Robotic Broccoli Harvesting With RGB-D Crown Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual harvesting of broccoli plants is labor-intensive, costly, and inefficient due to the obscuration of broccoli crowns by leaf canopies, making it difficult for mechanical harvesters to accurately identify and cut the plants, and existing mechanical harvesters are expensive and inconsistent.

Innovation Solution

A robotic automated harvesting apparatus using an RGB depth camera and microcomputer software to identify and cut broccoli plants with dual opposed cutting blades, enabling autonomous movement and accurate cutting with ⅛-inch precision, and can be paired with devices to move leaves for unobstructed access.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If manual harvesting is used, then labor flexibility is maintained, but harvesting cost and time consumption increase significantly

Engineering Contradiction:

Improveharvesting costVSAvoidharvesting speed

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The patent replaces manual mechanical harvesting with an automated robotic system that uses computer vision and automated cutting mechanisms. The robotic harvester autonomously navigates, identifies broccoli crowns through image processing, and executes precise cuts, eliminating the need for human labor while maintaining high harvesting speed and accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The robotic harvester is designed to autonomously perform all harvesting operations without human intervention. The system self-navigates through the field, self-identifies target broccoli plants using onboard cameras and image processing algorithms, and self-executes the cutting and collection processes, making the entire system self-sufficient.

Inventive Principle:

Principle #25Self-service

2Extent of automation

If traditional mechanical harvesters are used, then harvesting automation is achieved, but equipment cost becomes prohibitively high for small farms

Engineering Contradiction:

Improveharvesting automationVSAvoidequipment cost

Core Design Contradiction:

Extent of automationVSEase of manufacture

Solution Approach 1:

The patent divides the harvesting system into modular, independent components: navigation module, vision processing module, cutting mechanism, and collection system. Each module can be independently developed, tested, and replaced, reducing overall system complexity and cost. This modular approach allows small farms to acquire automation capability without investing in expensive integrated traditional harvesters.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system uses adjustable parameters in the image processing algorithms and cutting mechanism to adapt to different broccoli varieties and growing conditions. By changing software parameters rather than hardware configurations, the system maintains versatility across different farm scenarios without requiring expensive reconfiguration, making automation accessible to small farms.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If broccoli crowns are obscured by leaf canopies, then identification accuracy decreases, but manual harvesting can still locate and cut plants

Engineering Contradiction:

Improvecrown identification accuracyVSAvoidharvesting efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent transitions from two-dimensional image analysis to three-dimensional spatial understanding by processing images from multiple camera angles and incorporating depth information. This multi-dimensional approach allows the system to penetrate leaf canopies, identify crowns hidden from single-view perspectives, and accurately locate targets even when obscured, thereby maintaining high identification accuracy and harvesting efficiency simultaneously.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

4Manufacturing precision

If cutting precision is increased to ⅛-inch accuracy, then product uniformity improves, but system complexity and cost increase

Engineering Contradiction:

Improvecut length uniformityVSAvoidsystem complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent replaces complex mechanical precision positioning systems with software-based image processing and computer vision algorithms. The system uses digital image analysis to calculate precise cutting positions and controls motors to execute cuts with ⅛-inch accuracy, eliminating the need for complex mechanical measurement and positioning mechanisms while achieving superior cutting uniformity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11343967B1Robotic automation of mechanical field harvesting of broccoli plants

Publication Date: 2022.05.31 CV ROBOTICS BOOSTER CLUB

AI summary

A robotic automated broccoli plant harvesting apparatus uses a vision system implemented with an RGB depth camera that provides imaging signals. Software operating on a microcomputer processes the imaging signals to identify the height and position of a broccoli plant to sever it with dual opposed cutting blades. In a preferred embodiment, the software algorithm combines color, texture, and distance information of the broccoli plant to reliably cut the broccoli stalk with ⅛-inch (3.175-millimeter) accuracy. Broccoli stalks of consistent lengths result in uniform, commercially viable products.