An Evolved, Vision-Based Behavioral Model of Coordinated Group Motion

by Craig Reynolds

Coordinated motion in a group of simulated critters can evolve under selection pressure from an appropriate fitness criteria. Evolution is modeled with the Genetic Programming paradigm. The simulated environment consists of a group of critters, some static obstacles, and a predator. In order to survive, the critters must avoid collisions (with obstacles as well as with each other) and must avoid predation. They must steer a safe path through the dynamic environment using only information received through their visual sensors. The arrangement of visual sensors, as well as the mapping from sensor data to motor action is determined by the evolved controller program. The motor model assumes an innate constant forward velocity and limited steering. The predator preferentially targets isolated "stragglers" and so encourages aggregation. Fitness is based on the sum of all critter lifetimes.

autonomous characters, steering behaviors, flocks, herds, evolution, genetic programming.

Reynolds, C. W. (1993) An Evolved, Vision-Based Behavioral Model of Coordinated Group Motion, in From Animals to Animats 2: Proceedings of the Second International Conference on Simulation of Adaptive Behavior (SAB92), Meyer, Roitblat and Wilson editors, ISBN 0-262-63149-0, MIT Press, Cambridge, Massachusetts, pages 384-392.

Online resources:
Full article (PDF, 0.2 MB)

Subsequent work related to "evolution of flocking": Evolutionary Dynamics Discovered via Visualization in the BREVE Simulation Environment (2002) by Lee Spector, and (Not) Evolving Collective Behaviours in Synthetic Fish (1996) by Nahum Zaera, Dave Cliff and Janet Bruten. Note that my SAB92 paper was also in the "(Not)..." category.

Send comments to Craig Reynolds <>
Last update: November 26, 2002