding, Yifan Ding, Yuzhu Dong, Nicole Drumheller, Yilun Du, Aigul Dzhumamuratova, Aleksandr Efitorov, Hamid Eghbalzadeh, Naomi Eigbe, Imad El Hanafi, Hassan Eslami, Benedikt Falk, Jiaojiao Fan, Jim Fan, Amol Fasale, Sergiy Fefilatyev, Liang Feng, Francesco Ferroni, Sanja Fidler, Xiao Fu, Vikram Fugro, Prashant Gaikwad, TJ Galda, Katelyn Gao, Yihuai Gao, Wenhang Ge, Sreyan Ghosh, Arushi Goel, Vivek Goel, Akash Gokul, Rama Govindaraju, Jinwei Gu, Miguel Guerrero, Elfie Guo, Aryaman Gupta, Siddharth Gururani, Hugo Hadfield, Song Han, Ankur Handa, Zekun Hao, Mohammad Harrim, Ali Hassani, Nathan Hayes-Roth, Yufan He, Chris Helvig, Cyrus Hogg, Madison Huang, Michael Huang, Sophia Huang, Yufan Huang, Jacob Huffman, DeLesley Hutchins, Suneel Indupuru, Boris Ivanovic, Arihant Jain, Joel Jang, Ryan Ji, Yanan Jian, Dongfu Jiang, Jingyi Jin, Atharva Joshi, Nikhilesh Joshi, Pranjali Joshi, Andy Ju, Jaehun Jung, Weiwei Kang, Scott Kassekert, Jan Kautz, Ashna Khetan, Julia Kiczka, Slawek Kierat, Gwanghyun Kim, Kuno Kim, Sunny Kim, Kezhi Kong, Xin Kong, Zhifeng Kong, Tomasz Kornuta, Egor Krivov, Hui Kuang, Saurav Kumar, Chia-Wen Kuo, George Kurian, Wojciech Kutak, JF Lafleche, Himangshu Lahkar, Omar Laymoun, Jayjun Lee, Sanggil Lee, Gabriele Leone, Boyi Li, Freya Li, Jiajun Li, Jinfeng Li, Ling Li, Pengcheng Li, Shangru Li, Tingle Li, Xiaolong Li, Xuan Li, Zhaoshuo Li, Zhiqi Li, Hao Liang, Maosheng Liao, Chen-Hsuan Lin, Tsung-Yi Lin, Ming-Yu Liu, Sifei Liu, Zihan Liu, Hai Loc Lu, Xiangyu Lu, Alice Luo, Ruipu Luo, Wenjie Luo, Jiangran Lyu, Martin Ding Ma, Nic Ma, Qianli Ma, Dawid Majchrowski, Louis Marcoux, Miguel Martin, Qing Miao, Ashkan Mirzaei, Shreyas Misra, Kaichun Mo, Durra Mohsin, Hyejin Moon, Pawel Morkisz, Saeid Motiian, Kirill Motkov, Seungjun Nah, Yashraj Narang, Deepak Narayanan, Thabang Ngazimbi, Julian Ouyang, Shubham Pachori, David Page, Yatian Pang, Sehwi Park, Mahesh Patekar, Mostofa Patwary, Marco Pavone, Trung Pham, Wei Ping, Soha Pouya, Shrimai Prabhumoye, Varun Praveen, Delin Qu, Hesam Rabeti, Morteza Ramezanali, Marilyn Reeb, Xuanchi Ren, Kristen Rumley, Wojciech Rymer, Jun Saito, Yeongho Seol, John Shao, Piyush Shekdar, Tianwei Shen, Humphrey Shi, Min Shi, Stella Shi, Kevin Shih, Mohammad Shoeybi, Mateusz Sieniawski, Shuran Song, Alexander Sotelo, Amir Sotoodeh, Sunil Srinivasa, Vignesh Srinivasakumar, Bartosz Stefaniak, Rahul Heinrich Steiger, Shangkun Sun, Jiaxiang Tang, Shitao Tang, Yangyang Tang, Yue Tang, Tolou Tavakkoli, Kayley Ting, Krzysztof Tomala, Wei-Cheng Tseng, Jibin Varghese, Sergei Vasilev, Thomas Volk, Raju Wagwani, Roger Waleffe, Andrew Z. Wang, Boxiang Wang, Haoxiang Wang, Qiao Wang, Shihao Wang, Shijie Wang, Ting-Chun Wang, Yan Wang, Yu Wang, Rohit Watve, David Wehr, Fangyin Wei, Xinshuo Weng, Jay Zhangjie Wu, Kedi Wu, Hongchi Xia, Summer Xiao, Tianjun Xiao, Kevin Xie, Daguang Xu, Jiashu Xu, Mengyao Xu, Ruqing Xu, Xingqian Xu, Yao Xu, Dinghao Yang, Dong Yang, Hans Yang, Xiaodong Yang, Xuning Yang, Yichu Yang, Yurong You, Zhiding Yu, Hao Yuan, Simon Yuen, Xiaohui Zeng, Pengcuo Zeren, Cindy Zha, Haotian Zhang, Jenny Zhang, Jing Zhang, Liangkai Zhang, Paris Zhang, Shun Zhang, Xuanmeng Zhang, Zhizheng Zhang, Ann Zhao, Yilin Zhao, Yuliya Zhautouskaya, Charles Zhou, Fengzhe Zhou, Shilin Zhu, Yuke Zhu, Dima Zhylko, Artur Zolkowski

