Sensor Error Handling for Autonomous Vehicle Navigation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current sensor calibration methods for autonomous vehicles are inefficient, as they require frequent recalibration and continuous data processing, leading to a computational burden and potential errors due to spectral distribution and optical phenomena, limiting navigation capabilities.

Innovation Solution

A system and method for determining sensor calibration status and implementing error handling, which includes selecting from options like initiating a backup sensor, recalibrating, or eliminating erroneous data, based on factors such as system load, sensor history, and environmental conditions, to minimize computational load and ensure accurate navigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If continuous sensor data collection and processing is performed, then navigation accuracy is improved, but computational burden increases

Engineering Contradiction:
Improvenavigation accuracyVSAvoidcomputational burden
Core Design Contradiction:
Measurement precisionVSPower

Solution Approach 1:

The system performs selective error handling only when calibration errors are detected, rather than continuously processing all sensor data. The error handling system activates based on validation results, eliminating unnecessary computational operations when sensors are functioning correctly.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system implements a feedback loop where sensor data is validated against calibration parameters, and error handling actions are triggered based on validation results. This closed-loop approach ensures computational resources are allocated only when needed to maintain navigation accuracy.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If frequent sensor recalibration is performed, then measurement accuracy is improved, but system availability decreases

Engineering Contradiction:
Improvesensor calibration accuracyVSAvoidsystem availability
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system performs validation checks continuously in the background to detect calibration errors before they significantly impact navigation accuracy. This allows recalibration to be initiated at optimal times rather than forcing frequent interruptions to maintain accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The error handling system dynamically selects from multiple strategies (backup sensor activation, recalibration scheduling, data elimination) based on current system conditions, allowing flexible response that maintains both accuracy and availability.

Inventive Principle:
Principle #15Dynamics

3Reliability

If multiple error handling options are available, then system reliability is improved, but device complexity increases

Engineering Contradiction:
Improvesystem reliabilityVSAvoiderror handling complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The error handling system automatically selects and executes appropriate error handling strategies based on validation results and system conditions, without requiring manual intervention. This self-service approach maintains reliability while managing complexity through automated decision-making.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The error handling system acts as an intermediary layer between sensor validation and navigation processing, managing multiple error handling strategies through a unified interface that abstracts the complexity from the main navigation system.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS11899140B2System and method for error handling of an uncalibrated sensor
Publication Date: 2024.02.13 PONY AI INC
  • US11899140B2 patent drawing
  • US11899140B2 patent drawing
  • US11899140B2 patent drawing

AI summary

Provided herein is a system and method for determining whether a sensor is calibrated and error handling of an uncalibrated sensor. The system comprises a sensor system comprising a sensor and an analysis engine configured to determine whether the sensor is uncalibrated. The system further comprises an error handling system configured to perform an error handling in response to the sensor system determining that the sensor is uncalibrated. The method comprises determining, by a sensor system, whether the sensor is uncalibrated, and performing, by an error handling system, an error handling in response to the sensor system determining that the sensor is uncalibrated.