Object Goal Navigation with Recursive Implicit Maps

TL;DR

This paper introduces a recursive implicit map for object goal navigation that combines the advantages of explicit mapping and end-to-end learning, leading to improved performance and real-world deployment.

Contribution

It proposes a novel implicit spatial map updated with a transformer, integrating auxiliary tasks for enhanced spatial reasoning and generalization.

Findings

Outperforms state-of-the-art on MP3D dataset

Generalizes well to HM3D dataset

Successfully deployed on a real robot in real scenes

Abstract

Object goal navigation aims to navigate an agent to locations of a given object category in unseen environments. Classical methods explicitly build maps of environments and require extensive engineering while lacking semantic information for object-oriented exploration. On the other hand, end-to-end learning methods alleviate manual map design and predict actions using implicit representations. Such methods, however, lack an explicit notion of geometry and may have limited ability to encode navigation history. In this work, we propose an implicit spatial map for object goal navigation. Our implicit map is recursively updated with new observations at each step using a transformer. To encourage spatial reasoning, we introduce auxiliary tasks and train our model to reconstruct explicit maps as well as to predict visual features, semantic labels and actions. Our method significantly outperforms the state of the art on the challenging MP3D dataset and generalizes well to the HM3D dataset. We successfully deploy our model on a real robot and achieve encouraging object goal navigation results in real scenes using only a few real-world demonstrations. Code, trained models and videos are available at \url{https://www.di.ens.fr/willow/research/onav_rim/}.