Learning Reactive Dexterous Grasping via Hierarchical Task-Space RL Planning and Joint-Space QP Control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911647002525696 |
|---|---|
| author | Lee, Ho Jae Lee, Yonghyeon Alexiev, Alexander Lin, Tzu-Yuan Jeon, Se Hwan Kim, Sangbae |
| author_facet | Lee, Ho Jae Lee, Yonghyeon Alexiev, Alexander Lin, Tzu-Yuan Jeon, Se Hwan Kim, Sangbae |
| contents | In this work, we propose a hybrid hierarchical control framework for reactive dexterous grasping that explicitly decouples high-level spatial intent from low-level joint execution. We introduce a multi-agent reinforcement learning architecture, specialized into distinct arm and hand agents, that acts as a high-level planner by generating desired task-space velocity commands. These commands are then processed by a GPU-parallelized quadratic programming controller, which translates them into feasible joint velocities while strictly enforcing kinematic limits and collision avoidance. This structural isolation not only accelerates training convergence but also strictly enforces hardware safety. Furthermore, the architecture unlocks zero-shot steerability, allowing system operators to dynamically adjust safety margins and avoid dynamic obstacles without retraining the policy. We extensively validate the proposed framework through a rigorous simulation-to-reality pipeline. Real-world hardware experiments on a 7-DoF arm equipped with a 20-DoF anthropomorphic hand demonstrate highly robust zero-shot transferability for dexterous grasping to a diverse set of unseen objects, highlighting the system's ability to reactively recover from unexpected physical disturbances in unstructured environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03363 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Reactive Dexterous Grasping via Hierarchical Task-Space RL Planning and Joint-Space QP Control Lee, Ho Jae Lee, Yonghyeon Alexiev, Alexander Lin, Tzu-Yuan Jeon, Se Hwan Kim, Sangbae Robotics Systems and Control In this work, we propose a hybrid hierarchical control framework for reactive dexterous grasping that explicitly decouples high-level spatial intent from low-level joint execution. We introduce a multi-agent reinforcement learning architecture, specialized into distinct arm and hand agents, that acts as a high-level planner by generating desired task-space velocity commands. These commands are then processed by a GPU-parallelized quadratic programming controller, which translates them into feasible joint velocities while strictly enforcing kinematic limits and collision avoidance. This structural isolation not only accelerates training convergence but also strictly enforces hardware safety. Furthermore, the architecture unlocks zero-shot steerability, allowing system operators to dynamically adjust safety margins and avoid dynamic obstacles without retraining the policy. We extensively validate the proposed framework through a rigorous simulation-to-reality pipeline. Real-world hardware experiments on a 7-DoF arm equipped with a 20-DoF anthropomorphic hand demonstrate highly robust zero-shot transferability for dexterous grasping to a diverse set of unseen objects, highlighting the system's ability to reactively recover from unexpected physical disturbances in unstructured environments. |
| title | Learning Reactive Dexterous Grasping via Hierarchical Task-Space RL Planning and Joint-Space QP Control |
| topic | Robotics Systems and Control |
| url | https://arxiv.org/abs/2605.03363 |