Abstract
We present an evolution of an agent, remotely operating a fast running scale model of a car. The agent perceives the environment from overhead video camera and conveys its actions via radio control transmitter. In order to cope with the video feed latency we propose an anticipatory modeling in which the agent considers its actions based on the anticipated state of the car. The agent is first evolved offline on a software simulator and then adapted online to the real world. During the online evolution, the lap times improve to the values much close to the values obtained from the offline evolution. An online evolutionary optimization of the avoidance of a small static obstacle with a priori known properties results in lap times that are virtually the same as the best lap times achieved on the same track without obstacles. This work can be viewed as a step towards the automated design of controllers of remotely operated vehicles capable to find an optimal solution to various tasks in a priori known environments.
Similar content being viewed by others
References
Abbott, E., Powell, D.: Land-vehicle navigation using GPS. Proc. I.E.E.E 87(1), 145–162 (1999)
Angeline, P. J.: Genetic programming and emergent intelligence. In: Kinnear Jr., K. E. (ed.) Advances in Genetic Programming, pp. 75–98. MIT, Cambridge, MA (1994)
Arcara, P., Melchiorri, C.: Control schemes for teleoperation with time delay: a comparative study. Robot. Auton. Syst. 38(1), 49–64 (2002)
Bentley, B.: Speed Secrets: Professional Race Driving Techniques. Motorbooks International, Osceola, WI (1998)
Chaperot, B., Fyfe, C.: Improving Artificial Intelligence in a Motocross Game. IEEE Symposium on Computational Intelligence and Games, pp.1435–1500. CIG’06, May (2006)
Frere, P.: Sports Cars and Competition Driving. Bentley, Sudbury, MA (1992)
Funge, J.D.: Artificial Intelligence for Computer Games. AK Peters, Wellesley, MA (2004)
Goldberg, D.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison–Wesley, Reading, MA (1989)
IBM Corporation. Deep Blue. http://www.research.ibm.com/deepblue/ (1997)
Jacobi, N.: Minimal simulations for evolutionary robotics. Ph.D. thesis, School of Cognitive and Computing Sciences, Sussex University (1998)
Kalman, R.E.: A new approach to linear filtering and prediction problems. J Basic Eng 82, 35–45 (1960)
Lane, J.C., Carignan, C., Akin, D.: Time delay and communication bandwidth limitation on telerobotic control. In: Proc. SPIE Mobile Robots XV and Telemanipulator and Telepresence Technologies VII, 405–419 (2001)
Meeden, L., Kumar, D.: Trends in evolutionary robotics. In: Jain, L.C., Fukuda, T. (eds.) Soft Computing for Intelligent Robotic Systems, pp. 215–233. Physica, New York, NY (1998)
Miller, B.L., Goldberg, D.E.: Genetic algorithms, tournament selection, and the effects of noise. Complex Syst. 9(3), 193–212 (1995)
Montana, D.: Strongly typed genetic programming. Evol. Comput. 3(2), 199–230 (1995)
Niemeyer, G., Slotine, J.-J.E.: Telemanipulation with time delays. Int. J. Rob. Res. 23, 873–890 (2004). (9)
Robocup (2005) http://www.robocup.org/02.html
Rosen, R.: Anticipatory Systems. Pergamon, New York (1985)
Togelius J., Lucas S.M.: Evolving Controllers for Simulated Car Racing. In: Proceedings of IEEE Congress on Evolutionary Computations (CEC-2005). 1906–1913, Edinburgh, UK, September 2–5 (2005)
Tanev, I., Joachimczak, M., Hemmi H., Shimohara, K.: Evolution of the Driving Styles of Anticipatory Agent Remotely Operating a Scaled Model of Racing Car. In: Proceedings of the 2005 IEEE Congress on Evolutionary Computation (CEC-2005), 1891–1898, Edinburgh, UK, September 2–5 (2005)
Tanev, I., Shimohara, K.: On human competitiveness of the evolved agent operating a scale model of a car. In: IEEE Congress on Evolutionary Computation (CEC-2007), pp. 3646–3653, Singapore, September 25–28 (2007)
Wloch, K., Bentley, P.: Optimizing the performance of a formula one car using a genetic algorithm. In: Proceedings of the 8th International Conference on Parallel Problem Solving from Nature, pp. 702–711. Birmingham, UK, September 18–22 (2004)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tanev, I., Shimohara, K. Evolution of Agent, Remotely Operating a Scale Model of a Car Through a Latent Video Feedback. J Intell Robot Syst 52, 263–283 (2008). https://doi.org/10.1007/s10846-008-9212-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-008-9212-y