Visual Navigation 벤치마크
Visual Navigation on SOON Test
Nav-SPL
- 2021-03-31 — GBE: Nav-SPL 13.3
- 2022-02-23 — DUET: Nav-SPL 21.42
- 2022-08-24 — AutoVLN: Nav-SPL 27.83
| Rank | Model | Nav-SPL | SR | Paper | Code | Year |
|---|---|---|---|---|---|---|
| 1 | AutoVLN | 27.83 | 40.36 | Learning from Unlabeled 3D Environments for Vision-and-Language Navigation | cshizhe/HM3DAutoVLN | 2022 |
| 2 | NaviLLM | 26.26 | 35.04 | Towards Learning a Generalist Model for Embodied Navigation | zd11024/NaviLLM · lavi-lab/navillm | 2023 |
| 3 | Meta-Explore | 25.8 | 39.1 | Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding | 2023 | |
| 4 | SUSA | 25.47 | 36.87 | Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation | HCI-LMC/VLN-SUSA | 2024 |
| 5 | DUET | 21.42 | 33.44 | Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation | cshizhe/vln-duet | 2022 |
| 6 | GBE | 13.3 | 19.5 | SOON: Scenario Oriented Object Navigation with Graph-based Exploration | zhufengdaaa/soon | 2021 |