Farming Machine Calibration Pass for Tunable Plant Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Agronomists desire greater control over autonomous or semi-autonomous farming machines by enabling 'human in the loop' decision making, as current models lack transparency and insight into their performance.
Innovation Solution
A farming machine adjusts performance characteristics by capturing images, identifying plants, calculating performance characteristics, accessing target performance characteristics, and modifying models to achieve desired outcomes, allowing agronomists to tune the machine's operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous or semi-autonomous farming machines are used to treat plants, then productivity and automation level are improved, but human control and transparency into decision-making deteriorate
Solution Approach 1:
The system implements feedback by continuously monitoring actual plant treatment outcomes and comparing them against expected performance characteristics. The performance model receives feedback data from the farming machine's operations and adjusts its predictions accordingly, providing transparent insight into autonomous decision-making processes while maintaining high automation levels.
Solution Approach 2:
The performance model performs preliminary actions by predicting expected performance characteristics before actual treatment operations occur. This allows agronomists to review and understand the decision-making logic in advance, providing transparency into autonomous operations while maintaining productivity benefits.
2Speed
If the performance model uses original identification sensitivity to identify plants, then processing speed is improved, but treatment accuracy may deteriorate
Solution Approach 1:
The system dynamically adjusts the performance model's identification sensitivity based on the specific treatment objectives and performance characteristics being evaluated. The model can flex between high-speed processing with original sensitivity and high-accuracy processing with modified sensitivity, resolving the contradiction between speed and precision through dynamic adaptation rather than fixed parameters.
Solution Approach 2:
The performance model changes its identification sensitivity parameter based on the calibration pass results and target performance characteristics. By modifying this key parameter, the system can optimize the balance between processing speed and identification accuracy for different operational contexts, resolving the contradiction between these two parameters.
3Measurement precision
If the performance model is modified to achieve target performance characteristics, then treatment accuracy is improved, but computational complexity increases
Solution Approach 1:
The system performs preliminary calibration passes to determine the necessary model modifications before actual treatment operations. By conducting these complexity-intensive calculations in advance during calibration, the system avoids adding computational complexity to routine treatment operations, resolving the contradiction between accuracy and complexity.
Solution Approach 2:
The performance model creates a simplified representation or copy of the actual treatment process to evaluate expected performance characteristics. This allows the system to assess accuracy requirements without fully complex simulations, reducing computational complexity while maintaining predictive accuracy.
Data Source
AI summary
A method for calibrating performance characteristics of a farming machine using a performance report is described. The farming machine accesses images of plants in a field captured during the calibration pass. The images are input into a performance model to generate a performance report by identifying plants in the images using a plurality of identification sensitivities and determining expected performance characteristics of the farming machine for each of the identification sensitivities. As such, the performance report includes expected performance characteristics for each identification sensitives. The farming machine accesses a target performance characteristic (e.g., from an operator) for the farming machine corresponding identification sensitivity. Images are input into a plant identification model during a treatment pass which identify a plant in the field using the identification sensitivity corresponding to the target performance characteristic. The farming machine treats the plant in the field using a treatment array of the farming machine.