发表机构
NVIDIA; University of California San Diego; University of Southern California（英伟达; 加利福尼亚大学圣迭戈分校; 南加利福尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出基于世界模型的通用机器人插入框架，融合本体感觉与视觉，在90个任务上训练，零样本成功率56%，远超基线，且具可扩展性与微调优势。
AI 中文摘要
高混合场景下的机器人装配需要能够处理多样零部件的自适应系统，然而当前方法通常依赖于针对每个插入任务专门化的策略。尽管这可以达到高成功率，但使得为新问题部署系统的过程变得繁琐且耗时。我们提出了一种利用世界模型实现通用插入的框架，该框架将机器人本体感觉信息与腕部相机捕获的原始视觉观测相结合。我们的基于模型的方法在多达90个具有几何多样零部件的插入任务上训练单一世界模型，在未见过的未知几何物体上实现了56%的零样本成功率，而基于无模型的基线仅为7%。重要的是，随着训练数据集中包含更多物体，性能不断提升，展示了强大的可扩展性。最后，在保留物体上微调通用模型显著提高了数据效率，相比从零训练，在某些情况下甚至达到了更好的渐近性能。据我们所知，这是首个完全以数据驱动方式装配未见物体的系统，因此代表了向可扩展、通用机器人装配系统迈出的重要一步。
英文摘要
Robotic assembly in high-mixture settings requires adaptable systems that can handle diverse parts, yet current approaches typically rely on policies specialized to each insertion task. Although this can reach high success rates, it makes the process of deploying systems for new problems tedious and time consuming. We present a framework for generalizable insertion using world models that combine robot proprioceptive information with raw visual observations captured by a wrist-mounted camera. Our model-based approach trains a single world model on up to 90 insertion tasks with geometrically diverse parts, achieving 56% zero-shot success on unseen objects with unknown geometry compared to just 7% with a model-free baseline. Importantly, performance improves as more objects are included in the training dataset, demonstrating strong scalability. Lastly, finetuning the generalist model on held-out objects significantly enhances data-efficiency compared to training from scratch and, in some cases, achieves better asymptotic performance. To our knowledge, this is the first system capable of assembling unseen objects in an entirely data-driven manner, and thus represents a significant step toward scalable, generalizable robotic assembly systems.
CommentsIROS 2026
