Cover Image

Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Tianxing, Wang, Kaixuan, Yang, Zhaohui, Zhang, Yuhao, Chen, Zanxin, Chen, Baijun, Dong, Wanxi, Liu, Ziyuan, Chen, Dong, Yang, Tianshuo, Yu, Haibao, Yang, Xiaokang, Qin, Yusen, Xie, Zhiqiang, Mu, Yao, Luo, Ping, Nian, Tian, Deng, Weiliang, Ge, Yiheng, Liu, Yibin, Li, Zixuan, Wang, Dehui, Liang, Zhixuan, Xie, Haohui, Zeng, Rijie, Ge, Yunfei, Cong, Peiqing, He, Guannan, Han, Zhaoming, Yin, Ruocheng, Guo, Jingxiang, Lin, Lunkai, Xu, Tianling, Bi, Hongzhe, Lin, Xuewu, Lin, Tianwei, Luo, Shujie, Li, Keyu, Zhao, Ziyan, Fan, Ke, Xu, Heyang, Peng, Bo, Gao, Wenlong, Li, Dongjiang, Jin, Feng, Shen, Hui, Li, Jinming, Cui, Chaowei, Chen, Yu, Peng, Yaxin, Zeng, Lingdong, Dong, Wenlong, Li, Tengfei, Ke, Weijie, Chen, Jun, Bao, Erdemt, Lan, Tian, Liu, Tenglong, Yang, Jin, Zhuang, Huiping, Jia, Baozhi, Zhang, Shuai, Zou, Zhengfeng, Guan, Fangheng, Jia, Tianyi, Zhou, Ke, Zhang, Hongjiu, Han, Yating, Fang, Cheng, Zou, Yixian, Xu, Chongyang, Zhang, Qinglun, Cheng, Shen, Wang, Xiaohe, Tan, Ping, Fan, Haoqiang, Liu, Shuaicheng, Chen, Jiaheng, Huang, Chuxuan, Lin, Chengliang, Luo, Kaijun, Yue, Boyu, Liu, Yi, Chen, Jinyu, Tan, Zichang, Deng, Liming, Xu, Shuo, Cai, Zijian, Yin, Shilong, Wang, Hao, Liu, Hongshan, Li, Tianyang, Shi, Long, Xu, Ran, Xu, Huilin, Zhang, Zhengquan, Xu, Congsheng, Yang, Jinchang, Xu, Feng
Format:	Preprint
Published:	2025
Subjects:	Robotics Artificial Intelligence Machine Learning Multiagent Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866916823813849088
author	Chen, Tianxing Wang, Kaixuan Yang, Zhaohui Zhang, Yuhao Chen, Zanxin Chen, Baijun Dong, Wanxi Liu, Ziyuan Chen, Dong Yang, Tianshuo Yu, Haibao Yang, Xiaokang Qin, Yusen Xie, Zhiqiang Mu, Yao Luo, Ping Nian, Tian Deng, Weiliang Ge, Yiheng Liu, Yibin Li, Zixuan Wang, Dehui Liang, Zhixuan Xie, Haohui Zeng, Rijie Ge, Yunfei Cong, Peiqing He, Guannan Han, Zhaoming Yin, Ruocheng Guo, Jingxiang Lin, Lunkai Xu, Tianling Bi, Hongzhe Lin, Xuewu Lin, Tianwei Luo, Shujie Li, Keyu Zhao, Ziyan Fan, Ke Xu, Heyang Peng, Bo Gao, Wenlong Li, Dongjiang Jin, Feng Shen, Hui Li, Jinming Cui, Chaowei Chen, Yu Peng, Yaxin Zeng, Lingdong Dong, Wenlong Li, Tengfei Ke, Weijie Chen, Jun Bao, Erdemt Lan, Tian Liu, Tenglong Yang, Jin Zhuang, Huiping Jia, Baozhi Zhang, Shuai Zou, Zhengfeng Guan, Fangheng Jia, Tianyi Zhou, Ke Zhang, Hongjiu Han, Yating Fang, Cheng Zou, Yixian Xu, Chongyang Zhang, Qinglun Cheng, Shen Wang, Xiaohe Tan, Ping Fan, Haoqiang Liu, Shuaicheng Chen, Jiaheng Huang, Chuxuan Lin, Chengliang Luo, Kaijun Yue, Boyu Liu, Yi Chen, Jinyu Tan, Zichang Deng, Liming Xu, Shuo Cai, Zijian Yin, Shilong Wang, Hao Liu, Hongshan Li, Tianyang Shi, Long Xu, Ran Xu, Huilin Zhang, Zhengquan Xu, Congsheng Yang, Jinchang Xu, Feng
