Pathdreamer: A World Model for Indoor Navigation
This work addresses the challenge of embodied navigation for AI agents in unfamiliar indoor settings, representing an incremental advance by applying a novel method to a known bottleneck in model-based navigation.
The paper tackles the problem of enabling computational agents to navigate novel indoor environments by introducing Pathdreamer, a visual world model that generates plausible high-resolution 360-degree observations (RGB, semantic segmentation, depth) for unvisited viewpoints, and demonstrates its utility in Vision-and-Language Navigation by showing that planning ahead with Pathdreamer achieves about half the benefit of using actual observations.
People navigating in unfamiliar buildings take advantage of myriad visual, spatial and semantic cues to efficiently achieve their navigation goals. Towards equipping computational agents with similar capabilities, we introduce Pathdreamer, a visual world model for agents navigating in novel indoor environments. Given one or more previous visual observations, Pathdreamer generates plausible high-resolution 360 visual observations (RGB, semantic segmentation and depth) for viewpoints that have not been visited, in buildings not seen during training. In regions of high uncertainty (e.g. predicting around corners, imagining the contents of an unseen room), Pathdreamer can predict diverse scenes, allowing an agent to sample multiple realistic outcomes for a given trajectory. We demonstrate that Pathdreamer encodes useful and accessible visual, spatial and semantic knowledge about human environments by using it in the downstream task of Vision-and-Language Navigation (VLN). Specifically, we show that planning ahead with Pathdreamer brings about half the benefit of looking ahead at actual observations from unobserved parts of the environment. We hope that Pathdreamer will help unlock model-based approaches to challenging embodied navigation tasks such as navigating to specified objects and VLN.