Vision-Language Navigation on AerialVLN unseen S (val)
60.2Navigation Error (NE)CityNavAgent
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| CityNavAgentS.RGB=false, Depth=true, Pano.=true, Odo.=true2025.12 | 60.2 | 11.7 | 35.2 | 5 | |
| CityNavAgentCategory=Zero-Shot, LLM=GPT-4V, Method Environment Type=Aerial2026.04 | 60.2 | 11.7 | 35.2 | 5 | |
| NavGPTCategory=Zero-Shot, LLM=GPT-4, Method Environment Type=Indoor2026.04 | 82.1 | 0 | 0 | 0 | |
| OursS.RGB=true, Depth=false, Pano.=false, Odo.=false2025.12 | 95.8 | 8.1 | 28.9 | 2.2 | |
| LookasideVLNCategory=Zero-Shot, LLM=Qwen2.5-VL-72B, Method Environment Type=Aerial2026.04 | 100.9 | 12.6 | 36 | 3.6 | |
| NavidS.RGB=true, Depth=false, Pano.=false, Odo.=false2025.12 | 106.9 | 6.1 | 12.3 | 0.7 | |
| MapGPTS.RGB=true, Depth=false, Pano.=false, Odo.=false2025.12 | 107 | 0 | 0 | 0 | |
| MapGPTCategory=Zero-Shot, LLM=GPT-4V, Method Environment Type=Indoor2026.04 | 107 | 0 | 0 | 0 | |
| OpenflyS.RGB=true, Depth=false, Pano.=false, Odo.=false2025.12 | 113.8 | 7.6 | 18.2 | 1.5 | |
| SMTRS.RGB=true, Depth=true, Pano.=false, Odo.=false2025.12 | 119.5 | 10.8 | 23 | 1.9 | |
| STMRCategory=Zero-Shot, LLM=GPT-4o, Method Environment Type=Aerial2026.04 | 119.5 | 10.8 | 23 | — | |
| Grid-based VSS.RGB=false, Depth=false, Pano.=true, Odo.=true2025.12 | 121.3 | 7.4 | 16.1 | 2.5 | |
| LAGS.RGB=true, Depth=true, Pano.=false, Odo.=false2025.12 | 127.9 | 5.1 | 10.5 | 1.4 | |
| LAGCategory=Learning-Based, LLM=-2026.04 | 127.9 | 5.1 | 10.5 | 1.4 | |
| Random SamplingS.RGB=false, Depth=false, Pano.=false, Odo.=false2025.12 | 149.7 | 0 | 0 | 0 | |
| RandomCategory=Statistical, LLM=-2026.04 | 149.7 | 0 | 0 | 0 | |
| CMAS.RGB=true, Depth=true, Pano.=false, Odo.=false2025.12 | 172.1 | 3.2 | 16 | 1.1 | |
| CMACategory=Learning-Based, LLM=-2026.04 | 172.1 | 3.2 | 16 | 1.1 | |
| Seq2SeqS.RGB=true, Depth=true, Pano.=false, Odo.=false2025.12 | 218.9 | 2.3 | 11.7 | 0.7 | |
| Seq2SeqCategory=Learning-Based, LLM=-2026.04 | 218.9 | 2.3 | 11.7 | 0.7 | |
| Action SamplingS.RGB=false, Depth=false, Pano.=false, Odo.=false2025.12 | 237.6 | 0.2 | 1.1 | 0.1 | |
| Action SamplingCategory=Statistical, LLM=-2026.04 | 237.6 | 0.2 | 1.1 | 0.1 | |
| LingUNetS.RGB=true, Depth=true, Pano.=false, Odo.=false2025.12 | 368.4 | 0.4 | 3.6 | 0.9 |