Estimating Map Completeness in Robot Exploration

TL;DR

This paper introduces a deep learning-based method for estimating map completeness during robot exploration, enabling efficient stopping criteria that significantly reduce exploration time.

Contribution

It presents a novel neural network approach to assess explored area and determine when to stop exploration, improving efficiency in indoor mapping tasks.

Findings

Reduces exploration time by 40% on average

Accurately estimates explored area and remaining coverage

Provides a reliable stopping criterion for exploration

Abstract

In this paper, we propose a method that, given a partial grid map of an indoor environment built by an autonomous mobile robot, estimates the amount of the explored area represented in the map, as well as whether the uncovered part is still worth being explored or not. Our method is based on a deep convolutional neural network trained on data from partially explored environments with annotations derived from the knowledge of the entire map (which is not available when the network is used for inference). We show how such a network can be used to define a stopping criterion to terminate the exploration process when it is no longer adding relevant details about the environment to the map, saving, on average, 40% of the total exploration time with respect to covering all the area of the environment.