← 研踪 PaperTrailarXiv:2502.04873 · v5
Training-free Task-oriented Grasp Generation
首次提交 2025-02-07 20:26
版本更新 2026-11-14 22:04
雷达观测 2026-11-17 12:06
摘要
This paper presents a training-free pipeline for task-oriented grasp generation that combines pre-trained grasp generation models with vision-language models (VLMs). Unlike traditional approaches that focus solely on stable grasps, our method incorporates task-specific requirements by leveraging the semantic reasoning capabilities of VLMs. We evaluate five querying strategies, each utilizing different visual representations of candidate grasps, and demonstrate significant improvements over a baseline method in both grasp success and task compliance rates, with absolute gains of up to 36.9\% in overall success rate. Our results underline the potential of VLMs to enhance task-oriented manipulation, providing insights for future research in robotic grasping and human-robot interaction.
作者备注:Jiaming Wang, Diwen Liu, and Jizhuo Chen contributed equally
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v5 · 2026-11-14 22:04 · 最新观测版本
Training-free Task-oriented Grasp Generation
This paper presents a training-free pipeline for task-oriented grasp generation that combines pre-trained grasp generation models with vision-language models (VLMs). Unlike traditional approaches that focus solely on stable grasps, our method incorporates task-specific requirements by leveraging the semantic reasoning capabilities of VLMs. We evaluate five querying strategies, each utilizing different visual representations of candidate grasps, and demonstrate significant improvements over a baseline method in both grasp success and task compliance rates, with absolute gains of up to 36.9\% in overall success rate. Our results underline the potential of VLMs to enhance task-oriented manipulation, providing insights for future research in robotic grasping and human-robot interaction.
查看此版本解读 →查看此版本原文 ↗