# OpenDoge uses observation-history implicit state estimation to control quadruped robot locomotion

- Source: Guyuehome
- Published: 2026-10-29T06:26:00.000Z
- RoboHot: https://robohot.news/en/items/aw8adw2gshhy0q601jpnrvwm5
- Original: https://www.guyuehome.com/detail?id=2103921402324217858

## Summary

OpenDoge proposes a hybrid internal model for quadruped robot locomotion control that, without terrain maps or contact sensors, encodes observation history into a velocity estimate and a 16-dimensional latent state to determine gait phase and external disturbances. The article combines real inference data to examine what information the latent state carries and what it lacks.