Task-informed grasping of partially observed objects - Robotique, Perception et Interaction pour le Biomédical
Article Dans Une Revue IEEE Robotics and Automation Letters Année : 2024

Task-informed grasping of partially observed objects

Résumé

In this paper, we address the problem of task-informed grasping in scenarios where only incomplete or partial object information is available. Existing methods, which either focus on task-aware grasping or grasping under partiality, typically require extensive data and long training durations. In contrast, we propose a one-shot task-informed methodology that enables the transfer of grasps computed for a stored object model in the database to another object of the same category that is partially perceived. Our method leverages the reconstructed shapes from Gaussian Process Implicit Surfaces (GPIS) and employs the Functional Maps (FM) framework to transfer task specific grasping functions. By defining task functions on the objects' manifolds and incorporating an uncertainty metric from GPIS, our approach provides a robust solution for part-specific and task-oriented grasping. Validated through simulations and real-world experiments with a 7-axis collaborative robotic arm, our methodology demonstrates a success rate exceeding 90% in achieving task-informed grasps on a variety of objects.
Fichier principal
Vignette du fichier
RALb_2024.pdf (9.71 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04679112 , version 1 (27-08-2024)

Identifiants

Citer

Cristiana de Farias, Brahim Tamadazte, Maxime Adjigble, Rustam Stolkin, Naresh Marturi. Task-informed grasping of partially observed objects. IEEE Robotics and Automation Letters, 2024, 9 (10), pp.8394-8401. ⟨10.1109/LRA.2024.3445633⟩. ⟨hal-04679112⟩
3 Consultations
3 Téléchargements

Altmetric

Partager

More