Skip to content

Opening book details…

Can I read Navigating to Objects in the Real World on EtoBox?

Navigating to Objects in the Real World by Gervet, Theophile; Chintala, Soumith; Batra, Dhruv; Malik, Jitendra; Chaplot, Devendra Singh is a scholarly article available to read on EtoBox.

What is Navigating to Objects in the Real World about?

Semantic navigation is necessary to deploy mobile robots in uncontrolled environments like our homes, schools, and hospitals. Many learning-based approaches have been proposed in response to the lack of semantic understanding of the classical pipeline for spatial navigation, which builds a geometric map using depth sensors and plans to reach point goals. Broadly, end-to-end learning approaches reactively map sensor inputs to actions with deep neural networks, while modular learning approaches enrich the classical pipeline with learning-based semantic sensing and exploration. But learned visual navigation policies have predominantly been evaluated in simulation. How well do different classes of methods work on a robot? We present a large-scale empirical study of semantic visual navigation methods comparing representative methods from classical, modular, and end-to-end learning approaches across six homes with no prior experience, maps, or instrumentation. We find that modular learning works well in the real world, attaining a 90% success rate. In contrast, end-to-end learning does not, dropping from 77% simulation to 23% real-world success rate due to a large image domain gap betwee

Author
Gervet, Theophile; Chintala, Soumith; Batra, Dhruv; Malik, Jitendra; Chaplot, Devendra Singh
Published
2022
Language
EN

More by Gervet, Theophile; Chintala, Soumith; Batra, Dhruv; Malik, Jitendra; Chaplot, Devendra Singh

Browse all works by Gervet, Theophile; Chintala, Soumith; Batra, Dhruv; Malik, Jitendra; Chaplot, Devendra Singh