Maximizing UAV Cellular Connectivity with Reinforcement Learning for BVLoS Path Planning

2025-09-11

AI Summary

This work addresses the joint optimization of cellular connectivity quality and flight distance for beyond-visual-line-of-sight (BVLoS) unmanned aerial vehicle (UAV) operations. We propose a reinforcement learning–based path planning method that explicitly incorporates empirically derived aerial channel models and base station connectivity assessments into the reward function—departing from conventional geometric planning by dynamically modeling airspace coverage constraints and time-varying link quality. The agent autonomously learns optimal three-dimensional trajectories that simultaneously ensure communication reliability and minimize path length. Simulation results demonstrate that the method improves link reliability significantly (average reference signal received power increases by ≥8 dB) while reducing path length by up to 12.6%, with 100% of generated trajectories satisfying the prescribed connectivity threshold. The framework is designed as an offline planning module compatible with existing UAV ground control systems, enabling safe, long-range, and highly reliable BVLoS missions.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: Motion and Path Planning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper presents a reinforcement learning (RL) based approach for path planning of cellular connected unmanned aerial vehicles (UAVs) operating beyond visual line of sight (BVLoS). The objective is to minimize travel distance while maximizing the quality of cellular link connectivity by considering real world aerial coverage constraints and employing an empirical aerial channel model. The proposed solution employs RL techniques to train an agent, using the quality of communication links between the UAV and base stations (BSs) as the reward function. Simulation results demonstrate the effectiveness of the proposed method in training the agent and generating feasible UAV path plans. The proposed approach addresses the challenges due to limitations in UAV cellular communications, highlighting the need for investigations and considerations in this area. The RL algorithm efficiently identifies optimal paths, ensuring maximum connectivity with ground BSs to ensure safe and reliable BVLoS flight operation. Moreover, the solution can be deployed as an offline path planning module that can be integrated into future ground control systems (GCS) for UAV operations, enhancing their capabilities and safety. The method holds potential for complex long range UAV applications, advancing the technology in the field of cellular connected UAV path planning.

Problem

• Optimizing UAV path planning for cellular connectivity
• Minimizing travel distance while maximizing link quality
• Ensuring reliable BVLoS operations with reinforcement learning

Innovation

• Reinforcement learning for UAV path planning
• Maximizing cellular connectivity with BS links
• Offline module integration into ground control systems