Adaptively Coordinating Heterogeneous Robot Teams through Asynchronous Situated Coevolution

Adapting to changing situations and objectives and selforganazing without a central controller in order to achieve an objective has become one of the main challenges in the design and operation of multirobot systems. The Asynchronous Situated Coevolution (ASiCO) algorithm has been successfully applied in surveillance tasks defined by just one global objective. In this paper we present the results obtained with ASiCO in more complex multirobot problems with several objectives that require a heterogeneous population of robot controllers that autonomously distribute the tasks. The paper focuses on the benefits of evolving an affinity coefficient that characterizes the individual genotypes.

[1]  Kagan Tumer,et al.  Efficient Evaluation Functions for Evolving Coordination , 2008, Evolutionary Computation.

[2]  Chaomin Luo,et al.  Real-time path planning with deadlock avoidance of multiple cleaning robots , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[3]  Wolfram Burgard,et al.  Coordinated multi-robot exploration , 2005, IEEE Transactions on Robotics.

[4]  Francesco Mondada,et al.  Evolutionary neurocontrollers for autonomous mobile robots , 1998, Neural Networks.

[5]  Israel A. Wagner,et al.  Cooperative Cleaners: A Study in Ant Robotics , 2008, Int. J. Robotics Res..

[6]  Dario Floreano,et al.  Genetic Team Composition and Level of Selection in the Evolution of Cooperation , 2009, IEEE Transactions on Evolutionary Computation.

[7]  Stefano Carpin,et al.  Multi-robot surveillance: An improved algorithm for the GRAPH-CLEAR problem , 2008, 2008 IEEE International Conference on Robotics and Automation.

[8]  Dave Cliff,et al.  Challenges in evolving controllers for physical robots , 1996, Robotics Auton. Syst..

[9]  José R. Álvarez,et al.  A Multi-robot Surveillance System Simulated in Gazebo , 2007, IWINAC.

[10]  Martijn C. Schut,et al.  Is situated evolution an alternative for classical evolution? , 2009, 2009 IEEE Congress on Evolutionary Computation.

[11]  Kurt Konolige,et al.  Distributed Multirobot Exploration and Mapping , 2005, Proceedings of the IEEE.

[12]  José R. Álvarez,et al.  Nature Inspired Problem-Solving Methods in Knowledge Engineering, Second International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2007, La Manga del Mar Menor, Spain, June 18-21, 2007, Proceedings, Part II , 2007, IWINAC.

[13]  Jordan B. Pollack,et al.  Embodied Evolution: Distributing an evolutionary algorithm in a population of robots , 2002, Robotics Auton. Syst..

[14]  Inman Harvey,et al.  Artificial evolution and real robots , 1997, Artificial Life and Robotics.