Object Goal Navigation with Recursive Implicit Maps - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Object Goal Navigation with Recursive Implicit Maps

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 https://www.di.ens.fr/willow/research/onav_rim/.
Fichier principal
Vignette du fichier
2308.05602.pdf (4.13 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04215744 , version 1 (22-09-2023)

Licence

Identifiers

  • HAL Id : hal-04215744 , version 1

Cite

Shizhe Chen, Thomas Chabal, Ivan Laptev, Cordelia Schmid. Object Goal Navigation with Recursive Implicit Maps. The 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023), Oct 2023, Detroit (Michigan), United States. ⟨hal-04215744⟩
24 View
8 Download

Share

Gmail Mastodon Facebook X LinkedIn More