Crop Row Mapping for Reliable Autonomous Field Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current unmanned agricultural robots face challenges in navigating agricultural fields due to variable accuracy in geospatial data, mis-planted rows, and weeds, which existing precision planting technologies cannot fully address.
Innovation Solution
An unmanned agricultural robot system that generates an anticipatory geospatial data map by combining measured actual crop row positions with anticipated positions, using aerial mapping sensors and onboard algorithms to refine the map in real-time, even in the presence of obstacles or unexpected vegetation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS-based precision planting systems are used to create as-planted maps, then geospatial data can be obtained for navigation, but the accuracy is variable and insufficient for robust autonomous navigation
Solution Approach 1:
The system performs preliminary mapping actions by deploying aerial mapping sensors to capture geospatial data and create an anticipatory map of crop rows before the autonomous robot begins navigation. This pre-established geographic framework allows the robot to plan its path in advance, improving both measurement precision and navigation reliability by having accurate reference data available before operation begins.
Solution Approach 2:
The patent introduces an intermediary anticipatory map that mediates between the GPS-based as-planted data and the actual real-time sensor data. This intermediate representation combines predicted crop row positions with measured positions, smoothing out inaccuracies from either source alone and providing a more reliable navigation reference that improves both precision and reliability.
2Adaptability or versatility
If traditional as-planted maps are used for navigation, then pre-existing field information is utilized, but the system cannot adapt to mis-planted rows, weeds, or unexpected obstacles
Solution Approach 1:
The mapping system transitions from a static as-planted map to a dynamic anticipatory map that is continuously updated during robot operation. The system adapts to mis-planted rows, weeds, and obstacles by integrating real-time sensor measurements with predicted crop row positions, allowing the map to evolve and reflect actual field conditions while maintaining a manageable computational framework.
Solution Approach 2:
The anticipatory map serves multiple functions: it provides navigation guidance, identifies obstacles, detects mis-planted rows, and adapts to various field conditions. This multi-functional approach increases adaptability to different field scenarios while using a unified data structure that prevents excessive system complexity.
3Measurement precision
If real-time sensor feedback is used for fine-scale navigation between crop rows, then precise positioning is achieved, but the system requires high-quality as-planted maps to be effective
Solution Approach 1:
The system implements feedback by continuously comparing real-time sensor measurements of crop row positions with the anticipatory map predictions. This feedback loop allows the system to correct deviations and adapt to actual field conditions, reducing dependency on the quality of pre-existing as-planted maps while maintaining high measurement precision through ongoing verification and adjustment.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables robust and flexible navigation of unmanned agricultural robots, allowing them to perform in-season management tasks with high accuracy and minimal pre-existing information, while minimizing crop damage and adapting to field complexities.
Implementation Method 1
One or more aerial mapping sensors can be deployed at a height above the annual crop rows, so as to enable the one or more aerial mapping sensors to capture geospatial data within an observation window of the agricultural field
Data Source
AI summary
A method of using an unmanned agricultural robot to generate an anticipatory geospatial data map of the positions of annual crop rows planted within a perimeter of an agricultural field, the method including the step of creating a geospatial data map of an agricultural field by plotting actual annual crop row positions in a portion of the geospatial data map that corresponds to a starting point observation window, and filling in a remainder of the geospatial data map with anticipated annual crop row positions corresponding to the annual crop rows outside of the starting point observation window, and refining the geospatial data map by replacing the anticipated annual crop row positions with measured actual annual crop row positions when an unexpected obstacle is encountered.