Skeleton-Based Swarm Routing (SSR): Intelligent Smooth Routing for Dynamic UAV Networks

Abstract

A swarm of unmanned aerial vehicles (UAVs) requires the transmission of mission-related data across the network. The resource constraints and dynamic nature of the swarm bring critical challenges to the design of UAV routing protocols. Most of the conventional ad hoc routing schemes are not intelligent and cannot adapt to the dynamic nature of UAV swarming networks. On the other hand, some artificial intelligence (AI)-based routing schemes may consume significant computational resources in the UAVs. In this article, a low-cost, adaptive routing protocol, namely skeleton-based swarm routing (SSR), is proposed, which exploits an intelligent online learning algorithm and the topology features of the mission-driven UAV swarm to distribute the traffic over optimal routes. Here, the skeleton represents the most stable parts of the swarm formation. SSR architecture consists of three modules: 1) A geometric addressing module, which assigns geometric coordinates to each node based on the swarm skeleton structure; 2) A leaf-like routing pipe which allows the selection of multiple candidate routes around the shortest path; 3) An intelligent low-complexity learning model which determines how to distribute the packets inside the routing pipe to achieve load-balanced, high-throughput transmissions. The proposed skeleton-based scheme can also facilitate the UAV formation construction and morphing. The simulation results show that the proposed SSR protocol can noticeably improve the network performance (up to 100% throughput improvement) compared to the single path routing schemes, such as the ad-hoc on-demand distance vector (AODV) and link-quality and traffic-load aware optimized link state routing (LTA-OLSR) protocols.

Keywords

• Geometric routing
• quality of service
• reinforcement learning
• stochastic dynamic programming
• swarm networks
• UAV communication