Seminar: Human-Swarm Interaction and Swarm Intelligence in Search and Rescue
M.Sc. Thesis Proposal
Supervisor: Dr. Andrew Vardy
"Human-Swarm Interaction and Swarm Intelligence in Search and Rescue"
Department of Computer Science
Thursday, January 28, 2016, 2:20 p.m., Room EN 2022
"A robot swarmemploys a large number ofrobots to facilitate sophisticated problem-solving as well as improved load-balancing and time efficiency compared to single robot systems. Swarm Intelligence is based on the local interactions between agents of the swarm that enables the emergence of a desired global behaviour, thus allowing the swarm to be autonomous. While
autonomy is much efficient for straightforward applications, in complex problems and environments human intervention proves much more efficient. Human control of a swarm remains an open problem with multiple approaches proposed to solve it, each ideal for a specific type of application.
This work proposes the combination of four well known Human-Swarm Interaction techniques to control the swarm on a high level, mainly choosing what global behaviour is to emerge. Swarm Intelligence is then used on a low level to carry out the chosen behaviour. To illustrate the functionality of this approach and its applicability to real-world problems, it is applied to the Search and Rescue problem, a type of Area Coverage problem. The solution needs to be fast and efficient, and able to handle any sudden changes in the environment."