LIDAR Coordinate Converter Calibration for Real-Time Obstacle Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for calibrating LIDAR devices in autonomous vehicles lack efficiency, making it challenging for mass production and real-time processing, as they do not effectively optimize the transformation of LIDAR images from a local to a global coordinate system for accurate obstacle detection and navigation.
Innovation Solution
A computer-implemented method that receives LIDAR images, determines obstacle locations using perception methods, and iteratively adjusts parameters of a coordinate converter to optimize the transformation from a local to a global coordinate system, ensuring consistency and accuracy for real-time processing during autonomous driving.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional LIDAR calibration methods are used to maximize correlation between depth discontinuities and image edges, then calibration accuracy is improved, but processing time and computational complexity increase significantly
Solution Approach 1:
The patent extracts and focuses only on the essential calibration parameters (coordinate converter parameters) rather than performing full sensor calibration. By isolating the specific transformation parameters that need optimization, the system achieves adequate calibration accuracy without the computational burden of comprehensive calibration methods.
Solution Approach 2:
The system performs preliminary transformation of LIDAR images from local to global coordinate systems using an initial coordinate converter before optimization. This preliminary action establishes a baseline framework that reduces the complexity of subsequent parameter optimization, enabling faster processing while maintaining accuracy.
2Reliability
If comprehensive LIDAR calibration is performed to ensure accurate obstacle detection, then detection reliability is improved, but system complexity and processing requirements increase
Solution Approach 1:
The coordinate converter serves multiple functions: it transforms LIDAR images from local to global coordinate systems, provides calibration parameters, and enables real-time processing. This multi-functional approach eliminates the need for separate calibration systems while maintaining detection reliability.
Solution Approach 2:
The system optimizes parameters of the coordinate converter through iterative adjustment based on obstacle position consistency. By focusing optimization on these specific parameters rather than comprehensive sensor calibration, the system achieves reliable obstacle detection with reduced computational complexity.
3Manufacturing precision
If iterative optimization of coordinate converter parameters is performed to maximize obstacle position consistency, then transformation accuracy is improved, but real-time processing capability is compromised
Solution Approach 1:
The system performs iterative optimization on a subset of LIDAR images to determine coordinate converter parameters, then applies these pre-determined parameters to subsequent real-time processing. This partial optimization approach achieves sufficient transformation accuracy without compromising real-time processing speed for actual autonomous driving operations.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
In one embodiment, a set of LIDAR images representing LIDAR point cloud data captured by a LIDAR device of an ADV at different points in time is received. For each of the LIDAR images, a perception method is utilized to determine a location of an obstacle captured in the LIDAR image in a local coordinate system. The LIDAR image is transformed using a coordinate converter (e.g., a LIDAR to GPS coordinate conversion logic or function) from the local coordinate system to a global coordinate system. The coordinate converter is optimized based on the transformed LIDAR images by adjusting one or more parameters of the coordinate converter and the above operations are iteratively performed to obtain a set of optimal parameters. The optimized coordinate converter can then be utilized to process subsequent LIDAR images during autonomous driving at real-time.