Age based controller stabilization in Evolutionary Robotics

Evolutionary Robotics is a collection of heuristics where robotic control systems are developed by following the example of natural evolution. An evolutionary run is performed by mutating the robots' controllers randomly and selecting for some desired behavioral properties. Overall, these properties should be improved over time leading to a stable increase of fitness. However, random mutations on critical controller parts can lead to a rapid degradation lowering the performance of evolution. This paper presents an approach to reduce the loss of desirable behavior during an evolution process. A notion of age is introduced as a quality criterion to indicate the contribution of parts of a controller to the robot's overall behavior. To preserve the behavior evolved so far, mutations are channeled to affect controller parts with a lower age more than those with a higher age. As a result, controller parts that contribute to a good behavior are stabilized and the evolved desirable behavior is maintained. Experiments have been performed in a decentralized online evolutionary scenario with controllers based on finite state machines (FSMs). The results show an improvement in the number of successful evolutions and the number of successfully evolved robots compared to previous studies.

[1]  Joanne H. Walker,et al.  Evolving Controllers for Real Robots: A Survey of the Literature , 2003, Adapt. Behav..

[2]  Vito Trianni,et al.  Evolutionary Swarm Robotics - Evolving Self-Organising Behaviours in Groups of Autonomous Robots , 2008, Studies in Computational Intelligence.

[3]  V. Braitenberg.  Vehicles, Experiments in Synthetic Psychology , 1984 .

[4]  Sanaz Mostaghim,et al.  Decentralized evolution of robotic behavior using finite state machines , 2009, Int. J. Intell. Comput. Cybern..

[5]  Yaochu Jin,et al.  A comprehensive survey of fitness approximation in evolutionary computation , 2005, Soft Comput..

[6]  Hartmut Schmeck,et al.  A Completely Evolvable Genotype-Phenotype Mapping for Evolutionary Robotics , 2009, 2009 Third IEEE International Conference on Self-Adaptive and Self-Organizing Systems.

[7]  Jeffrey L. Krichmar,et al.  Evolutionary robotics: The biology, intelligence, and technology of self-organizing machines , 2001, Complex..

[8]  Risto Miikkulainen,et al.  Efficient Reinforcement Learning Through Evolving Neural Network Topologies , 2002, GECCO.

[9]  Phil Husbands,et al.  Evolutionary robotics , 2014, Evolutionary Intelligence.

[10]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[11]  Matthew Quinn,et al.  Some Problems (and a Few Solutions) for Open-Ended Evolutionary Robotics , 1998, EvoRobots.

[12]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .