VLAD-Grasp: Zero-shot Grasp Detection via Vision-Language Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kulshrestha, Manav, Bukhari, S. Talha, Conover, Damon, Bera, Aniket
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911516785115136
author Kulshrestha, Manav
Bukhari, S. Talha
Conover, Damon
Bera, Aniket
author_facet Kulshrestha, Manav
Bukhari, S. Talha
Conover, Damon
Bera, Aniket
contents Robotic grasping is a fundamental capability for enabling autonomous manipulation, with usually infinite solutions. State-of-the-art approaches for grasping rely on learning from large-scale datasets comprising expert annotations of feasible grasps. Curating such datasets is challenging, and hence, learning-based methods are limited by the solution coverage of the dataset, and require retraining to handle novel objects. Towards this, we present VLAD-Grasp, a Vision-Language model Assisted zero-shot approach for Detecting Grasps. Our method (1) prompts a large vision-language model to generate a goal image where a virtual cylindrical proxy intersects the object's geometry, explicitly encoding an antipodal grasp axis in image space, then (2) predicts depth and segmentation to lift this generated image into 3D, and (3) aligns generated and observed object point clouds via principal components and correspondence-free optimization to recover an executable grasp pose. Unlike prior work, our approach is training-free and does not require curated grasp datasets, while achieving performance competitive with the state-of-the-art methods on the Cornell and Jacquard datasets. Furthermore, we demonstrate zero-shot generalization to real-world objects on a Franka Research 3 robot, highlighting vision-language models as powerful priors for robotic manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05791
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VLAD-Grasp: Zero-shot Grasp Detection via Vision-Language Models
Kulshrestha, Manav
Bukhari, S. Talha
Conover, Damon
Bera, Aniket
Robotics
Artificial Intelligence
Machine Learning
Robotic grasping is a fundamental capability for enabling autonomous manipulation, with usually infinite solutions. State-of-the-art approaches for grasping rely on learning from large-scale datasets comprising expert annotations of feasible grasps. Curating such datasets is challenging, and hence, learning-based methods are limited by the solution coverage of the dataset, and require retraining to handle novel objects. Towards this, we present VLAD-Grasp, a Vision-Language model Assisted zero-shot approach for Detecting Grasps. Our method (1) prompts a large vision-language model to generate a goal image where a virtual cylindrical proxy intersects the object's geometry, explicitly encoding an antipodal grasp axis in image space, then (2) predicts depth and segmentation to lift this generated image into 3D, and (3) aligns generated and observed object point clouds via principal components and correspondence-free optimization to recover an executable grasp pose. Unlike prior work, our approach is training-free and does not require curated grasp datasets, while achieving performance competitive with the state-of-the-art methods on the Cornell and Jacquard datasets. Furthermore, we demonstrate zero-shot generalization to real-world objects on a Franka Research 3 robot, highlighting vision-language models as powerful priors for robotic manipulation.
title VLAD-Grasp: Zero-shot Grasp Detection via Vision-Language Models
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2511.05791