Research on Multi-source Information Fusion based on Extended Kalman Filter

Aiming at the problems of poor robustness and of single low accuracy sensor in obstacle detection, this paper proposes multi-source information fusion method based on extended Kalman filter for position data of radar and LiDAR. By means of coordinate transformation, the obstacle position data collected by the two radars are unified to the polar coordinate system, and the extended Kalman filter is constructed according to the state vector of the obstacle position data, and the specific parameters of the extended Kalman filter are selected to fuse the location information collected by the two sensors. The simulation results show that the algorithm can effectively fuse the location information collected by different sensors and improve the accuracy and stability of obstacle location information detection.