Evolving Coverage Behaviours For MAVs Using NEAT

Dynamic coverage - the problem of covering an area evenly and continuously in order to visit all areas of interest - is an important procedure to optimise for any autonomous surveillance system. This work introduces a novel solution to the multi-agent version of this problem in that it achieves high performance in a completely decentralised manner with no reliance on GPS. It does so by using NEAT to optimise agent neural controllers. The controllers are first realised via simulation and then transferred to Micro-Aerial Vehicles (MAVs). The MAVs are modified to include a Ultra-wideband Frequency (UWB) chip which use radio waves to communicate inter drone distances to one another.

[1]  Eliseo Ferrante,et al.  ARGoS: a modular, parallel, multi-engine simulator for multi-robot systems , 2012, Swarm Intelligence.

[2]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[3]  Dario Izzo,et al.  Controlling spacecraft landings with constantly and exponentially decreasing time-to-contact , 2015, IEEE Transactions on Aerospace and Electronic Systems.

[4]  B. Remes,et al.  Optic-Flow Based Slope Estimation for Autonomous Landing , 2013 .

[5]  Gerhard Weiss,et al.  A Multi-robot Coverage Approach Based on Stigmergic Communication , 2012, MATES.

[6]  Anders Lyhne Christensen,et al.  Evolution of Collective Behaviors for a Real Swarm of Aquatic Surface Robots , 2015, PloS one.

[7]  Sven Koenig,et al.  Terrain coverage with ant robots: a simulation study , 2001, AGENTS '01.

[8]  Israel A. Wagner,et al.  Distributed covering by ant-robots using evaporating traces , 1999, IEEE Trans. Robotics Autom..

[9]  Petros G. Voulgaris,et al.  Supervised coverage control of multi-agent systems , 2014, Autom..

[10]  Mahyar Naraghi,et al.  Coverage control of a dynamic large-scale environment using sector-based sensors , 2014, 2014 Second RSI/ISM International Conference on Robotics and Mechatronics (ICRoM).

[11]  Karl Tuyls,et al.  Multi-Robot Coverage: A Bee Pheromone Signalling Approach , 2014, ALIA.

[12]  Elizabeth Sklar,et al.  Social Insect-Inspired Multi-Robot Coverage , 2015, AAMAS.

[13]  Hilbert J. Kappen,et al.  Local histogram matching for efficient optical flow computation applied to velocity estimation on pocket drones , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).