通过随机玩具学习抓取任何物体
Learning to Grasp Anything by Playing with Random Toys
AI总结：
本文通过随机组装的简单玩具训练机器人，使其具备泛化抓取能力，采用对象中心视觉表示实现零样本性能，实现在YCB数据集上的67%抓取成功率。
摘要：
机器人操控策略常难以泛化到新物体，限制了其实际应用。相比之下，认知科学表明儿童通过掌握少量简单玩具发展出可泛化的灵巧操控技能。受此启发，我们研究机器人是否也能通过类似方式实现泛化能力。我们的结果表明，机器人可通过仅由四个基本形状组成随机组装的物体学习泛化抓取能力。我们证明训练这些
英文摘要：
Robotic manipulation policies often struggle to generalize to novel objects, limiting their real-world utility. In contrast, cognitive science suggests that children develop generalizable dexterous manipulation skills by mastering a small set of simple toys and then applying that knowledge to more complex items. Inspired by this, we study if similar generalization capabilities can also be achieved by robots. Our results indicate robots can learn generalizable grasping using randomly assembled objects that are composed from just four shape primitives: spheres, cuboids, cylinders, and rings. We show that training on these "toys" enables robust generalization to real-world objects, yielding strong zero-shot performance. Crucially, we find the key to this generalization is an object-centric visual representation induced by our proposed detection pooling mechanism. Evaluated in both simulation and on physical robots, our model achieves a 67% real-world grasping success rate on the YCB dataset, outperforming state-of-the-art approaches that rely on substantially more in-domain data. We further study how zero-shot generalization performance scales by varying the number and diversity of training toys and the demonstrations per toy. We believe this work offers a promising path to scalable and generalizable learning in robotic manipulation. Demonstration videos, code, checkpoints and our dataset are available on our project page: https://lego-grasp.github.io/ .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
