VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision
Overview
This research presents VEGA, a framework for training navigation Vision-Language-Action (VLA) models using unlabeled egocentric videos.
Generated from attributed reports · Updated 1 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · trajectories: 5000000 other · trajectory count
“trajectory distribution is then used to train a flow-matching VLA navigation policy. By using geometry exclusively during training, VEGA distills obstacle-aware planning directly into a vision-based policy. Furthermore, we introduce VEGA-Bench, a benchmark containing 250k scenes and approximately 5 million navigation goals paired with scene geometry, designed to evaluate goal progress, collision avoidance, and obstac”
Exact source · revision 1Source owner not reported
Reported quantity · scenes: 250000 other · Basis not reported
“trajectory distribution is then used to train a flow-matching VLA navigation policy. By using geometry exclusively during training, VEGA distills obstacle-aware planning directly into a vision-based policy. Furthermore, we introduce VEGA-Bench, a benchmark containing 250k scenes and approximately 5 million navigation goals paired with scene geometry, designed to evaluate goal progress, collision avoidance, and obstac”
Exact source · revision 1Source owner not reported
Artifact availability · code: reported pending
“upervision provides a scalable and effective signal for training obstacle-aware navigation VLAs. The code and benchmark will be released at the time of publication.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalVEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision
This research presents VEGA, a framework for training navigation Vision-Language-Action (VLA) models using unlabeled egocentric videos.
Event coverage history
Current attention 3·Peak within the comparable range 7（2026-11-02 18:00 UTC）·Change within the comparable range over 24 hours -51%
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).