Evolving Complex Group Behaviors Using Genetic Programming with Fitness Switching
|
Abstract:
Genetic programming provides a useful tool for emergent computation and artificial life. However, conventional genetic programming is not efficient enough to solve realistic multiagent tasks consisting of several emergent behaviors that need to be coordinated in proper sequence. In this paper, we describe a novel method, called fitness switching, for evolving composite cooperative behaviors of multiple robotic agents using genetic programming. The method maintains a pool of basis fitness functions which are switched from simpler ones to more complex ones. The performance is demonstrated and compared in the context of a table transport problem. Experimental results show that the fitness switching method is an effective mechanism for evolving collective behaviors which may not be solved by simple genetic programming. 1
Citations
| 1782 | Genetic Programming: On the Programming of Computers by Means of Natural Selection Cambridge – Koza - 1992 |
| 65 | Collective Robotics: From Social Insects to Robots. Adaptive Behavior – Kube, Zhang - 1993 |
| 49 | Evolving teamwork and coordination with genetic programming – Luke, Spector - 1996 |
| 28 | Evolving a Team – Haynes, Sen, et al. - 1995 |
| 15 | Automatic creation of an efficient multi-agent architecture using genetic programming with architecture-altering operations – Bennett - 1996 |
| 6 | Multiple-agent learning for a robot navigation task by genetic programming – Iba - 1997 |
| 4 | Fitness switching: Evolving complex group behaviors using genetic programming – Zhang, Cho - 1998 |
| 1 | Evolution of herding behavior of multiple autonomous mobile robots – Zhang, Hong - 1998 |
