Intelligent Trajectory Planning in UAV-Mounted Wireless Networks: A Quantum-Inspired Reinforcement Learning Perspective

In this letter, we consider a wireless uplink transmission scenario in which an unmanned aerial vehicle (UAV) serves as base station collecting data from ground users. To optimize the expected sum transmit rate without any prior knowledge of users (e.g., locations, channel state information and power), trajectory planning problem is optimized via quantum-inspired reinforcement learning (QiRL) approach. Specifically, QiRL method adopts novel probabilistic action selection policy new strategy, are inspired by collapse phenomenon amplitude amplification quantum computation theory, respectively. Numerical results demonstrate that proposed solution can offer natural balancing between exploration exploitation ranking probabilities possible actions, compared to traditional approaches highly dependent on tuned parameters.