Map Matched Trajectory Accuracy via Forward Probability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accuracy of map matched vehicle trajectories is compromised due to interference in GPS signals and inaccuracies in map data, leading to incorrect identification of road segments traveled by vehicles.
Innovation Solution
A forward probability algorithm of a Hidden Markov Model is used to calculate the likelihood of aligning GPS signals with road segments, employing supervised and unsupervised metrics to evaluate the accuracy of map matching processes, with unsupervised metrics determining the joint probability of emission and transition probabilities to assess map matching accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If map matching is performed using GPS signals and map data, then vehicle trajectory can be determined, but accuracy is compromised due to signal interference and map data inaccuracies
Solution Approach 1:
The system calculates forward probability metrics and compares them against threshold values to validate map matching results. When the calculated forward probability falls below the threshold, the system identifies this as feedback indicating potential errors in the map matching process, allowing for corrective actions or alternative route consideration.
Solution Approach 2:
The patent introduces forward probability calculation as an intermediary validation layer between raw GPS matching and final trajectory determination. This intermediary metric acts as a mediator that assesses the quality of map matching results before they are accepted, reducing the impact of GPS interference and map data errors.
2Measurement precision
If supervised metrics are used to evaluate map matching accuracy, then trajectory similarity can be measured, but ground truth data is required which increases system complexity
Solution Approach 1:
The system performs self-validation by calculating forward probability metrics from the map matching process itself without requiring external ground truth data. The forward probability calculation uses the same map data and GPS signals already being processed, allowing the system to assess its own matching quality independently.
3Productivity
If unsupervised metrics are used without ground truth, then map matching accuracy can be evaluated, but the metric may not reflect true accuracy
Solution Approach 1:
The forward probability metric serves as an intermediary measure that bridges unsupervised evaluation with reliability. While it doesn't require ground truth data for computation, the metric provides a probabilistic assessment that correlates with actual matching quality, making it a reliable proxy for accuracy evaluation.
Data Source
AI summary
A transport service system determines the accuracy of a map matched trajectory using a forward probability algorithm. A transport vehicle on a trip relays location data to the system. The system uses a map of the corresponding area and the location data to calculate an emission probability, the likelihood of a candidate road being associated with a location data point, and a transition probability, the likelihood of a second state occurring after a first state. The joint probability of the emission and transition probabilities is used to determine a total number of zero forward probability occurrences and an average forward probability associated with the trip. These metrics are used to measure the accuracy of the map matching algorithm for the trip.