2020/12/10 by Benjamin Sliwa, Cedrik Schüler, Sliwa, Benjamin +5 · 1 citation
Computer Science · Engineering · #Distributed Control Multi-Agent Systems #FOS: Computer and information sciences #Networking and Internet Architecture (cs.NI) #UAV Applications and Optimization #Vehicular Ad Hoc Networks (VANETs)
paper · pdf · doi:10.48550/arxiv.2012.05490
openalex publication_date 2020/12/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Swarms of collaborating Unmanned Aerial Vehicles (UAVs) that utilize ad-hoc\nnetworking technologies for coordinating their actions offer the potential to\ncatalyze emerging research fields such as autonomous exploration of disaster\nareas, demanddriven network provisioning, and near field packet delivery in\nIntelligent Transportation Systems (ITSs). As these mobile robotic networks are\ncharacterized by high grades of relative mobility, existing routing protocols\noften fail to adopt their decision making to the implied network topology\ndynamics. For addressing these challenges, we present Predictive Ad-hoc Routing\nfueled by Reinforcement learning and Trajectory knowledge (PARRoT) as a novel\nmachine learning-enabled routing protocol which exploits mobility control\ninformation for integrating knowledge about the future motion of the mobile\nagents into the routing process. The performance of the proposed routing\napproach is evaluated using comprehensive network simulation. In comparison to\nestablished routing protocols, PARRoT achieves a massively higher robustness\nand a significantly lower end-to-end latency.\n