Work Machine Control Using Real-Time Predictive Field Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for controlling work machines, such as combine harvesters, rely on a priori data to generate predictive models that do not represent actual, ground truth data, leading to inefficiencies and inaccuracies in harvesting operations.
Innovation Solution
A system that generates predictive models using both a priori and in situ data during the harvesting operation, dynamically evaluates the model quality, and switches to alternative models or manual control if the quality is insufficient, ensuring accurate and real-time control of the work machine.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If a priori data is used to generate predictive models, then the system can operate without real-time data collection, but the model accuracy and representation of ground truth data deteriorates
Solution Approach 1:
The system merges a priori data (pre-harvest aerial imagery and vegetative index data) with in situ data (real-time sensor data from the combine harvester) to generate a hybrid predictive model. This combination allows the system to benefit from both the time-saving aspects of pre-collected data and the accuracy improvements from ground truth measurements, resolving the contradiction between speed and precision.
Solution Approach 2:
The system performs preliminary data collection and model generation using a priori data before the harvesting operation begins. This preliminary model provides initial guidance and allows the system to start operations immediately, while simultaneously collecting in situ data to refine and update the model during operation, thus maintaining both time efficiency and accuracy.
2Measurement precision
If predictive models are dynamically generated and evaluated during operation, then the model accuracy improves, but the system complexity and computational requirements increase
Solution Approach 1:
The system implements partial model re-generation and evaluation during operation rather than complete model reconstruction. It dynamically evaluates model quality metrics and selectively updates only the portions of the model that require refinement based on in situ data, reducing computational overhead while maintaining accuracy improvements.
Solution Approach 2:
The system incorporates feedback mechanisms where in situ sensor data is continuously compared against predictive model outputs, and model quality metrics are calculated based on this comparison. This feedback loop enables automatic model refinement and validation during operation, improving accuracy through a structured process that manages system complexity.
3Reliability
If the system switches to alternative models or manual control when model quality is insufficient, then the control reliability improves, but the operational efficiency and automation level deteriorates
Solution Approach 1:
The system dynamically adjusts the level of automation and model usage based on real-time model quality assessments. When model quality metrics indicate sufficient accuracy, the system operates in fully automated mode using the predictive model. When quality falls below thresholds, the system adaptively switches to alternative models or manual control, creating a flexible system that maintains reliability while minimizing interruptions to operational efficiency.
Data Source
AI summary
A priori georeferenced vegetative index data is obtained for a worksite, along with field data that is collected by a sensor on a work machine that is performing an operation at the worksite. A predictive model is generated, while the machine is performing the operation, based on the georeferenced vegetative index data and the field data. A model quality metric is generated for the predictive model and is used to determine whether the predictive model is a qualified predicative model. If so, a control system controls a subsystem of the work machine, using the qualified predictive model, and a position of the work machine, to perform the operation.