UAV Landing Control Using Visual Marker Tracking Without GPS

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing UAV landing technologies face challenges in precision and reliability, particularly due to reliance on GPS signals that may be unavailable or weak, and limitations in visual marker detection by cameras with limited fields of view.

Innovation Solution

A computer-implemented method for controlling UAVs involves detecting target markers using imaging devices, determining spatial relationships, and controlling the UAV to approach the markers while tracking them, using processors onboard or offboard the UAV to maintain the markers within the camera's field of view, and employing concentric features and security markers for authentication.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If GPS-based landing guidance is used, then landing automation is achieved, but reliability deteriorates when GPS signals are unavailable or weak

Engineering Contradiction:

Improveautonomous landingVSAvoidlanding reliability

Core Design Contradiction:

Extent of automationVSReliability

Solution Approach 1:

The patent introduces visual markers as an intermediary between the UAV and the landing site. These markers serve as a reliable reference that does not depend on GPS signals, allowing the UAV to accurately determine its position and guide landing through image processing and spatial relationship calculation.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the GPS-based electronic navigation system with a vision-based mechanical/optical system. By using cameras to capture images of visual markers and processing these images to determine spatial relationships, the system substitutes the GPS mechanical/electronic signal dependency with a visual recognition approach that works independently of satellite signals.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If camera field of view is limited, then device complexity is reduced, but measurement precision deteriorates in detecting target markers

Engineering Contradiction:

Improveimaging system complexityVSAvoidmarker detection precision

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent makes the imaging device dynamic by enabling it to move and track the target marker. The imaging device adjusts its orientation and position to keep the marker within the field of view during the approach, allowing a simple camera to achieve high measurement precision through active tracking rather than requiring a complex wide-field or multi-camera system.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements feedback control where the detected marker position is used to adjust the imaging device's orientation and the UAV's approach path. This closed-loop feedback allows the limited field of view camera to maintain precise tracking of the marker throughout the landing approach by continuously adjusting its viewing angle.

Inventive Principle:

Principle #23Feedback

Data Source

PatentEP3901728B1Methods and system for autonomous landing

Publication Date: 2023.10.04 SZ DJI TECH CO LTD

Figure 1
Figure 2
Figure 3

AI summary

Techniques are provided for autonomously landing an unmanned aerial vehicle (UAV). A target marker can be detected based on a plurality of images captured by an imaging devices carried by the UAV. A spatial relationship can be determined between the UAV and the target marker based on the plurality of images. The UAV can be controlled to approach the target marker based on the spatial relationship while the imaging device is controlled to track the target marker.