Lane Keeping Control Error Detection via Vehicle State Correlation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional lane keeping systems are prone to erroneous control due to degraded lane recognition performance from varying road environments and climate conditions, leading to potential accidents and hindering widespread adoption.

Innovation Solution

A system that generates lane parameters and analyzes time flow-related correlations between camera-acquired lane data and vehicle state information to determine erroneous detection, using an equivalent model to classify errors and adjust torque control factors to mitigate erroneous torque influences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If lane recognition is performed using camera-based systems, then lane keeping control can be implemented, but the system becomes vulnerable to erroneous detection under varying road environments and climate conditions

Engineering Contradiction:
Improvelane keeping control reliabilityVSAvoidlane parameter detection accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The system establishes equivalent models that represent normal vehicle behavior patterns and continuously compares actual vehicle state information against these models. When deviations exceed threshold values, the system identifies erroneous lane parameter detection and adjusts torque control factors accordingly, creating a closed-loop feedback mechanism that maintains reliability despite environmental variations

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent introduces vehicle state information (acceleration, yaw rate, steering angle) as an intermediary element to verify lane parameter accuracy. Instead of directly trusting camera-based lane detection, the system uses vehicle dynamic responses as a mediator to cross-validate lane parameter correctness, filtering out erroneous detections caused by environmental factors

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If torque control factors are applied based on lane parameters, then lane keeping assistance is provided, but erroneous torque may be applied when lane data is abnormal

Engineering Contradiction:
Improvelane keeping assistanceVSAvoiderroneous torque influence
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary verification of lane parameter accuracy by comparing vehicle state information against equivalent models before applying torque control. This advance checking prevents erroneous torque application by identifying detection errors in advance, allowing the system to adjust torque control factors or disable assistance when lane data is determined to be abnormal

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9469343B2System, method, and computer-readable recording medium for lane keeping control
Publication Date: 2016.10.18 HL KLEMOVE CORP
  • US9469343B2 patent drawing
  • US9469343B2 patent drawing
  • US9469343B2 patent drawing

AI summary

A lane keeping control system includes: a lane parameter generation unit configured to generate a relative position between a lane and a vehicle as a lane parameter based on information received from a camera installed on the vehicle; a vehicle state information reception unit configured to receive vehicle state information sensed or measured by each vehicle sensor or device installed on the vehicle; an equivalent model generation unit configured to receive the lane parameter from the lane parameter generation unit, receive the vehicle state information from the vehicle state information reception unit, analyze a time flow-related correlation between the vehicle parameter and the vehicle state information, and generate an equivalent model of each; an erroneous detection determination unit configured to determine and classify a situation of erroneous detection of a lane parameter by simultaneously analyzing a case.