Multiagent $Q$-Learning With Particle Filtering for UAV Tracking in Open-RAN Environment

This paper introduces a method for target tracking that leverages mobile sensor nodes and Unmanned Aerial Vehicles (UAVs) within an Open- Radio Access Network (RAN) framework. Open-RAN is a flexible and standardized architecture that allows open and interoperable components in RANs, promoting efficiency and adaptability. The core methodology involves improving the accuracy and energy consumption tracking in urban areas filled with obstacles and dynamic conditions. Mobile sensor nodes use a particle filtering algorithm to detect and estimate target positions, and this information is relayed to nearby Evolved/Next Generation Node Bs (e/gNBs), which function as the radio access network infrastructure. The e/gNBs manage clusters of UAVs using a specialized xApp integrated into the near-real-time RAN Intelligent Controller (RIC). The UAVs utilize a comprehensive tracking strategy based on received signal strength (RSS), a trilateration algorithm, and an enhanced multi agent Q-learning algorithm (eMAQL). This approach enables UAVs to optimize their flight paths while balancing accuracy, power usage, and communication delays The experimental results show that the system achieves optimal performance with eight discrete actions for eMAQL, with UAVs consuming an average of 90 (watts) of power and maintaining a root mean square error (RMSE) of less than 0.5 (meters) for target position estimation. These results highlight the system's effectiveness in providing precise and energy-efficient tracking in complex urban environments.