A Base Station Placement Method For High-precision Positioning Using Reinforcement Learning

Although location-based services (LBS) are available in various applications, achieving higher positioning performance is crucial, especially in an unmanned robot environment. Base station (BS) placement is a fundamental factor that significantly affects positioning performance. This study introduces a BS placement technique using a deep deterministic policy gradient (DDPG). We implemented symmetrical initial BS placement within the designated environment. In addition, we developed a value function based on the received signal strength indicator and dilution of precision for DDPG. Thus, our findings indicate an enhancement in positioning performance by approximately 12.5%.