Vehicle Map Updating Using Reliability-Weighted Data Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional map generation apparatuses face accuracy issues when updating existing maps with new data, as errors in difference data can significantly decrease the accuracy of basic map data, affecting vehicle movement and safety.
Innovation Solution
A map generation apparatus that includes an in-vehicle detector, a microprocessor, and memory to recognize external environments, generate maps with position information, calculate reliability for each position, and update existing maps based on the reliability of new and existing data, prioritizing data with higher reliability during fusion processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing basic map data is updated using newly collected probe data, then map data can be improved and kept current, but accuracy decreases when difference data contains many errors
Solution Approach 1:
The system implements feedback by calculating reliability values for map data and using these reliability values to control the update process. When reliability is low, the system adjusts the update strategy to prevent error propagation, thereby maintaining basic map data precision while still allowing updates when reliable
Solution Approach 2:
The system changes the parameter of reliability calculation and uses it as a control variable in the update process. By adjusting the reliability threshold and update weight based on calculated reliability values, the system dynamically controls how much new data influences the basic map, preventing accuracy degradation from erroneous data
2Productivity
If difference data is averaged to update existing map data, then map updates can be performed efficiently, but accuracy decreases under the great influence of erroneous difference data
Solution Approach 1:
The system introduces feedback through reliability calculation that monitors the quality of difference data before averaging. This feedback mechanism allows the system to adjust the updating process dynamically, maintaining efficiency through automated processing while preventing precision loss by reducing the influence of low-reliability difference data
Solution Approach 2:
The system changes the updating parameter by incorporating reliability-weighted averaging instead of simple averaging. The update formula adjusts the weight of new map data based on its reliability value, allowing efficient automated updates while maintaining precision by giving less weight to potentially erroneous data
Data Source
AI summary
A map generation apparatus includes an in-vehicle detector and a microprocessor. The microprocessor is configured to perform: recognizing an exterior environment situation around a subject vehicle by using a detection data of the in-vehicle detector, generating a map including position information of a predetermined feature based on recognition information acquired in the recognizing; calculating a reliability of the generated map, for each piece of position information; storing the map and reliability information indicating the reliability as map information; and updating, when at least a part of a new map newly generated in the generating is included in the existing map, data of a corresponding section of the existing map corresponding to a generation section of the new map based on data and the reliability of the new map in the generation section and data and the reliability of the existing map in the corresponding section.