3D Vehicle Imaging for Row-End Detection in GPS-Degraded Fields

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle control systems face challenges in maintaining precise navigation, especially in areas with degraded GPS signals due to obstructions like trees and buildings, and struggle with accuracy in identifying row boundaries and vehicle position using imaging systems, which can drift and be affected by varying objects in the field.

Innovation Solution

A control system that combines 3-D image data, visual odometry (VO) data, and global navigation satellite system (GNSS) data to accurately steer a vehicle, using 3-D sensors like stereo cameras or LIDAR, and inertial navigation systems to determine vehicle position and orientation, even in areas with limited GPS availability, by generating electronic maps and simultaneous localization and mapping (SLAM) to correct for drift and identify row boundaries and obstacles.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If wheel odometry and inertial navigation systems are used to maintain GPS position, then vehicle positioning can be maintained in degraded GPS areas, but the system complexity increases and positioning accuracy deteriorates over time due to drift

Engineering Contradiction:
Improvevehicle positioning reliabilityVSAvoidnavigation system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple navigation systems (GNSS, visual odometry, inertial navigation) into a unified navigation system that integrates their respective strengths. The system merges GPS data with image-based visual odometry and inertial sensor data to maintain reliable positioning in degraded GPS areas without relying solely on one system, thereby reducing overall system complexity while maintaining reliability.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces an intermediary integration module that processes and reconciles data from multiple navigation sources. This mediator component combines GNSS positions with visual odometry estimates and inertial navigation data, allowing the system to maintain accurate positioning in degraded GPS areas without directly coupling the complexity of all subsystems, thus managing system complexity while improving reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If imaging systems are used to identify row boundaries and vehicle position, then navigation can be maintained without GPS, but accuracy deteriorates due to drift and varying objects in the field

Engineering Contradiction:
Improvenavigation availabilityVSAvoidposition identification accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent implements feedback mechanisms where the system continuously monitors positioning accuracy from multiple sources and adjusts its reliance on each system accordingly. When visual odometry shows signs of drift or when GPS becomes available, the system provides feedback to correct position estimates, thereby maintaining measurement precision while ensuring navigation availability in GPS-denied environments.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent merges imaging-based visual odometry with GNSS and inertial navigation systems to create a composite positioning solution. By combining these systems, the patent maintains navigation availability when GPS is degraded while correcting the measurement precision issues of visual odometry through integration with more accurate reference systems when available.

Inventive Principle:
Principle #5Merging (Combining)

3Reliability

If 3-D image data is used to identify rows and obstacles, then navigation can proceed in degraded GPS areas, but the system requires additional sensors increasing complexity

Engineering Contradiction:
Improvenavigation continuityVSAvoidsensor system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent makes the 3-D imaging system multi-functional by using it for multiple purposes: identifying row boundaries for navigation, detecting obstacles for avoidance, and providing visual odometry data for positioning. This universal use of the imaging system justifies the added complexity by eliminating the need for separate specialized sensors for each function, thereby maintaining navigation continuity without proportionally increasing system complexity.

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

Solution Approach 2:

The patent combines the functions of row identification, obstacle detection, and position estimation into a single integrated imaging system. By merging these functions into one multi-purpose sensor system rather than using separate specialized sensors, the patent maintains navigation continuity in degraded GPS areas while managing the overall sensor system complexity through functional integration.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3642683B13-d image system for vehicle control
Publication Date: 2022.12.14 AGJUNCTION LLC
  • EP3642683B1 patent drawingFigure 1
  • EP3642683B1 patent drawingFigure 2
  • EP3642683B1 patent drawingFigure 3

AI summary

A control system uses visual odometry (VO) data to identify a position of the vehicle while moving along a path next to the row and to detect the vehicle reaching an end of the row. The control system can also use the VO image to turn the vehicle around from a first position at the end of the row to a second position at a start of another row. The control system may detect an end of row based on 3-D image data, VO data, and GNSS data. The control system also may adjust the VO data so the end of row detected from the VO data corresponds with the end of row location identified with the GNSS data.