Predictive Field Maps for Automated Harvester Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Agricultural machines face performance degradation due to varying field topography, biomass, and vegetative conditions, leading to issues like grain loss, quality, and tailings characteristics, which current systems struggle to predict and adjust to effectively.
Innovation Solution
Generate predictive maps using in-situ sensors and prior information maps to model relationships between agricultural characteristics, enabling automated control of machines to optimize operations based on topography, biomass, and vegetative indices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If automated control systems use basic sensor data without predictive modeling, then system complexity is reduced, but machine performance degradation occurs due to inability to predict and adjust to varying field conditions
Solution Approach 1:
The system performs preliminary actions by generating predictive maps that forecast agricultural characteristics ahead of time using in-situ sensor data and machine learning models. This allows the automated control system to proactively adjust machine operations before encountering varying field conditions, thereby maintaining reliable performance without requiring complex real-time decision-making infrastructure
Solution Approach 2:
The predictive map generation system acts as an intermediary layer between raw in-situ sensor data and the automated control system. This intermediary processes and interprets sensor data to create actionable predictive information, enabling the control system to make informed adjustments without directly handling the complexity of raw sensor processing and pattern recognition
2Measurement precision
If the system collects and processes extensive in-situ sensor data to generate predictive maps, then prediction accuracy improves, but data processing time and computational resources increase
Solution Approach 1:
The system performs preliminary data processing by continuously collecting and pre-processing in-situ sensor data during field operations. Machine learning models are trained and updated in advance using this accumulated data, enabling accurate predictions to be generated quickly when needed without requiring extensive real-time computational resources
Solution Approach 2:
The system creates simplified representations of complex field conditions through predictive maps that copy essential agricultural characteristic patterns. These map-based representations allow the control system to make accurate predictions using compact data structures rather than processing vast amounts of raw sensor data in real-time
Data Source
AI summary
One or more information maps are obtained by an agricultural work machine. The one or more information maps map one or more agricultural characteristic values at different geographic locations of a field. An in-situ sensor on the agricultural work machine senses an agricultural characteristic as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural characteristic at different locations in the field based on a relationship between the values in the one or more information maps and the agricultural characteristic sensed by the in-situ sensor. The predictive map can be output and used in automated machine control.