Sparse Road Map Crowdsourcing for Low-Data AV Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating efficiently due to the sheer volume of data required for traditional mapping technologies, which can limit navigation accuracy and increase storage and update complexities.
Innovation Solution
The use of a sparse map system that includes line representations of road surface features and landmarks, constructed and distributed through crowdsourced data from multiple vehicles, allowing for efficient navigation with reduced data storage and transfer requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional mapping technology is used for autonomous vehicle navigation, then navigation accuracy is maintained, but data storage requirements and update complexities increase significantly
Solution Approach 1:
The patent extracts only the essential navigation elements from complete maps, creating sparse maps that contain only critical road geometry and landmark information needed for autonomous navigation. This selective extraction reduces data storage requirements while maintaining sufficient navigation accuracy by removing redundant map data that is not essential for vehicle guidance.
Solution Approach 2:
The patent segments the map data into discrete, manageable components including polynomial representations of road paths and digital signatures of road features. This segmentation allows the system to store and process only necessary navigation elements rather than complete map datasets, reducing overall data storage requirements while preserving navigation functionality.
2Loss of information
If traditional mapping technology is used for autonomous vehicle navigation, then complete road information is available, but storage and update complexities increase
Solution Approach 1:
The patent transforms road geometry into polynomial representations and road features into digital signatures, changing the data parameters from detailed spatial information to compact mathematical models. This parameter transformation maintains the essential road information needed for navigation while significantly reducing storage complexity and update requirements compared to traditional detailed mapping approaches.
3Measurement precision
If detailed maps are used for autonomous navigation, then comprehensive route guidance is provided, but data transfer requirements increase
Solution Approach 1:
The patent extracts only the critical geometric and landmark information needed for precise route guidance from complete map data. By taking out only the essential navigation elements and representing them through compact polynomial and signature formats, the system achieves sufficient route guidance precision while minimizing data transfer requirements between vehicles and navigation systems.
Data Source
AI summary
Systems and methods are provided for crowdsourcing a sparse map for autonomous vehicle navigation. In one implementation, a non-transitory computer-readable medium may include a sparse map for autonomous vehicle navigation along a road segment. The sparse map may include at least one line representation of a road surface feature extending along the road segment, each line representation representing a path along the road segment substantially corresponding with the road surface feature, and wherein the road surface feature is identified through image analysis of a plurality of images acquired as one or more vehicles traverse the road segment and a plurality of landmarks associated with the road segment.