This article explores the application of genetic algorithms to the learning of local robot navigation behaviors for reactive control systems. Our approach evolves reactive control systems in various environments, thus creating sets of "ecological niches" that can be used in similar environments. The use of genetic algorithms as an unsupervised learning method for a reactive control architecture greatly reduces the effort required to configure a navigation system. Unlike standard genetic algorithms, our method uses a floating point gene representation. The system is fully implemented and has been evaluated through extensive computer simulations of robot navigation through various types of environments.
Albus, J., McCain, H., & Lumia, R. (1987). NBS standard reference modelfor telerobot control system architecture (NASREM) (NBS Tech. Note 1235). Washington, DC: Robot Systems Division, National Bureau of Standards .
2.
Anderson, T., & Donath, M. (1991). Animal behavior as a paradigm for developing robot autonomy. In P. Maes (Ed.), Designing autonomous agents. Cambridge, MA: MIT Press.
3.
Arkin, R. (1989). Motor schema-based mobile robot navigation. International Journal of Robotics Research, 8(4), 92-112.
4.
Arkin, R., & Murphy, R. (1990). Autonomous navigation in a manufacturing environment . IEEE Transactions on Robotics and Automation, 6(4), 445-454.
5.
Arkin, R., Riseman, E., & Hanson, A. (1987). AuRA: An architecture for vision-based robot navigation . DARPA Image Understanding Workshop, Los Angeles: 417-431.
6.
Barto, A., Anderson, C., & Sutton, R. (1982). Synthesis of nonlinear control surfaces by a layered associative search network. Biological Cybernetics, 43, 175-185.
7.
Brooks, R. (1989a). The whole iguana. In M. Brady (Ed.), Robotics Science, 433-456. Cambridge, MA: MIT Press.
8.
Brooks, R. (1989b). A robot that walks: emergent behaviors from a carefully evolved network. IEEE International Conference on Robotics and Automation, 2, 692-696.
9.
Davis, L. (Ed.). (1991). Handbook of genetic algorithms. New York: Van Nostrand Reinhold.
10.
Dorigo, M., & Schnepf, U. (1991). Organization of robot behavior through genetic learning processes. Fifth International Conference on Advanced Robotics, 2, 1456-1460.
11.
Elfes, A. (1987). Sonar-based real-world mapping and navigation . IEEE Journal of Robotics and Automation, R-A-3(3), 249-265.
12.
Fikes, R., Hart, P., & Nilsson, N. (1972). Learning and executing generalized robot plans . Artificial Intelligence, 3, 251-288.
13.
Goldberg, D. (1989). Genetic algorithms in search, optimization, and machine learning. Reading, MA: Addison-Wesley.
14.
Gordon, D.E., & Subramanian, D. (1993). A multistrategy learning schema for assimilating advice in embedded agents. In Second International Workshop on Multistrategy Learning
15.
Grefenstette, J.J., Ramsey, C.L., & Schultz, A.C. (1990). Learning sequential decision rules using simulation models and competition. Machine Learning, 5(4), 355-381.
16.
Janikow, C., & Michalewicz, Z. (1991). An experimental comparison of binary and floating point representations in genetic algorithms. Fourth International Conference on Genetic Algorithms, 31-36.
17.
Kaelbling, L. (1986). An architecture for intelligent reactive systems (SRI Tech. Note). SRI International, 400 (October).
18.
Payton, D. (1986). An architecture for reflexive autonomous vehicle control. IEEE Conference on Robotics and Automation , 1838-1845.
19.
Payton, D., Keirsey, D., Krozel, J., & Rosenblatt, K. (1992). Do whatever works: A robust approach to fault-tolerant autonomous control. Applied Intelligence , 2(3), 225-250.
20.
Ram, A., Arkin, R.C., Moorman, K., & Clark, R.J. (1992). Case-based reactive navigation: A case-based method for on-line selection and adaptation of reactive control parameters in autonomous robotic systems (Tech. Rep. GIT-CC-92/57). Atlanta, GA : College of Computing, Georgia Institute of Technology .
21.
Ram, A., & Santamaria, J.C. (1993). Multistrategy learning in reactive control systems for autonomous robotic navigation. Informatica, 17(4), 347-369.
22.
Whitley, D. (1989). The Genitor algorithm and selection pressure: Why rank-based allocation of reproductive trials is best. In Third International Conference on Genetic Algorithms
