DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917500911878144 |
|---|---|
| author | Wang, Hanwen Zhao, Weizhi Wang, Xiangyu Huang, Siyuan Lin, He Zheng, Boyuan Xu, Rongtao Wang, Gang Mu, Yao Wang, He Fan, Lue Li, Hongsheng Zhang, Zhaoxiang Tan, Tieniu |
| author_facet | Wang, Hanwen Zhao, Weizhi Wang, Xiangyu Huang, Siyuan Lin, He Zheng, Boyuan Xu, Rongtao Wang, Gang Mu, Yao Wang, He Fan, Lue Li, Hongsheng Zhang, Zhaoxiang Tan, Tieniu |
| contents | Achieving human-level manipulation requires dexterous robotic hands capable of complex object interactions. Advancing such capabilities further demands standardized benchmarks for systematic evaluation. However, existing dexterous benchmarks lack tasks that reflect the unique manipulation capabilities of dexterous hands over parallel grippers, as well as comprehensive evaluation pipelines. In this paper, we present DexJoCo, a benchmark and toolkit for task-oriented dexterous manipulation, comprising 11 functionally grounded tasks that evaluate tool-use, bimanual coordination, long-horizon execution, and reasoning. We develop a low-cost data collection system and collect 1.1K trajectories across these tasks, with support for domain randomization to assess robustness. We benchmark modern models under diverse settings, including visual and dynamics randomization, multi-task training, and action-head adaptation. Through extensive empirical analysis, we identify several important insights and common limitations of current policies in dexterous manipulation, highlighting key challenges for future research in dexterous hand robot learning. Project page available at: https://dexjoco.github.io |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16257 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo Wang, Hanwen Zhao, Weizhi Wang, Xiangyu Huang, Siyuan Lin, He Zheng, Boyuan Xu, Rongtao Wang, Gang Mu, Yao Wang, He Fan, Lue Li, Hongsheng Zhang, Zhaoxiang Tan, Tieniu Robotics Achieving human-level manipulation requires dexterous robotic hands capable of complex object interactions. Advancing such capabilities further demands standardized benchmarks for systematic evaluation. However, existing dexterous benchmarks lack tasks that reflect the unique manipulation capabilities of dexterous hands over parallel grippers, as well as comprehensive evaluation pipelines. In this paper, we present DexJoCo, a benchmark and toolkit for task-oriented dexterous manipulation, comprising 11 functionally grounded tasks that evaluate tool-use, bimanual coordination, long-horizon execution, and reasoning. We develop a low-cost data collection system and collect 1.1K trajectories across these tasks, with support for domain randomization to assess robustness. We benchmark modern models under diverse settings, including visual and dynamics randomization, multi-task training, and action-head adaptation. Through extensive empirical analysis, we identify several important insights and common limitations of current policies in dexterous manipulation, highlighting key challenges for future research in dexterous hand robot learning. Project page available at: https://dexjoco.github.io |
| title | DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo |
| topic | Robotics |
| url | https://arxiv.org/abs/2605.16257 |