Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer

作者：Gemini Robotics Team, Abbas Abdolmaleki, Saminda Abeyruwan, Joshua Ainslie, Jean-Baptiste Alayrac, Montserrat Gonzalez Arenas, Ashwin Balakrishna, Nathan Batchelor, Alex Bewley, Jeff Bingham, Michael Bloesch, Konstantinos Bousmalis, Philémon Brakel, Anthony Brohan, Thomas Buschmann, Arunkumar Byravan, Serkan Cabi, Ken Caluwaerts, Federico Casarini, Christine W. Chan, Oscar Chang, London Chappellet-Volpini, José Enrique Chen, Xi Chen, Hao-Tien Lewis Chiang, Krzysztof Choromański, Adrian Collister, David B. D’Ambrosio, Sudeep Dasari, Todor Davchev, Meet Dave, Coline Devin, Norman Di Palo, Tianli Ding, Carl Doersch, Adil Dostmohamed, Yilun Du, Debidatta Dwibedi, Sathish Thoppay Egambaram, Michael Elabd, Tom Erez, Xiaolin Fang, Claudio Fantacci, Cody Fong, Erik Frey, Chuyuan Fu, Gao, Ruiqi, Marissa Giustina, Keerthana Gopalakrishnan, Laura Graesser, Oliver Groth, Agrim Gupta, Roland Hafner, S. M. Hansen, Leonard Hasenclever, Sam Haves, Nicolas Heess, Brandon Hernaez, Alex Hofer, Jasmine Hsu, Lü Huang, Sandy H. Huang, Atıl Işçen, Mithun George Jacob, Deepali Jain, Sally Jesmonth, Abhishek Jindal, Ryan Julian, Dmitry Kalashnikov, Mustafa Emre Karagozler, Stefani Karp, Matija Kecman, J. Chase Kew, Donnie Kim, Frank Kim, Junkyung Kim, Thomas Kipf, Sean Kirmani, Ksenia Konyushkova, Li Yang Ku, Yuheng Kuang, Thomas Lampe, Antoine Laurens, Tuan Anh Lê, Isabel Leal, Alex X. Lee, Tsang-Wei Edward Lee, Guy Lever, Jacky Liang, Li-Heng Lin, Fangchen Liu, Shangbang Long, C.-W. Lu, Sharath Maddineni, Anirudha Majumdar, Kevis-Kokitsi Maninis, Andrew Marmon, Sergio Martinez, Assaf Hurwitz Michaely, Niko Milonopoulos, Joss Moore, Moreno, Robert, Michael Neunert, Francesco Nori, Joy Ortiz, Kenneth Oslund, Carolina Parada, Emilio Parisotto, Amaris Paryag, Acorn Pooley, Thomas Power, Alessio Quaglino, Haroon Qureshi, Rajkumar Vasudeva Raju, Ran, Helen, Dushyant Rao, Kanishka Rao, Isaac Reid, David Rendleman, Krista Reymann, M.A. Rivas, F. Romanò, Yulia Rubanova, Peter Pastor Sampedro, Pannag Sanketi, Dhruv Shah, Mohit Sharma, Shea, Kathryn, M.H Shridhar, Charles Shu, Vikas Sindhwani, Sumeet Singh, Radu Soricut, Rachel Sterneck, Ian Storz, Razvan Surdulescu, Jie Tan, Jonathan Tompson, Saran Tunyasuvunakool, Jake Varley, Grace Vesom, Giulia Vezzani, Maria Bauzá Villalonga, Oriol Vinyals, René Wagner, Ayzaan Wahid, Stefan Welker, Paul Wohlhart, Chengda Wu, Markus Wulfmeier, Fei Xia, Ted Xiao, Annie Xie, Jinyu Xie, Peng Xu, Sichun Xu, Ying Xu, Zhuo Xu, Jimmy Yan, Sherry Yang, Yang, Skye, Yuxiang Yang, Hongnian Yu, Wenhao Yu, Wentao Yuan, Yuan Yuan, Jingwei Zhang, Tingnan Zhang, Zhiyuan Zhang, Allan Zhou, Guangyao Zhou, Yuxiang Zhou · 发表于：arXiv (Cornell University) · 年份：2025 · DOI：10.48550/arxiv.2510.03342 · 被引用次数：1 · 研究领域：AI-based Problem Solving and Planning、Modular Robots and Swarm Intelligence、Robot Manipulation and Learning

General-purpose robots need a deep understanding of the physical world, advanced reasoning, and general and dexterous control. This report introduces the latest generation of the Gemini Robotics model family: Gemini Robotics 1.5, a multi-embodiment Vision-Language-Action (VLA) model, and Gemini Robotics-ER 1.5, a state-of-the-art Embodied Reasoning (ER) model. We are bringing together three major innovations. First, Gemini Robotics 1.5 features a novel architecture and a Motion Transfer (MT) mechanism, which enables it to learn from heterogeneous, multi-embodiment robot data and makes the VLA more general. Second, Gemini Robotics 1.5 interleaves actions with a multi-level internal reasoning process in natural language. This enables the robot to "think before acting" and notably improves its ability to decompose and execute complex, multi-step tasks, and also makes the robot's behavior more interpretable to the user. Third, Gemini Robotics-ER 1.5 establishes a new state-of-the-art for embodied reasoning, i.e., for reasoning capabilities that are critical for robots, such as visual and spatial understanding, task planning, and progress estimation. Together, this family of models takes us a step towards an era of physical agents-enabling robots to perceive, think and then act so they can solve complex multi-step tasks.