Vehicle Perception Sensor Pose Verification for Misalignment Detection

Solution Overview

Problem

Autonomous vehicles rely on accurate perception systems for safe navigation, but these systems can become misaligned due to damage or misplacement during maintenance, storage, or transport, necessitating a method to verify their accuracy before activation.

Innovation Solution

A method involving a vehicle traversing a path around a fixed target with a known pose to verify the accuracy of perception sensors by comparing the detected pose with the known pose, or using a target with a high-accuracy position solution to align perception sensors by comparing measured poses.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If perception sensors are installed on the autonomous vehicle, then the vehicle can detect objects in its environment for safe navigation, but the sensors can become damaged or misaligned during maintenance, storage, and transport

Engineering Contradiction:

Improveperception system accuracyVSAvoidsensor misalignment

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent performs accuracy verification of perception sensors before activating the autonomous vehicle's navigation system. A test vehicle traverses a predetermined path around a target with known pose, and the perception sensors capture images of the target at multiple positions. The system determines the target's pose from these images and compares it to the known pose to verify sensor alignment accuracy before allowing autonomous operation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements a feedback mechanism where the determined pose from perception sensor images is compared against the known reference pose of the target. This comparison provides feedback on the accuracy of the perception sensors, allowing the system to identify and correct misalignments before autonomous navigation is activated, ensuring reliable object detection.

Inventive Principle:

Principle #23Feedback

2Reliability

If the perception system is activated for navigation, then the autonomous vehicle can navigate safely, but the system may not detect misaligned sensors causing inaccurate object detection

Engineering Contradiction:

Improvenavigation safetyVSAvoidobject detection accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent performs accuracy verification of perception sensors before activating the autonomous vehicle's navigation system. A test vehicle traverses a predetermined path around a target with known pose, and the perception sensors capture images of the target at multiple positions. The system determines the target's pose from these images and compares it to the known pose to verify sensor alignment accuracy before allowing autonomous operation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements a feedback mechanism where the determined pose from perception sensor images is compared against the known reference pose of the target. This comparison provides feedback on the accuracy of the perception sensors, allowing the system to identify and correct misalignments before autonomous navigation is activated, ensuring reliable object detection.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If the vehicle traverses a path around a fixed target to verify sensor accuracy, then misalignments can be detected, but time is required for the verification process

Engineering Contradiction:

Improvesensor alignment verificationVSAvoidverification time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent captures images of the target at multiple predetermined positions along a traversal path, which may include more positions than strictly necessary for basic verification. This excessive sampling ensures comprehensive coverage of the sensor's field of view and provides redundant data for accurate pose determination, allowing robust verification while maintaining reasonable time efficiency through parallel processing.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20250269872A1Accuracy verification of a perception system of a vehicle

Publication Date: 2025.08.28 TRIMBLE INC

AI summary

A method of verifying accuracy of a perception system of a vehicle includes causing the vehicle to traverse a path around a target that is fixed in an environment. The target has a known pose. The path is configured so that the target comes into a respective field of view (FOV) of each respective perception sensor of one or more perception sensors of the perception system along the path. The method further includes, for each respective perception sensor of the one or more perception sensors, while the target is within the respective FOV of the respective perception sensor, acquiring a respective image of the target using the respective perception sensor; at the perception system, determining a respective pose of the target based on the respective image; and at a computer system communicatively coupled with the perception system, determining whether the respective pose matches the known pose of the target.