AI RESEARCH
Expand Your SCOPE: Semantic Cognition over Potential-Based Exploration for Embodied Visual Navigation
arXiv CS.CV
•
ArXi:2511.08935v2 Announce Type: replace-cross Embodied visual navigation remains a challenging task, as agents must explore unknown environments with limited knowledge. Existing zero-shot studies have shown that incorporating memory mechanisms to goal-directed behavior can improve long-horizon planning performance. However, they overlook visual frontier boundaries, which fundamentally dictate future trajectories and observations, and fall short of inferring the relationship between partial visual observations and navigation goals.