3D Neural Pruning of Complex Foliage With Heated Scissor Cutting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current agricultural practices face challenges in automating the pruning and harvesting of plants with complex morphologies, particularly in differentiating subtle variations in foliage health, maturity, and chemical composition, which hinders efficient robotic systems for tasks like trimming marijuana buds with intricate structures.

Innovation Solution

A robotic system utilizing a combination of stereoscopic cameras, neural networks, and a heated, spring-biased scissor-type cutting tool to analyze and trim complex plant structures by identifying low resin-density areas and adapting cutting operations based on depth, texture, and color data, overcoming issues of resin build-up and clogging.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated pruning systems are used for complex morphology foliage, then productivity is improved, but measurement precision deteriorates due to difficulty in differentiating subtle variations in foliage health, maturity, and chemical composition

Engineering Contradiction:

Improvepruning efficiencyVSAvoidfoliage differentiation accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system combines multiple sensing modalities (stereoscopic vision for 3D structure, thermal imaging for water content, hyperspectral imaging for chemical composition) into a single integrated measurement system. This merging of sensors allows the automated pruning system to accurately differentiate subtle variations in foliage health, maturity, and chemical composition while maintaining high productivity

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces machine learning algorithms as intermediaries that process and interpret data from multiple sensors. These algorithms differentiate between subtle variations in foliage characteristics by analyzing patterns across multiple data dimensions, enabling precise identification of pruning targets without sacrificing automation speed

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of operation

If standard cutting tools are used for resinous plants, then ease of operation is maintained, but reliability deteriorates due to resin build-up and clogging

Engineering Contradiction:

Improvetool operation simplicityVSAvoidcutting tool functionality

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system changes the temperature parameter of the cutting tool by applying localized heat to the blade surface. This thermal parameter change prevents resin from solidifying and clogging the cutting edges, maintaining tool reliability throughout the pruning operation while keeping the operation simple and automated

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The cutting tool implements periodic heating cycles during operation, applying thermal energy at regular intervals to prevent resin accumulation. This periodic thermal action maintains blade functionality without requiring continuous complex interventions, preserving ease of operation while ensuring reliability

Inventive Principle:

Principle #19Periodic action

3Measurement precision

If manual pruning methods are used, then measurement precision is maintained for identifying low resin-density areas, but productivity deteriorates due to high labor costs and time consumption

Engineering Contradiction:

Improveresin density differentiation accuracyVSAvoidprocessing speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system replaces manual visual inspection and mechanical decision-making with automated optical sensing and computational analysis. Multispectral and hyperspectral sensors capture detailed foliage characteristics, while machine learning algorithms automatically identify low resin-density areas, maintaining measurement precision while dramatically increasing processing speed and productivity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

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 system enables efficient and precise automated pruning and harvesting of complex plant morphologies, reducing human labor costs and improving the efficiency of agricultural operations by accurately differentiating and removing low resin-density areas, thus enhancing the processing of cannabis and other crops.

Implementation Method 1

a heated, spring-biased scissor-type cutting tool to analyze and trim complex plant structures

Methodology Applied

Scientific EffectHeating: Heating

Implementation Method 2

a heated, spring-biased scissor-type cutting tool

Methodology Applied

Scientific EffectSpring: Spring

Data Source

PatentUS11425866B2Automated pruning or harvesting system for complex morphology foliage

Publication Date: 2022.08.30 BURDEN KEITH CHARLES

AI summary

Method and apparatus for automated operations, such as pruning, harvesting, spraying and/or maintenance, on plants, and particularly plants with foliage having features on many length scales or a wide spectrum of length scales, such as female flower buds of the marijuana plant. The invention utilizes a convolutional neural network for image segmentation classification and/or the determination of features. The foliage is imaged stereoscopically to produce a three-dimensional surface image, a first neural network determines regions to be operated on, and a second neural network determines how an operation tool operates on the foliage. For pruning of resinous foliage the cutting tool is heated or cooled to avoid having the resins make the cutting tool inoperable.