ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation
This addresses the challenge of generating physically plausible dexterous manipulations for robotics or animation, representing an incremental advance in simulation-based hand-object interaction synthesis.
The paper tackles the problem of synthesizing bi-manual hand-object interactions for grasping and articulation, achieving this by training a unified reinforcement learning policy that controls both global wrist motions and precise finger poses, with evaluation showing efficacy in dynamic object grasping and articulation tasks.
We present ArtiGrasp, a novel method to synthesize bi-manual hand-object interactions that include grasping and articulation. This task is challenging due to the diversity of the global wrist motions and the precise finger control that are necessary to articulate objects. ArtiGrasp leverages reinforcement learning and physics simulations to train a policy that controls the global and local hand pose. Our framework unifies grasping and articulation within a single policy guided by a single hand pose reference. Moreover, to facilitate the training of the precise finger control required for articulation, we present a learning curriculum with increasing difficulty. It starts with single-hand manipulation of stationary objects and continues with multi-agent training including both hands and non-stationary objects. To evaluate our method, we introduce Dynamic Object Grasping and Articulation, a task that involves bringing an object into a target articulated pose. This task requires grasping, relocation, and articulation. We show our method's efficacy towards this task. We further demonstrate that our method can generate motions with noisy hand-object pose estimates from an off-the-shelf image-based regressor.