Extrinsic Sensor Calibration via 3D Scanning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in accurately calibrating environmental sensors such as LiDAR and cameras due to difficulties in determining sensor positions, especially after vehicle collisions, manufacturing tolerance errors, and during retrofitting or repair scenarios, where precise sensor-to-sensor positioning is hard to achieve.

Innovation Solution

The method involves identifying a vehicle coordinate origin through data collection and analysis, followed by a 3D scan using external scanners like stereo cameras or laser scanning technologies to accurately localize sensor positions, facilitating extrinsic sensor calibration without relying on intrinsic measurements or precise vehicle positioning.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If intrinsic measurements or precise vehicle positioning are used for sensor calibration, then measurement precision is improved, but device complexity and ease of operation deteriorate

Engineering Contradiction:

Improvesensor position accuracyVSAvoidcalibration system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an external scanner as an intermediary device that captures images of the vehicle and sensors from outside the vehicle. This mediator enables precise sensor localization without requiring complex internal measurement systems or precise vehicle positioning equipment, thus resolving the contradiction between measurement precision and device complexity

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent creates a digital copy or representation of the vehicle and sensor positions through external imaging and processing. By capturing images and generating a processed image with sensor locations rather than using complex physical measurement equipment, the system achieves accurate sensor positioning while reducing device complexity

Inventive Principle:

Principle #26Copying

2Measurement precision

If traditional sensor calibration methods are used, then measurement precision is improved, but productivity deteriorates

Engineering Contradiction:

Improvesensor calibration accuracyVSAvoidcalibration process efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent performs preliminary actions by capturing multiple images of the vehicle and sensors before processing. The external scanner collects image data in advance, and the system processes these pre-captured images to determine sensor positions, enabling quick and accurate calibration without time-consuming traditional methods

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces complex mechanical positioning and measurement systems with an optical imaging system. By using external cameras to capture images and processing these images computationally to determine sensor positions, the system achieves both high precision and high productivity, eliminating the need for time-consuming mechanical calibration procedures

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If sensor positions are determined after vehicle collisions or during retrofitting, then adaptability is improved, but measurement precision deteriorates

Engineering Contradiction:

Improvecalibration flexibilityVSAvoidsensor-to-sensor positioning accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent inverts the traditional calibration approach by having the external scanner capture images of the vehicle and sensors from outside, then processing these images to determine sensor positions relative to each other. This inverted approach works equally well for new vehicles, collision-damaged vehicles, and retrofitted vehicles, providing both adaptability and precision by eliminating the need for precise vehicle positioning or intrinsic measurements

Inventive Principle:

Principle #13The other way round (Inversion)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enables quick and accurate sensor localization, streamlining the calibration process and improving efficiency in various use cases, including sensor retrofits and repairs, by providing precise location information for environmental sensors.

Implementation Method 1

a 3D scan using external scanners like stereo cameras or laser scanning technologies to accurately localize sensor positions

Methodology Applied

Scientific EffectLight reflection: Reflection

Implementation Method 2

external scanners like stereo cameras or laser scanning technologies

Methodology Applied

Scientific EffectStereo vision: Parallax

Data Source

PatentUS11429757B2Sensor calibration via extrinsic scanning

Publication Date: 2022.08.30 GM CRUISE HOLDINGS LLC

AI summary

The subject technology provides solutions for performing extrinsic sensor calibration for vehicle sensors, such as environmental sensors deployed in an autonomous vehicle (AV) context. In some aspects, the disclosed technology relates to a sensor localization system that is configured to: perform a scan, using a 3D scanner, to collect surface data associated with an autonomous vehicle (AV), analyze the surface data to identify a coordinate origin of the AV, and calculate a position of at least one or more AV sensors based on the surface data. Methods and computer-readable media are also provided.