AI RESEARCH

Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering

arXiv CS.CV

ArXi:2602.11183v2 Announce Type: replace-cross Continuous navigation in complex environments is critical for Unmanned Aerial Vehicle (UAV). However, the existing Vision-Language Navigation (VLN) models follow the dead-reckoning, which iteratively updates its position for the next waypoint prediction, and subsequently construct the complete trajectory.