Showing 2024Show all
2 papers · 1 filter
cs.RO2024
FloNa: Floor Plan Guided Embodied Visual Navigation
Jiaxin Li, Weiqi Huang, Zan Wang +3
Humans naturally rely on floor plans to navigate in unfamiliar environments, as they are readily available, reliable, and provide rich geometrical guidance. However, existing visua…
cs.CV2024
R2G: Reasoning to Ground in 3D Scenes
Yixuan Li, Zan Wang, Wei Liang
We propose Reasoning to Ground (R2G), a neural symbolic model that grounds the target objects within 3D scenes in a reasoning manner. In contrast to prior works, R2G explicitly mod…