Ground then Navigate: Language-guided Navigation in Dynamic Scenes

Understand

We investigate the Vision-and-Language Navigation (VLN) problem in the context of autonomous driving in outdoor settings.

• We solve the problem by explicitly grounding the navigable regions corresponding to the textual command.
• At each timestamp, the model predicts a segmentation mask corresponding to the intermediate or the final navigable region.
• Our work contrasts with existing efforts in VLN, which pose this task as a node selection problem, given a discrete connected graph corresponding to the environment.