Vehicle Positioning Using Probability Distributions on Road Network Edges
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining a vehicle's position in a road network struggle with accuracy when using imprecise sensor data, which can lead to incorrect or unsafe position determinations.
Innovation Solution
A method that utilizes a sensor group to detect first and second sensor data, associating probabilities with edges of a road network based on the data, and refining the position determination using a Bayes filter to account for imprecise data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data is used for position determination, then position information can be obtained, but accuracy deteriorates when sensor data is imprecise
Solution Approach 1:
The system uses feedback by comparing detected sensor data with expected data from the road network model. The probability calculation mechanism continuously refines position determination by feeding back the match between actual sensor readings and predicted readings from each candidate edge, allowing the system to converge on the most likely position even with imprecise initial sensor data
Solution Approach 2:
The system changes parameters by transforming raw sensor data into probability distributions across multiple road network edges. Instead of directly mapping sensor data to a single position, the system adjusts the probability parameters for each edge based on how well the sensor data matches expected characteristics of that edge, enabling accurate position determination despite sensor imprecision
2Measurement precision
If probability-based position determination is used, then accuracy with imprecise data improves, but computational complexity increases
Solution Approach 1:
The system segments the road network into discrete edges and calculates probabilities independently for each edge. This segmentation allows the complex problem of position determination to be broken down into manageable comparisons between sensor data and each individual edge's expected characteristics, reducing overall computational complexity while maintaining accuracy
Solution Approach 2:
The system performs partial action by calculating probabilities for only the most relevant edges rather than all possible positions. By focusing computational resources on edges that are geographically close to the vehicle's last known position or that match key sensor observations, the system achieves accurate position determination with reduced computational effort
Data Source
AI summary
A method is described in which a position of a vehicle is determined in a road network, having a plurality of edges, each of them being associated with a road section or a driving lane on a road section, by means of a sensor group of the vehicle, wherein first sensor data are detected by means of the sensor group, on the basis of the first sensor data each edge of a plurality of first edges of the road network is associated with a first probability that the vehicle is located in the road section associated with the first edge or in the driving lane associated with the first edge, second sensor data are detected by means of the sensor group, on the basis of the second sensor data and the probabilities associated with the first edges, a second probability is associated with each edge of a plurality of second edges of the road network that the vehicle is located in the road section associated with the second edge or in the driving lane associated with the second edge, and the second edge with the highest associated probability is determined to be the position of the vehicle.