Control of Distributed Micro Air Vehicles for Varying Topologies and Teams Sizes

  • Published : 2002.06.01

Abstract

This paper focuses on the study of simulation and evolution of Micro Air Vehicles. Micro Air Vehicles or MAVs are small flying robots that are used for surveillance, search and rescue, and other missions. The simulated robots are designed based on realistic characteristics and the brains (controllers) of the robots are generated using genetic algorithms, i .e., simulated evolution. The objective for the experiments is to investigate the effects of robot team size and topology (simulation environment) on the evolution of simulated robots. The testing of team sizes deals with finding an ideal number of robots to be deployed for a given mission. The goal of the topology experiments is to see if there is an ideal topology (environment) to evolve the robots in order to increase their utility in most environments. We compare the results of the various experiments by evaluating the fitness values of the robots i .e., performance measure. In addition, evolved robot teams are tested in different situation in order to determine if the results can be generalized, and statistical analysis is performed to evaluate the evolved results.

Keywords

References

  1. Proceedings of the IEEE International Conference on Robotics and Automation Robots playing to win: evolutionary soccer strategies A. Agah;K. Tanie
  2. Proceedings of the IEEE International Conference on Evolutionary Computation A genetic algorithm-based controller for decentralized multi-agent robotic systems A. Agah;G. A. Bekey
  3. Toward a Practice of Autonomus Systems The maximum entropy principle and sensing in swarm intelligence G. Beni;S. Hackwood
  4. Student's Test for Independent Samples D. R. Caprette
  5. Adaptive Behavior v.2 Explorations in evolutionary robotics D. Cliff;I. Harvey;P. Husbands https://doi.org/10.1177/105971239300200104
  6. M. S. Thesis, Department of Electrical Engineering and Computer Science, The University of Kansas Evolutionary Brains For Distributed Flying Robots D. J. Collins
  7. Proceedings of the IEEE International Conference on Robotics and Automation The Bugs "Basic UXO gathering system" Project for UXO Clearance and Mine Countermeasures C. Debolt;C. O'Donnell;C. Freed;T. Nguyen
  8. From Animals to Animats The dynamics of collective sorting robot-like ants and ant-like robots J. L. Deneubourg;S. Goss;N. Franks;A. Sendova-Franks;C. Detrain;L. Chretien;J. A. Meyer(ed.);S. W. Wilson(ed.)
  9. Toward a Practice of Autonomous Systems Swarmmade architectures J. L. Deneubourg;G. Theraulaz;R. Beckers
  10. Proceedings of the IEEE International Conference on Evolutionary Computing A survey of penalty techniques in genetic algorithms M. Gen;R. Cheng
  11. Genetic Algorithms in Search , Optimization and Learning D. Goldberg