Sparse Road Map Navigation Using Elevation Signatures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating due to the sheer volume of data required for traditional mapping technologies, which can limit navigation efficiency and effectiveness.
Innovation Solution
The use of a sparse map system that includes a polynomial representation of a target trajectory and predetermined landmarks, allowing for efficient data storage and navigation with cameras, GPS, and sensor data, enabling adaptive and self-aware navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional mapping technology is used for autonomous vehicle navigation, then navigation accuracy can be maintained, but data storage requirements and computational demands increase significantly
Solution Approach 1:
The patent extracts only the essential navigation elements from complete traditional maps, creating sparse maps that contain only critical trajectory polynomials and key landmark information. This extraction approach maintains navigation accuracy by preserving essential geometric and positional data while eliminating redundant information, thereby significantly reducing data storage requirements.
Solution Approach 2:
The navigation map is segmented into discrete, manageable components including trajectory polynomials, landmark descriptors, and key position markers. This segmentation allows the system to store and process only necessary navigation elements rather than complete map data, reducing overall data volume while maintaining the ability to provide accurate navigation guidance.
2Reliability
If traditional mapping technology is used for autonomous vehicle navigation, then comprehensive navigation information is available, but computational processing time and resources increase
Solution Approach 1:
The system extracts only the most critical navigation information elements needed for safe and effective autonomous vehicle operation. By focusing on essential trajectory data and key landmarks rather than processing complete map datasets, the system maintains navigation reliability while significantly reducing computational processing time and resource requirements.
Solution Approach 2:
The patent applies partial action by implementing sparse mapping that provides sufficient navigation information without requiring complete map data. The selective inclusion of essential trajectory polynomials and landmark information enables the system to achieve adequate navigation functionality with reduced computational burden, avoiding the excessive processing required by traditional complete mapping approaches.
3Quantity of substance
If sparse map with landmarks spaced at least 50 meters apart is used, then data density is reduced to no more than 1 megabyte per kilometer, but navigation detail resolution decreases
Solution Approach 1:
The patent applies local quality by concentrating detailed navigation information at key landmark positions while using polynomial trajectories to connect these points. Each landmark serves as a local reference point with precise positional data, and the polynomial curves between landmarks provide sufficient navigational guidance without requiring dense sampling. This approach reduces overall data density while maintaining adequate navigation detail resolution through localized precision at critical points.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A system for autonomously navigating a vehicle along a road segment, the system comprising at least one processor. The processor is programmed to receive, from at least one sensor, information relating to elevation of the road segment; determine elevation of the road segment at a current location of the vehicle based on the received information; compare the determined elevation to a predetermined signature elevation profile for the road segment; and determine a current location of the vehicle along a predetermined road model trajectory associated with the road segment based on the comparison of the determined elevation and the predetermined signature elevation profile.