Evolution of driving agent, remotely operating a scale model of a car with obstacle avoidance capabilities

ABSTRACT

We present an approach for evolutionary design of an agent, remotely operating a scale model of a car running in a fastest possible way. The agent perceives the environment from a video camera and conveys its actions to the car via standard radio control transmitter. In order to cope with the video feed latency we propose an anticipatory modeling in which the agent considers its current actions based on the anticipated intrinsic (rather than currently available, outdated) state of the car and its surrounding. The agent is first evolved on software models of the car and tracks, and then adapted to the real world. During the adaptation, the lap times improve steadily to the values close to the values obtained from the evolution on the models. An evolutionary optimization of the avoidance of a small obstacle results in lap times that are virtually the same as the best lap times achieved on the same track without obstacles. Presented work can be viewed as a step towards developing a racing game in which the human competes against a computer, both operating scale models of racing cars.

REFERENCES

• 1: Abbott, E. and Powell D. (1999) "Land-vehicle Navigation Using GPS", The Proceedings of the IEEE January 1999, vol 87, no 1, pp 145--162
• 2: John David Funge, Artificial Intelligence For Computer Games: An Introduction, A. K. Peters, Ltd., Natick, MA, 2004
• 3: David E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1989
• 4: IBM Corporation (1997), "Deep Blue", URL: http://www.research.ibm.com/deepblue/
• 5: Jacobi, N. (1998) "Minimal Simulations for Evolutionary Robotics", Ph.D. thesis, School of Cognitive and Computing Sciences, Sussex University
• 6: Kalman, R. E. (1960) "A New Approach to Linear Filtering and Prediction Problems", Transactions of the ASME-Journal of Basic Engineering, Vol.82, Number Series D, pp. 35--45
• 7: Lane, J. C., Carignan, C. and Akin, D (2001) "Time Delay and Communication Bandwidth Limitation on Telerobotic Control", Proc. SPIE Mobile Robots XV and Telemanipulator and Telepresence Technologies VII, SPIE, pp.405--419
• 8: Meeden, L. and Kumar, D. (1998) "Trends in Evolutionary Robotics", Soft Computing for Intelligent Robotic Systems, edited by L.C. Jain and T. Fukuda, Physica-Verlag, New York, NY, 1998, pp.215--233
• 9: Miller, B. L., & Goldberg, D. E. (1995). Genetic algorithms, tournament selection, and the effects of noise. Complex System, 9(3), 193--212.
• 10: Montana, D. (1995) "Strongly Typed Genetic Programming", Evolutionary Computation, Vol.3, No.2, pp.199--230
• 11: Robocup (2005) URL: http://www.robocup.org/02.html
• 12: Rosen, R. (1985) "Anticipatory Systems", Pergamon Press
• 13: Togelius J., and Lucas S. M. (2005) "Evolving Controllers for Simulated Car Racing". Proceedings of IEEE Congress on Evolutionary Computations (CEC-2005), Edinburgh, UK, September 2-5, 2005, pp.1906--1913
• 14: Tanev, I., Joachimczak, M., Hemmi H. and Shimohara, K. (2005) "Evolution of the Driving Styles of Anticipatory Agent Remotely Operating a Scaled Model of Racing Car", Proceedings of the 2005 IEEE Congress on Evolutionary Computation (CEC-2005), Edinburgh, UK, September 2-5, 2005, pp.1891--1898
• 15: Wloch, K. and Bentley, P. (2004) "Optimizing the Performance of a Formula One Car Using a Genetic Algorithm", Proceedings of the 8th International Conference on Parallel Problem Solving from Nature, Birmingham, UK, September 18-22, pp.702--711

INDEX TERMS

Primary Classification:
  G. Mathematics of Computing
  G.1 NUMERICAL ANALYSIS
      G.1.6 Optimization
          Subjects: Global optimization

Additional Classification:
  J. Computer Applications
  J.2 PHYSICAL SCIENCES AND ENGINEERING
      Subjects: Physics

General Terms:
Algorithms, Design

Keywords:
anticipatory modeling, driving agent, feedback latency, genetic algorithms