Indoor Ultrasonic Localization Using Artificial Rabbit Optimization Algorithm and BP Neural Network

Abstract

Although traditional BP neural networks have shown some improvement in ultrasonic indoor localization accuracy, it has a tendency to fall into the problem of local optimal solutions, which limits the localization accuracy. To address this issue, we propose the use of the artificial rabbit optimization (ARO) algorithm as an optimization strategy. The ARO algorithm dynamically adjusts and searches for weights and thresholds during the initialization and training of BP neural networks to find the global optimal solution. This approach efficiently explores the weight space and enhances the BP neural network's performance in ultrasonic localization tasks. Experiments have confirmed that the hybrid ARO-BP localization algorithm performs well in matching predicted trajectories with actual positions, especially in a 3D localization scenario constructed by six base stations. The algorithm produces excellent results in both line-of-sight (LOS) and non–line-of-sight (NLOS) environments, which are typical indoor settings. The ARO-BP neural network effectively reduces the average localization error and ensures high-precision localization under various transmission conditions and obstacle effects. In NLOS conditions, the positioning accuracy is improved by 16.05% with four tags and 10.92% with six tags, resulting in an average error reduction of 8.02 cm. The ARO-BP algorithm enhances positioning accuracy by 13.99% with four tags and 21.76% with six tags, resulting in an average error reduction of 12.01 cm. In conclusion, ARO-BP significantly improves the accuracy of ultrasonic localization in both LOS and NLOS indoor environments with reflections and diffractions. This advancement provides a new direction for the development of indoor positioning technology and is expected to lead to significant progress in practical applications within related fields.