Key points are not available for this paper at this time.
In the urban environment or under complex traffic situation, conventional localization methods like GPS, dead reckoning or SLAM are not precise enough for autonomous driving. So high-precision localization for intelligent vehicles becomes a hot problem. Among all the high-precision localization methods, the category based on sensor maps outperforms others because of its accuracy and real-time property. In this paper, a detailed review and comparison of sensor-map based localization algorithms and the key techniques in it are presented. First we categorize the localization methods according to the sensors used and types of map. We summarize there are three key problems in localization: 1) model of maps: the form of map according to different environments; 2) high-precision map generation: methods of generating such a high-precision map; 3) localization: methods of estimating vehicle's position and pose from the detected environment information aligned with the maps generated in advance. In light of the above, in this paper, the state-of-the-art techniques of high-precision localization for intelligent vehicles are reviewed in detail, and the corresponding pro and con are discussed.
Li et al. (Wed,) studied this question.