专题命中 机器人基础模型 ：为具身智能体提供通用骨干网络

AI总结 提出基于统一混合Transformer架构的全模态世界模型Cosmos 3，联合处理语言、图像、视频、音频和动作序列，在理解和生成任务上达到新最优，为具身智能体提供可扩展的通用骨干。

DexSynRefine: Synthesizing and Refining Human-Object Interaction Motion for Physically Feasible Dexterous Robot Actions

DexSynRefine：合成与精炼人-物交互运动以实现物理可行的灵巧机器人动作

Hyesung Lee, Hyunwoo Jung, Si-Hwan Heo, Sungwook Yang

专题命中 机器人操作 ：提出DexSynRefine框架，实现灵巧机器人操作。

AI总结 提出DexSynRefine框架，通过HOI-MMFP运动先验合成手-物轨迹，结合任务空间残差强化学习和接触动力学适应，将人-物交互数据转化为物理可行的灵巧操作，在五个任务上成功率提升50-70个百分点。

Comments Project page: https://dexsynrefine.github.io/

STORM: Slot-based Task-aware Object-centric Representation for robotic Manipulation

STORM：基于槽的任务感知面向对象的机器人操作表示

Alexandre Chapin, Emmanuel Dellandréa, Liming Chen

专题命中 机器人操作 ：提出STORM模块用于机器人操作表示学习。

AI总结 提出STORM模块，通过多阶段训练策略将冻结的视觉基础模型与语义感知槽结合，生成面向对象的任务感知表示，提升机器人操作在视觉干扰下的泛化性和控制性能。

R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations

R2BC: 从单智能体演示进行多智能体模仿学习

Connor Mattson, Varun Raveendra, Ellen Novoseller, Nicholas Waytowich, Vernon J. Lawhern, Daniel S. Brown

专题命中 机器人学习 ：多机器人模仿学习，核心是机器人学习

AI总结 提出R2BC方法，通过轮换单智能体演示训练多机器人系统，无需联合动作空间演示，在模拟和实物任务中性能媲美或超越基于特权同步演示的基线方法。

Comments 8 pages, 6 figures. In Proceedings: IEEE International Conference on Robotics & Automation (ICRA 2026)

Bench-Push: Benchmarking Pushing-based Navigation and Manipulation Tasks for Mobile Robots

Bench-Push：基于推动的移动机器人导航与操作任务基准测试

Ninghan Zhong, Steven Caro, Megnath Ramesh, Rishi Bhatnagar, Avraiem Iskandar, Stephen L. Smith

