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

arXiv cs.RO / 4/14/2026

💬 OpinionDeveloper Stack & InfrastructureSignals & Early TrendsTools & Practical UsageModels & Research

共有:

Key Points

RoboCOIN is an open-sourced, large-scale bimanual manipulation dataset with 180,000+ demonstrations gathered from 15 different robotic platforms to address dataset scarcity caused by hardware heterogeneity.
The dataset covers 16 diverse environments and includes 421 bimanual tasks spanning 39 collaboration action categories and 432 objects.
RoboCOIN introduces a hierarchical capability pyramid that supplies fine-grained annotations from trajectory-level concepts down to segment-level subtasks and frame-level kinematics.
The accompanying CoRobot pipeline uses RTML (Robot Trajectory Markup Language) to support quality assessment, automated annotation, and unified multi-embodiment data management.
Experiments reported in the paper show RoboCOIN improves performance across multiple bimanual manipulation models, and both the dataset and codebase are fully open-sourced.

Abstract

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.