Vehicle Map Reliability Assessment for Autonomous Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in maintaining accurate map information due to errors in spatial data collection, which affects their location estimation and driving stability, necessitating a technology to determine map reliability and control vehicle operations accordingly.
Innovation Solution
A device and method that assess map reliability using covariance values of six degrees of freedom and other factors, adjusting driving modes, speeds, and updating map information to ensure accurate navigation and safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If map information is collected and stored for autonomous driving, then navigation capability is improved, but errors in spatial data accumulate reducing location estimation accuracy
Solution Approach 1:
The system performs preliminary actions by collecting spatial data from multiple vehicles and pre-processing it to generate map information before autonomous driving operations begin. This includes accumulating spatial data, generating initial map information, and determining reliability values in advance, so that when vehicles need navigation, accurate and pre-validated map data is already available.
Solution Approach 2:
The system implements feedback mechanisms by continuously comparing actual vehicle positions and spatial observations against the stored map information. When discrepancies are detected, the system uses this feedback to update and correct the map data, thereby improving location estimation accuracy while maintaining navigation capability.
2Measurement precision
If map data is frequently updated to maintain accuracy, then location estimation accuracy is improved, but system complexity and computational load increase
Solution Approach 1:
The system applies local quality by updating map information selectively based on spatial and temporal characteristics. Instead of uniformly updating all map data, it focuses updates on specific regions where discrepancies are detected or where reliability values indicate improvement is needed, thereby reducing overall system complexity while maintaining accuracy where it matters most.
Solution Approach 2:
The system changes parameters by using reliability values as a threshold criterion for updates. Map information is updated only when reliability values exceed certain thresholds or when specific conditions are met, rather than continuously updating all data. This parameter-based approach balances accuracy maintenance with computational efficiency.
3Area of stationary object
If autonomous vehicles operate in areas with low map reliability, then coverage area is improved, but driving stability and safety deteriorate
Solution Approach 1:
The system applies dynamics by making autonomous driving operations adaptive to map reliability conditions. Vehicles dynamically adjust their operating modes based on real-time reliability values - operating autonomously in high-reliability areas and switching to manual or assisted modes in low-reliability areas. This dynamic adaptation allows expanded coverage while maintaining safety through context-aware operational adjustments.
Data Source
Figure 1~3(d)
Figure 4
Figure 5~6
AI summary
Provided are a method and a device for assisting with driving of a vehicle, the method including sensing an ambient environment of location of a vehicle by using one or more sensors mounted on or in the vehicle; obtaining sensing information about the ambient environment based on the sensing of the ambient environment; comparing map information stored in the vehicle with the obtained sensing information; determining a map reliability of the map information based on a result of the comparing; and controlling the driving of the vehicle based on the determined map reliability.