专题命中 机器人学习 ：提出推动式移动机器人导航与操作基准

AI总结 提出首个统一的推动式移动机器人导航与操作基准Bench-Push，包含多种模拟环境、新评估指标和基线实现，用于解决可移动障碍物环境中的机器人推动任务评估问题。

Comments Published in CRV 2026

Tilt-Ropter: A Fully Actuated Hybrid Aerial-Terrestrial Vehicle with Tilt Rotors and Passive Wheels

Tilt-Ropter: 一种带有倾转旋翼和被动轮的全驱动混合空中-地面车辆

Ruoyu Wang, Xuchen Liu, Zongzhou Wu, Zixuan Guo, Wendi Ding, Ben M. Chen

专题命中 机器人学习 ：提出混合空中-地面车辆Tilt-Ropter，属于机器人。

AI总结 提出全驱动混合空中-地面车辆Tilt-Ropter，通过倾转旋翼和被动轮实现高效多模态运动，并设计统一非线性模型预测控制器实现低跟踪误差和地面运动功耗降低92.8%。

Comments 8 pages, 10 figures. Accepted by the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)

Mutual Adaptation in Human-Robot Co-Transportation with Human Preference Uncertainty

人机协同运输中考虑人类偏好不确定性的相互适应

Al Jaber Mahmud, Weizi Li, Xuan Wang

专题命中 机器人学习 ：人机协同运输中的相互适应

AI总结 针对人机协同运输中人类偏好参数不确定及适应策略平衡问题，提出统一框架，通过建模偏好概率分布、时变固执度及协调规划模型，结合位姿优化策略，实现相互适应以提升任务性能。

Comments 9 pages, 6 figures

TurboMap: GPU-Accelerated Local Mapping for Visual SLAM

TurboMap: 面向视觉SLAM的GPU加速局部建图

Parsa Hosseininejad, Kimia Khabiri, Shishir Gopinath, Soudabeh Mohammadhashemi, Karthik Dantu, Steven Y. Ko

专题命中 机器人学习 ：SLAM是机器人感知的核心技术

AI总结 针对视觉SLAM中局部建图延迟问题，提出GPU并行化与CPU优化结合的TurboMap后端，通过重构地图点创建、融合及关键帧管理，实现1.3-1.6倍加速且保持精度。

Comments Accepted for presentation at IROS 2026, preprint

Embedding Semantic Risk into Distance Fields and CBFs for Online Monocular Safe Control

将语义风险嵌入距离场和CBF用于在线单目安全控制

Dawei Zhang, Nuo Chen, Shuo Liu, Roberto Tron, Zhiwen Fan

专题命中 具身导航 ：单目安全控制，语义风险嵌入距离场用于导航

AI总结 提出一种在线单目感知到控制框架，通过将语义风险直接嵌入欧几里得符号距离场（ESDF），在控制优化前编码风险，实现基于控制障碍函数（CBF）的语义感知安全导航与遥操作。

RSLCPP -- Deterministic Simulations Using ROS 2

RSLCPP——使用ROS 2进行确定性仿真

Simon Sagmeister, Marcel Weinmann, Phillip Pitschi, Markus Lienkamp

专题命中 其他机器人 ：使用ROS 2实现确定性仿真，用于机器人开发

AI总结 针对ROS异步多进程设计导致仿真结果不可复现的问题，提出RSLCPP库，通过确定性回调执行实现跨平台可复现仿真，无需修改现有节点代码。

Comments Accepted for publication at the 'IEEE Robotics and Automation Practice'

Why Automate This? Exploring Correlations Between Desire for Robotic Automation, Invested Time and Well-Being

为什么自动化这个？探索机器人自动化愿望、投入时间与幸福感之间的相关性

Ruchira Ray, Leona Pang, Sanjana Srivastava, Li Fei-Fei, Samantha Shorey, Roberto Martín-Martín

专题命中 其他机器人 ：探索机器人自动化偏好与时间、幸福感的相关性。

AI总结 本研究利用BEHAVIOR-1K等数据集，发现活动时间并非自动化偏好的强预测因子，而幸福感和痛苦感是最强指标，并揭示了性别和收入水平的差异。

Comments 26 pages, 14 figures