LiDAR Calibration via Static Map Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional sensor calibration methods for autonomous vehicles, such as LiDAR sensors, require additional resources and time, as they necessitate operating the vehicle in a confined environment to capture point cloud data from pre-selected objects, which diverts resources from other critical tasks like environment mapping and autonomous driving improvements.
Innovation Solution
A method and system for calibrating a first sensor, like a LiDAR, using statically mapped objects in a vehicle's environment, where point cloud data is captured and aligned with a pre-calibrated second sensor, such as a GPS IMU, to achieve calibration within a global coordinate system, allowing for iterative refinement of the transformation matrix for accurate calibration without additional resource expenditure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional sensor calibration methods are used, then calibration accuracy can be achieved, but additional resources and time are required due to operating in confined environments
Solution Approach 1:
The system performs preliminary mapping of static objects in the environment before calibration is needed. This pre-established knowledge base of object locations and characteristics allows the calibration process to quickly identify suitable calibration targets without requiring confined environments or additional resource expenditure during actual calibration operations.
Solution Approach 2:
The calibration system utilizes naturally occurring static objects in the vehicle's operating environment as calibration targets, rather than requiring external calibration facilities. The vehicle's own sensors and the ambient environment serve the calibration function, eliminating the need for dedicated calibration resources and confined spaces.
2Reliability
If conventional sensor calibration methods are used, then calibration can be performed, but time is lost diverting resources from other critical tasks
Solution Approach 1:
The system performs calibration using static objects that are continuously present in the vehicle's operating environment during normal autonomous driving operations. This allows calibration to occur continuously alongside other critical tasks rather than requiring separate calibration sessions, eliminating time loss and maintaining sensor reliability without diverting resources.
3Productivity
If static objects are used for calibration, then resource allocation is optimized, but the objects must satisfy specific criteria for accurate calibration
Solution Approach 1:
The system implements feedback mechanisms to verify that detected static objects satisfy the necessary calibration criteria. The calibration process monitors object characteristics, location accuracy, and sensor data quality, providing feedback to determine whether the current static object is suitable for calibration or if alternative objects should be selected, ensuring accurate calibration while maintaining resource efficiency.
Data Source
AI summary
Improved calibration of a vehicle sensor based on static objects detected within an environment being traversed by the vehicle is disclosed. A first sensor such as a LiDAR can be calibrated to a global coordinate system via a second pre-calibrated sensor such as a GPS IMU. A static object present in the environment is detected such as signage. A type of the detected object is determined from static map data. Point cloud data representative of the static object is captured by the first sensor and a first transformation matrix for performing a transformation from a local coordinate system of the first sensor to a local coordinate system of the second sensor is iteratively redetermined until a desired calibration accuracy is achieved. Transformation to the global coordinate system is then achieved via application of the first transformation matrix followed by a second known transformation matrix.