The problem of finding a target and forming a path to it is known and is well-explored in the field of swarm robotics. Using swarm intelligence, even swarms of simple robots are capable of solving this problem. However, often these works assume that two robots can perceive each other can physically reach each other, or that robots can detect any target within communication range. These assumptions do not hold for all swarms and environments. This thesis introduces the CSP (Concurrent Searching and Pathfinding) algorithm to make path finding possible in simple swarms without relying on these assumptions. By strategically constructing and reconstructing an ephemeral network of stationary robots and relocating the rest of the robots throughout this network, swarms performing CSP can efficiently find targets with minimal risk of fracturing the network. The effect of packet loss, and swarm size, as well as the the execution time vis-à-vis creation of new anchors are shown.

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.