Camera-Based Lane Offset Control Using Leading Vehicle Cues

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current autonomous vehicle navigation systems face challenges in accurately identifying and responding to various environmental factors such as lane boundaries, obstacles, and traffic signals, which can lead to unsafe navigation and collisions.

Innovation Solution

A camera-based system that uses multiple cameras with different fields of view to perform monocular and stereo image analysis, enabling the vehicle to detect lane markings, obstacles, traffic signals, and other road features, and adjust its navigation accordingly, including lane offset and default lane selection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single camera is used for autonomous navigation, then device complexity is reduced, but measurement precision and reliability of environmental factor identification deteriorate

Engineering Contradiction:
Improvecamera system complexityVSAvoidlane boundary detection precision
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent combines multiple cameras (front-facing, side-facing, rear-facing) into an integrated imaging system that captures comprehensive environmental data. This merging of multiple sensing elements improves measurement precision for lane boundary detection and obstacle identification while maintaining systematic complexity through unified processing architecture

Inventive Principle:
Principle #5Merging (Combining)

2Measurement precision

If multiple cameras with different fields of view are used, then measurement precision and coverage are improved, but device complexity increases

Engineering Contradiction:
Improveobstacle detection precisionVSAvoidimage processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the imaging function across multiple cameras with specialized fields of view (front, side, rear) to optimize detection precision for different environmental factors. Each camera captures specific spatial zones, and the processing system segments analysis by vehicle orientation and environmental factor type, managing complexity through structured division of sensing and processing tasks

Inventive Principle:
Principle #1Segmentation

3Reliability

If real-time image analysis is performed, then navigation safety is improved, but processing time and computational resources increase

Engineering Contradiction:
Improvenavigation safetyVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by continuously capturing and pre-processing images from multiple cameras, pre-identifying potential environmental factors before critical navigation decisions are required. This allows real-time safety analysis by having processed data ready for immediate evaluation when navigation actions are needed

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3761223B1Adjusting lane offset autonomously
Publication Date: 2024.10.09 MOBILEYE VISION TECH LTD
  • EP3761223B1 patent drawingFigure 1
  • EP3761223B1 patent drawingFigure 2A
  • EP3761223B1 patent drawingFigure 2B

AI summary

Systems and methods use cameras to provide autonomous navigation features. In one implementation, a driver assist navigation system is provided for a primary vehicle. The system may include at least one image capture device configured to acquire a plurality of images of an area in a vicinity of the primary vehicle; a data interface; and at least one processing device. The at least one processing device may be configured to: locate in the plurality of images a leading vehicle; determine, based on the plurality of images, at least one action taken by the leading vehicle; and cause the primary vehicle to mimic the at least one action of the leading vehicle.