EVOR: an online evolutionary algorithm for car racing games

In this paper, we present evolutionary racer (EVOR) a simulated car dynamically controlled by an online evolutionary algorithm (EA). The key distinction between EVOR and earlier car racing methods is that it considers car racing as a dynamic optimization problem and is addressed by an evolutionary algorithm. Our approach calculates a car trajectory based on a controller decision and adjusts this decision according to the suitability of its resultant trajectory with the current track status. Furthermore, it allows to integrate features such as opponent handling implicitly. Our experimental results show that EVOR outperforms current best AI controllers on a wide range of tracks.

[1]  Daniele Loiacono,et al.  Interactive evolution for the procedural generation of tracks in a high-end racing game , 2011, GECCO '11.

[2]  Daniele Loiacono,et al.  Simulated Car Racing Championship: Competition Software Manual , 2013, ArXiv.

[3]  C. Edmondson Fast Car Physics , 2011 .

[4]  Kyung-Joong Kim,et al.  Generalization of TORCS car racing controllers with artificial neural networks and linear regression analysis , 2012, Neurocomputing.

[5]  Günter Rudolph,et al.  Driving Faster Than a Human Player , 2011, EvoApplications.

[6]  Vicente Milanés Montero,et al.  On-line learning of a fuzzy controller for a precise vehicle cruise control system , 2013, Expert Syst. Appl..

[7]  Simon M. Lucas,et al.  Rolling horizon evolution versus tree search for navigation in single-player real-time games , 2013, GECCO '13.

[8]  Pedro Isasi Viñuela,et al.  Evolving a fuzzy controller for a Car Racing Competition , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[9]  Vicente Milanés Montero,et al.  An evolutionary tuned driving system for virtual car racing games: The AUTOPIA driver , 2012, Int. J. Intell. Syst..

[10]  Daniele Loiacono,et al.  Advanced overtaking behaviors for blocking opponents in racing games using a fuzzy architecture , 2013, Expert Syst. Appl..

[11]  Anastasios Tefas,et al.  Evolutionary Optimization of a Neural Network Controller for Car Racing Simulation , 2012, SETN.

[12]  Julian Togelius,et al.  Evolving controllers for simulated car racing using object oriented genetic programming , 2007, GECCO '07.

[13]  Julian Togelius,et al.  The 2007 IEEE CEC simulated car racing competition , 2008, Genetic Programming and Evolvable Machines.

[14]  Hans B. Pacejka,et al.  Tire and Vehicle Dynamics , 1982 .

[15]  Shengxiang Yang,et al.  Evolutionary dynamic optimization: A survey of the state of the art , 2012, Swarm Evol. Comput..

[16]  Araceli Sanchis,et al.  A human-like TORCS controller for the Simulated Car Racing Championship , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[17]  Kyung-Joong Kim,et al.  Optimization of an Autonomous Car Controller Using a Self-Adaptive Evolutionary Strategy: , 2012 .

[18]  Christos Dimitrakakis,et al.  TORCS, The Open Racing Car Simulator , 2005 .