Fruit Tree Cane Cut-Point Detection for Automated Pruning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Automating pruning work for fruit trees, particularly in vineyards, is challenging due to the need for comprehensive judgments on health status, sun exposure, and ventilation, which are difficult to replicate in unmanned systems.

Innovation Solution

A method and system for generating cut-point data using sensors to determine the three-dimensional position of canes to be cut or retained, considering attributes like color, thickness, and bud direction, and a controller to guide a cutter based on this data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated pruning systems are implemented, then productivity is improved, but the ability to make comprehensive judgments on health status, sun exposure, and ventilation deteriorates

Engineering Contradiction:
Improvepruning work efficiencyVSAvoidjudgment accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent replaces human mechanical judgment with sensor-based detection systems. Multiple sensors (cameras, LIDAR, environmental sensors) automatically detect and evaluate cane attributes such as color, thickness, position, and surrounding conditions, substituting human sensory and cognitive processes with automated electronic detection and analysis systems.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces a computer system as an intermediary between the physical cane characteristics and the pruning decision. The computer processes sensor data, applies pruning algorithms, and generates cut-point recommendations, serving as a mediator that translates raw sensor information into actionable pruning instructions without requiring direct human judgment.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Manufacturing precision

If multiple attributes are measured for each cane, then manufacturing precision is improved, but device complexity increases

Engineering Contradiction:
Improvecut-point accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent employs multi-functional sensors and a unified data processing system that handles multiple attributes (color, thickness, position, orientation, environmental conditions) through a single integrated platform. The same sensor array and computer system used for detection also perform evaluation, decision-making, and control functions, reducing the need for separate specialized devices for each measurement task.

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

Solution Approach 2:

The patent combines multiple sensing functions and data processing operations into an integrated system. Rather than using separate devices for each attribute measurement, the system merges camera, LIDAR, and environmental sensing capabilities into a unified detection platform that simultaneously captures and processes multiple cane attributes through coordinated sensor arrays and integrated software algorithms.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP4578270A1Method for generating cut point data, system for generating cut point data, and agricultural machine
Publication Date: 2025.07.02 KUBOTA CORP
  • EP4578270A1 patent drawingFigure 1
  • EP4578270A1 patent drawingFigure 2
  • EP4578270A1 patent drawingFigure 3A

AI summary

The invention concerns a method for using a computer or computers to generate cut-point data including information indicating a three-dimensional position of a point on a cane of a fruit tree where the cane is to be cut off includes, for each of one or more canes of the fruit tree, acquiring measurement values concerning two or more attributes, including an attribute concerning buds on the cane and an attribute other than buds (S236), based on sensor data of the one or more canes being acquired by a sensor or sensors, determining the one or more canes each as a cane to be removed or a cane to be retained based on the measurement values (S240), and generating the cut-point data for each cane determined as a cane to be removed (S300).