author_facet	Chen, Tianxing Wang, Kaixuan Yang, Zhaohui Zhang, Yuhao Chen, Zanxin Chen, Baijun Dong, Wanxi Liu, Ziyuan Chen, Dong Yang, Tianshuo Yu, Haibao Yang, Xiaokang Qin, Yusen Xie, Zhiqiang Mu, Yao Luo, Ping Nian, Tian Deng, Weiliang Ge, Yiheng Liu, Yibin Li, Zixuan Wang, Dehui Liang, Zhixuan Xie, Haohui Zeng, Rijie Ge, Yunfei Cong, Peiqing He, Guannan Han, Zhaoming Yin, Ruocheng Guo, Jingxiang Lin, Lunkai Xu, Tianling Bi, Hongzhe Lin, Xuewu Lin, Tianwei Luo, Shujie Li, Keyu Zhao, Ziyan Fan, Ke Xu, Heyang Peng, Bo Gao, Wenlong Li, Dongjiang Jin, Feng Shen, Hui Li, Jinming Cui, Chaowei Chen, Yu Peng, Yaxin Zeng, Lingdong Dong, Wenlong Li, Tengfei Ke, Weijie Chen, Jun Bao, Erdemt Lan, Tian Liu, Tenglong Yang, Jin Zhuang, Huiping Jia, Baozhi Zhang, Shuai Zou, Zhengfeng Guan, Fangheng Jia, Tianyi Zhou, Ke Zhang, Hongjiu Han, Yating Fang, Cheng Zou, Yixian Xu, Chongyang Zhang, Qinglun Cheng, Shen Wang, Xiaohe Tan, Ping Fan, Haoqiang Liu, Shuaicheng Chen, Jiaheng Huang, Chuxuan Lin, Chengliang Luo, Kaijun Yue, Boyu Liu, Yi Chen, Jinyu Tan, Zichang Deng, Liming Xu, Shuo Cai, Zijian Yin, Shilong Wang, Hao Liu, Hongshan Li, Tianyang Shi, Long Xu, Ran Xu, Huilin Zhang, Zhengquan Xu, Congsheng Yang, Jinchang Xu, Feng
contents	Embodied Artificial Intelligence (Embodied AI) is an emerging frontier in robotics, driven by the need for autonomous systems that can perceive, reason, and act in complex physical environments. While single-arm systems have shown strong task performance, collaborative dual-arm systems are essential for handling more intricate tasks involving rigid, deformable, and tactile-sensitive objects. To advance this goal, we launched the RoboTwin Dual-Arm Collaboration Challenge at the 2nd MEIS Workshop, CVPR 2025. Built on the RoboTwin Simulation platform (1.0 and 2.0) and the AgileX COBOT-Magic Robot platform, the competition consisted of three stages: Simulation Round 1, Simulation Round 2, and a final Real-World Round. Participants totally tackled 17 dual-arm manipulation tasks, covering rigid, deformable, and tactile-based scenarios. The challenge attracted 64 global teams and over 400 participants, producing top-performing solutions like SEM and AnchorDP3 and generating valuable insights into generalizable bimanual policy learning. This report outlines the competition setup, task design, evaluation methodology, key findings and future direction, aiming to support future research on robust and generalizable bimanual manipulation policies. The Challenge Webpage is available at https://robotwin-benchmark.github.io/cvpr-2025-challenge/.
