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

In this letter, a novel multi-modal intelligent vehicular channel model is proposed by scatterer recognition via Synesthesia of Machines (SoM). A new intelligent sensing-communication integration vehicular dataset is constructed, where the mapping relationship between scatterers in electromagnetic space and LiDAR point clouds in physical environment is explored via multilayer perceptron (MLP). By using light detection and ranging (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%, and the accuracy of the proposed model is further verified.