Autonomous Driving Map Change Detection With Local-Global Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving technologies face challenges in detecting environmental changes, such as vehicle flow, pedestrian flow, and construction, which affect the precision of laser positioning maps, necessitating a method to automatically update these maps.
Innovation Solution
A method involving the comparison of a pre-built global map with real-time local maps to determine the probability of environmental changes, facilitating the update of the global positioning map by integrating local map data when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the positioning map is updated frequently to reflect real-time environmental changes, then the accuracy of laser positioning is improved, but the system complexity and computational resources increase
Solution Approach 1:
The patent segments the positioning map into multiple local maps, each covering a specific sub-area. By comparing local maps with the global map independently, the system can detect environmental changes more efficiently without processing the entire map, thus improving accuracy while reducing computational complexity.
Solution Approach 2:
The patent implements partial map updates by only updating portions of the positioning map where environmental changes are detected, rather than updating the entire map. This is achieved through probabilistic change detection that identifies specific sub-areas requiring updates, reducing unnecessary computational resources while maintaining positioning accuracy.
2Reliability
If the entire positioning map is updated to ensure accuracy, then the reliability of autonomous driving is improved, but the time and computational resources are wasted
Solution Approach 1:
The patent divides the positioning map into multiple local maps corresponding to different sub-areas. By performing change detection on individual local maps rather than the entire global map, the system reduces the time and computational resources required for updates while maintaining reliability in areas where changes are detected.
Solution Approach 2:
The system implements self-service through automatic environmental change detection and probabilistic assessment. The map updates are triggered automatically when changes are detected in specific sub-areas, eliminating the need for manual intervention or unnecessary full-map updates, thus saving time and resources while ensuring reliability when needed.
3Measurement precision
If local maps are compared with the global map to detect changes, then the detection precision of environmental changes is improved, but the computational load increases
Solution Approach 1:
The patent compares local maps with the corresponding global map for each sub-area independently, rather than performing a comprehensive comparison of the entire map. This segmented approach improves detection precision by focusing on specific areas of interest while reducing the overall computational load through localized processing.
Data Source
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.