Scatterer Recognition for Multi-Modal Intelligent Vehicular Channel Modeling via Synesthesia of Machines

TL;DR

This paper introduces a multi-modal vehicular channel model using LiDAR data and machine learning to recognize scatterers, enhancing the realism and accuracy of intelligent transportation system simulations.

Contribution

It presents a novel approach combining LiDAR point clouds and machine learning for scatterer recognition in vehicular channels, supported by a new dataset and high accuracy results.

Findings

Scatterer recognition accuracy exceeds 90% using the proposed method.

The model closely matches ray-tracing simulation results.

A new dataset for vehicular sensing-communication integration is constructed.

Abstract

In this paper, a novel multi-modal intelligent vehicular channel model is proposed by scatterer recognition from light detection and ranging (LiDAR) point clouds via Synesthesia of Machines (SoM). The proposed model can support the design of intelligent transportation systems (ITSs). To provide a robust data foundation, a new intelligent sensing-communication integration dataset in vehicular urban scenarios is constructed. Based on the constructed dataset, the complex SoM mechanism, i.e., mapping relationship between scatterers in electromagnetic space and LiDAR point clouds in physical environment, is explored via multilayer perceptron (MLP) in consideration of electromagnetic propagation mechanism. By using LiDAR point clouds to implement scatterer recognition, channel non-stationarity and consistency are captured closely coupled with the environment. Using ray-tracing (RT)-based results as the ground truth, the scatterer recognition accuracy exceeds 90%. The accuracy of the proposed model is further verified by the close fit between simulation results and RT results.