Copertina

RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Shihan, Liu, Xuecheng, Xie, Shaoxuan, Wang, Pengwei, Li, Xinghang, Yang, Bowen, Li, Zhe, Zhu, Kai, Wu, Hongyu, Liu, Yiheng, Long, Zhaoye, Xu, Runtian, Wang, Yue, Liu, Chong, Wang, Dihan, Ni, Ziqiang, Yang, Xiang, Liu, You, Feng, Ruoxuan, Zhang, Lei, Huang, Denghang, Jin, Chenghao, Yin, Anlan, Wang, Xinlong, Sun, Zhenguo, Zhao, Junkai, Du, Mengfei, Cao, Mingyu, Chen, Xiansheng, Cheng, Hongyang, Zhang, Xiaojie, Fu, Yankai, Chen, Ning, Chi, Cheng, Chen, Sixiang, Lyu, Huaihai, Hao, Xiaoshuai, Wang, Yequan, Lei, Bo, Liu, Dong, Yang, Xi, Jiao, Yance, Pan, Tengfei, Zhang, Yunyan, Wang, Songjing, Zhang, Ziqian, Liu, Xu, Zhang, Ji, Meng, Caowei, Zhang, Zhizheng, Gao, Jiyang, Wang, Song, Leng, Xiaokun, Xie, Zhiqiang, Zhou, Zhenzhen, Huang, Peng, Yang, Wu, Guo, Yandong, Zhu, Yichao, Zheng, Suibing, Cheng, Hao, Ding, Xinmin, Yue, Yang, Wang, Huanqian, Chen, Chi, Pang, Jingrui, Qian, YuXi, Geng, Haoran, Gao, Lianli, Li, Haiyuan, Fang, Bin, Huang, Gao, Yang, Yaodong, Dong, Hao, Wang, He, Zhao, Hang, Mu, Yadong, Hu, Di, Zhao, Hao, Huang, Tiejun, Zhang, Shanghang, Lin, Yonghua, Wang, Zhongyuan, Yao, Guocai
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

_version_	1866910124010897408
author	Wu, Shihan Liu, Xuecheng Xie, Shaoxuan Wang, Pengwei Li, Xinghang Yang, Bowen Li, Zhe Zhu, Kai Wu, Hongyu Liu, Yiheng Long, Zhaoye Xu, Runtian Wang, Yue Liu, Chong Wang, Dihan Ni, Ziqiang Yang, Xiang Liu, You Feng, Ruoxuan Zhang, Lei Huang, Denghang Jin, Chenghao Yin, Anlan Wang, Xinlong Sun, Zhenguo Zhao, Junkai Du, Mengfei Cao, Mingyu Chen, Xiansheng Cheng, Hongyang Zhang, Xiaojie Fu, Yankai Chen, Ning Chi, Cheng Chen, Sixiang Lyu, Huaihai Hao, Xiaoshuai Wang, Yequan Lei, Bo Liu, Dong Yang, Xi Jiao, Yance Pan, Tengfei Zhang, Yunyan Wang, Songjing Zhang, Ziqian Liu, Xu Zhang, Ji Meng, Caowei Zhang, Zhizheng Gao, Jiyang Wang, Song Leng, Xiaokun Xie, Zhiqiang Zhou, Zhenzhen Huang, Peng Yang, Wu Guo, Yandong Zhu, Yichao Zheng, Suibing Cheng, Hao Ding, Xinmin Yue, Yang Wang, Huanqian Chen, Chi Pang, Jingrui Qian, YuXi Geng, Haoran Gao, Lianli Li, Haiyuan Fang, Bin Huang, Gao Yang, Yaodong Dong, Hao Wang, He Zhao, Hang Mu, Yadong Hu, Di Zhao, Hao Huang, Tiejun Zhang, Shanghang Lin, Yonghua Wang, Zhongyuan Yao, Guocai
author_facet	Wu, Shihan Liu, Xuecheng Xie, Shaoxuan Wang, Pengwei Li, Xinghang Yang, Bowen Li, Zhe Zhu, Kai Wu, Hongyu Liu, Yiheng Long, Zhaoye Xu, Runtian Wang, Yue Liu, Chong Wang, Dihan Ni, Ziqiang Yang, Xiang Liu, You Feng, Ruoxuan Zhang, Lei Huang, Denghang Jin, Chenghao Yin, Anlan Wang, Xinlong Sun, Zhenguo Zhao, Junkai Du, Mengfei Cao, Mingyu Chen, Xiansheng Cheng, Hongyang Zhang, Xiaojie Fu, Yankai Chen, Ning Chi, Cheng Chen, Sixiang Lyu, Huaihai Hao, Xiaoshuai Wang, Yequan Lei, Bo Liu, Dong Yang, Xi Jiao, Yance Pan, Tengfei Zhang, Yunyan Wang, Songjing Zhang, Ziqian Liu, Xu Zhang, Ji Meng, Caowei Zhang, Zhizheng Gao, Jiyang Wang, Song Leng, Xiaokun Xie, Zhiqiang Zhou, Zhenzhen Huang, Peng Yang, Wu Guo, Yandong Zhu, Yichao Zheng, Suibing Cheng, Hao Ding, Xinmin Yue, Yang Wang, Huanqian Chen, Chi Pang, Jingrui Qian, YuXi Geng, Haoran Gao, Lianli Li, Haiyuan Fang, Bin Huang, Gao Yang, Yaodong Dong, Hao Wang, He Zhao, Hang Mu, Yadong Hu, Di Zhao, Hao Huang, Tiejun Zhang, Shanghang Lin, Yonghua Wang, Zhongyuan Yao, Guocai
