Multi-Attribute Cut-Point Data for Automated Fruit Tree Pruning
Find Innovative SolutionsGenerate 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 automated systems.
Innovation Solution
A method and system for generating cut-point data that includes grouping canes based on sensor data, determining which canes to remove or retain, and controlling a cutter's three-dimensional position using generated data, incorporating attributes like color, thickness, and bud direction to optimize pruning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual pruning is performed by human workers, then comprehensive judgment on health status, sun exposure, and ventilation can be made, but labor intensity and time consumption are high
Solution Approach 1:
The patent replaces manual visual inspection and judgment with automated sensing systems including cameras, LIDAR, and other sensors that capture multi-dimensional data about cane health, sun exposure, and ventilation conditions. This substitution enables objective, quantifiable measurements of pruning criteria without human labor
Solution Approach 2:
The system creates digital replicas and models of the fruit tree canopy structure, cane positions, and environmental conditions through sensor data. These digital copies allow for virtual analysis and optimization of pruning decisions before actual execution, enabling comprehensive judgment without time-consuming manual inspection
2Productivity
If automated pruning is implemented, then productivity increases, but the ability to make comprehensive judgments on health status, sun exposure, and ventilation deteriorates
Solution Approach 1:
The automated pruning system integrates multiple sensing modalities (visual, spatial, environmental) into a single multi-functional platform that simultaneously assesses health status, sun exposure, and ventilation conditions. This universal system performs comprehensive judgments across all pruning criteria without requiring separate manual assessments for each factor
Solution Approach 2:
The system introduces AI algorithms and data processing intermediaries that bridge the gap between raw sensor data and pruning decisions. These intermediaries analyze sensor inputs, apply pruning expertise rules, and generate optimized cutting recommendations, enabling automated systems to make judgment-accurate decisions at high speed
3Manufacturing precision
If multiple attributes of canes are measured for precise pruning, then pruning quality improves, but system complexity and measurement difficulty increase
Solution Approach 1:
The patent combines multiple measurement functions into integrated sensor systems. A single automated pruning system simultaneously captures visual data, spatial coordinates, health indicators, and environmental conditions through merged sensor arrays, reducing the need for separate measurement devices while maintaining multi-attribute assessment capabilities
Solution Approach 2:
The system performs preliminary scanning and data collection of all cane attributes before pruning decisions are made. By pre-capturing comprehensive data about cane position, health, orientation, and environmental context, the system simplifies the actual pruning execution phase while ensuring all necessary measurement information is already available for precise decision-making
Data Source
Figure 1
Figure 2
Figure 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 based on sensor data of the one or more canes being acquired by a sensor or sensors (S230), acquiring information on priority levels of the two or more attributes (S250), determining the one or more canes each as a cane to be removed or a cane to be retained based on the measurement values and the priority levels (S252), and generating the cut-point data for each cane determined as a cane to be removed (S300).