DeepAI AI Chat
Log In Sign Up

Pathdreamer: A World Model for Indoor Navigation

by   Jing Yu Koh, et al.

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.


page 1

page 4

page 5

page 6

page 8


Learning and Planning with a Semantic Model

Building deep reinforcement learning agents that can generalize and adap...

Knowledge-driven Scene Priors for Semantic Audio-Visual Embodied Navigation

Generalisation to unseen contexts remains a challenge for embodied navig...

ESNI: Domestic Robots Design for Elderly and Disabled People

Our paper focuses on the research of the possibility for speech recognit...

VisualEchoes: Spatial Image Representation Learning through Echolocation

Several animal species (e.g., bats, dolphins, and whales) and even visua...

Embodied Learning for Lifelong Visual Perception

We study lifelong visual perception in an embodied setup, where we devel...

Optimizing Indoor Navigation Policies For Spatial Distancing

In this paper, we focus on the modification of policies that can lead to...

The Replica Dataset: A Digital Replica of Indoor Spaces

We introduce Replica, a dataset of 18 highly photo-realistic 3D indoor s...