Rui-Tian Pang

TADreamer is presented, a zero-shot framework that grounds video-imagined navigation in measured geometry without task-specific training or fine-tuning, and reduces mean absolute depth error and mean absolute relative depth error compared with NavDreamer.

Achieving decimeter-level positioning accuracy with low-cost single-frequency GNSS receivers could revolutionize autonomous navigation by eliminating the need for expensive infrastructure.

FLAP enables UAVs to navigate complex 3D environments safely and efficiently by integrating active perception into trajectory planning, overcoming traditional sensor limitations.

Prior maps, even when flawed, can significantly boost UAV exploration efficiency, achieving over 34% better performance in complex environments.