Radar Sensor-Based Estimation of Vehicle Orientation for Autonomous Driving
Sohee Lim, Jaehoon Jung, Byeong-Ho Lee, Jeongsik Choi, Seong-Cheol Kim
Abstract
Automotive sensors are essential to autonomous driving, which performs various functions to perceive the surrounding environment. Among the various functions of the automotive sensors, the estimation of vehicle orientation is considered significant in responding to unpredictable situations in a dynamic driving environment. In this article, we propose a method of estimating the vehicle orientation using a cascaded multiple-input multiple-output (MIMO) frequency-modulated continuous-wave (FMCW) radar system. The radar signal is collected by varying the orientation angle of the vehicle, and the point cloud data corresponding to the vehicle are extracted through signal preprocessing. Because the processed point cloud data are distributed along the axis of vehicle orientation, the orientation angle can be estimated by applying regression algorithms. We used the principal component analysis (PCA), decision tree, and convolutional neural network (CNN) algorithms for regression and compared their performances. The comparison of various estimation methods showed that the proposed method of using the CNN framework can accurately estimate the orientation angle of a vehicle within a root mean square error (RMSE) of 4°.