一次扫描即可：语言引导导航的无演示适配方法 Scan2Instruction + PRPT-KS
One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation
AI 导读
RealNav 框架用一次 iPhone 扫描替代人工演示，实现语言引导导航策略在新环境的适配：Scan2Instruction 将扫描结果编译为训练环境并自动合成带指令的导航片段，PRPT-KS 通过闭环 Pareto 效用直接从重建场景读取信号，无需学习 critic 和人工标注。
正文 · 原文
Abstract:Deploying a language-guided navigation policy in a new building usually means watching it fail. Public-benchmark VLAs degrade scene by scene as layout, appearance, and language drift, and the standard fix of teleoperating fresh trajectories on site does not scale. We replace human demonstration with a single brief iPhone scan. Scan2Instruction compiles that scan into a complete training environment, automatically synthesizing executable navigation episodes with grounded instructions. PRPT-KS then adapts the policy through a closed-form Pareto utility read directly off the reconstructed scene, with no learned critic and no human labels. Across five real environments, the two designs together drive our RealNav to an 85% real-robot success rate, compared with 49% for a RealNav baseline post-trained on human demonstrations, and still achieve 82% in unscanned regions of the same buildings, compared with 41% for the same baseline. Our work turns demonstration-free scene adaptation for language-guided navigation from an aspiration into a working reality.
| Comments: | NeurIPS 2026 |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.33794 [cs.RO] |
| (or arXiv:2610.33794v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33794 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuxing Long [view email]
[v1]
Sat, 24 Oct 2026 16:53:59 UTC (2,725 KB)
来源：arXiv cs.AI · arxiv.org