Text2Grasp: Grasp synthesis by text prompts of object grasping parts

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chang, Xiaoyun, Sun, Yi
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916219731312640
author Chang, Xiaoyun
Sun, Yi
author_facet Chang, Xiaoyun
Sun, Yi
contents The hand plays a pivotal role in human ability to grasp and manipulate objects and controllable grasp synthesis is the key for successfully performing downstream tasks. Existing methods that use human intention or task-level language as control signals for grasping inherently face ambiguity. To address this challenge, we propose a grasp synthesis method guided by text prompts of object grasping parts, Text2Grasp, which provides more precise control. Specifically, we present a two-stage method that includes a text-guided diffusion model TextGraspDiff to first generate a coarse grasp pose, then apply a hand-object contact optimization process to ensure both plausibility and diversity. Furthermore, by leveraging Large Language Model, our method facilitates grasp synthesis guided by task-level and personalized text descriptions without additional manual annotations. Extensive experiments demonstrate that our method achieves not only accurate part-level grasp control but also comparable performance in grasp quality.
format Preprint
id arxiv_https___arxiv_org_abs_2404_15189
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Text2Grasp: Grasp synthesis by text prompts of object grasping parts
Chang, Xiaoyun
Sun, Yi
Artificial Intelligence
The hand plays a pivotal role in human ability to grasp and manipulate objects and controllable grasp synthesis is the key for successfully performing downstream tasks. Existing methods that use human intention or task-level language as control signals for grasping inherently face ambiguity. To address this challenge, we propose a grasp synthesis method guided by text prompts of object grasping parts, Text2Grasp, which provides more precise control. Specifically, we present a two-stage method that includes a text-guided diffusion model TextGraspDiff to first generate a coarse grasp pose, then apply a hand-object contact optimization process to ensure both plausibility and diversity. Furthermore, by leveraging Large Language Model, our method facilitates grasp synthesis guided by task-level and personalized text descriptions without additional manual annotations. Extensive experiments demonstrate that our method achieves not only accurate part-level grasp control but also comparable performance in grasp quality.
title Text2Grasp: Grasp synthesis by text prompts of object grasping parts
topic Artificial Intelligence
url https://arxiv.org/abs/2404.15189