Research map / Reinforcement learning / Visual and representation RL
Cross-Embodied Co-Design for Dexterous Hands
Kehlani Fay, Darin Anthony Djapri, Anya Zorin, James Clinton, Ali El Lahib, Hao Su, Michael T. Tolley, Sha Yi, Xiaolong Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add fine-tuning of the best design with domain randomization (ablation) | co-designed hand · In-hand rotation (sim) | continuous angular velocity (rad/s): 1.85 -> 3.3 | Improved |
| use RL cross-embodied control instead of MPPI (ablation) | co-design framework · In-hand rotation (sim) | continuous angular velocity (rad/s): 0.62 -> 3.3 | Improved |
| use graph heuristic search with learned value network instead of RoboGrammar | design search · In-hand rotation (sim) | continuous angular velocity (rad/s): 0.26 -> 3.3 | Improved |
| use graph heuristic search instead of Monte Carlo tree search | design search · In-hand rotation (sim) | time to fall: 2.71 seconds -> no fall over three minutes | Improved |
| use co-designed 3-finger radially symmetric hand instead of anthropomorphic hand | blind in-hand rotation · In-hand rotation, blind policy (sim) | angular velocity (rad/s): 0.73 -> 1.85 | Improved |
| use co-designed 3-finger hand instead of blind Leap hand | blind in-hand rotation · In-hand rotation (sim) | continuous angular velocity (rad/s): 0.0 -> 3.3 | Improved |
| use cross-embodied policy instead of individual PPO per morphology | design evaluation · 5-finger symmetric hand rotation | angular velocity (rad/s): 0.56 rad/s -> 65% improvement | Improved |
| use cross-embodied evaluation instead of individual PPO per design | design evaluation runtime · Co-design evaluation | runtime: 20 designs at 47 minutes each -> 2,000 designs in 5.18 hours (400x speedup) | Improved |
| use thin fingertips instead of standard fingertips (ablation) | in-hand rotation hands · In-hand rotation (sim) | rotation stability | Hurt |
| increase finger body length scale (ablation) | LEAP hand parameters · Isaac-Reorient-Cube-Leap | correlation with rotation reward: r=0.748 | Improved |
| increase palm width scale (ablation) | LEAP hand parameters · Isaac-Reorient-Cube-Leap | correlation with rotation reward: r=-0.729 | Hurt |
| increase actuator damping (ablation) | LEAP hand parameters · Isaac-Reorient-Cube-Leap | correlation with rotation reward: r=-0.476 | Hurt |
Closest papers by meaning
- Cross-Embodiment Dexterous Grasping with Reinforcement Learning (ICLR 2025 · similarity 0.90)
- ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning (CVPR 2025 · similarity 0.89)
- Dexterous Manipulation Transfer via Progressive Kinematic-Dynamic Alignment (AAAI 2026 · similarity 0.89)
- Scalable Cross-embodiment Dexterous Grasping via Morphology-Prior Diffusion (ECCV 2026 · similarity 0.88)
- Scaffolding Dexterous Manipulation with Vision-Language Models (NeurIPS 2025 · similarity 0.88)
- HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
