A Deep Q-Learning Connectivity-Aware Pheromone Mobility Model for Autonomous UAV Networks

Low size, weight, and power (SWaP) fixed-wing UAVs are used in many applications, including search and rescue, surveillance, and tracking. To carry out these operations efficiently, there is a need to develop scalable, decentralized autonomous UAV network architectures with high network connectivity. However, the area coverage and the network connectivity requirements exhibit a fundamental trade-off. In this paper, we design a connectivity-aware pheromone mobility model using a deep Q-learning policy (CAP-DQN). We use stigmergy-based digital pheromone maps along with distance-based local connectivity information to autonomously coordinate the UAV movements in order to improve its map coverage efficiency while maintaining high network connectivity. The DQN policy helps in tuning and improving the coverage and connectivity trade-off. The proposed model facilitates efficient coverage and strong inter-UAV connectivity in autonomous UAV networks.