Swarm intelligence: from natural to artificial systems
Swarm intelligence: from natural to artificial systems
Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 3
ECAI '96 Selected papers from the Workshop on Distributed Artificial Intelligence Meets Machine Learning, Learning in Multi-Agent Environments
Collective and Cooperative Group Behaviors: Biologically Inspired Experiments in Robotics
The 4th International Symposium on Experimental Robotics IV
Emergent Specialization in Swarm Systems
IDEAL '02 Proceedings of the Third International Conference on Intelligent Data Engineering and Automated Learning
Division of labor in a group of robots inspired by ants' foraging behavior
ACM Transactions on Autonomous and Adaptive Systems (TAAS)
Auction-based multi-robot task allocation in COMSTAR
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Neuro-evolution for a gathering and collective construction task
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Heterogeneous particle swarm optimizers
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Specialization as an optimal strategy under varying external conditions
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Distributed task selection in multi-agent based swarms using heuristic strategies
SAB'06 Proceedings of the 2nd international conference on Swarm robotics
Task-driven species in evolutionary robotic teams
IWINAC'11 Proceedings of the 4th international conference on Interplay between natural and artificial computation - Volume Part I
Costs and benefits of behavioral specialization
TAROS'11 Proceedings of the 12th Annual conference on Towards autonomous robotic systems
Foraging swarm robots system adopting honey bee swarm for improving energy efficiency
Proceedings of the 6th International Conference on Ubiquitous Information Management and Communication
A survey of swarm robotics system
ICSI'12 Proceedings of the Third international conference on Advances in Swarm Intelligence - Volume Part I
Evolving team behaviors with specialization
Genetic Programming and Evolvable Machines
Costs and benefits of behavioral specialization
Robotics and Autonomous Systems
Hi-index | 0.00 |
This paper addresses qualitative and quantitative diversity and specialization issues in the framework of self-organizing, distributed, artificial systems. Both diversity and specialization are obtained via distributed learning from initially homogeneous swarms. While measuring diversity essentially quantifies differences among the individuals, assessing the degree of specialization implies correlation between the swarm's heterogeneity with its overall performance. Starting from the stick-pulling experiment in collective robotics, a task that requires the collaboration of two robots, we abstract and generalize in simulation the task constraints to k robots collaborating sequentially or in parallel. We investigate quantitatively the influence of task constraints and types of reinforcement signals on performance, diversity, and specialization in these collaborative experiments. Results show that, though diversity is not explicitly rewarded in our learning algorithm, even in scenarios without explicit communication among agents the swarm becomes specialized after learning. The degrees of both diversity and specialization are affected strongly by environmental conditions and task constraints. While the specialization measure reveals characteristics related to performance and learning in a clearer way than diversity does, the latter measure appears to be less sensitive to different noise conditions and learning parameters.