arXiv cs.AI· Manav Kulshrestha, Shreyans Jain, Apoorva Vashisth, Ankush Gupta, Damon Conover, Aniket Bera·· 1 小时前AI 评分36
LAGR:面向任务抓取的语言感知重排序方法
LAGR: Language-Aware Grasp Re-Ranking for Task Oriented Grasping
AI 导读
研究者提出 LAGR,一种任务导向抓取检测方法:先生成任务无关的抓取提案并给出物理可行性分数,再用语言条件重排序器对所有提案联合打分。团队构建了包含 100,911 个图像-任务对、17 类物体共 268 万条带评分 5-DoF 抓取标注的数据集。实验显示 LAGR 较次优方法提升 9.3 个百分点,并在 Franka Research 3 机器人上完成真实物体验证。
正文 · 原文
Abstract:Grasping is a fundamental capability for robotic manipulation, with the appropriate grasp depending on the downstream task. For example, a hammer should be held by its handle for hammering but by its head when it is handed over. Selecting such a grasp requires consideration of two criteria: physical feasibility on the object and suitability for the task. Developing such an approach requires dense grasp labels with both feasibility and task scores on real observations, but existing task-oriented grasping datasets are small, synthetic, or costly to annotate. To address this gap, we construct a dataset of 2.68 million scored 5-DoF grasp annotations over 100,911 image-task pairs from $17$ object categories. Additionally, we introduce LAGR, a task-oriented grasp detection method that explicitly addresses both these challenges. Given vision-language inputs, LAGR first generates task-independent grasp proposals along with a physical feasibility score, and then scores the generated grasps with a language-conditioned re-ranker that reasons over all proposals jointly. Experiments show that LAGR outperforms the next best method by 9.3 percentage points. We further validate LAGR on real objects by executing task-oriented grasps with a Franka Research 3 robot.
| Comments: | Manav Kulshrestha and Shreyans Jain contributed equally to this work |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.23858 [cs.RO] |
| (or arXiv:2611.23858v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23858 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Manav Kulshrestha [view email]
[v1]
Wed, 18 Nov 2026 05:04:12 UTC (9,727 KB)
来源:arXiv cs.AI · arxiv.org