Grasping a Handful: Sequential Multi-Object Dexterous Grasp Generation
This addresses the challenge of efficient and robust multi-object grasping in robotics, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of generating stable grasps for multiple objects using a robotic hand with partial degrees of freedom, resulting in an 8.71%-43.33% higher grasp success rate and approximately 1000 times faster generation compared to the state-of-the-art method.
We introduce the sequential multi-object robotic grasp sampling algorithm SeqGrasp that can robustly synthesize stable grasps on diverse objects using the robotic hand's partial Degrees of Freedom (DoF). We use SeqGrasp to construct the large-scale Allegro Hand sequential grasping dataset SeqDataset and use it for training the diffusion-based sequential grasp generator SeqDiffuser. We experimentally evaluate SeqGrasp and SeqDiffuser against the state-of-the-art non-sequential multi-object grasp generation method MultiGrasp in simulation and on a real robot. The experimental results demonstrate that SeqGrasp and SeqDiffuser reach an 8.71%-43.33% higher grasp success rate than MultiGrasp. Furthermore, SeqDiffuser is approximately 1000 times faster at generating grasps than SeqGrasp and MultiGrasp. Project page: https://yulihn.github.io/SeqGrasp/.