Autonomous Vehicle Sensor Calibration Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately calibrating relationships between different onboard sensors, such as cameras and lidar, due to varying sampling rates and viewpoints, which can lead to inaccurate environmental data and potential anomalous conditions affecting vehicle control.
Innovation Solution
A method and system for detecting stationary conditions to correlate edge regions from imaging and ranging data, validating transformation parameter values, and initiating remedial actions when anomalous conditions are detected, ensuring accurate calibration and operation of sensors like cameras and lidar.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple different types of sensing devices are used to analyze the environment, then the ability to accurately establish correlations between different types of data is improved, but the device complexity increases
Solution Approach 1:
The patent introduces calibration target objects with known geometric features as intermediaries between the imaging device and ranging device. These targets serve as reference mediators that enable accurate correlation between different sensor types by providing common geometric features (edges, corners) that can be detected by both sensors and used to compute transformation parameters.
Solution Approach 2:
The system dynamically adjusts transformation parameters (rotation, translation, scaling) based on detected calibration targets and computes optimal sampling rates for different devices. The parameters are changed adaptively to maintain accurate spatial correlation between imaging and ranging data despite varying operating conditions.
2Productivity
If devices operate at different sampling rates, then the productivity of data collection is improved, but the measurement precision of correlated data deteriorates
Solution Approach 1:
The system dynamically adjusts the sampling rates of different sensing devices based on their respective roles and data collection needs. The imaging device and ranging device operate at different, optimized sampling rates rather than being synchronized, allowing each to collect data at its optimal rate while the calibration correlation process integrates these asynchronous data streams.
Solution Approach 2:
The system performs preliminary calibration by detecting calibration targets and computing transformation parameters before processing actual environmental data. This preliminary action establishes the spatial relationship between devices, enabling accurate correlation of subsequently collected data even when sampled at different rates.
3Reliability
If calibration verification is performed continuously, then the reliability of autonomous vehicle operation is improved, but the use of computational resources increases
Solution Approach 1:
The system performs calibration verification periodically by detecting stationary conditions and checking whether calibration parameters remain valid, rather than continuously processing calibration data. The controller monitors for stationary events and triggers calibration verification only at these periodic intervals, reducing computational load while maintaining reliability.
Solution Approach 2:
The system extracts and processes only the essential calibration verification data during stationary conditions, rather than processing all sensor data continuously. By focusing computation only on calibration-related data during appropriate moments, the system maintains accuracy while minimizing resource consumption.
4Measurement precision
If edge region correlation is used for calibration validation, then the measurement precision of transformation parameters is improved, but the difficulty of detecting and measuring increases
Solution Approach 1:
The system segments the image and ranging data into distinct edge regions for calibration analysis. By focusing computation on specific edge features (horizontal edges in images, corresponding edges in ranging data) rather than processing entire data sets, the system achieves precise transformation parameter validation while managing computational complexity through selective analysis.
Data Source
AI summary
Systems and method are provided for controlling a vehicle. In one embodiment, a vehicle includes a camera onboard the vehicle, a lidar device onboard the vehicle, a data storage element onboard the vehicle maintaining one or more transformation parameter values associated with a pairing of the camera and the lidar device, one or more sensors onboard the vehicle, and a controller. The controller detects a stationary condition based on output of the one or more sensors, obtains a first set of image data from the camera during the stationary condition, filters horizontal edge regions from the first set, obtains a second set of the ranging data during the stationary condition, and validates the one or more transformation parameter values based on a relationship between the filtered set of the image data and the second set of the ranging data.