Automotive Radar Range Spectrum-Based Road Surface Classification by Using Machine Learning

The awareness of different road surface types is crucial for the safe operation of automated vehicles in on- and off-road modes. This paper focuses on the classification of different road surface types using automotive radar and Machine Learning (ML) Artificial Intelligence (AI) models. This analysis is based on the range spectrum of the backscattered radar signals from different road surfaces. The dataset for training and testing is formed by combining the range data from various road surface types. A Random Forest (RF) classifier is built for the identification and classification of four different road surface types. The proposed method is compared using range data obtained from two different mounting positions of the radar. Under dry conditions, a generalization error of 84.5% in the forward-looking position of the radar is achieved. The proposed classifier is also able to distinguish between wet and dry asphalt surfaces with a generalization error of 88.7%.