Showing cs.ROShow all
3 papers · 1 filter
cs.RO2026
ReVNM: Learning-Based Visual Navigation from a Remote Camera
Michikuni Eguchi, Kohei Honda, Masafumi Endo +2
Visual Navigation Models (VNMs) enable robots to navigate from egocentric visual observations without geometric localization and planning, but long-range navigation still requires…
cs.RO2025
VLG-Loc: Vision-Language Global Localization from Labeled Footprint Maps
Mizuho Aoki, Kohei Honda, Yasuhiro Yoshimura +2
This paper presents Vision-Language Global Localization (VLG-Loc), a novel global localization method that uses human-readable labeled footprint maps containing only names and area…
cs.RO2025
GSplatVNM: Point-of-View Synthesis for Visual Navigation Models Using Gaussian Splatting
Kohei Honda, Takeshi Ishita, Yasuhiro Yoshimura +1
This paper presents a novel approach to image-goal navigation by integrating 3D Gaussian Splatting (3DGS) with Visual Navigation Models (VNMs), a method we refer to as GSplatVNM. V…