Vehicle Sensor Fusion Error Estimation for Accurate Target Grouping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems inaccurately group targets due to constant observation error assumptions across sensors, leading to lowered recognition accuracy and failure to integrate high-accuracy sensor values, especially influenced by varying environmental conditions.
Innovation Solution
A vehicle control system that estimates position and speed errors based on sensor characteristics and environmental factors, integrating correlated detection results to calculate accurate errors and improve grouping accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a constant value is used for observation error of sensors, then the system is simple to implement, but target grouping may be erroneously performed and recognition accuracy is lowered
Solution Approach 1:
The patent changes the error estimation approach from using constant values to dynamically estimating errors based on sensor characteristics and environmental factors. The integration unit estimates position and speed errors by considering sensor-specific parameters and external field conditions, allowing the error values to vary according to actual operating conditions rather than remaining fixed.
2Device complexity
If observation error is not considered according to sensor characteristics, then the system is simpler, but high-accuracy sensor values are not selected and integration accuracy is reduced
Solution Approach 1:
The patent applies local quality by evaluating error characteristics specifically for each sensor type rather than using a uniform error model. The integration unit determines correlation between detection results of multiple sensors and estimates errors according to each sensor's specific characteristics and the external field environment, allowing each sensor to be weighted appropriately based on its actual performance in given conditions.
3Ease of operation
If environmental factors are not taken into consideration, then the system is simpler to operate, but sensor error estimation is inaccurate under varying external conditions
Solution Approach 1:
The patent introduces dynamics by making the error estimation adaptive to changing environmental conditions. The integration unit continuously evaluates sensor errors based on current external field characteristics, allowing the system to automatically adjust error estimates as conditions change rather than relying on fixed pre-set values, thereby maintaining accuracy across varying operational environments.
Data Source
AI summary
To improve accuracy of a grouping process by accurately obtaining an error of an observation value of a sensor.A vehicle control system includes an integration unit that estimates information on a position and a speed of a target existing in an external field, and errors of the position and the speed based on information from a sensor that acquires information on the external field of an own vehicle. The integration unit estimates an error of a detection result from the detection result of a sensor that detects an external field of a vehicle in accordance with a characteristic of the sensor, determines correlation between detection results of a plurality of the sensors, and integrates correlated detection results and calculates the errors of the position and the speed of the target.