Hierarchical swarm intelligence system for multiple UAVs

Abstract

As a task assigned to an UAV becomes more complicated, the efficiency of operating these systems was encountered to the certain limitation using only a single UAV. On the other hand, managing the multiple UAVs system rises as an alternative way. To prevent from failing under the complicated missions, multiple UAVs system has been researched for risked missions such as the salvage works or the military operations owing to their high achievement ratio. In addition, this system is more resilient and adaptable to many kinds of missions than single UAV system, and it is also scalable and flexible to perform tasks and to achieve goals. Therefore, future systems of UAVs will be carried out by a large number of heterogeneous groups of both manned and unmanned sub-systems, which interact one another in systematic, hierarchical, and highly organic manners, so that a mission can be carried out with minimal collateral loss while maximizing the outcome. This thesis aims to develop the architecture and algorithms for the multi-UAV systems, an indispensible component of future network-centric warfare systems or civil operations such as rescues or transportations. This thesis also pursue such a goal by researching on the component technologies for efficient operation of multiple UAVs, namely mission planning and assignment, information fusion and inference, dynamic mission allocation, path planning, and collision avoidance. The research outcomes on these component technologies will be then integrated, implemented, and validated in a series of simulations. Moreover, the final goal of this thesis is to propose the hierarchical architecture of the swarm intelligence system. To achieve the objectives of this research, a hierarchical swarm intelligence system is presented. The overall system architecture is based on the objects. Four objects in this system will be presented: UAVs statuses, environments, missions and tasks, and communications and data sharing. In addition, each a...