Grasping a Handful: Sequential Multi-Object Dexterous Grasp Generation

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 SeqDa...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE robotics and automation letters Ročník 10; číslo 11; s. 11880 - 11887
Hlavní autoři: Lu, Haofei, Dong, Yifei, Weng, Zehang, Pokorny, Florian T., Lundell, Jens, Kragic, Danica
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.11.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Data Sets for Robot Learning
Degrees of freedom
Dexterous Manipulation
End effectors
Grasping
Grasping (robotics)
Hands
Kinematics
Robot learning
Robots
Silicon
Thumb
Training
Visualization
ISSN:2377-3766, 2377-3766
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2025.3614051