AI RESEARCH
AERR-Nav: Adaptive Exploration-Recovery-Reminiscing Strategy for Zero-Shot Object Navigation
arXiv CS.CV
•
ArXi:2603.17712v1 Announce Type: cross Zero-Shot Object Navigation (ZSON) in unknown multi-floor environments presents a significant challenge. Recent methods, mostly based on semantic value greedy waypoint selection, spatial topology-enhanced memory, and Multimodal Large Language Model (MLLM) as a decision-making framework, have led to improvements.