arXiv：cs.LG（机器学习，全量分类）· Giulio Schiavi, Andrei Cramariuc, Michael Pantic, Roland Siegwart·· 7 小时前AI 评分43
通过经验与演示实现 6-DoF 抓取合成的持续学习框架
Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations
AI 导读
研究者提出一种面向平行夹爪、杂乱场景下单视角 6-DoF 抓取合成的持续学习框架，不微调大参数模型，而是在学习到的嵌入空间中通过记忆自适应：抓取结果更新未来抓取分数，可选的用户演示被召回并迁移到新场景作为候选抓取。
正文
Abstract:Most current grasp synthesis systems are trained offline and remain fixed during deployment. While this works well when deployment conditions resemble the training data, performance can degrade when robots encounter conditions they have not seen before, such as unfamiliar objects. In this work, we present a continual-learning framework for single-view 6-DoF grasp synthesis for a parallel-jaw gripper in cluttered scenes. Rather than finetuning a large parametric model, our method adapts through memory in a learned embedding space: grasp outcomes update future grasp scores, while optional user demonstrations are recalled and transferred to new scenes as additional candidate grasps. We evaluate our method in simulation and in extensive real-world experiments comprising over 1500 grasp trials. We show that our method matches the performance of existing 6-DoF grasping baselines even before adaptation, improves online on unseen objects from categories absent or underrepresented during training, and supports long-horizon continual learning with limited forgetting. In real-world experiments, our method reaches over 90\% success rates on several challenging object categories after only 50 online grasp attempts. Videos and code at this https URL.
| Comments: | Accepted to CoRL 2026 |
| Subjects: | Robotics (cs.RO); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.01301 [cs.RO] |
| (or arXiv:2610.01301v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01301 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Giulio Schiavi [view email]
[v1]
Thu, 1 Oct 2026 08:36:06 UTC (9,442 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org