Lane Keeping Controller Sensor Switching Logic

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current environmental sensing systems for vehicle lane position detection in autonomous vehicles face reliability issues due to poorly marked lane markers and sun glare, leading to temporary disengagement of autonomous control and reliance on secondary sensors, which is not a reliable long-term solution.

Innovation Solution

The system employs a controller that switches from a primary sensor to a secondary sensor if the primary sensor cannot provide desired lane marker confidence, using a control algorithm and filter to determine lane marker edges and similarity with previous data, and returns steering control to the driver if the secondary sensor data is not reliable within a predetermined time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a primary sensor (front facing camera) is used for lane position detection, then the system can provide accurate lane marker detection under normal conditions, but the sensor becomes unreliable when affected by sun glare or poor lane markings

Engineering Contradiction:
Improvelane marker detection accuracyVSAvoidsensor reliability under glare conditions
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The system merges data from multiple sensors (primary front-facing camera and secondary side/rear cameras) to detect lane markers. When the primary sensor fails due to glare, the system seamlessly transitions to using secondary sensors, combining their data to maintain continuous lane position detection capability.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system implements multi-functionality by enabling secondary sensors to serve dual purposes: normal operation assistance and emergency takeover when primary sensor fails. The same sensor array that provides enhanced field of view also serves as a backup system, eliminating single points of failure.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Reliability

If the system switches to secondary sensors when primary sensor fails, then continuous lane position control can be maintained, but the system complexity increases due to sensor switching logic and data fusion requirements

Engineering Contradiction:
Improvecontinuous autonomous controlVSAvoidsensor switching and data fusion complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system dynamically adjusts sensor configuration based on operational conditions. The controller continuously monitors primary sensor reliability and automatically reconfigures the active sensor set, transitioning from primary-only mode to secondary-backup mode when needed, and managing this dynamic switching through standardized data fusion protocols.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements feedback mechanisms where the controller continuously evaluates lane marker confidence from the primary sensor and automatically triggers sensor switching when confidence thresholds are not met. This closed-loop feedback ensures reliable autonomous control while managing system complexity through rule-based decision logic.

Inventive Principle:
Principle #23Feedback

3Reliability

If multiple sensors are used to provide overlapping images for lane marker recognition, then reliability under sun glare improves, but the processing time and computational load increase

Engineering Contradiction:
Improvelane marker recognition under glareVSAvoidprocessing time for multiple sensor data
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by continuously capturing and pre-processing images from all sensors, maintaining a buffer of pre-processed data ready for immediate analysis. When lane marker confidence drops below thresholds, the system can immediately utilize pre-processed secondary sensor data without additional processing delays.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system applies local quality optimization by processing only the relevant portions of sensor data needed for lane detection. Rather than fully processing all image data from multiple sensors, the system focuses computational resources on extracting lane marker information from critical regions, reducing overall processing time while maintaining detection reliability.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3257729B1Lane keeping system for autonomous vehicle during camera drop-outs
Publication Date: 2019.08.07 APTIV TECHNOLOGIES LTD
  • EP3257729B1 patent drawingFigure 1a
  • EP3257729B1 patent drawingFigure 1b
  • EP3257729B1 patent drawingFigure 2

AI summary

An environmental sensing system (16) relating to vehicle (10) lane (12) position includes first and second sensors (18, 20) respectively configured to provide first and second signals (26) indicative of a vehicle (10) lane (12) position. A steering system achieves a desired lane (12) position in response to a command from a controller to keep the vehicle (10) in its lane (12), for example, during autonomous control of the vehicle (10). The controller uses the first signal if the first sensor (18) provides a desired lane (12) marker confidence. The controller switches to the second sensor (25) and uses the second signal if the first sensor (18) cannot provide the desired lane (12) marker confidence and the second sensor (25) can provide the desired lane (12) marker confidence.