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)42 | 677 | |
| Vision-and-Language Navigation | R2R (val unseen) | Success Rate (SR)25 | 448 | |
| Vision-Language Navigation | RxR-CE (val-unseen) | SR40 | 426 | |
| Vision-and-Language Navigation | R2R-CE (val-seen) | SR37 | 79 | |
| Vision-and-Language Navigation | R2R-CE (test-unseen) | SR28 | 63 | |
| Vision-Language Navigation | RxR (val-unseen) | Success Rate (SR)13.9 | 62 | |
| Vision-and-Language Navigation | R2R-CE v1.0 (val unseen) | SR (Success Rate)41 | 44 | |
| Vision-Language Navigation | VLN-CE R2R (val unseen) | Navigation Error (NE)7.77 | 41 | |
| Vision-and-Language Navigation | R2R-CE unseen continuous (val) | SR41 | 35 | |
| Vision-Language Navigation | HA-VLN Unseen (val) | SR7 | 32 |