Diffusion for Multi-Embodiment Grasping

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Freiberg, Roman, Qualmann, Alexander, Vien, Ngo Anh, Neumann, Gerhard
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912084462141440
author Freiberg, Roman
Qualmann, Alexander
Vien, Ngo Anh
Neumann, Gerhard
author_facet Freiberg, Roman
Qualmann, Alexander
Vien, Ngo Anh
Neumann, Gerhard
contents Grasping is a fundamental skill in robotics with diverse applications across medical, industrial, and domestic domains. However, current approaches for predicting valid grasps are often tailored to specific grippers, limiting their applicability when gripper designs change. To address this limitation, we explore the transfer of grasping strategies between various gripper designs, enabling the use of data from diverse sources. In this work, we present an approach based on equivariant diffusion that facilitates gripper-agnostic encoding of scenes containing graspable objects and gripper-aware decoding of grasp poses by integrating gripper geometry into the model. We also develop a dataset generation framework that produces cluttered scenes with variable-sized object heaps, improving the training of grasp synthesis methods. Experimental evaluation on diverse object datasets demonstrates the generalizability of our approach across gripper architectures, ranging from simple parallel-jaw grippers to humanoid hands, outperforming both single-gripper and multi-gripper state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18835
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diffusion for Multi-Embodiment Grasping
Freiberg, Roman
Qualmann, Alexander
Vien, Ngo Anh
Neumann, Gerhard
Robotics
I.2.9
Grasping is a fundamental skill in robotics with diverse applications across medical, industrial, and domestic domains. However, current approaches for predicting valid grasps are often tailored to specific grippers, limiting their applicability when gripper designs change. To address this limitation, we explore the transfer of grasping strategies between various gripper designs, enabling the use of data from diverse sources. In this work, we present an approach based on equivariant diffusion that facilitates gripper-agnostic encoding of scenes containing graspable objects and gripper-aware decoding of grasp poses by integrating gripper geometry into the model. We also develop a dataset generation framework that produces cluttered scenes with variable-sized object heaps, improving the training of grasp synthesis methods. Experimental evaluation on diverse object datasets demonstrates the generalizability of our approach across gripper architectures, ranging from simple parallel-jaw grippers to humanoid hands, outperforming both single-gripper and multi-gripper state-of-the-art methods.
title Diffusion for Multi-Embodiment Grasping
topic Robotics
I.2.9
url https://arxiv.org/abs/2410.18835