arXiv：cs.AI· Jingxuan Zhu, Jingyi Li, LiangLiang Chen, Zhiyuan Jing, Jidong Zhang, Hongming Li·· 5 小时前
RoboCousin：为双臂机器人操作构建可扩展仿真数据生成平台
RoboCousin: Build Your Own Simulation Playground for Robust Bimanual Robotic Manipulation
AI 导读
RoboCousin 是构建在 RoboTwin 2.0 上的可扩展仿真数据生成平台，可将用户提供的物体图像转为带视觉与碰撞几何、语义物理元数据及自动抓取接触候选的仿真资产，并构造变换物体、背景与指令的 digital cousins。
正文
Abstract:Bimanual manipulation policies require large and diverse training datasets, yet collecting demonstrations on physical robots is expensive and difficult to scale. Simulation can generate data efficiently, but existing pipelines typically operate within closed asset libraries and predefined scenes: adding a newly observed object or environment still requires substantial effort to reconstruct geometry, specify physical and semantic properties, annotate interactions, and integrate the result into executable tasks. We present RoboCousin, an extensible simulation-based data-generation platform that turns user-provided observations into reusable assets, scenes, and expert trajectories for bimanual manipulation. Built on RoboTwin~2.0, RoboCousin converts object images into simulation-ready assets with visual and collision geometry, semantic and physical metadata, and automatically generated grasp-contact candidates. It further constructs digital cousins that vary compatible objects, backgrounds, layouts, and language instructions while preserving task-relevant affordances and spatial relations. The same asset system supports tabletop and room-level scene construction, with collision-aware base control for interaction beyond a fixed workspace. We release RoboCousin-OBD, containing more than 3,000 annotated object instances and 50 background environments, and use RoboCousin to generate over one million expert trajectories across 50 tasks. Simulation and real-robot experiments show that the automatically generated interaction annotations are comparable to curated annotations, generated assets provide effective sim-to-real supervision, and tabletop cousins can improve transfer beyond training on a single reconstructed scene. RoboCousin therefore provides a practical path for expanding both the scale and coverage of synthetic bimanual manipulation data.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.08339 [cs.RO] |
| (or arXiv:2609.08339v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2609.08339 arXiv-issued DOI via DataCite |
Submission history
From: Jingxuan Zhu [view email]
[v1]
Tue, 8 Sep 2026 07:13:07 UTC (28,161 KB)
[v2]
Tue, 13 Oct 2026 00:59:38 UTC (28,434 KB)
来源：arXiv：cs.AI · arxiv.org