Joint Sensor Calibration and Fusion for Moving Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor fusion methods struggle with calibrating sensors installed in moving vehicles, particularly under varying road conditions, and often result in inaccurate calibration due to low sensor resolution, necessitating a method that jointly optimizes calibration and fusion for improved output.
Innovation Solution
A joint calibration and fusion method that updates calibration parameters and fused measurements recursively, using a cost function to improve the geometric mapping between sensors and enhance resolution, particularly for low-resolution depth sensors like LIDAR combined with high-resolution optical cameras.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If offline calibration using known alignment targets is performed, then calibration accuracy is improved, but the system cannot adapt to moving vehicles with varying road conditions
Solution Approach 1:
The patent implements dynamic calibration by continuously updating calibration parameters online using current sensor data from moving vehicles, rather than relying on static offline calibration. The system adapts to varying road conditions by performing real-time calibration adjustments based on actual sensor measurements, making the calibration process dynamic and adaptable to changing environments.
2Adaptability or versatility
If calibration is performed online using edge matching, then adaptability to moving conditions is improved, but measurement accuracy deteriorates due to low sensor resolution
Solution Approach 1:
The patent merges calibration and fusion processes into a unified joint optimization framework. Instead of performing calibration and fusion as separate sequential steps, the system combines them into a single integrated process that simultaneously optimizes both calibration parameters and fusion outputs, leveraging information from both sensors to improve overall accuracy.
Solution Approach 2:
The system implements feedback mechanisms where the fusion output quality is continuously evaluated and used to adjust calibration parameters. The cost function monitors the quality of fused measurements and provides feedback to iteratively refine calibration parameters, improving accuracy through continuous self-correction based on actual performance.
3Device complexity
If separate calibration and fusion processes are used, then process simplicity is maintained, but final output quality deteriorates
Solution Approach 1:
The patent merges calibration and fusion processes into a unified joint optimization framework. Instead of performing calibration and fusion as separate sequential steps, the system combines them into a single integrated process that simultaneously optimizes both calibration parameters and fusion outputs, leveraging information from both sensors to improve overall accuracy.
Data Source
AI summary
A method for fusing measurements of sensors having different resolutions performs jointly a calibration of the sensors and a fusion of the their measurements to produce calibration parameters defining a geometrical mapping between coordinate systems of the sensors and a fused set of measurements that includes the modality of a sensor with resolution greater than its resolution. The calibration and the fusion are performed jointly to update the calibration parameters and the fused set of measurements in dependence on each other.