A Novel Vehicle Localization System Using Vision Module for Heading Feedback
- 5 Downloads
Traditional vehicle localization systems use GNSS signals for global localization or Lidar or vision based systems for Simultaneous Mapping and Localization (SLAM). However, the signals of GNSS might be contaminated or even blocked in areas where there are tall buildings or trees, especially for autonomous sweeper vehicles that usually work along the road. There are additional information that can be used to improve the accuracy and robustness of vehicle localization system when applied in autonomous sweeper vehicles. Thus, a novel vehicle localization system based on GNSS, vision, wheel speed and Inertial Measurement Unit (IMU) is proposed. When the vehicle works in areas where GNSS signals are good, accurate position information from GNSS is used. Besides, wheel speed and IMU information is fused to improve the output rate of position information. When the vehicle enters areas where GNSS signals are unavailable, the heading information from vision is used as measurement to estimate the heading angle of vehicle and then fused with wheel speed and IMU to estimate the position. Real vehicle experiments are conducted to validate the effectiveness of the proposed system.
KeywordsVehicle localization Lane map Wheel speed
This research is supported by “National Key R&D Program of China” (Grant No. 2018YFB0104805 and Grant No. 2016YFB0100901).
- 3.Rohde, J., Volz, B., Mielenz, H., et al.: Precise vehicle localization in dense urban environments. In: 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), 1–4 November 2016Google Scholar
- 5.Shamseldin, T., Manerikar, A., Elbahnasawy, M., et al.: SLAM-based Pseudo-GNSS/INS localization system for indoor LiDAR mobile mapping systems. In: 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), pp. 197–208. IEEE (2018)Google Scholar
- 10.Obst, M., Bauer, S., Reisdorf, P., et al.: Multipath detection with 3D digital maps for robust multi-constellation GNSS/INS vehicle localization in urban areas. In: 2012 IEEE Intelligent Vehicles Symposium, 3–7 June 2012Google Scholar
- 13.Li, T., Yang, M., Zhou, X., et al.: A robust terrain-based road vehicle localization algorithm. In: 2016 IEEE Intelligent Vehicles Symposium (IV), 19–22 June 2016Google Scholar