Intersection Visibility Mapping for Autonomous Vehicle Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating intersections due to occluded or blocked visibility of traffic lights and signs, making it difficult to differentiate traffic-control features from non-traffic-control features, which affects safe navigation.
Innovation Solution
A computing device stores and queries a map for visibility information, allowing the vehicle to select the best driving behavior based on visibility data, such as lane positions that provide the best view of intersection features, thereby improving navigation through intersections by pre-calculating and storing visibility information ahead of time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the vehicle performs real-time visibility calculations during intersection navigation, then the navigation accuracy and safety are improved, but the computational load and processing time increase
Solution Approach 1:
The system pre-calculates visibility information for multiple potential vehicle positions at intersections before the vehicle arrives. This visibility data, including occlusion analysis for different lanes and positions, is stored in advance so that during actual navigation, the vehicle can quickly query and use pre-computed visibility information without performing complex real-time calculations, thus maintaining navigation safety while reducing computational load during critical moments
Solution Approach 2:
The system extracts and separates the visibility calculation function from the real-time navigation control function. By pre-calculating and storing visibility information for various positions and features (traffic lights, signs, pedestrians) at intersections, the complex visibility analysis is performed in advance and stored as lookup data, allowing the navigation system to simply query and apply pre-determined visibility information during actual operation without bearing the full computational burden in real-time
2Productivity
If the vehicle uses pre-calculated visibility information from stored maps, then the computational load during navigation is reduced, but the map data storage requirements increase
Solution Approach 1:
The system applies local quality by storing detailed visibility information only for critical locations such as intersections, rather than for all possible positions along the entire route. The pre-calculated visibility data includes position-specific occlusion analysis for traffic lights, signs, and other features only where needed for navigation decisions, reducing overall data storage requirements while maintaining navigation efficiency at critical points
Solution Approach 2:
The visibility information is segmented and organized by specific locations (intersections), features (traffic lights, signs, pedestrians), and vehicle positions (lanes, lateral positions). This segmentation allows the system to store and retrieve only the relevant visibility data needed for current navigation context, reducing redundant data storage while maintaining comprehensive visibility analysis where required
3Measurement precision
If the vehicle queries detailed visibility information for multiple positions, then the observation quality at intersections is improved, but the query processing time increases
Solution Approach 1:
The system pre-calculates and stores visibility information for multiple potential vehicle positions at intersections before the vehicle arrives. This includes pre-computing occlusion analysis for different lanes, lateral positions, and viewing angles for various features (traffic lights, signs, pedestrians). During actual navigation, the vehicle can quickly query and compare pre-computed visibility data for multiple positions without performing time-consuming real-time calculations, thus maintaining high measurement precision while minimizing query processing time
Data Source
AI summary
Disclosed herein are methods and apparatus for controlling autonomous vehicles utilizing maps that include visibility information. A map is stored at a computing device associated with a vehicle. The vehicle is configured to operate in an autonomous mode that supports a plurality of driving behaviors. The map includes information about a plurality of roads, a plurality of features, and visibility information for at least a first feature in the plurality of features. The computing device queries the map for visibility information for the first feature at a first position. The computing device, in response to querying the map, receives the visibility information for the first feature at the first position. The computing device selects a driving behavior for the vehicle based on the visibility information. The computing device controls the vehicle in accordance with the selected driving behavior.