MOSU improves outdoor robot traversability by about 10% over prior state-of-the-art on the GND benchmark by fusing geometric, semantic, and vision-language-model scores for candidate trajectories.
IEEE transactions on pattern analysis and machine intelligence 43(12) (2020) 4338–4364
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MOSU: Autonomous Long-range Robot Navigation with Multi-modal Scene Understanding
MOSU improves outdoor robot traversability by about 10% over prior state-of-the-art on the GND benchmark by fusing geometric, semantic, and vision-language-model scores for candidate trajectories.