Autonomous Vehicle LiDAR Calibration via Static Object Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional sensor calibration methods for autonomous vehicles, such as LiDAR, 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 refining environmental maps or improving driving capabilities.
Innovation Solution
A method and system for calibrating a first sensor, like a LiDAR, using detected static objects in a vehicle's environment, where point cloud data is captured and a transformation matrix is determined to align the sensor with a global coordinate system via a pre-calibrated second sensor, such as a GPS IMU, allowing calibration during typical operation without additional resource expenditure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional sensor calibration methods are used, then calibration accuracy is achieved, but additional resources and time are required
Solution Approach 1:
The system performs calibration using static objects detected during normal vehicle operation, eliminating the need for separate calibration sessions. The calibration process is integrated into the vehicle's regular operational workflow, allowing calibration to occur in advance of when it would traditionally be performed.
Solution Approach 2:
The vehicle's sensor system calibrates itself autonomously by detecting static objects in the environment and using these objects as reference points. The system uses its own operational data and environment perception capabilities to perform calibration without requiring external calibration equipment or dedicated calibration procedures.
2Measurement precision
If conventional sensor calibration methods are used, then calibration accuracy is achieved, but time is diverted from other critical tasks
Solution Approach 1:
The calibration process occurs continuously during normal vehicle operation rather than requiring interruption of other tasks. The system maintains continuous perception of the environment and uses this ongoing data stream to perform calibration, ensuring that calibration is an ongoing process that does not interrupt the refinement of environmental maps or other critical operations.
Solution Approach 2:
The calibration function is merged with the vehicle's normal environmental perception and mapping operations. By using the same sensor data and processing pipelines for both calibration and environmental understanding, the system eliminates the need for separate calibration time and resources.
3Measurement precision
If conventional sensor calibration methods are used, then calibration accuracy is achieved, but resource expenditure increases
Solution Approach 1:
The system uses its own operational resources and existing sensor data to perform calibration, rather than requiring additional dedicated calibration equipment or external resources. The vehicle's perception system and processing capabilities are leveraged to perform calibration as a byproduct of normal operation.
Solution Approach 2:
The sensor system and processing pipeline serve multiple functions simultaneously - environmental perception, mapping, and calibration. By making the system universal and multi-functional, the same hardware and software resources are used for multiple purposes, eliminating the need for additional resources dedicated solely to calibration.
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. Static objects present in the environment are detected such as signage. Point cloud data representative of the static objects are 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 application of a second known transformation matrix to transition from the local coordinate system of the second pre-calibrated sensor to the global coordinate system.