A methodological approach for the analysis and design of Human–Swarm interactions based upon feedback loops

Abstract

A new era of humans interacting seamlessly with devices has began. Systems composed of humans and devices are being deployed over a wide range of domains such as smart grids, smart cities, industry 4.0, among others. In many cases, the algorithms proposed to achieve the intelligent decision-making are based on decentralized and collective behaviours including swarm intelligence. Although clear benefits can be attributed to these approaches, the analysis and design of such systems is a difficult task. Furthermore, enabling humans (e.g. operators) to guide and influence the swarms is still an open research question. In this paper we propose a methodological approach to enable swarms to be influenced by humans with minimal intervention or modification (if any) to the original underlying principles. This approach allows to translate high level goals, as conceptualized by human operators, into influencing factors to the swarm algorithms; and thus allowing humans to guide and interpret the resolution process. To illustrate and evaluate this proposal, we apply the methodology to a swarm of drones using Particle Swarm Optimization (PSO) algorithm for search and rescue operations. Experimentations show that, by using the resulting system, humans are able to influence the PSO algorithm overall results using high level abstractions. Even more, the PSO algorithm mechanics are not modified and influences are derived solely by following the proposed steps. Finally, we discuss the limitations of the approach and application to other swarm intelligence algorithms.