Sparse 3D Navigation Maps for Accurate Autonomous Vehicle Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating due to the vast amount of data they need to process, analyze, and store, including visual information, GPS data, sensor data, and map data, which can limit their navigation efficiency and accuracy.
Innovation Solution
A system for navigating autonomous vehicles using a sparse map that includes three-dimensional polynomial representations of preferred vehicle paths and landmarks, allowing for efficient navigation without the need for extensive data storage or processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional mapping technology is used for autonomous navigation, then navigation coverage and detail are improved, but data storage requirements and processing complexity increase significantly
Solution Approach 1:
The patent extracts only the essential navigational elements from complete map data, creating sparse maps that contain only critical information such as road boundaries, intersections, and key landmarks. This extraction approach maintains navigation accuracy while dramatically reducing data storage requirements by eliminating redundant detailed information.
Solution Approach 2:
The patent applies local quality by providing high-detail map data only in critical areas such as intersections, complex road configurations, and areas with frequent navigation decisions, while using lower-detail sparse representations in straightforward road sections. This selective detail distribution optimizes both navigation accuracy and data efficiency.
2Reliability
If complete map data is stored and processed, then navigation reliability is improved, but processing time and computational resources increase
Solution Approach 1:
The system extracts only the necessary navigational parameters from complete map data, storing and processing only essential information such as road topology, key waypoints, and critical landmarks. This extraction maintains navigation reliability by preserving essential route planning data while reducing processing time through minimized data volumes.
Solution Approach 2:
The patent segments map data into hierarchical levels, with sparse maps providing essential navigational structure and detailed maps available on-demand for specific areas. This segmentation allows the system to process only the necessary data level for current navigation needs, improving response time while maintaining reliability through multi-level data availability.
3Manufacturing precision
If high-resolution map data is used, then route planning accuracy is improved, but data transmission requirements and storage costs increase
Solution Approach 1:
The patent extracts essential route planning information from high-resolution map data, creating sparse representations that retain critical geometric and topological properties needed for accurate route planning. This extraction maintains routing precision while reducing storage capacity requirements by eliminating redundant detailed surface and texture information.
Solution Approach 2:
Instead of storing complete high-resolution maps and downscaling for processing, the patent inverts the approach by directly creating sparse high-precision representations from source data. This inversion stores only the essential navigational geometry at full precision, achieving route planning accuracy with minimal storage by what is not stored.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A system for navigating a host vehicle may include a at least one processing device. The at least one processing device may be programmed to receive, from an image capture device, at least one image representative of an environment of the host vehicle. The at least one processing device may also be programmed to analyze the at least one image to identify an object in the environment of the host vehicle. The at least one processing device may also be programmed to determine a location of the host vehicle. The at least one processing device may also be programmed to receive map information associated with the determined location of the host vehicle, wherein the map information includes elevation information associated with the environment of the host vehicle. The at least one processing device may also be programmed to determine a distance from the host vehicle to the object based on at least the elevation information. The at least one processing device may further be programmed to determine a navigational action for the host vehicle based on the determined distance.