%A Sylvain Cussat-Blanc
%A Jean Disset
%A Stéphane Sanchez
%T Dangerousness Metric for Gene Regulated Car Driving
%X In this paper, we show how a dangerousness metric can be used to modify the input of a gene regulatory network when plugged to a virtual car. In the context of the 2015 Simulated Car Racing Championship organized during GECCO 2015, we have developed a new cartography methodology able to inform the controller of the car about the incoming complexity of the track: turns (slipperiness, angle, etc.) and bumps. We show how this dangerousness metric improves the results of our controller and outperforms other approaches on the tracks used in the competition.
%K Gene regulatory network - Virtual car racing - Dangerousness measure
%P 620-635
%D 2016
%C Porto, Portugal
%I Springer
%L publications28867