A novel swarm-based optimisation algorithm inspired by artificial neural glial network for autonomous robots
The term swarm intelligence, which is denoted by [12] as: ‘the discipline that deals with natural and artificial systems composed of many individuals that coordinate using decentralised control and self-organization. In particular, the discipline focuses on the collective behaviours that result from...
| Main Authors: | , |
|---|---|
| Format: | Monograph |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/71690/ http://irep.iium.edu.my/71690/1/Final%20Report.pdf |
| Summary: | The term swarm intelligence, which is denoted by [12] as: ‘the discipline that deals with natural and artificial systems composed of many individuals that coordinate using decentralised control and self-organization. In particular, the discipline focuses on the collective behaviours that result from the local interactions of the individuals with each other and with their environment’. Several areas of engineering have adopted the idea that swarms can solve complex problems and some of them are described in [13]. Some of the examples highlighted by [13] are a combinatorial optimisation, routing communications network, as well as solving robotics applications. According to [13], the two best-known swarm intelligence algorithms are Particle Swarm Optimisation (PSO) and Ant Colony Optimisation (ACO). The ideas of PSO emerged from the swarming behaviours observed in flocks of birds, swarms of bees and school of fish.The individuals in PSO communicate either directly or indirectly with one another. As an algorithm, PSO can be applied to solve various function optimisation problems, as the main strength of the algorithm is its fast convergence [14]. The main idea in this algorithm is the indirect communication between the ants which is established by the means of pheromones in finding the shortest path between their nest and food [14]. This is also in accordance with the terms ‘stigmergy’ to describe the particular type of communication that is stimulated by the ants in the environment, which is observed in colonies of ants. Once the presence of the pheromone is perceived by the other ants in the environment, they tend to follow the paths where the pheromone concentration is higher. Through this mechanism, ants are able to transport food to their nest in a remarkably effective way [15]. Communication among robots depends on distinct factors such as environment, the number of robots, the task and other factors. Normally, robots talk to each other by a common language to coordinate their teamwork, to give feedback or to adjust for each other in case of unplanned situations. Therefore this research proposed a novel model for artificial neuro-glial networks and swarm-inspired algorithm for autonomous robots’ communication. Artificial neuro-glial networks is proposed to be combined in the swarm-based communication algorithm to provide a human-like model for the robot's communication and optimization. |
|---|