UAV Marker Tracking Across Multiple Cameras for Autonomous Landing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing UAV landing technologies are insufficient due to reliance on GPS signals, which may be unavailable or imprecise, and vision-based systems that struggle with limited field of view, leading to unreliable landing operations.

Innovation Solution

A computer-implemented method and system that uses imaging devices on UAVs to detect and track target markers, such as concentric ring patterns, to determine spatial relationships and control the UAV's movement for precise and reliable landing, incorporating processors to adjust the imaging device's position and the UAV's velocity for accurate alignment and descent.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If GPS-based landing systems are used, then landing automation is achieved, but reliability deteriorates due to signal unavailability or imprecision

Engineering Contradiction:
Improvelanding automationVSAvoidlanding reliability
Core Design Contradiction:
Extent of automationVSReliability

Solution Approach 1:

The patent introduces visual markers as an intermediary reference system between the UAV and landing site. These markers serve as a reliable intermediary that provides precise positional and orientational information without depending on GPS signals, thereby resolving the contradiction between automation and reliability

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the GPS-based electromagnetic signal system with a vision-based optical recognition system. By substituting the mechanical/electromagnetic sensing approach with optical image processing of visual markers, the system achieves both automation and improved reliability in GPS-denied environments

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If vision-based landing systems are used, then landing precision is improved, but field of view limitation causes detection failure

Engineering Contradiction:
Improvelanding precisionVSAvoidfield of view
Core Design Contradiction:
Measurement precisionVSArea of stationary object

Solution Approach 1:

The patent transitions from a two-dimensional image plane problem to a three-dimensional spatial solution by introducing vertically stacked imaging devices. This dimensional change allows the system to maintain precise marker detection while expanding the effective field of view coverage area

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent divides the imaging function into multiple segmented imaging devices positioned at different locations and orientations. Each imaging device covers a specific sector, and their combined coverage eliminates blind spots while maintaining high precision for each individual device

Inventive Principle:
Principle #1Segmentation

3Device complexity

If single imaging device is used, then device complexity is reduced, but marker tracking reliability deteriorates during UAV movement

Engineering Contradiction:
Improveimaging system complexityVSAvoidmarker tracking reliability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent implements a dynamic multi-imaging-device configuration where the system adaptively selects and switches between different imaging devices based on real-time UAV position and marker location. This dynamic approach maintains reliable tracking throughout the landing sequence without requiring all devices to operate simultaneously, thus managing complexity

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3497530B1Methods and system for autonomous landing
Publication Date: 2021.07.21 SZ DJI TECH CO LTD
  • EP3497530B1 patent drawingFigure 1
  • EP3497530B1 patent drawingFigure 2
  • EP3497530B1 patent drawingFigure 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.