2 citations · 6 across the 32 of their papers we have counts for
Showing cs.ROShow all
2 papers · 1 filter
cs.RO2026
Revealing and Bridging the Physical Executability Gap in Vision-Language Navigation
Gang He, Zhile Cheng, Kepeng Xu +2
Continuous vision-and-language navigation (VLN) is typically evaluated by goal-reaching success, assuming it reflects an agent's ability to execute language-grounded behavior. We s…
cs.RO2026
ReasonNavi: Human-Inspired Global Map Reasoning for Zero-Shot Embodied Navigation
Yuzhuo Ao, Anbang Wang, Yu-Wing Tai +1
Embodied agents often struggle with efficient navigation because they rely primarily on partial egocentric observations, which restrict global foresight and lead to inefficient exp…