https://rwin2.github.io/erwinpoussi.github.io/tag/autonomous-navigation/Autonomous NavigationHugo Blox Builder (https://hugoblox.com)en-usSat, 01 Aug 2026 00:00:00 +0000https://rwin2.github.io/erwinpoussi.github.io/media/icon_hu0b7a4cb9992c9ac0e91bd28ffd38dd00_9727_512x512_fill_lanczos_center_3.pnghttps://rwin2.github.io/erwinpoussi.github.io/tag/autonomous-navigation/https://rwin2.github.io/erwinpoussi.github.io/project/gait/Sat, 01 Aug 2026 00:00:00 +0000https://rwin2.github.io/erwinpoussi.github.io/project/gait/<h2 id="demo">Demo</h2> <video width="100%" height="420" autoplay loop muted playsinline> <source src="demo.mp4" type="video/mp4"> </video> <p><strong>GAIT</strong> (Graph-memory Agent with Interrupt-Triggered reasoning) builds a persistent, structured memory for vision-language-action (VLA) models by constructing semantic scene graphs online during navigation. The agent incrementally builds a graph-based spatial memory from egocentric observations, encoding object identities, spatial relations, and semantic attributes as it explores. An interrupt-triggered reasoning mechanism allows the agent to re-plan on the fly when novel or task-relevant cues are detected — bridging reactive control with deliberative graph-based reasoning.</p> <p>This enables <strong>open-vocabulary navigation</strong>: given a free-form language goal, the agent retrieves and reasons over its scene graph memory to localize targets it has previously observed, or to plan exploration strategies for unseen goals — without requiring a fixed object vocabulary or pre-built map.</p> <p><strong>Status:</strong> More to come soon!</p>