Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments
This addresses the challenge of more realistic navigation for AI agents, though it is incremental by adapting existing methods to a new setting.
The paper tackles the problem of language-guided navigation in continuous 3D environments, dropping assumptions like known topologies and perfect localization, and finds significantly lower performance compared to prior graph-based settings, indicating inflated results due to those assumptions.
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.