Vehicle Sensor Calibration via Reference Feature Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Vehicle sensors can become out of calibration due to continuous use, shock, and vibration, leading to inaccurate data, which is challenging for users to detect and correct, especially in autonomous driving systems.

Innovation Solution

A sensor calibration system that uses processors and memory to determine if environment sensors can detect a predetermined number of viable reference features, and if not, suggests and generates instructions for arranging additional features to facilitate calibration, allowing for automatic recalibration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If vehicle sensors are used continuously for autonomous driving decisions, then the system provides automated driving capability, but the sensors fall out of calibration over time due to shock and vibration

Engineering Contradiction:

Improveautonomous driving capabilityVSAvoidsensor calibration accuracy

Core Design Contradiction:

Extent of automationVSReliability

Solution Approach 1:

The system performs preliminary calibration actions by capturing images of reference features at multiple known positions before actual driving operations. This preliminary calibration data is stored and used to correct sensor drift that occurs during operation, preventing calibration loss rather than reacting to it after it happens.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors sensor data against the stored reference feature positions and uses this feedback to detect when calibration drift occurs. When drift is detected, the system automatically initiates recalibration by capturing new reference feature images and updating the calibration parameters, creating a closed-loop feedback system that maintains sensor accuracy.

Inventive Principle:

Principle #23Feedback

2Measurement precision

If sensors are recalibrated at a dealer, then calibration accuracy is restored, but the user loses time and must transport the vehicle

Engineering Contradiction:

Improvesensor calibration accuracyVSAvoidvehicle downtime for calibration

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables the vehicle to perform its own calibration service by automatically detecting reference features in the environment, comparing their positions against stored calibration data, and adjusting sensor parameters accordingly. This eliminates the need for professional dealer intervention and allows calibration to be performed anytime the vehicle is in normal operation.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system pre-stores calibration data for multiple reference features at known positions during manufacturing or initial setup. This preliminary preparation enables rapid field recalibration by simply comparing current sensor readings against the pre-stored reference data, avoiding time-consuming calibration procedures at the dealer.

Inventive Principle:

Principle #10Preliminary action

3Reliability

If the system checks sensor calibration continuously, then calibration accuracy is maintained, but the computational load and processing time increase

Engineering Contradiction:

Improvesensor calibration accuracyVSAvoidcalibration system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

Instead of continuously analyzing all sensor data for calibration drift, the system performs partial calibration checks by selectively monitoring specific reference features or using simplified comparison algorithms. This reduces computational complexity while maintaining sufficient calibration accuracy for safe operation.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system pre-processes and stores reference feature data in optimized formats during manufacturing, including pre-calculated position relationships and comparison criteria. This preliminary preparation reduces the computational burden during operation, allowing rapid calibration checks without complex real-time processing.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11514681B2System and method to facilitate calibration of sensors in a vehicle

Publication Date: 2022.11.29 TOYOTA JIDOSHA KK

AI summary

A sensor calibration system for a vehicle includes one or more processors. The system also includes a memory communicably coupled to the one or more processors and storing a sensor calibration module including instructions that when executed by the one or more processors cause the one or more processors to, for an environment sensor of the vehicle, determine if the sensor can detect at least a predetermined number of viable reference features in an environment of the vehicle. The module also includes processor-executable instructions to, if the sensor cannot not detect at least a predetermined number of viable reference features, determine at least one suggested positional arrangement of viable reference features with respect to a current position the sensor. The module also includes processor-executable instructions to generate instructions to arrange viable reference features in the at least one suggested positional arrangement.