Vision-and-Language Navigation on HM3D Simulation
90.63SR (B)OmniNav
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OmniNavLevel=L02026.03 | 90.63 | 12.5 | 78.13 | 82 | 6 | 76 | 96.88 | 18.75 | 78.13 | 1.3 | 9.54 | 8.24 | |
| OmniNavLevel=L12026.03 | 80.63 | 18.75 | 61.88 | 76 | 13 | 63 | 87.5 | 18.75 | 68.75 | 2.35 | 9.84 | 7.49 | |
| HaltNavLevel=L02026.03 | 79.38 | 50 | 29.38 | 73 | 44 | 29 | 81.88 | 50 | 31.88 | 2.53 | 6.1 | 3.57 | |
| Uni-navidLevel=L02026.03 | 75.63 | 6.25 | 69.38 | 68 | 2 | 66 | 81.88 | 12.5 | 69.38 | 3.04 | 7.58 | 4.53 | |
| NavidLevel=L02026.03 | 73.13 | 6.25 | 66.88 | 68 | 5 | 63 | 83.13 | 6.25 | 76.88 | 2.82 | 9.64 | 6.82 | |
| StreamVLNLevel=L02026.03 | 72.5 | 37.5 | 35 | 62 | 19 | 43 | 83.75 | 37.5 | 46.25 | 3.06 | 6.61 | 3.55 | |
| HaltNavLevel=L12026.03 | 66.25 | 43.75 | 22.5 | 62 | 40 | 22 | 71.25 | 43.75 | 27.5 | 3.52 | 7.01 | 3.49 | |
| StreamVLNLevel=L12026.03 | 63.75 | 18.75 | 45 | 57 | 9 | 48 | 68.13 | 25 | 43.13 | 4.43 | 9.71 | 5.28 | |
| Uni-navidLevel=L12026.03 | 60.63 | 6.25 | 54.38 | 53 | 4 | 50 | 71.25 | 6.25 | 65 | 3.95 | 8.22 | 4.27 | |
| InternVLA-N1Level=L02026.03 | 58.75 | 12.5 | 46.25 | 42 | 11 | 31 | 70 | 12.5 | 57.5 | 3.35 | 5.45 | 2.1 | |
| NavidLevel=L12026.03 | 58.13 | 6.25 | 51.88 | 52 | 2 | 50 | 61.25 | 6.25 | 55 | 4.24 | 7.87 | 3.62 | |
| HaltNavLevel=L22026.03 | 55.63 | 31.25 | 24.38 | 52 | 29 | 23 | 57.5 | 37.5 | 26.25 | 4.61 | 9.16 | 4.55 | |
| OmniNavLevel=L22026.03 | 54.38 | 6.25 | 48.13 | 47 | 4 | 43 | 60 | 6.25 | 53.75 | 5.02 | 8.96 | 3.94 | |
| Uni-navidLevel=L22026.03 | 53.75 | 6.25 | 47.5 | 46 | 3 | 42 | 60.63 | 6.25 | 54.38 | 4.98 | 8.5 | 3.52 | |
| NavidLevel=L22026.03 | 49.38 | 0 | 49.38 | 43 | 0 | 43 | 56.25 | 0 | 56.25 | 5.16 | 8.45 | 3.29 | |
| InternVLA-N1Level=L12026.03 | 44.38 | 12.5 | 31.88 | 34 | 11 | 23 | 52.5 | 12.5 | 40 | 4.53 | 5.99 | 1.46 | |
| StreamVLNLevel=L22026.03 | 36.25 | 18.75 | 17.5 | 28 | 13 | 15 | 43.13 | 31.25 | 5.63 | 6.66 | 7.62 | 0.96 | |
| InternVLA-N1Level=L22026.03 | 33.13 | 0 | 33.13 | 28 | 0 | 28 | 43.13 | 0 | 43.13 | 5.17 | 7.45 | 2.28 |