Outline for a Logical Theory of Adaptive Systems
Journal of the ACM (JACM)
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Adaptive task assignment for multiple mobile robots via swarm intelligence approach
Robotics and Autonomous Systems
| Hi-index | 0.00 |
One of the captivating characteristics of social insects, in spite of their rudimentary individual constitution, is the ability by which they have to solve complicated problems in an elastic and robust way. This includes elasticity which ensures the adaptation of the insect system to the unpredictable changes of their environment, and robustness which guarantees a functioning continuity of the system, in spite of the possible failure of a certain number of its elements in the achievement of their individual missions. From this point of view, fields of research have emerged over the past decades, with the aim of trying to reveal the secret behind the relationship between individual and society, so perfectly designed in nature. Collective robotics is one of those fields where we try to find microscopic rules allowing a group of autonomous robots, mobile and with limited capacity, to carry out a specific macro-task, such as exclusive positioned heap formation. The idea, behind this, is to use a model of oriented reactive agent simulation, to seek the relations which can link the local perceptions of the simulated robots with their basic actions, in order to make the above mentioned gathering task a success. An evolutionary approach is used for this purpose, making it possible to discover the functional control relations of these simulated robots. An analogy with the precepts specific to the ant community is established and results of simulation indicating the effectiveness of the detected rules are presented.