Research on Unmodulated LED Indoor Visible Light Positioning System Based on OPTICS-AJAYA-UGRNN Hybrid Optimization Algorithm

In recent years, visible light-based indoor positioning technology has become a prominent research topic within the academic community. To address the issues of high localization errors in low-light and corner regions of indoor environments, this paper proposes a solution based on OPTICS clustering coupled with partitioned linear interpolation. The proposed approach first segments the indoor area into zones; within dark regions, the OPTICS clustering algorithm is employed to identify zones of dense optical power, followed by the correction of discrete point light intensity data to reduce localization errors in low-light areas. In corner regions, edge data points are used for linear interpolation to enhance the feature set and improve positioning accuracy. To enhance neural network training efficiency, a hybrid method combining an adaptive JAYA algorithm (AJAYA) with Update Gate Recurrent Neural Network (UGRNN) is introduced. This approach leverages AJAYA for efficient hyperparameter tuning of the UGRNN, thereby improving training speed and system robustness. To overcome the challenge of differentiating between unmodulated LED devices, RFID technology is integrated with the visible light positioning system by deploying Ultra-High Frequency (UHF) RFID tags to enable effective distinction of different LEDs. Simulation results demonstrate that, within a large space of 7 m × 4 m × 4.6 m, the system achieves an average localization error of 0.08 m. Experimental validation shows that the static positioning error averages 0.28 m, and dynamic positioning accuracy is improved by 35.14% after using IMU data to correct the light intensity measurements. Additionally, applying rectangular trajectory tracking yields a 30.2% improvement in positioning accuracy. These results verify the effectiveness and stability of the proposed method in complex indoor scenarios.