Semantic Landmark-based HD Map Localization Using Sliding Window Max-Mixture Factor Graphs

Among many components in automated driving, localization is one fundamental task that provides the context for scene understanding and motion planning. This contribution focuses on localization in high-definition (HD) maps, which provide detailed information of the driving environment. An important problem in localization is the data association (DA) between measurements and landmarks in the HD map. While other approaches mainly use geometric measurement information as well as the most likely DA hypothesis, this contribution proposes a localization algorithm capable of handling DA ambiguities using semantic information in a sliding window factor graph. By incorporating a max-mixture scheme, the algorithm is able to recover from potentially false estimations. Furthermore, a realistic simulation employing the CARLA simulator is used to generate controlled scenarios and evaluate the performance of the proposed algorithm. The experiments suggest that the proposed approach is able to achieve accurate and robust pose estimations in the presence of measurement uncertainties.