format	Preprint
id	arxiv_https___arxiv_org_abs_2506_23351
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop Chen, Tianxing Wang, Kaixuan Yang, Zhaohui Zhang, Yuhao Chen, Zanxin Chen, Baijun Dong, Wanxi Liu, Ziyuan Chen, Dong Yang, Tianshuo Yu, Haibao Yang, Xiaokang Qin, Yusen Xie, Zhiqiang Mu, Yao Luo, Ping Nian, Tian Deng, Weiliang Ge, Yiheng Liu, Yibin Li, Zixuan Wang, Dehui Liang, Zhixuan Xie, Haohui Zeng, Rijie Ge, Yunfei Cong, Peiqing He, Guannan Han, Zhaoming Yin, Ruocheng Guo, Jingxiang Lin, Lunkai Xu, Tianling Bi, Hongzhe Lin, Xuewu Lin, Tianwei Luo, Shujie Li, Keyu Zhao, Ziyan Fan, Ke Xu, Heyang Peng, Bo Gao, Wenlong Li, Dongjiang Jin, Feng Shen, Hui Li, Jinming Cui, Chaowei Chen, Yu Peng, Yaxin Zeng, Lingdong Dong, Wenlong Li, Tengfei Ke, Weijie Chen, Jun Bao, Erdemt Lan, Tian Liu, Tenglong Yang, Jin Zhuang, Huiping Jia, Baozhi Zhang, Shuai Zou, Zhengfeng Guan, Fangheng Jia, Tianyi Zhou, Ke Zhang, Hongjiu Han, Yating Fang, Cheng Zou, Yixian Xu, Chongyang Zhang, Qinglun Cheng, Shen Wang, Xiaohe Tan, Ping Fan, Haoqiang Liu, Shuaicheng Chen, Jiaheng Huang, Chuxuan Lin, Chengliang Luo, Kaijun Yue, Boyu Liu, Yi Chen, Jinyu Tan, Zichang Deng, Liming Xu, Shuo Cai, Zijian Yin, Shilong Wang, Hao Liu, Hongshan Li, Tianyang Shi, Long Xu, Ran Xu, Huilin Zhang, Zhengquan Xu, Congsheng Yang, Jinchang Xu, Feng Robotics Artificial Intelligence Machine Learning Multiagent Systems Embodied Artificial Intelligence (Embodied AI) is an emerging frontier in robotics, driven by the need for autonomous systems that can perceive, reason, and act in complex physical environments. While single-arm systems have shown strong task performance, collaborative dual-arm systems are essential for handling more intricate tasks involving rigid, deformable, and tactile-sensitive objects. To advance this goal, we launched the RoboTwin Dual-Arm Collaboration Challenge at the 2nd MEIS Workshop, CVPR 2025. Built on the RoboTwin Simulation platform (1.0 and 2.0) and the AgileX COBOT-Magic Robot platform, the competition consisted of three stages: Simulation Round 1, Simulation Round 2, and a final Real-World Round. Participants totally tackled 17 dual-arm manipulation tasks, covering rigid, deformable, and tactile-based scenarios. The challenge attracted 64 global teams and over 400 participants, producing top-performing solutions like SEM and AnchorDP3 and generating valuable insights into generalizable bimanual policy learning. This report outlines the competition setup, task design, evaluation methodology, key findings and future direction, aiming to support future research on robust and generalizable bimanual manipulation policies. The Challenge Webpage is available at https://robotwin-benchmark.github.io/cvpr-2025-challenge/.
title	Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop
topic	Robotics Artificial Intelligence Machine Learning Multiagent Systems
url	https://arxiv.org/abs/2506.23351