Representative Vehicle Trajectory Selection for Road Geometry Drift
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face safety risks due to inaccuracies in road geometry maps, particularly when road maintenance causes lane closures or shifts, leading to potential collisions with barriers or road blocks.
Innovation Solution
The method involves tracking multiple vehicle trajectories to generate combined trajectories, using an expectation-maximization process to select and adjust vehicle speed and direction based on the most reliable paths, thereby updating road maps and avoiding obstacles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the autonomous vehicle uses a pre-stored map to navigate, then the navigation process is simple and efficient, but the road geometry map becomes inaccurate when road maintenance causes lane closures or shifts
Solution Approach 1:
The system pre-stores map data for efficient navigation, but also prepares trajectory tracking and map updating mechanisms in advance to handle road changes. Multiple vehicle trajectories are collected and stored for future reference when discrepancies are detected.
Solution Approach 2:
The system continuously compares observed vehicle trajectories against the pre-stored map data. When inconsistencies are detected (such as lane closures or shifts), the map is updated with corrected geometry information, creating a feedback loop that maintains accuracy while preserving navigation efficiency.
2Stability of the object's composition
If the autonomous vehicle follows the inaccurate road model from the map, then the vehicle can maintain steady operation, but it risks crashing into barriers or road blocks
Solution Approach 1:
The system dynamically adjusts the navigation approach by switching between following the pre-stored map and tracking actual vehicle trajectories. When road conditions change, the system transitions from static map-following to dynamic trajectory-based navigation, maintaining stability while improving safety.
Solution Approach 2:
The system introduces trajectory analysis as an intermediary layer between the map data and vehicle control. By comparing map-based road models with actual vehicle trajectories and using the expectation-maximization algorithm to identify discrepancies, the system mediates between steady operation and safety, allowing the vehicle to adapt to road changes without abandoning stable navigation.
3Measurement precision
If the autonomous vehicle tracks and combines multiple observed trajectories to generate a representative trajectory, then the accuracy of road geometry is improved, but the computational complexity increases
Solution Approach 1:
The system segments the trajectory processing into distinct phases: collecting individual vehicle trajectories, combining them to generate a representative trajectory using the expectation-maximization algorithm, and then comparing against the map. This segmentation allows complex computations to be performed only when needed rather than continuously.
Solution Approach 2:
The system changes computational parameters by adjusting the frequency and intensity of trajectory analysis based on detected discrepancies. When the map shows inconsistencies with actual road conditions, the system intensifies trajectory tracking and processing. When the map is accurate, computational resources are reduced, balancing accuracy with complexity management.
Data Source
AI summary
A method and apparatus is provided for controlling the operation of an autonomous vehicle. According to one aspect, the autonomous vehicle may track the trajectories of other vehicles on a road. Based on the other vehicle's trajectories, the autonomous vehicle may generate a pool of combined trajectories. Subsequently, the autonomous vehicle may select one of the combined trajectories as a representative trajectory. The representative trajectory may be used to change at least one of the speed or direction of the autonomous vehicle.