# LANav in depth: when robots stop revisiting history and learn to organize memory

- Source: Guyuehome
- Published: 2026-10-27T01:37:00.000Z
- RoboHot: https://robohot.news/en/items/ljzuvywi6hswvqf6b0pgpd55g
- Original: https://www.guyuehome.com/detail?id=2110289142253383682

## Summary

LANav targets the open-vocabulary object goal navigation (OVON) task, in which a robot must find a target in an unfamiliar indoor environment using only its current first-person image. Its approach is to have the robot stop repeatedly reviewing past frames and instead organize its memory to support navigation decisions.
