Autonomous Driving Map Change Detection for Laser Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving technologies face challenges in detecting environmental changes that affect laser positioning, such as construction or seasonal changes, which require updates to the positioning map to maintain precision.
Innovation Solution
A method that compares a pre-built global map with real-time local maps in sub-areas to determine the probability of environmental changes, facilitating the update of the global map based on these probabilities, using point cloud data and probability models to identify changes in height and laser reflection information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a pre-built global map is used for positioning, then positioning map availability is maintained, but positioning accuracy deteriorates when environmental changes occur
Solution Approach 1:
The system performs preliminary comparison between local maps and global map before positioning operations. By pre-identifying environmental changes through map comparison and calculating change probabilities, the system prepares updated positioning information in advance, ensuring both map availability and positioning accuracy are maintained when environmental changes occur.
2Measurement precision
If real-time environmental monitoring is implemented, then positioning accuracy is improved, but system complexity increases
Solution Approach 1:
The system divides the monitoring area into multiple sub-areas and processes each sub-area independently. By segmenting the global map into grid cells and comparing local maps sub-area by sub-area, the system reduces computational complexity while maintaining positioning accuracy. This segmented approach allows parallel processing and reduces the burden on single processing units.
Solution Approach 2:
The system applies different processing strategies to different sub-areas based on their specific characteristics. By calculating environmental change probabilities locally for each sub-area and only updating regions where changes are detected, the system avoids unnecessary processing in stable areas, reducing overall system complexity while maintaining accuracy where needed.
3Measurement precision
If frequent map updates are performed, then positioning accuracy is improved, but processing time increases
Solution Approach 1:
The system changes the parameter of map update frequency from fixed/frequent to dynamic/conditional. By introducing environmental change probability as a decision parameter, the system updates the global map only when and where changes are detected, rather than performing frequent universal updates. This reduces processing time while maintaining positioning accuracy through targeted updates.
Data Source
Figure 1~2
Figure 3
Figure 4~5
AI summary
The present disclosure provides a method, an apparatus, a computing device and a computer readable storage medium for detecting an environmental change, and relates to the field of autonomous driving. The method obtains a global map for an area and a first local map built in real time for a sub-area in the area; and determines an environmental change in the first sub-area by comparing the first local map and the global map and determining a first probability of the environmental change. Techniques of the present disclosure can automatically detect environmental changes that affect the positioning of autonomous driving, thereby facilitating the updating of positioning maps.