UAV Border Detection and Flight Path Correction for Field Coverage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous UAV systems for pesticide/fertilizer application face challenges in accurately defining field boundaries, leading to potential missed areas or overspray due to position errors in digital maps, which are labor-intensive and costly to correct with high-end positioning systems.
Innovation Solution
A vision-based border identification and dynamic route planning system that uses image sensors and machine learning to predict and adjust the flight path of UAVs in real-time, allowing for accurate coverage of agricultural fields without manual surveying or high-end positioning systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If digital map boundary information is used to plan the UAV route, then the route planning is simple and quick, but the position errors of 3-6 meters cause incomplete coverage or overspray beyond field boundaries
Solution Approach 1:
The patent replaces traditional mechanical surveying methods with a vision-based system using cameras and image processing algorithms. The UAV captures images of the field boundary, and computer vision algorithms automatically identify and locate the boundary features, substituting physical surveying equipment and manual measurement processes with optical detection and computational analysis.
Solution Approach 2:
The patent introduces visual features (natural or artificial boundary markers) as intermediaries between the UAV's positioning system and the actual field boundary. These features serve as reference points that the vision system detects and uses to calculate precise boundary locations, mediating the relationship between GPS coordinates and ground reality.
2Measurement precision
If high-end positioning systems are used on the UAV to achieve accurate positions, then the boundary detection accuracy is improved, but the cost and complexity of the system increases significantly
Solution Approach 1:
The patent replaces complex high-precision positioning systems (such as RTK-GPS or laser ranging equipment) with a vision-based detection system using standard cameras and image processing. The boundary location is determined through visual recognition of boundary features rather than through complex positioning hardware, achieving comparable accuracy with simpler equipment.
Solution Approach 2:
The patent creates a visual copy or representation of the field boundary by capturing images and processing them to extract boundary information. Instead of directly measuring the boundary with precision instruments, the system creates an image-based model of the boundary that can be analyzed and used for route planning.
3Manufacturing precision
If manual surveying is conducted to accurately identify field borders, then the position error is reduced to centimeter level, but the process becomes time-consuming and labor-intensive
Solution Approach 1:
The patent replaces manual surveying operations with an automated vision-based system. The UAV flies over the field capturing images, and computer vision algorithms automatically process these images to identify and locate boundary features, eliminating the need for operators to physically walk the perimeter and manually record coordinates.
Solution Approach 2:
The patent performs preliminary boundary identification by having the UAV capture images of the field boundary before the actual pesticide application mission. The vision system processes these images in advance to determine boundary locations and generate corrected route information, so that when the UAV begins spraying, the accurate boundary data is already available.
4Extent of automation
If the UAV follows a route based on digital map boundaries with position errors, then the autonomous operation is simple, but the pesticides may be missed in areas within 3-6 meters of the border or sprayed outside the field
Solution Approach 1:
The patent implements a feedback mechanism where the vision system continuously monitors the UAV's position relative to detected boundary features during flight. The system compares the actual boundary location (detected via vision) with the planned route (based on GPS coordinates) and provides feedback to the flight control system to make real-time corrections, ensuring the UAV maintains proper positioning relative to the actual field boundary.
Solution Approach 2:
The patent makes the boundary detection dynamic by using real-time or near-real-time image capture and processing during the UAV's flight mission. Rather than relying on static pre-surveyed boundary data, the system dynamically identifies and tracks boundary features as the UAV moves, allowing the route to adapt to the actual field geometry encountered during operation.
Data Source
AI summary
A specification of an expected border of a bounded area is received. One or more images of at least a portion of the bounded area that is at least a threshold distance away from the expected border are received to generate a model of the bounded area. A current location position of the aerial vehicle is used to determine that the aerial vehicle is within the threshold distance away from the expected border. In response, an updated expected border is determined using the generated model of the bounded area and a border image of at least a portion of the expected border captured by an image sensor.