Gas Source Localization Using physics Guided Neural Networks

arXiv:2405.04151v1 Announce Type: new
Abstract: This work discusses a novel method for estimating the location of a gas source based on spatially distributed con- centration measurements taken, e.g., by a mobile robot or flying platform that follows a predefined trajectory to collect samples. The proposed approach uses a Physics-Guided Neural Network to approximate the gas dispersion with the source location as an additional network input. After an initial offline training phase, the neural network can be used to efficiently solve …

abstract arxiv cs.lg distributed flying localization location mobile network networks neural network neural networks novel physics platform robot samples trajectory type work