Autonomous Specialization in a Multi-Robot System using Evolving Neural Networks

Artificial evolution is one of the emerging approach in the design of controllers for autonomous mobile robots. In general, a robot controller, which is represented as an evolving artificial neural network (EANN), is evolved in a simulated or a physical environment such that it exhibits the behaviour required to perform a certain task. The field of research on autonomous robots with EANNs is called evolutionary robotics (ER) (Cliff, et al., 1993) (Harvey, et al., 2005). There has been a great deal of interest in EANNs. A good summary of EANNs carried out until 1999 can be found in a study of Yao (1999). Traditionally, EANNs have been classified into the following three categories on the basis of their network structure:

[1]  Inman Harvey,et al.  Evolutionary robotics: the Sussex approach , 1997, Robotics Auton. Syst..

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

[3]  Goran Trajkovski,et al.  Handbook of Research on Agent-Based Societies: Social and Cultural Interactions , 2009 .

[4]  Dario Floreano,et al.  Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs , 2003, EvoWorkshops.

[5]  Pattie Maes,et al.  Toward the Evolution of Dynamical Neural Networks for Minimally Cognitive Behavior , 1996 .

[6]  Diana Pérez-Marín,et al.  Conversational Agents and Natural Language Interaction : Techniques and Effective Practices , 2011 .

[7]  Josefina Santibáñez,et al.  Propositional Logic Syntax Acquisition Using Induction and Self-Organisation , 2009 .

[8]  M. L. Valarmathi,et al.  An Agent Based Approach to Patient Scheduling Using Experience Based Learning , 2010, Int. J. Agent Technol. Syst..

[9]  Hong Lin.  Architectural Design of Multi-Agent Systems: Technologies and Techniques , 2007 .

[10]  Inman Harvey,et al.  Evolutionary Robotics: A New Scientific Tool for Studying Cognition , 2005, Artificial Life.

[11]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[12]  Stefano Nolfi,et al.  Evolving Mobile Robots Able to Display Collective Behaviors , 2003, Artificial Life.

[13]  Thomas Bäck,et al.  Evolutionary algorithms in theory and practice - evolution strategies, evolutionary programming, genetic algorithms , 1996 .

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

[15]  Kazuhiro Ohkura,et al.  MBEANN: Mutation-Based Evolving Artificial Neural Networks , 2007, ECAL.

[16]  Francesco Mondada,et al.  Evolution of neural control structures: some experiments on mobile robots , 1995, Robotics Auton. Syst..

[17]  Risto Miikkulainen,et al.  Solving Non-Markovian Control Tasks with Neuro-Evolution , 1999, IJCAI.

[18]  Jason Noble,et al.  Modelling Animal Behaviour in Contests: Conventions for Resource Allocation , 2001, ECAL.

[19]  Hao Wang,et al.  Three Perspectives on Multi-Agent Reinforcement Learning , 2007 .

[20]  Stefano Nolfi,et al.  Social Facilitation on the Development of Foraging Behaviors in a Population of Autonomous Robots , 2007, ECAL.

[21]  Marco Dorigo,et al.  From Solitary to Collective Behaviours: Decision Making and Cooperation , 2007, ECAL.

[22]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.