外观
论文arXiv 2609.121031 个月前
RodForesight：用于细长杆插入的世界模型增强扩散策略
原文链接：RodForesight: A World Model Enhanced Diffusion Policy for Slender Rod Insertion（arXiv 2609.12103 · 发布日期：2026-09-10）
RodForesight: A World Model Enhanced Diffusion Policy for Slender Rod Insertion
针对细长杆插入中杆体弯曲导致的对准控制难题，RodForesight结合视觉伺服、扩散策略与动作条件世界模型，并在插入实验中验证提升成功率。
核心要点
- 细长杆会在操作中弯曲，传统刚性 peg-in-hole 的固定尖端位姿假设失效。
- 框架分为粗接近与预测插入两阶段，也可封装为端到端设计。
- 插入时扩散策略生成候选动作块，世界模型预测杆孔对准效果以选择动作。
- 实验比较各阶段和端到端设置，相较扩散策略等基线成功率由88.9%提升至96.7%。
验证范围与局限：验证限于细长杆插入任务，摘要未说明仿真或真机环境。
英文摘要 (Abstract)
Slender rod insertion arises in precision manufacturing, where millimetre scale diameter and tight clearances demand accurate perception and control. Conventional peg-in-hole methods assume a rigid object whose tip pose is fixed relative to the gripper. This assumption breaks down for a high aspect ratio rod, which can bend during manipulation, making its tip motion dependent on the rod configuration, grasp, material properties, and contact. We present RodForesight, a learning framework that factorises the task into two stages: 1) coarse approaching, which uses visual servoing to map diverse initial configurations into a compact near hole hand-off region; and 2) predictive insertion, which performs fine alignment and completes the insertion. It is worth noting that the two stages can be wrapped into an end-to-end design. During insertion, a diffusion policy generates candidate action chunks, while an action conditioned world model predicts their effects on rod-hole alignment. This pre-execution evaluation enables RodForesight to select the best action chunk based on predicted tilt and radial errors before execution. Experiments investigate the performance of different stages and the end-to-end setting, where RodForesight improves the success rate from 88.9% to 96.7%, compared to baseline methods such as diffusion policy.
作者：Chuanbo Yu, Mingyu Yue, Yan Lyu, Chuhan Song, Peng Wang
来源
本页事实对应的公开页面，以原文为准。