改进抓取候选排序，让机器人更准地抓到东西。
GraRe: Grasp Candidate Re-Ranking for Frozen 6-DoF Grasp Detectors
- 用属性、几何和上下文信息重排抓取候选
- 在GraspNet-1Billion上最高提升13.60点平均精度
- 适合想优化现成抓取模型的工程师
现有6-DoF抓取检测器通常根据检测置信度对抓取候选进行排序。但我们在GraspNet-1Billion上的分析发现，置信度与抓取质量常不匹配，导致有效抓取候选被排得太靠后。为此，我们提出针对冻结检测器的抓取候选重排序任务，旨在不修改检测器或其候选结果的前提下优化排序。GraRe通过候选属性、壳层分层局部几何和物体上下文来估计抓取质量，属性用于调节局部几何与上下文表征，再由Transformer融合三类特征。最终将预测质量与检测置信度结合生成排序结果。在GraspNet-1Billion上使用三个冻结检测器的实验显示一致提升，平均精度最高提高13.60点。真实机器人实验也证明在杂乱场景下具备鲁棒抓取能力。结果表明，优化候选排序是提升冻结6-DoF抓取检测器的有效途径。
原文摘要 · Abstract (English)
Existing 6-DoF grasp detectors typically rank grasp candidates by detector confidence. However, our analysis on GraspNet-1Billion shows that detector confidence is often poorly aligned with grasp quality, causing successful grasp candidates to be ranked too low during execution. Motivated by this observation, we formulate grasp candidate re-ranking as a separate task for frozen detectors, aiming to improve candidate ordering without changing the detector or its grasp candidates. We propose GraRe, which estimates grasp quality from candidate attributes, shell-stratified local geometry, and object context. Candidate attributes condition the local geometric and object-context representations, and a Transformer fuses all three feature types. The predicted quality is combined with detector confidence to produce the final ranking. Experiments on GraspNet-1Billion with three frozen detectors show consistent improvements, with gains of up to 13.60 points in Average AP. Real-robot experiments further demonstrate robust grasping in cluttered scenes. These results show that improving candidate ranking provides a practical way to enhance frozen 6-DoF grasp detectors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。