Answers are grounded in this paper and cite their sources.
The updating of high-definition (HD) map is notably necessary to autonomous vehicle, ensuring the normal operation of the vehicle. This paper proposes an incremental fusing method for HD map updating, which can continuously improve the accuracy of the map during the running of vehicle. To describe the accuracy of map, the concept of position confidence and semantic confidence are presented. A framework of HD map updating is described, enhancing the frequency of updating and saving the cost. We analyze the map fusing model and propose a fusing algorithm based on Kalman filtering, which can increase the position and semantic confidence of map. Meanwhile, time damping term is contained in the fusing algorithm, which can make the map element approach the true value much faster when the real environment has been changed slightly. The experimental results show that the method proposed is effective.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2019) studied this question.
Synapse has enriched 7 closely related papers on similar clinical questions. Consider them for comparative context: