Print Email Facebook Twitter AudioLocNet Title AudioLocNet: Deep Neural Network Based Audio Source Localization for Inter Robot Localization Author van der Horst, Casper (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Embedded and Networked Systems) Contributor Venkatesha Prasad, Ranga Rao (mentor) Rajan, R.T. (graduation committee) Amjad Yousef Majid, Amjad (graduation committee) Degree granting institution Delft University of Technology Programme Electrical Engineering | Embedded Systems Date 2022-12-09 Abstract For my Master’s thesis, I developed and trained an audio-based localization system for indoor localization called AudioLocNet. AudioLocNet is based on convolutional neural networks and maps recordings from a small(10cm diameter) microphone array to a grid of locations around said array. AudioLocNet was made to be used by swarms of small robots to locate each other using audio signals. AudioLocNet was trained using orthogonal chirp signals which have a low cross-correlation. Said signals can also be used for simultaneous communications between multiple robots. These signals were recorded in indoor environments ranging from simple line-of-sight environments to reverberant non-line-of-sight ones. Audio signals are used since they form a propagational middle class when compared to radio frequency (RF) and light-based signals for localization. Whereas light requires a line of sight, audio can bend around corners; and whereas RF signals pass through walls, reaching robots that are outside of each other’s spheres of influence, audio will not.AudioLocNet reaches high accuracies for both a coarse grid (99.96 %) and a fine grid (99.89 %) of possible locations, where only the final layer of the network architecture must be changed to account for the increased resolution of the fine grid. Subject Sound Source LocalizationDNNSwarm Robotics To reference this document use: http://resolver.tudelft.nl/uuid:650f171a-ddb6-4795-8afb-f94950caf3ec Part of collection Student theses Document type master thesis Rights © 2022 Casper van der Horst Files PDF AudioLocNet_MSc_Thesis.pdf 19.48 MB Close viewer /islandora/object/uuid:650f171a-ddb6-4795-8afb-f94950caf3ec/datastream/OBJ/view