论文/arXiv 2610.20901·14 天前

TGrasp6D：任务信息视觉-语言先验与位姿精化实现零样本任务导向6DoF抓取

TGrasp6D用视觉-语言先验与6DoF位姿优化解决零样本任务导向抓取，并在TaskGrasp和真实物体上验证。

AI 整理

• 数据与采集
• 评测与安全

Franka FR3

原文链接：TGrasp6D: Task-Informed Vision-Language Priors and Pose Refinement enable Zero-Shot Task-Oriented 6DoF Grasping（arXiv 2610.20901 · 发布日期：2026-10-14）

TGrasp6D: Task-Informed Vision-Language Priors and Pose Refinement enable Zero-Shot Task-Oriented 6DoF Grasping

TGrasp6D用视觉-语言先验与6DoF位姿优化解决零样本任务导向抓取，并在TaskGrasp和真实物体上验证。

核心要点

• 任务导向抓取需按用途选择抓取部位，现有方法受2D、任务无关或有限标注数据限制。
• 方法从单张RGB-D图像和任务推理语义可供性，生成任务信息先验。
• 再通过6DoF位姿优化细化抓取，避免碰撞并保持任务一致性。
• 在TaskGrasp上成功率94%，优于74%的最佳基线，并部署到Franka Research 3。

验证范围与局限：验证包括TaskGrasp数据集和一台Franka Research 3机器人上的真实物体零样本泛化演示。

英文摘要 (Abstract)

Task-Oriented Grasping (TOG) has emerged as an important skill for purposeful robotic manipulation. Given the task of using a knife to "slice bread," a robot must choose to grasp from the handle, whereas for "hand[ing] the knife over," it is preferable for the handle to remain unobstructed for safe handoff. Current approaches for TOG either focus on 2D planar grasping, remain limited by their reliance on task-agnostic grasp generators, or are constrained by reliance on finite, manually-annotated, task-specific grasp datasets that cannot cover all possible grasp-task pairs. To that end, we present TGrasp6D, a vision-language based approach for generating task-oriented 6DoF grasps in a zero-shot manner. Given a task and a single RGB-D image of an associated object, TGrasp6D reasons about the appropriate semantic affordance for the given task and object geometry to produce an initial task- informed prior. This generated prior is further refined via 6DoF pose optimization for collision avoidance while preserving task consistency. Our approach achieves state-of-the-art success rate of 94% on the TaskGrasp dataset, with the best baseline at 74%. We also deploy our approach on a Franka Research 3 robot to demonstrate zero-shot generalization to real world objects

作者：Manav Kulshrestha, Apoorva Vashisth, Damon Conover, Aniket Bera

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.20901：TGrasp6D: Task-Informed Vision-Language Priors and Pose Refinement enable Zero-Shot Task-Oriented 6DoF Grasping访问 2026-10-21