Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments
About
We develop a language-guided navigation task set in a continuous 3D environment where agents must execute low-level actions to follow natural language navigation directions. By being situated in continuous environments, this setting lifts a number of assumptions implicit in prior work that represents environments as a sparse graph of panoramas with edges corresponding to navigability. Specifically, our setting drops the presumptions of known environment topologies, short-range oracle navigation, and perfect agent localization. To contextualize this new task, we develop models that mirror many of the advances made in prior settings as well as single-modality baselines. While some of these techniques transfer, we find significantly lower absolute performance in the continuous setting -- suggesting that performance in prior `navigation-graph' settings may be inflated by the strong implicit assumptions.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Vision-Language Navigation | R2R-CE (val-unseen) | Success Rate (SR)41 | 433 | |
| Vision-and-Language Navigation | R2R (val unseen) | Success Rate (SR)25 | 344 | |
| Vision-Language Navigation | RxR-CE (val-unseen) | SR26.5 | 280 | |
| Vision-and-Language Navigation | R2R-CE (test-unseen) | SR28 | 63 | |
| Vision-and-Language Navigation | R2R-CE (val-seen) | SR37 | 49 | |
| Vision-and-Language Navigation | R2R-CE unseen continuous (val) | SR41 | 35 | |
| Vertical Perception | NavSpace | Navigation Error (NE)7.88 | 30 | |
| Precise Movement | NavSpace | Navigation Error (NE)6.85 | 27 | |
| Vision-Language Navigation | RxR (val-unseen) | Navigation Error (NE)12.1 | 25 | |
| Vision-Language Navigation | HA-VLN Unseen (val) | NE7.34 | 23 |