Intersection Lane Passability from Obstacle Trajectory Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in determining the passable state of lanes at intersections due to the complexity of traffic light states and lane configurations, which current methods struggle to accurately assess.
Innovation Solution
The method involves acquiring intersection information, including lane data and historical obstacle trajectories, matching these trajectories with lane center lines to identify the lane with the smallest matching error, and determining the passable state based on this lane, potentially using traffic light information to verify the lane's state.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple traffic lights are monitored and logical relationships are analyzed to determine lane passability, then the accuracy of traffic light state determination is improved, but the computational complexity and processing time increase
Solution Approach 1:
The patent introduces an intermediary obstacle (vehicle or pedestrian) as a mediator to indirectly determine traffic light states. Instead of directly analyzing multiple traffic lights and their logical relationships, the system observes the trajectory of obstacles in the intersection. The obstacle's movement pattern serves as evidence of the actual traffic light state, simplifying the determination process while maintaining high accuracy.
Solution Approach 2:
The system uses feedback from obstacle trajectories to verify and determine traffic light states. By continuously monitoring whether obstacles are moving through the intersection, the system receives real-time feedback about the actual traffic light state, allowing it to accurately determine passability without complex logical analysis of multiple traffic light signals.
2Measurement precision
If obstacle trajectories are tracked and matched with lane center lines to identify passable lanes, then the accuracy of lane passability determination is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary actions by pre-storing lane center line data and preparing trajectory matching algorithms before actual intersection approach. When the autonomous vehicle nears the intersection, the system quickly matches observed obstacle trajectories against pre-loaded lane center lines, significantly reducing processing time while maintaining high accuracy in lane passability determination.
3Reliability
If the system monitors multiple obstacles and verifies traffic light states through trajectory analysis, then the reliability of passage determination is improved, but the device complexity and energy consumption increase
Solution Approach 1:
The system applies partial action by monitoring only the necessary number of obstacles sufficient to determine traffic light state, rather than continuously tracking all possible obstacles. Once enough trajectory data is collected to confidently determine passability, the system stops additional monitoring, reducing energy consumption while maintaining high reliability through selective observation of key obstacles.
Data Source
AI summary
A method for determining passage of an autonomous vehicle includes: acquiring information about an intersection on a driving route of the autonomous vehicle, wherein the information about the intersection comprises lane data; acquiring a historical trajectory of an obstacle in the intersection within a specific time; acquiring, by matching the historical trajectory of the obstacle with center lines of respective lanes in the lane data, a lane with smallest matching error; and determining that the lane with the smallest matching error is in a passable state, wherein the lane with the smallest matching error is a lane where the obstacle is located.