Episode

DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo

Podcast
Daily Paper Cast
Published
May 19, 2026
Duration seconds
1392
Processing state
not_requested
Canonical source
https://share.transistor.fm/s/8743282c
Audio
https://media.transistor.fm/8743282c/a46d3bf0.mp3
JSON
/v1/public/podcasts/daily-paper-cast-7079649/episodes/dexjoco-a-benchmark-and-toolkit-for-task-oriented-dexterous-manipulation-on-mujoco
Markdown
/podcast/daily-paper-cast-7079649/dexjoco-a-benchmark-and-toolkit-for-task-oriented-dexterous-manipulation-on-mujoco.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/dexjoco-a-benchmark-and-toolkit-for-task-oriented-dexterous-manipulation-on-mujoco/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/daily-paper-cast-7079649/dexjoco-a-benchmark-and-toolkit-for-task-oriented-dexterous-manipulation-on-mujoco.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

🤗 Upvotes: 47 | cs.RO Authors: Hanwen Wang, Weizhi Zhao, Xiangyu Wang, Siyuan Huang, He Lin, Boyuan Zheng, Rongtao Xu, Gang Wang, Yao Mu, He Wang, Lue Fan, Hongsheng Li, Zhaoxiang Zhang, Tieniu Tan Title: DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo Arxiv: http://arxiv.org/abs/2605.16257v1 Abstract: 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