Learning to model the grasp space of an underactuated robot gripper using variational autoencoder

Clément Rolinat (1, 2, 3) , Mathieu Grossard (1, 2, 3) , Saifeddine Aloui (4, 2, 5) , Christelle Godin (4, 2, 5)

1 LIST (CEA) - Laboratoire d'Intégration des Systèmes et des Technologies
2 CEA - Commissariat à l'énergie atomique et aux énergies alternatives
3 Université Paris-Saclay
4 CEA-LETI - Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information
5 UGA - Université Grenoble Alpes

Grasp planning and most specifically the grasp space exploration is still an open issue in robotics. This article presents a data-driven oriented methodology to model the grasp space of a multi-fingered adaptive gripper for known objects. This method relies on a limited dataset of manually specified expert grasps, and uses variational autoencoder to learn grasp intrinsic features in a compact way from a computational point of view. The learnt model can then be used to generate new non-learnt gripper configurations to explore the grasp space.

Domains: Automatic; Neural and Evolutionary Computing [cs.NE]

Clément Rolinat, Mathieu Grossard, Saifeddine Aloui, Christelle Godin. Learning to model the grasp space of an underactuated robot gripper using variational autoencoder. IFAC-PapersOnLine, 2021, 19th IFAC Symposium on System Identification SYSID 2021, 54 (7), pp.523-528. ⟨10.1016/j.ifacol.2021.08.413⟩. ⟨cea-03347668⟩