Crowdsourcing-based auxiliary driving map real-time matching and updating method

Abstract

A crowdsourcing map data acquisition, data processing and updating method comprises the steps of construction of a crowdsourcing data reliability evaluation model, evaluation and verification of the model, fusion and adoption of data meeting the reliability requirement, and updating of the fusion result into the map, so that the map data updating speed is higher, and the cost is lower. According to real-time matching of the high-precision map for assisting driving, track and event data reported by an automobile are matched to the high-precision map in real time, a method for real-time map matching of the data reported by the automobile is provided, and distributed map matching in a commercial environment is achieved; the credibility evaluation of crowdsourcing data enables the result of system evaluation to be closer to an objective actual environment, and meanwhile, cross validation is carried out by utilizing deep learning and a mathematical statistical model, so that the reliability of credibility evaluation is ensured; and the crowdsourcing map is fused and updated in real time to update the data of which the reliability meets the requirement into the map, and finally a high-precision map meeting the auxiliary driving production requirement is obtained.

Description

technical field [0001] The present application relates to a method for real-time matching and updating of an assisted driving map, in particular to a method for real-time matching and updating of an assisted driving map based on crowdsourcing, which belongs to the technical field of map matching and updating. Background technique [0002] Intelligent driving and assisted driving will become the trend of the future and are receiving unprecedented attention. The intelligent driving system is composed of map, perception layer, decision-making layer and control layer. Each layer of the intelligent driving system is a complex system engineering. As a necessary module of intelligent driving technology, the importance of map is getting more and more attention. However, the update of maps has been a slow process for a long time, which cannot meet the real-time map requirements for intelligent driving. At present, there is an urgent need to solve the key technology of automatic upda...

AI Technical Summary

Problems solved by technology

The data acquired by the sensor can restore the real environment very well, but the sensor has limitations, which cannot be solved for a while

[0010] First, the update of maps in existing technologies has been a slow process for a long time, which cannot meet the real-time requirements of intelligent driving for maps. At present, it is urgent to solve the key technology of automatic update of assisted driving maps to improve the cycle and reliability of map updates. When assisted driving vehicles use maps for assisted positioning, environmental perception, and decision-making, the map is required to have three high points: high precision, high accuracy, and high current situation. However, the existing assisted driving maps obviously cannot meet these three requirements. Traditional It is very difficult to ensure the real-time performance of the map in the current map production process. Since the real-time performance cannot be guaranteed, the data changed during the map production will affect the correctness. The accuracy, accuracy and current situation of the map matching update in the existing technology cannot meet the needs of intelligent driving. need;

[0011] Second, the crowdsourced data map of the existing technology is subject to the bottleneck brought by its own model. The accuracy, safety and cost cannot meet the application requirements of intelligent driving. The map tasks and results provided by non-professionals are difficult to make People are convinced, especially many crowdsourcing map tasks cannot be quantified, and cost is another bottleneck of crowdsourcing maps. The data collection, data processing and update methods of the existing crowdsourcing map update methods are not mature enough, and there is a lack of crowdsourcing. The data reliability evaluation model and the evaluation and verification of the model cannot effectively update the qualified crowdsourcing data fusion results into the map. The update speed of map data is slow and the cost is high. The bottleneck of crowdsourcing seriously restricts the crowdsourcing model map. Applications;

[0012] Third, the map matching update of the prior art lacks a method that can match events and car trajectories with maps, and cannot match trajectories with high-precision maps in real time, and the accuracy of matching events with road networks is low

The map matching update of the existing technology lacks a method that can analyze the reliability of event data streams in real time, and cannot comprehensively use historical data, map data and third-party data for learning to improve the reliability analysis model parameters, and lacks the quality of crowdsourced map data. However, the data fitting, data accuracy and economic benefits of map data fusion cannot meet the needs of real-time matching and updating of assisted driving maps.

Images