Cross-Sensor Auto-Calibration for Vehicle Sensors

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing vehicle sensors face challenges in self-calibration due to displacement and misalignment caused by collisions, vibrations, and loosening of mounting screws, requiring costly and inconvenient re-calibration methods that are not effective in various scenarios.

Innovation Solution

A cross-sensor auto-calibration process using a reference sensor to calibrate another sensor by comparing overlapping scenes and creating calibration parameters, allowing for real-time self-calibration of vehicle sensors while in operation, including the use of 3D localization and feature mapping.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional re-calibration methods are used at service centers, then sensor alignment accuracy can be restored, but vehicle downtime increases and operational convenience deteriorates

Engineering Contradiction:

Improvesensor alignment accuracyVSAvoidvehicle downtime

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system enables sensors to automatically self-calibrate using their own captured images and processing capabilities, eliminating the need for external service center intervention. The sensor compares its captured image with reference images from a database, automatically detects misalignment, and adjusts calibration parameters without human involvement.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Reference images of calibration targets are pre-captured and stored in a database before field operation. These reference images serve as the basis for subsequent automatic comparison and calibration decisions, allowing the sensor to quickly determine its alignment status without real-time external assistance.

Inventive Principle:

Principle #10Preliminary action

2Ease of operation

If self-calibration systems are implemented, then operational convenience improves and vehicle downtime reduces, but the system fails to operate effectively in many different scenarios

Engineering Contradiction:

Improvefield calibration capabilityVSAvoidscenario coverage

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system uses universally recognizable calibration targets (such as checkerboard patterns or specific geometric markers) that can be found in diverse environments. The image processing algorithms are designed to detect these targets under various lighting conditions, angles, and distances, making the calibration system adaptable to different scenarios including urban streets, rural roads, and parking areas.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The calibration process dynamically adapts to different operating conditions by adjusting image processing parameters based on detected scene characteristics. The system can handle varying lighting conditions, target distances, and camera angles by modifying its detection and measurement algorithms in real-time during the calibration process.

Inventive Principle:

Principle #15Dynamics

3Measurement precision

If sensors are frequently re-calibrated at service centers, then measurement precision is maintained, but loss of time and operational efficiency worsen

Engineering Contradiction:

Improvesensor calibration accuracyVSAvoidcalibration time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The sensor performs its own calibration using onboard image processing capabilities, eliminating the need to transport the vehicle to a service center. The entire calibration process occurs in-field using the sensor's own computational resources and pre-stored reference images, dramatically reducing calibration time.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The physical process of manual sensor adjustment and mechanical realignment at service centers is replaced by an automated image-based optical measurement system. The sensor captures images, processes them computationally to detect misalignment, and automatically adjusts calibration parameters, replacing time-consuming mechanical procedures with rapid digital processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20230314578A1Auto-calibrating a target sensor using scene mapping information from a reference sensor

Publication Date: 2023.10.05 RIVIAN HOLDINGS LLC

AI summary

Systems and methods for performing auto-calibration for a target sensor from information gained by a reference sensor, thereby enabling cross-sensor self-calibration for a set of sensors. A method includes the step of obtaining a first mapping of a first observable scene from a first scene sensing device and a second mapping of a second observable scene from a second scene sensing device. The first and second scene sensing devices are positioned on a test object (e.g., vehicle) in a substantially fixed relationship with respect to each other. The first and second observable scenes have common reference objects and/or overlapping portions. The method also includes comparing the common reference object and/or overlapping portion of the first mapping with the common reference object and/or overlapping portion of the second mapping to determine a difference. Also, the method includes creating calibration parameters, based on the difference, for calibrating the second scene sensing device.