Autonomous Work Machine Control for Camera Backlight Avoidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous work machines face challenges in recognizing external world information due to complex image processing requirements and issues with sunlight interference, as existing technologies either ignore or eliminate sunlight-affected image data, or plan routes to avoid direct sunlight, but do not effectively control the machine to avoid backlighting.

Innovation Solution

An autonomous work machine equipped with cameras and an electronic control unit that determines if backlighting has occurred and controls the machine to stop and adjust its path to avoid backlighting, using a determination unit and control unit to assess image data and execute backlight avoidance maneuvers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If image processing is applied to correct lane marker position under backlighting conditions, then lane recognition accuracy is improved, but image processing complexity increases

Engineering Contradiction:
Improvelane recognition accuracyVSAvoidimage processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

Instead of correcting the image when backlighting occurs, the invention inverts the approach by controlling the autonomous vehicle to avoid backlighting conditions. The system detects backlighting and adjusts travel direction or stops to prevent the camera from capturing images under backlighting conditions, thereby eliminating the need for complex correction processing.

Inventive Principle:
Principle #13The other way round (Inversion)

2Measurement precision

If the autonomous work machine stops to avoid backlighting, then image capture accuracy is improved, but travel time increases

Engineering Contradiction:
Improveimage capture accuracyVSAvoidtravel time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system dynamically adjusts the autonomous vehicle's travel behavior based on real-time backlighting detection. Rather than always stopping, the control unit determines whether to stop, change direction, or continue based on the severity and persistence of backlighting conditions, optimizing the balance between image quality and travel efficiency.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3874924B1Autonomous work machine, autonomous work machine control method, and program
Publication Date: 2023.08.09 HONDA MOTOR CO LTD
  • EP3874924B1 patent drawingFigure 1A~1B
  • EP3874924B1 patent drawingFigure 2
  • EP3874924B1 patent drawingFigure 3

AI summary

An autonomous work machine that includes a camera configured to capture an image of an external world, comprises a determination unit configured to determine, based on an image captured by the camera, whether backlighting has occurred, and a control unit configured to control, in a case in which the determination unit has determined that the backlighting has occurred, the autonomous work machine so as to avoid the backlighting.