Vehicle Sensor Calibration Using Lane-Line Targets in Motion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional sensor calibration methods for autonomous vehicles require the vehicle to be parked on a rotating substrate within a room filled with targets, limiting the efficiency and practicality of the calibration process.
Innovation Solution
The vehicle can build a calibration target from sensor data captured while in motion, using lidar and camera data to estimate lane lines and adjust sensor calibration parameters, allowing for real-time calibration without the need for physical targets or a rotating substrate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional calibration process is used with rotating substrate and physical targets, then sensor calibration accuracy is achieved, but calibration time and operational efficiency deteriorate due to vehicle shutdown and specialized setup requirements
Solution Approach 1:
The patent creates a virtual calibration target by copying and processing actual road images captured by the vehicle's camera. Instead of using physical calibration targets, the system generates a digital representation of lane markings from real-world imagery, which serves as the calibration reference. This eliminates the need for specialized physical targets while maintaining calibration accuracy.
Solution Approach 2:
The patent replaces the mechanical rotating substrate system with a computational image processing approach. Instead of physically rotating the vehicle on a turntable to capture calibration data from multiple angles, the system uses software to process and analyze road images captured during normal vehicle operation, substituting mechanical calibration infrastructure with digital signal processing.
2Measurement precision
If traditional calibration process is used with rotating substrate, then sensor calibration is performed, but device complexity and ease of operation worsen due to specialized calibration rooms and manual target placement
Solution Approach 1:
The system performs calibration using data that the vehicle captures autonomously during its normal operation. The vehicle's existing camera and processing systems serve the dual purpose of both capturing road imagery for navigation and generating calibration targets, eliminating the need for separate calibration equipment and specialized facilities.
Solution Approach 2:
The patent makes the vehicle's camera and image processing system multi-functional by using it for both its primary purpose (road recognition and navigation) and for sensor calibration. The same imaging system that helps the vehicle navigate also generates the calibration targets, eliminating the need for dedicated calibration hardware and facilities.
3Measurement precision
If traditional calibration process is used with physical targets, then calibration data is obtained, but productivity and operational efficiency deteriorate due to vehicle shutdown and manual intervention requirements
Solution Approach 1:
The patent enables continuous calibration during vehicle operation by processing road images in real-time. Instead of requiring periodic shutdowns for calibration, the system continuously captures and processes road imagery to maintain and update sensor calibration parameters, ensuring uninterrupted vehicle operation and continuous improvement of calibration accuracy.
Data Source
AI summary
Provided are systems and methods for auto calibrating a vehicle using a calibration target that is generated from the vehicle's sensor data. In one example, the method may include receiving sensor data associated with a road captured by one or more sensors of a vehicle, identifying lane line data points within the sensor data, generating a representation which includes positions of a plurality of lane lines of the road based on the identified lane line data points, and adjusting a calibration parameter of a sensor from among the one or more sensors of the vehicle based on the representation of the plurality of lane lines.