Semantic Map Traffic Light State Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face computational challenges in efficiently and accurately identifying the state of traffic lights at intersections, which affects their navigation and decision-making processes.
Innovation Solution
The implementation of a semantic map system that provides traffic light location data in three spatial dimensions, allowing a computer vision system to focus on and assess the state of traffic lights using this data, and a vehicle control system to make decisions based on the assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the autonomous vehicle system searches for and assesses all traffic lights at intersections, then the accuracy of traffic light state identification is improved, but the computational load and processing time increase significantly
Solution Approach 1:
The patent segments the intersection environment into multiple lanes, with each lane associated with specific traffic lights. The system only searches for and assesses traffic lights relevant to the vehicle's current or intended lane, rather than processing all traffic lights at the intersection. This segmentation reduces computational complexity while maintaining identification accuracy for relevant traffic lights.
Solution Approach 2:
The system applies local quality by focusing computational resources on specific regions (lanes) rather than uniformly processing the entire intersection. Traffic light search and assessment are localized to lanes that the vehicle is currently in or plans to enter, optimizing resource allocation and reducing overall computational burden.
2Reliability
If the system processes all possible traffic lights at an intersection, then comprehensive coverage is achieved, but the time required for navigation decisions increases
Solution Approach 1:
The system performs preliminary actions by pre-identifying which lanes are relevant to the vehicle's route and pre-determining which traffic lights control those lanes. This preliminary filtering occurs before the actual traffic light state assessment, enabling the system to quickly focus on only the necessary traffic lights and reduce decision-making time while maintaining reliability.
3Measurement precision
If the autonomous vehicle uses detailed semantic map data with labelled intersection lanes, then the precision of traffic light location identification is improved, but the data processing requirements increase
Solution Approach 1:
The system extracts only the necessary information from the detailed semantic map data - specifically, the traffic light locations associated with the vehicle's current or intended lanes. Rather than processing all labelled intersection lanes and their associated traffic lights, the system extracts and processes only the subset relevant to the vehicle's navigation, reducing energy consumption while maintaining location precision.
Data Source
AI summary
Systems and method are provided for controlling a vehicle. In one embodiment, a method includes: receiving semantic map data, via a processor, wherein the semantic map data includes traffic light location data, calculating route data using the semantic map data, via a processor; viewing, via a sensing device, a traffic light and assessing a state of the viewed traffic light, via a processor, based on the traffic light location data, and controlling driving of an autonomous vehicle based at least on the route data and the state of the traffic light, via a processor.