contents	Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due to the significant hardware heterogeneity across bimanual robotic platforms. To bridge this gap, we introduce RoboCOIN, a large-scale multi-embodiment bimanual manipulation dataset comprising over 180,000 demonstrations collected from 15 distinct robotic platforms. Spanning 16 diverse environments-including residential, commercial, and industrial settings-the dataset features 421 bimanual tasks systematically categorized by 39 bimanual collaboration actions and 432 objects. A key innovation of our work is the hierarchical capability pyramid, which provides granular annotations ranging from trajectory-level concepts to segment-level subtasks and frame-level kinematics. Furthermore, we present CoRobot, an efficient data processing pipeline powered by the Robot Trajectory Markup Language (RTML), designed to facilitate quality assessment, automated annotation, and unified multi-embodiment and data management. Extensive experiments demonstrate the effectiveness of RoboCOIN in enhancing the performance of various bimanual manipulation models across a wide spectrum of robotic embodiments. The entire dataset and codebase are fully open-sourced, providing a valuable resource for advancing research in bimanual and multi-embodiment manipulation.
format	Preprint
id	arxiv_https___arxiv_org_abs_2511_17441
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation Wu, Shihan Liu, Xuecheng Xie, Shaoxuan Wang, Pengwei Li, Xinghang Yang, Bowen Li, Zhe Zhu, Kai Wu, Hongyu Liu, Yiheng Long, Zhaoye Xu, Runtian Wang, Yue Liu, Chong Wang, Dihan Ni, Ziqiang Yang, Xiang Liu, You Feng, Ruoxuan Zhang, Lei Huang, Denghang Jin, Chenghao Yin, Anlan Wang, Xinlong Sun, Zhenguo Zhao, Junkai Du, Mengfei Cao, Mingyu Chen, Xiansheng Cheng, Hongyang Zhang, Xiaojie Fu, Yankai Chen, Ning Chi, Cheng Chen, Sixiang Lyu, Huaihai Hao, Xiaoshuai Wang, Yequan Lei, Bo Liu, Dong Yang, Xi Jiao, Yance Pan, Tengfei Zhang, Yunyan Wang, Songjing Zhang, Ziqian Liu, Xu Zhang, Ji Meng, Caowei Zhang, Zhizheng Gao, Jiyang Wang, Song Leng, Xiaokun Xie, Zhiqiang Zhou, Zhenzhen Huang, Peng Yang, Wu Guo, Yandong Zhu, Yichao Zheng, Suibing Cheng, Hao Ding, Xinmin Yue, Yang Wang, Huanqian Chen, Chi Pang, Jingrui Qian, YuXi Geng, Haoran Gao, Lianli Li, Haiyuan Fang, Bin Huang, Gao Yang, Yaodong Dong, Hao Wang, He Zhao, Hang Mu, Yadong Hu, Di Zhao, Hao Huang, Tiejun Zhang, Shanghang Lin, Yonghua Wang, Zhongyuan Yao, Guocai Robotics Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due to the significant hardware heterogeneity across bimanual robotic platforms. To bridge this gap, we introduce RoboCOIN, a large-scale multi-embodiment bimanual manipulation dataset comprising over 180,000 demonstrations collected from 15 distinct robotic platforms. Spanning 16 diverse environments-including residential, commercial, and industrial settings-the dataset features 421 bimanual tasks systematically categorized by 39 bimanual collaboration actions and 432 objects. A key innovation of our work is the hierarchical capability pyramid, which provides granular annotations ranging from trajectory-level concepts to segment-level subtasks and frame-level kinematics. Furthermore, we present CoRobot, an efficient data processing pipeline powered by the Robot Trajectory Markup Language (RTML), designed to facilitate quality assessment, automated annotation, and unified multi-embodiment and data management. Extensive experiments demonstrate the effectiveness of RoboCOIN in enhancing the performance of various bimanual manipulation models across a wide spectrum of robotic embodiments. The entire dataset and codebase are fully open-sourced, providing a valuable resource for advancing research in bimanual and multi-embodiment manipulation.
title	RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation
topic	Robotics
url	https://arxiv.org/abs/2511.17441