Learning Embeddings that Capture Spatial Semantics for Indoor Navigation

TL;DR

This paper introduces a method for creating object embeddings that encode spatial semantics, improving indoor navigation by leveraging pre-trained language models and knowledge bases to guide search tasks in unseen environments.

Contribution

The work presents a novel approach to embed spatial semantic priors into object representations for indoor navigation, enhancing search efficiency in unseen environments.

Findings

Embeddings improve search success rate in indoor environments.

Pre-trained language models effectively encode spatial semantics.

Method outperforms baseline approaches in AI2Thor simulator.

Abstract

Incorporating domain-specific priors in search and navigation tasks has shown promising results in improving generalization and sample complexity over end-to-end trained policies. In this work, we study how object embeddings that capture spatial semantic priors can guide search and navigation tasks in a structured environment. We know that humans can search for an object like a book, or a plate in an unseen house, based on the spatial semantics of bigger objects detected. For example, a book is likely to be on a bookshelf or a table, whereas a plate is likely to be in a cupboard or dishwasher. We propose a method to incorporate such spatial semantic awareness in robots by leveraging pre-trained language models and multi-relational knowledge bases as object embeddings. We demonstrate using these object embeddings to search a query object in an unseen indoor environment. We measure the performance of these embeddings in an indoor simulator (AI2Thor). We further evaluate different pre-trained embedding onSuccess Rate(SR) and success weighted by Path Length(SPL).