Evolving neural networks through augmenting topologies
Evolutionary Computation
Evolving mobile robots able to display collective behaviors
Artificial Life
Fitness functions in evolutionary robotics: A survey and analysis
Robotics and Autonomous Systems
Sustaining diversity using behavioral information distance
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Revising the evolutionary computation abstraction: minimal criteria novelty search
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Efficiently evolving programs through the search for novelty
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Abandoning objectives: Evolution through the search for novelty alone
Evolutionary Computation
EvoApplications'11 Proceedings of the 2011 international conference on Applications of evolutionary computation - Volume Part I
Swarm robotics: from sources of inspiration to domains of application
SAB'04 Proceedings of the 2004 international conference on Swarm Robotics
Simbad: an autonomous robot simulation package for education and research
SAB'06 Proceedings of the 9th international conference on From Animals to Animats: simulation of Adaptive Behavior
Encouraging behavioral diversity in evolutionary robotics: An empirical study
Evolutionary Computation
Self-Organized Coordinated Motion in Groups of Physically Connected Robots
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Introducing novelty search in evolutionary swarm robotics
ANTS'12 Proceedings of the 8th international conference on Swarm Intelligence
| Hi-index | 0.00 |
Novelty search has shown to be a promising approach for the evolution of controllers for swarms of robots. In existing studies, however, the experimenter had to craft a task-specific behaviour similarity measure. The reliance on hand-crafted similarity measures places an additional burden to the experimenter and introduces a bias in the evolutionary process. In this paper, we propose and compare two generic behaviour similarity measures: combined state count and sampled average state. The proposed measures are based on the values of sensors and effectors recorded for each individual robot of the swarm. The characterisation of the group-level behaviour is then obtained by combining the sensor-effector values from all the robots. We evaluate the proposed measures in an aggregation task and in a resource sharing task. We show that the generic measures match the performance of task-specific measures in terms of solution quality. Our results indicate that the proposed generic measures operate as effective behaviour similarity measures, and that it is possible to leverage the benefits of novelty search without having to craft task-specific similarity measures.