Crop-Row Navigation Control for GNSS-Denied Turning Travel

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In high-density tree or crop environments, such as vineyards or orchards, the leaf canopies act as obstacles and multiple reflectors for radio waves, hindering accurate Global Navigation Satellite System (GNSS) positioning. Additionally, seasonal changes in leaf distribution render pre-created maps ineffective for autonomous vehicle navigation.

Innovation Solution

A work vehicle equipped with exterior sensors, such as LiDAR, to detect the distribution of geographic features and a controller that enables self-traveling by detecting crop rows, setting a turning coordinate system, and controlling the vehicle to travel along a path between the rows, while adapting to changing environmental conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If GNSS positioning is used for autonomous navigation, then positioning accuracy is improved, but it becomes ineffective in high-density tree environments with leaf canopies that block and reflect radio waves

Engineering Contradiction:

Improvepositioning accuracyVSAvoidenvironmental adaptability

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent introduces LiDAR sensors as an intermediary positioning method that operates independently of radio wave conditions. The LiDAR-based SLAM system creates local maps and determines vehicle position based on geometric features of the environment rather than satellite signals, enabling navigation in GNSS-denied environments like dense orchards and forests

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically switches between GNSS and LiDAR-based positioning modes based on environmental conditions. When GNSS signal quality deteriorates due to canopy interference, the system transitions to using LiDAR distance measurements and local feature mapping, changing the fundamental positioning parameters from satellite-based coordinates to sensor-based relative positioning

Inventive Principle:

Principle #35Parameter changes

2Productivity

If pre-created maps are used for autonomous travel, then navigation efficiency is improved, but seasonal changes in leaf distribution render the maps ineffective

Engineering Contradiction:

Improvenavigation efficiencyVSAvoidseasonal adaptability

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamic map update mechanism where the LiDAR system continuously creates and updates local maps during vehicle operation. Rather than relying on static pre-created maps, the system adapts to seasonal changes by generating current environmental representations, allowing the navigation system to remain effective throughout different growing seasons

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system performs preliminary scanning and map creation in advance of navigation tasks. By continuously building and updating local maps of the environment using LiDAR, the system prepares navigation data that reflects current seasonal conditions, enabling efficient autonomous travel adapted to the present state of crop rows and vegetation

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If SLAM is used for positioning in GNSS-denied environments, then autonomous travel becomes possible, but the system fails when tree leaf distribution changes significantly with seasons

Engineering Contradiction:

Improveenvironmental adaptabilityVSAvoidpositioning reliability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The LiDAR-based SLAM system continuously compares sensor measurements with the stored local map to determine vehicle position and orientation. This feedback mechanism allows the system to detect changes in environmental features due to seasonal variations and automatically update its positioning calculations, maintaining reliability despite changes in leaf distribution

Inventive Principle:

Principle #23Feedback

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution allows for smooth self-traveling among multiple crop rows in challenging environments where GNSS positioning is difficult, ensuring accurate navigation and adaptability to seasonal changes.

Implementation Method 1

exterior sensors, such as LiDAR, to detect the distribution of geographic features

Methodology Applied

Scientific EffectLiDAR: LIDAR

Data Source

PatentEP4541161A1Work vehicle and method for controlling work vehicle

Publication Date: 2025.04.23 KUBOTA CORP

Figure 1
Figure 2
Figure 3A~3B

AI summary

A work vehicle performs self-traveling among a plurality of crop rows. The work vehicle includes: an exterior sensor to output sensor data indicating a distribution of geographic features around the work vehicle; and a controller to control self-traveling of the work vehicle. The controller detects two crop rows existing on opposite sides of the work vehicle based on the sensor data, and causes the work vehicle to travel along a path between the two crop rows. During travel, if an end of at least a crop row that corresponds to a turning direction between the two crop rows is detected based on the sensor data, the controller sets a coordinate system for turning travel that is fixed to a ground surface and a target point for the turning travel. The controller controls the turning travel toward the target point based on the coordinate system.