Drivable Area Boundary Segmentation for Uncertain Road User Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately predicting the trajectory of uncertain road users like pedestrians within drivable areas due to the large, simplified representation of drivable areas not providing meaningful information about smaller discrete target locations, which can lead to collisions or hazardous situations.
Innovation Solution
The system segments the drivable area boundary into logical segments, representing potential goals for actors, allowing the autonomous vehicle to predict trajectories and avoid collisions by identifying concavities and shared edges in the drivable area, creating a data representation that includes these segments for navigation control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If drivable areas are represented as large simplified segments, then the navigation system can operate with reduced computational complexity, but the system cannot infer meaningful information about smaller discrete target locations
Solution Approach 1:
The patent divides the drivable area boundary into multiple logical segments based on concavity analysis. Each logical segment represents a potential target location (e.g., sidewalk corners, parking cutouts) where uncertain road users may exit the drivable area. This segmentation transforms the large simplified drivable area representation into discrete meaningful target locations while maintaining computational efficiency through algorithmic processing.
2Measurement precision
If the drivable area boundary is analyzed in detail to identify discrete target locations, then trajectory prediction accuracy improves, but the processing time and computational load increase
Solution Approach 1:
The patent changes the parameter representation of the drivable area boundary from continuous geometric data to discrete logical segments defined by concavity thresholds. By analyzing concavity values and comparing them against threshold parameters, the system efficiently identifies target locations without requiring exhaustive detailed analysis of every boundary point, thus reducing processing time while maintaining prediction accuracy.
3Reliability
If the system segments the drivable area into multiple logical segments, then the ability to predict pedestrian trajectories improves, but the complexity of the navigation system increases
Solution Approach 1:
The patent implements self-service through automated concavity analysis and logical segment identification algorithms. The system automatically processes the drivable area boundary data, identifies concavities exceeding thresholds, and generates logical segments without requiring manual configuration or complex external processing. This automation reduces system complexity while improving reliability through consistent algorithmic application.
Data Source
AI summary
Methods and systems for controlling navigation of an autonomous vehicle for traversing a drivable area are disclosed. The methods include receiving information relating to a drivable area that includes a plurality of polygons, identifying a plurality of logical edges that form a boundary of the drivable area, sequentially and repeatedly analyzing concavities of each the plurality of logical edges until identification of a first logical edge that has a concavity greater than a threshold, creating a first logical segment of the boundary of the drivable area. This segmentation may be repeated until each of the plurality of logical edges has been classified. The method may include creating and adding (to a map) a data representation of the drivable area that comprises an indication of the plurality of logical segments, and adding the data representation to a road network map comprising the drivable area.