外观
论文arXiv 2609.282581 个月前
基于世界模型的可泛化机器人插入
原文链接：Generalizable Robotic Insertion with World Models（arXiv 2609.28258 · 发布日期：2026-09-23）
Generalizable Robotic Insertion with World Models
该框架用结合本体感知与腕部相机视觉的世界模型解决多零件插入泛化，并在多种插入任务和未知几何物体上验证。
核心要点
- 高混合装配需要适应多样零件，现有方法通常依赖针对单个插入任务的专用策略。
- 方法训练单一世界模型，融合机器人本体感知与腕部相机采集的原始视觉观测。
- 在最多90个几何多样插入任务上训练，对未见未知几何物体零样本成功率达56%，高于无模型基线的7%。
- 训练物体增多时性能提升；在保留物体上微调比从零训练更具数据效率，部分情况渐近性能更好。
验证范围与局限：验证范围为几何多样零件的插入任务、未见未知几何物体及保留物体微调；摘要未说明仿真或真机设置。
英文摘要 (Abstract)
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.
作者：Nicklas Hansen, Iretiayo Akinola, Yijie Guo, Jie Xu, Bingjie Tang, Hao Su, Xiaolong Wang, Abhishek Gupta, Dieter Fox, Yashraj Narang
来源
本页事实对应的公开页面，以原文为准。