Intersection Completer for Autonomous Vehicle Roadgraph Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The generation of highly detailed maps for autonomous vehicles, which include information about roadways, traffic signals, and intersections, requires significant human resources and time, making it inefficient and labor-intensive.
Innovation Solution
A method and device for generating a roadgraph that allows users to input and visualize aspects of an intersection, including roadways and traffic control features, to calculate boundaries and identify necessary traffic observations, thereby automating the process of creating maps for autonomous navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual map generation by comparing multiple information sources is used, then mapping accuracy is improved, but human resources and time consumption increase significantly
Solution Approach 1:
The patent segments the map generation process into distinct functional modules: data acquisition from multiple sources, feature extraction and identification, relationship analysis and connection establishment, and validation. This modular approach allows automated processing while maintaining accuracy by applying specialized algorithms to each segment of the workflow.
Solution Approach 2:
The patent replaces the manual mechanical process of comparing information sources with automated computational systems. Algorithms automatically acquire data from multiple sources, extract features, analyze relationships, and establish connections without human intervention, thereby maintaining mapping accuracy while dramatically improving generation efficiency.
2Reliability
If detailed connections between traffic signals and vehicle locations are established manually, then navigation reliability is improved, but labor intensity increases
Solution Approach 1:
The system performs self-service by automatically acquiring data from multiple sources, extracting relevant features, analyzing spatial relationships, and establishing connections between traffic signals and vehicle locations. The automated algorithms independently complete the entire workflow without requiring manual operation, thereby ensuring navigation reliability while simplifying the operational process.
Solution Approach 2:
The patent introduces an intermediary automated processing system that mediates between raw data from multiple sources and the final navigation map. This intermediary layer automatically extracts features, analyzes relationships, and establishes connections, replacing manual operations while maintaining the reliability of navigation data.
3Loss of information
If comprehensive map data including multiple information sources is collected, then map detail quality is improved, but data processing complexity increases
Solution Approach 1:
The patent segments the complex data processing task into distinct stages: data acquisition from multiple sources, feature extraction, relationship analysis, and connection establishment. Each segment handles specific aspects of the data, reducing overall complexity while preserving information completeness through systematic processing at each stage.
Solution Approach 2:
The system extracts only the essential features and relationships from comprehensive data sources, separating relevant information from unnecessary details. This extraction process maintains information completeness by capturing all critical elements while reducing processing complexity by focusing computational resources on essential data elements.
Data Source
AI summary
Aspects of the disclosure relate generally to generating roadgraphs for use by autonomous vehicles. A computer may receive input defining aspects of a roadway including an intersection with another roadway, one or more traffic control features, and one or more locations at which a vehicle is required to observe at least one traffic signal before entering the intersection. A user may identify the intersection, for example, by tracing a perimeter around the intersection. In response, for each particular location of the one or more locations, the computer may identifying a route through the intersection from the particular location and determine, based on the boundary of the intersection and the particular location, a set of the one or more traffic control features must be observed by the vehicle before entering the intersection. This information may then be used to generate a roadgraph.