Drivable Area Detection and Vehicle Localization Based on Multi-Sensor Information

Multi-sensor information fusion framework is the eyes for unmanned driving and Advanced Driver Assistance System (ADAS) to perceive the surrounding environment. In addition to the perception of the surrounding environment, real-time vehicle localization is also the key and difficult point of unmanned driving technology. The disappearance of high-precision GPS signal suddenly and defect of the lane line will bring much more difficult and dangerous for vehicle localization when the vehicle is on unmanned driving. In this paper, a road boundary feature extraction algorithm is proposed based on multi-sensor information fusion of automotive radar and vision to realize the auxiliary localization of vehicles. Firstly, we designed a 79GHz (78-81GHz) Ultra-Wide Band (UWB) millimeter-wave radar, which can obtain the point cloud information of road boundary features such as guardrail or green belt and so on. Secondly, the boundary feature of the drivable area will be extracted based on image semantic segmentation. Then, the boundary feature point cloud is extracted to realize clustering and filtering based on the improved k-means algorithm and data fusion of millimeter wave radar and image. Finally, the least square method is used to reconstruct the road boundary equation in vehicle coordinates system. The Kalman filter is used to track the vehicle position and yaw angle relative to the road boundary for localization. The vehicle platform was built up and the experiments were carried out in the urban road. Experimental results have substantiated the effectiveness as well as the robustness of the proposed method. In conclusion, the method proposed in this paper has good robustness, economy, and application value.