Predictive Field Maps for Harvester Reel Position Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Variations in vegetation height across agricultural fields can degrade harvesting performance, as existing machines lack the ability to adapt settings in real-time to accommodate varying crop heights and weed presence.
Innovation Solution
An agricultural work machine obtains information maps of agricultural characteristics and uses in-situ sensors to generate predictive maps that forecast vegetation height or reel position at different field locations, enabling real-time adjustments for optimized harvesting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine settings are kept fixed, then device complexity is reduced, but harvesting performance degrades due to vegetation height variation
Solution Approach 1:
The system creates predictive maps in advance that forecast vegetation height or reel position at different field locations before harvesting begins. These pre-computed maps allow the machine to proactively adjust settings based on predicted conditions rather than reacting to actual measurements in real-time, improving harvesting performance while avoiding the complexity of continuous real-time sensing and control.
Solution Approach 2:
The system uses information maps containing agricultural characteristic values from previous passes or satellite data to create predictive maps that replicate expected vegetation conditions. This copying approach allows the machine to operate with predicted data rather than requiring complex real-time sensing systems, maintaining simplicity while improving performance through informed advance planning.
2Adaptability or versatility
If real-time sensor data is used alone, then adaptability to current conditions is improved, but measurement precision is limited by sensor accuracy
Solution Approach 1:
The system merges information from multiple sources including satellite imagery, historical yield maps, and current in-situ sensor data to generate predictive maps. This combination allows the system to leverage the broad spatial coverage and historical context of external data sources while incorporating real-time local measurements, achieving both high adaptability to vegetation variation and improved measurement precision through data fusion.
Solution Approach 2:
The predictive map acts as an intermediary between external information maps and in-situ sensor data. It synthesizes information from multiple sources into a unified forecast that guides machine settings, allowing the system to benefit from both remote sensing data and local measurements without requiring direct integration of their conflicting data formats and precision levels.
3Measurement precision
If external information maps are obtained, then measurement precision is improved, but loss of time occurs during data acquisition and processing
Solution Approach 1:
The system obtains and processes information maps from satellite imagery and historical data sources before the harvesting operation begins. By completing data acquisition and predictive map generation in advance, the system eliminates time loss during actual harvesting, allowing the machine to simply follow pre-computed guidance without interruption to the harvesting workflow.
Solution Approach 2:
The system dynamically balances between using pre-acquired information maps for areas with stable vegetation conditions and switching to real-time in-situ sensor data for areas where vegetation may have changed. This dynamic approach allows the system to minimize time loss by relying on preprocessed data when sufficient while maintaining measurement precision by using updated sensor data when necessary.
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.