NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation
Goal-conditioned visual navigation requires a robot to act under partial observability by anticipating how its motion...
Why it matters: arXiv (Daichi Azuma) is tied to AI research; research movement often signals where model capability, evaluation practice, and lab priorities are heading before products arrive.
Primary Source
arXiv (Daichi Azuma)
research / 1 source