Autonomous Navigation Map Weighting for Road Segment Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigation systems for autonomous vehicles are not reliable enough to cover entire road networks independently, as they rely on specific external information sources that may fail or be unavailable.
Innovation Solution
A method for developing a navigation autonomy map that uses a weighted average of primary autonomy indices from multiple distinct autonomy functions, such as GPS, LIDAR, and road markings, to calculate a final autonomy index for each section of a journey, improving reliability and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single autonomy function is used for navigation, then the system is simple to operate, but the reliability is insufficient to cover entire road networks
Solution Approach 1:
The patent combines multiple distinct autonomy functions (GPS, LIDAR, road marking detection, inertial navigation) into a unified navigation system. Each function evaluates specific road sections and produces autonomy indices that are integrated through weighted averaging to generate a comprehensive final autonomy index, thereby improving overall navigation reliability across diverse road networks
Solution Approach 2:
The navigation system is designed to perform multiple autonomy evaluation functions simultaneously using different sensing modalities. The system can adaptively select and weight different autonomy functions based on road section characteristics, making the system universally applicable to various road types and conditions while maintaining high reliability
2Reliability
If external information sources are used for autonomous navigation, then the navigation function can be implemented, but the system becomes vulnerable to information failure or unavailability
Solution Approach 1:
The system pre-evaluates road sections and stores autonomy indices in advance, creating a buffer that compensates for potential real-time information failures. By calculating and storing autonomy indices for different road sections beforehand, the system can rely on pre-computed data when external information sources fail or become unavailable during vehicle operation
Solution Approach 2:
The system dynamically adjusts the weighting coefficients of different autonomy functions based on road section characteristics and information availability. When certain external information sources fail, the system reweights the remaining functional sources to maintain reliable navigation, effectively adapting to information failures through parameter optimization
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
The method for producing an autonomous navigation map for a vehicle in a zone comprising route segments, comprises the steps of: identifying (1) the route segments for which the map should be produced; for each route segment, calculating (3) a primary autonomy index according to at least two distinct functions; and calculating (4) for each route segment, a final autonomy index by performing a weighted average of the primary autonomy indices. Autonomy map, application of this autonomy map and vehicle using such an autonomy map.