D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions
About
We introduce the dynamic grasp synthesis task: given an object with a known 6D pose and a grasp reference, our goal is to generate motions that move the object to a target 6D pose. This is challenging, because it requires reasoning about the complex articulation of the human hand and the intricate physical interaction with the object. We propose a novel method that frames this problem in the reinforcement learning framework and leverages a physics simulation, both to learn and to evaluate such dynamic interactions. A hierarchical approach decomposes the task into low-level grasping and high-level motion synthesis. It can be used to generate novel hand sequences that approach, grasp, and move an object to a desired location, while retaining human-likeness. We show that our approach leads to stable grasps and generates a wide range of motions. Furthermore, even imperfect labels can be corrected by our method to generate dynamic interaction sequences.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Static Grasp Evaluation | DexYCB MC (train) | Success Rate70 | 3 | |
| Static Grasp Evaluation | DexYCB MC (test) | Grasp Success Rate63 | 3 | |
| Static Grasp Evaluation | DexYCB SYN (train) | Success Rate75 | 2 | |
| Static Grasp Evaluation | DexYCB SYN (test) | Success Rate73 | 2 | |
| Static Grasp Evaluation | HO3D SYN (train) | Success Rate73 | 2 | |
| Static Grasp Evaluation | HO3D SYN (test) | Success Rate71 | 2 | |
| Static Grasp Evaluation | HO3D IMG (train) | Success Rate88 | 2 | |
| Static Grasp Evaluation | HO3D IMG (test) | Success Rate81 | 2 |