Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation

Benchmark Model Rank Results
object-localization-on-reverieSUSA#1RGSPL: 27.31Nav-Succ: 54.39Nav-SPL: 41.54Nav-Length: 17.86
visual-navigation-on-room-to-room-1SUSA#1spl: 0.6383
visual-navigation-on-soon-testSUSA#3Nav-SPL: 25.47SR: 36.87