Pedestrian Sensing and Positioning System Using 2D-LiDAR Based on Artificial Neural Networks Toward 6G

Author(s)

Neto, Egidio Raimundo ; Silva, Matheus Ferreira ; Sodre Jr, Arismar Cerqueira

• Document type: Journal article
• Source: IEEE ACCESS; v. 12, p. 21-pg., 2024-01-01.

Abstract

This work reports the implementation of a simple and accurate indoor sensing and positioning system using a two-dimensional (2D) Light Detecting and Ranging (LiDAR) to fulfill the vigorous requirements from the Beyond Fifth Generation of mobile networks (B5G), including the Sixth Generation of Mobile Networks (6G). Particularly, we present the development of an Artificial Neural Network (ANN)-based 2D-LiDAR system, renowned for its electromagnetic interference resilience and superior accuracy compared to radiofrequency signal methodologies. The proposed framework integrates 2D-LiDARs and Artificial Intelligence (AI) functionalities to enhance the performance of pedestrian sensing and positioning systems in indoor environments. The proposed system architecture incorporates an array of up to four LiDAR sensors, taking advantage of combined data as the input for the exploited ANN aiming to obtain precise user positions within the indoor environment. Those positional data are pivotal for B5G systems, enabling optimized control and management of antenna arrays and Reconfigurable Intelligent Surfaces (RIS), significantly improving the user experience. The main contributions include the development and implementation of the proposed system; the demonstration of this innovative system applicability for 6G, tested in a 16 m2 research laboratory space divided into up to 64 quadrants; and the experimental performance analysis under real indoor conditions, evaluated in terms of accuracy, precision, recall, and F1 score. Experimental results underscore and demonstrate the proposed system efficiency and applicability for accurately mapping pedestrian locations, achieving remarkable accuracy, precision, recall and F1 Score rates of up to 99%. (AU)

• FAPESP's process: 22/09319-9 - Center of Science for Development in Digital Agriculture - CCD-AD/SemeAr
• Grantee: Silvia Maria Fonseca Silveira Massruhá
• Support Opportunities: Research Grants - Science Centers for Development
• FAPESP's process: 21/06569-1 - High-speed strategic internet technologies
• Grantee: Evandro Conforti
• Support Opportunities: Research Projects - Thematic Grants