Evolution of corridor following behavior in a noisy world

Robust behavioral control programs for a simulated 2d vehicle can be constructed by artificial evolution. Corridor following serves here as an example of a behavior to be obtained through evolution. A controller’s fitness is judged by its ability to steer its vehicle along a collision free path through a simple corridor environment. The controller’s inputs are noisy range sensors and its output is a noisy steering mechanism. Evolution determines the quantity and placement of sensors. Noise in fitness tests discourages brittle strategies and leads to the evolution of robust, noise-tolerant controllers. Genetic Programming is used to model evolution, the controllers are represented as deterministic computer programs.

[1]  Craig W. Reynolds.  Flocks, herds, and schools: a distributed behavioral model , 1987, SIGGRAPH.

[2]  Inman Harvey,et al.  Evolving visually guided robots , 1993 .

[3]  W ReynoldsCraig.  Flocks, herds and schools: A distributed behavioral model , 1987 .

[4]  Jean-Arcady Meyer,et al.  The Computational Hoverfly; a Study in Computational Neuroethology , 1991 .

[5]  Craig W. Reynolds.  An Evolved, Vision-Based Model of Obstacle Avoidance Behavior , 1994 .

[6]  L. Altenberg.  The evolution of evolvability in genetic programming , 1994 .

[7]  Kenneth E. Kinnear,et al.  Generality and Difficulty in Genetic Programming: Evolving a Sort , 1993, ICGA.

[8]  Joe Marks,et al.  Spacetime constraints revisited , 1993, SIGGRAPH.

[9]  Piero Mussio,et al.  Toward a Practice of Autonomous Systems , 1994 .

[10]  Craig W. Reynolds.  Evolution of obstacle avoidance behavior: using noise to promote robust solutions , 1994 .

[11]  W. A. Tackett,et al.  The donut problem: scalability, generalization and breeding policies in genetic programming , 1994 .

[12]  R. Collins.  Studies in artificial evolution , 1992 .

[13]  Gilbert Syswerda,et al.  A Study of Reproduction in Generational and Steady State Genetic Algorithms , 1990, FOGA.

[14]  Gilbert Syswerda,et al.  Uniform Crossover in Genetic Algorithms , 1989, ICGA.

[15]  Simon Handley,et al.  The automatic generation of plans for a mobile robot via genetic programming with automatically defined functions , 1994 .

[16]  Inman Harvey,et al.  Issues in evolutionary robotics , 1993 .

[17]  Richard Dawkins,et al.  The Evolution of Evolvability , 1987, ALIFE.

[18]  Dave Cliff,et al.  Computational neuroethology: a provisional manifesto , 1991 .

[19]  Maja J. Matarić,et al.  Designing emergent behaviors: from local interactions to collective intelligence , 1993 .

[20]  René Zapata,et al.  Reactive behaviors of fast mobile robots in unstructured environments: sensor-based control and neural networks , 1993 .

[21]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[22]  P. Thompson,et al.  Reactive behaviors of fast mobile robots , 1994, J. Field Robotics.

[23]  Craig W. Reynolds.  The Difficulty of Roving Eyes. , 1994 .

[24]  Craig W. Reynolds.  An evolved, vision-based behavioral model of coordinated group motion , 1993 .

[25]  Inman Harvey,et al.  Explorations in Evolutionary Robotics , 1993, Adapt. Behav..

[26]  J. von Neumann,et al.  Probabilistic Logic and the Synthesis of Reliable Organisms from Unreliable Components , 1956 .