Robot Embodiment
Robot embodiment research investigates how a robot's physical form influences its capabilities and interactions. Current work focuses on developing control policies that generalize across diverse robot morphologies, employing architectures like transformers and leveraging large datasets to train single policies capable of controlling multiple robot types for various tasks (manipulation, locomotion, etc.). This research is crucial for advancing robust and adaptable robots, impacting fields ranging from manufacturing and logistics to human-robot collaboration and assistive technologies by enabling the creation of more versatile and efficient robotic systems.
Papers
The One RING: a Robotic Indoor Navigation Generalist
Ainaz Eftekhar, Luca Weihs, Rose Hendrix, Ege Caglar, Jordi Salvador, Alvaro Herrasti, Winson Han, Eli VanderBil, Aniruddha Kembhavi, Ali Farhadi, Ranjay Krishna, Kiana Ehsani, Kuo-Hao Zeng
RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
Kun Wu, Chengkai Hou, Jiaming Liu, Zhengping Che, Xiaozhu Ju, Zhuqin Yang, Meng Li, Yinuo Zhao, Zhiyuan Xu, Guang Yang, Zhen Zhao, Guangyu Li, Zhao Jin, Lecheng Wang, Jilei Mao, Xinhua Wang, Shichao Fan, Ning Liu, Pei Ren, Qiang Zhang, Yaoxu Lyu, Mengzhen Liu, Jingyang He, Yulin Luo, Zeyu Gao, Chenxuan Li, Chenyang Gu, Yankai Fu, Di Wu, Xingyu Wang, Sixiang Chen, Zhenyu Wang, Pengju An, Siyuan Qian, Shanghang Zhang, Jian Tang