Robotic Harvester Selective Crown Harvesting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated and semi-automated vegetable harvesting systems face challenges in accurately identifying and harvesting edible portions of plants like broccoli due to variations in size, shape, and field conditions, often requiring additional manual processing and resulting in inefficiencies, waste, and damage.
Innovation Solution
A harvester system equipped with imaging components, machine learning models, and robotic arms that use imaging systems to determine the maturity of edible crowns, remove leaves, and selectively harvest them, featuring a de-leafing component, imaging system, and end effectors with cutting mechanisms for precise harvesting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual harvesting is used, then workers can visually inspect and selectively harvest mature plants, but the process is labor-intensive and inefficient
Solution Approach 1:
The patent replaces manual visual inspection and harvesting with an automated system using imaging devices (optical sensors) to detect mature plants and robotic mechanisms to perform harvesting. This substitution of mechanical/manual operations with automated sensing and actuation systems directly resolves the contradiction by improving productivity while managing complexity through integration.
Solution Approach 2:
The harvesting system performs its own inspection and decision-making functions through integrated imaging devices and processing systems that automatically identify mature plants without human intervention. The system serves itself by combining detection, analysis, and harvesting functions in one autonomous unit, improving efficiency while containing complexity within a self-contained platform.
2Extent of automation
If conventional automated harvesting is used, then labor is reduced, but additional manual processing is still required
Solution Approach 1:
The robotic harvesting system is designed with multi-functional capabilities that perform inspection, harvesting, and initial sorting/processing in one integrated operation. The robotic mechanisms can adapt to different plant types and harvesting requirements, providing universal functionality that eliminates the need for separate manual processing stages while maintaining high automation levels.
3Productivity
If multiple handling stages are used in harvesting, then plants can be processed, but bruising or damage occurs
Solution Approach 1:
The patent combines multiple handling operations (inspection, harvesting, and initial processing) into a single integrated robotic system that operates in one coordinated motion. By merging these stages into one continuous operation rather than separate handling steps, the system maintains productivity while minimizing plant damage through reduced manipulation and smoother transitions between functions.
Solution Approach 2:
The imaging devices and processing systems perform preliminary identification and planning of harvesting actions before physical contact with plants. This preliminary digital inspection and path planning allows the robotic system to execute precise, damage-minimizing harvesting motions while maintaining efficient processing capability.
4Extent of automation
If automated harvesting systems are used, then labor is reduced, but challenges remain in observing and gripping plants under varying field conditions
Solution Approach 1:
The robotic harvesting system incorporates dynamic adaptation capabilities where imaging devices and robotic mechanisms can adjust their operation in real-time based on detected plant characteristics and field conditions. The system dynamically modifies gripping forces, motion paths, and inspection parameters to handle varying plant sizes, shapes, and environmental conditions while maintaining full automation.
Solution Approach 2:
The system uses feedback from imaging devices and sensors to continuously monitor plant positions, orientations, and conditions during harvesting. This real-time feedback allows the automated system to adjust its detection and gripping actions to account for varying field conditions, improving both automation reliability and detection accuracy under diverse environmental circumstances.
Data Source
AI summary
A harvester that determines whether edible crowns are ready to be harvested and selectively harvests the edible crowns that are ready for harvesting. The harvester may include sensors, such as an imaging system, for detecting the edible crowns of individual broccoli plants. Image data from the imaging system may be provided as an input to a machine-learning model to determine a maturity (or immaturity) of the edible crowns. If the edible crowns are ready for harvesting, mechanical pickers harvest the edible crowns. For example, the harvester may include robotic arms having end effectors that cut the edible crowns from a remainder of the broccoli plant. The harvester may be configured to continuously harvest the edible crowns as the harvester moves about a field. In some instances, the harvester may include any number of robotic arms for harvesting the edible crowns across multiple rows of broccoli plants.