Vision-and-Dialog Navigation

TL;DR

This paper introduces a new dataset and task for vision-and-dialog navigation, enabling robots to understand and use human language for cooperative environment exploration in photorealistic settings.

Contribution

It presents the Cooperative Vision-and-Dialog Navigation dataset and the Navigation from Dialog History task, advancing research in multimodal, cooperative robot navigation.

Findings

Longer dialog history improves navigation performance

Multi-modal sequence-to-sequence models can be trained for dialog-based navigation

The dataset facilitates studying human-robot cooperative navigation in realistic environments

Abstract

Robots navigating in human environments should use language to ask for assistance and be able to understand human responses. To study this challenge, we introduce Cooperative Vision-and-Dialog Navigation, a dataset of over 2k embodied, human-human dialogs situated in simulated, photorealistic home environments. The Navigator asks questions to their partner, the Oracle, who has privileged access to the best next steps the Navigator should take according to a shortest path planner. To train agents that search an environment for a goal location, we define the Navigation from Dialog History task. An agent, given a target object and a dialog history between humans cooperating to find that object, must infer navigation actions towards the goal in unexplored environments. We establish an initial, multi-modal sequence-to-sequence model and demonstrate that looking farther back in the dialog history improves performance. Sourcecode and a live interface demo can be found at https://cvdn.dev/