Semantic Road Map Positioning Using Characteristic Element Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for creating and updating semantic road maps for autonomous vehicles are inadequate for precise positioning and integration of environmental data, leading to outdated and incomplete map representations.
Innovation Solution
A method involving environmental sensor data processing to create a map representation, comparing characteristic elements with a semantic road map, and using descriptors and geometric alignment to accurately position the map representation within the semantic road map, incorporating features like roadway markings and traffic signs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If environmental sensor data is used to create map representations for autonomous vehicles, then the map detail and completeness are improved, but the positioning accuracy and integration with semantic road maps deteriorate
Solution Approach 1:
The patent segments the map representation into discrete characteristic elements (roadway markings, road signs, objects) that can be individually identified, described, and matched with corresponding elements in the semantic road map. This segmentation enables precise positioning by comparing specific features rather than treating the entire map as a single entity.
Solution Approach 2:
The patent introduces descriptors as an intermediary representation that bridges the map creation process and the positioning process. Descriptors capture key characteristics of characteristic elements and serve as the basis for matching between the created map representation and the semantic road map, thereby enabling accurate positioning.
2Reliability
If semantic road maps are continuously updated with environmental data, then the map relevance and accuracy are improved, but the processing time and computational complexity increase
Solution Approach 1:
The patent extracts only the essential characteristic elements (roadway markings, road signs, significant objects) from the environmental sensor data rather than processing all data. This extraction approach maintains map relevance by capturing key features while reducing processing time by focusing computational resources on important elements only.
Solution Approach 2:
The patent performs partial updating of the semantic road map by focusing on specific portions where characteristic elements are detected and matched, rather than continuously updating the entire map. This approach maintains map accuracy in relevant areas while minimizing overall processing time.
Data Source
AI summary
A method for positioning a map representation of an environment of a vehicle in a semantic road map. The method includes creating a map representation of an environment of the vehicle based on environmental sensor data; ascertaining characteristic elements in the map representation and in a semantic road map representing the environment; comparing the characteristic elements of the map representation to the characteristic elements of the semantic road map; ascertaining a portion of the semantic road map for which at least one characteristic element of the portion of the semantic road map matches at least one characteristic element of the map representation and for which the map representation and the semantic road map describe an identical region of the environment of the vehicle; and identifying a position of the portion within the semantic road map as the position of the map representation in the semantic road map.