RoCo Challenge at AAAI 2026: Benchmarking Robotic Collaborative Manipulation for Assembly Towards Industrial Automation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912968692727808 |
|---|---|
| author | Liu, Haichao Zhou, Yuheng Wu, Zhenyu Ji, Ziheng Shan, Ziyu Wang, Qianzhun Liu, Ruixuan Yang, Zhiyuan Gu, Yejun Khan, Shalman Yan, Shijun Liu, Jun Zhu, Haiyue Liu, Changliu Yang, Jianfei Zhang, Jingbing Wang, Ziwei |
| author_facet | Liu, Haichao Zhou, Yuheng Wu, Zhenyu Ji, Ziheng Shan, Ziyu Wang, Qianzhun Liu, Ruixuan Yang, Zhiyuan Gu, Yejun Khan, Shalman Yan, Shijun Liu, Jun Zhu, Haiyue Liu, Changliu Yang, Jianfei Zhang, Jingbing Wang, Ziwei |
| contents | Embodied Artificial Intelligence (EAI) is rapidly developing, gradually subverting previous autonomous systems' paradigms from isolated perception to integrated, continuous action. This transition is highly significant for industrial robotic manipulation, promising to free human workers from repetitive, dangerous daily labor. To benchmark and advance this capability, we introduce the Robotic Collaborative Assembly Assistance (RoCo) Challenge with a dataset towards simulation and real-world assembly manipulation. Set against the backdrop of human-centered manufacturing, this challenge focuses on a high-precision planetary gearbox assembly task, a demanding yet highly representative operation in modern industry. Built upon a self-developed data collection, training, and evaluation system in Isaac Sim, and utilizing a dual-arm robot for real-world deployment, the challenge operates in two phases. The Simulation Round defines fine-grained task phases for step-wise scoring to handle the long-horizon nature of the assembly. The Real-World Round mirrors this evaluation with physical gearbox components and high-quality teleoperated datasets. The core tasks require assembling an epicyclic gearbox from scratch, including mounting three planet gears, a sun gear, and a ring gear. Attracting over 60 teams and 170+ participants from more than 10 countries, the challenge yielded highly effective solutions, most notably ARC-VLA and RoboCola. Results demonstrate that a dual-model framework for long-horizon multi-task learning is highly effective, and the strategic utilization of recovery-from-failure curriculum data is a critical insight for successful deployment. This report outlines the competition setup, evaluation approach, key findings, and future directions for industrial EAI. Our dataset, CAD files, code, and evaluation results can be found at: https://rocochallenge.github.io/RoCo2026/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15469 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RoCo Challenge at AAAI 2026: Benchmarking Robotic Collaborative Manipulation for Assembly Towards Industrial Automation Liu, Haichao Zhou, Yuheng Wu, Zhenyu Ji, Ziheng Shan, Ziyu Wang, Qianzhun Liu, Ruixuan Yang, Zhiyuan Gu, Yejun Khan, Shalman Yan, Shijun Liu, Jun Zhu, Haiyue Liu, Changliu Yang, Jianfei Zhang, Jingbing Wang, Ziwei Robotics Artificial Intelligence Embodied Artificial Intelligence (EAI) is rapidly developing, gradually subverting previous autonomous systems' paradigms from isolated perception to integrated, continuous action. This transition is highly significant for industrial robotic manipulation, promising to free human workers from repetitive, dangerous daily labor. To benchmark and advance this capability, we introduce the Robotic Collaborative Assembly Assistance (RoCo) Challenge with a dataset towards simulation and real-world assembly manipulation. Set against the backdrop of human-centered manufacturing, this challenge focuses on a high-precision planetary gearbox assembly task, a demanding yet highly representative operation in modern industry. Built upon a self-developed data collection, training, and evaluation system in Isaac Sim, and utilizing a dual-arm robot for real-world deployment, the challenge operates in two phases. The Simulation Round defines fine-grained task phases for step-wise scoring to handle the long-horizon nature of the assembly. The Real-World Round mirrors this evaluation with physical gearbox components and high-quality teleoperated datasets. The core tasks require assembling an epicyclic gearbox from scratch, including mounting three planet gears, a sun gear, and a ring gear. Attracting over 60 teams and 170+ participants from more than 10 countries, the challenge yielded highly effective solutions, most notably ARC-VLA and RoboCola. Results demonstrate that a dual-model framework for long-horizon multi-task learning is highly effective, and the strategic utilization of recovery-from-failure curriculum data is a critical insight for successful deployment. This report outlines the competition setup, evaluation approach, key findings, and future directions for industrial EAI. Our dataset, CAD files, code, and evaluation results can be found at: https://rocochallenge.github.io/RoCo2026/. |
| title | RoCo Challenge at AAAI 2026: Benchmarking Robotic Collaborative Manipulation for Assembly Towards Industrial Automation |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2603.15469 |