Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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.

Sammy Christen, Muhammed Kocabas, Emre Aksan, Jemin Hwangbo, Jie Song, Otmar Hilliges• 2021

Related benchmarks

TaskDatasetResultRank
Static Grasp EvaluationDexYCB MC (train)
Success Rate70
3
Static Grasp EvaluationDexYCB MC (test)
Grasp Success Rate63
3
Static Grasp EvaluationDexYCB SYN (train)
Success Rate75
2
Static Grasp EvaluationDexYCB SYN (test)
Success Rate73
2
Static Grasp EvaluationHO3D SYN (train)
Success Rate73
2
Static Grasp EvaluationHO3D SYN (test)
Success Rate71
2
Static Grasp EvaluationHO3D IMG (train)
Success Rate88
2
Static Grasp EvaluationHO3D IMG (test)
Success Rate81
2
Showing 8 of 8 rows

Other info

Code

Follow for update