De-Leafing and Imaging for Selective Broccoli Crown Harvest
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Harvesting vegetable crops, such as cauliflower and broccoli, is labor-intensive, inefficient, and prone to bruising or damage due to manual handling and inconsistent automated systems that struggle with varying plant conditions and separation of edible from non-edible portions.
Innovation Solution
A harvester equipped with imaging systems, robotic arms, and machine learning algorithms to identify mature edible crowns, remove leaves, and selectively harvest them using robotic end effectors, while navigating through fields with GPS guidance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual harvesting is used, then workers can visually inspect each plant to determine readiness for harvesting, but the process becomes labor-intensive and inefficient
Solution Approach 1:
The patent replaces the manual visual inspection system with an automated imaging and machine learning system. Cameras capture images of crop plants, and machine learning models analyze these images to determine harvest readiness, replacing the mechanical action of human workers visually inspecting each plant while maintaining accurate detection of harvestable portions
Solution Approach 2:
The system enables the harvesting process to self-regulate through automated detection and decision-making. The imaging system and machine learning algorithms independently assess plant readiness and guide the robotic harvesting mechanism without requiring human intervention for each plant assessment, thereby improving both efficiency and consistency
2Ease of operation
If manual handling is used, then workers can handle each plant individually, but bruising or damage occurs due to multiple handling stages
Solution Approach 1:
The system performs preliminary detection and identification of harvest-ready plants before the harvesting action occurs. The imaging system captures images and the machine learning model determines readiness in advance, allowing the robotic system to plan a single-pass harvesting approach that minimizes handling stages and reduces damage to the crop
Solution Approach 2:
The patent introduces a robotic harvesting mechanism as an intermediary between detection and collection. This robotic system with specialized end effectors gently grasps and transfers plants in a controlled manner, replacing multiple manual handling stages with a streamlined automated process that reduces mechanical damage and bruising
3Extent of automation
If conventional automated harvesting techniques are used, then harvesting can be automated, but challenges remain in observing harvestable portions and separating edible from non-edible portions
Solution Approach 1:
The patent segments the harvesting task into distinct functional components: an imaging system for capturing plant images, a machine learning model for analyzing images and identifying harvestable portions, and a robotic system with specialized end effectors for execution. This segmentation allows each component to be optimized for its specific function, improving overall detection precision and automation capability
Solution Approach 2:
The machine learning model analyzes multiple parameters from the captured images including color, shape, size, and texture of different plant portions to determine harvest readiness. By evaluating multiple parameters simultaneously, the system achieves high precision in identifying edible versus non-edible portions, overcoming limitations of conventional automated systems that rely on simpler detection methods
4Productivity
If conventional automated harvesting is used, then some automation benefits are achieved, but additional manual processing is still required, negating some benefits
Solution Approach 1:
The robotic harvesting system is designed with multi-functional end effectors that can perform multiple operations: gentle grasping of plants, precise cutting or separation of harvestable portions, and careful placement into collection containers. This multi-functionality allows a single automated system to complete the entire harvesting process without requiring subsequent manual processing steps, achieving both high productivity and complete automation
Data Source
AI summary
A harvester selectively harvests edible crowns ready for harvesting. The harvester may include an imaging system for capturing image(s) of the edible crowns and a de-leafing component that removes leaves of the broccoli plant. For example, broccoli plants typically have an abundance of leaves that reside beneath, alongside of, and even above the edible crowns. The leaves may conceal the edible crowns and impact a quality of the image(s). The de-leafing component may be positioned in front of the imaging system, relative to a direction of travel of the harvester, to remove the leaves and isolate or expose the edible crown. Therein, the imaging system may image the edible crowns for use in determining whether the edible crowns are ready for harvesting.