Deep-Learning-Aided Path Planning and Map Construction for Expediting Indoor Mapping

TL;DR

This paper introduces a deep learning approach that uses a pre-trained neural network to predict maps, significantly reducing indoor mapping time when integrated with path planning and map construction.

Contribution

The novel integration of a generative neural network as a map predictor into indoor mapping processes accelerates mapping, achieving over 50% reduction in some cases.

Findings

Mapping time reduced by over 50% with the proposed method.

The neural network predictor improves efficiency in both path planning and map construction.

Simulation results confirm significant time savings across different datasets.

Abstract

The problem of autonomous indoor mapping is addressed. The goal is to minimize the time to achieve a predefined percentage of exposure with some desired level of certainty. The use of a pre-trained generative deep neural network, acting as a map predictor, in both the path planning and the map construction is proposed in order to expedite the mapping process. This method is examined in combination with several frontier-based path planners for two distinct floorplan datasets. Simulations are run for several configurations of the integrated map predictor, the results of which reveal that by utilizing the prediction a significant reduction in mapping time is possible. When the prediction is integrated in both path planning and map construction processes it is shown that the mapping time may in some cases be cut by over 50%.