UAV Descent Imaging for Planar Landing Surface Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for ensuring safe landing and delivery of packages by unmanned aerial vehicles (UAVs) lack efficient means to confirm the presence of a substantially planar surface at the destination, which is crucial for safe landing and delivery, often relying on stereo cameras or depth sensors that are complex and less accurate.

Innovation Solution

The method involves capturing and processing images at different altitudes to pair feature points, computing homographies to confirm planarity, and generating a depth disparity map to identify a safe landing area, using a location identifier to aid in image registration and determining the availability of a sufficient planar surface for landing and delivery.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If stereo cameras or depth sensors are used to confirm planar surface for UAV landing, then measurement precision of surface planarity is improved, but device complexity increases

Engineering Contradiction:
Improvesurface planarity detection accuracyVSAvoidstereo camera and depth sensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts the essential function of planarity detection from complex stereo/depth sensing systems and implements it using a single camera combined with homography computation. By taking out the unnecessary complexity of multiple sensors and focusing on the core geometric relationship between images captured at different altitudes, the system achieves accurate planarity detection with simpler equipment.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent uses image copying and registration techniques where a first image at a higher altitude is registered with a second image at a lower altitude. By computing homography between these copied images and analyzing the transformation, the system can determine surface planarity without needing specialized depth sensing hardware, thus reducing device complexity while maintaining measurement precision.

Inventive Principle:
Principle #26Copying

2Measurement precision

If stereo cameras or depth sensors are used to confirm planar surface for UAV landing, then measurement precision is improved, but loss of time increases

Engineering Contradiction:
Improvesurface planarity detection accuracyVSAvoidtime for descent confirmation and landing decision
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary image capture and homography computation during the descent process itself, rather than requiring separate measurement phases. By capturing images at different altitudes and computing the homography transformation in real-time during descent, the system determines planarity quickly and makes landing decisions without time-consuming separate measurement steps, thus reducing time loss while maintaining precision.

Inventive Principle:
Principle #10Preliminary action

3Device complexity

If a single camera is used instead of stereo cameras, then device complexity is reduced, but measurement precision of depth information decreases

Engineering Contradiction:
Improveimaging system complexityVSAvoiddepth and planarity measurement accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent transitions from analyzing single-image depth information (2D to 3D problem) to analyzing the geometric relationship between two images captured at different altitudes (adding the altitude dimension). By computing homography between images at different heights and examining how feature points transform, the system recovers depth and planarity information with a single camera, maintaining measurement precision while reducing device complexity.

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

Data Source

PatentEP3353710B1Method to determine a planar surface for unmanned aerial vehicle descent
Publication Date: 2021.12.08 AMAZON TECH INC
  • EP3353710B1 patent drawingFigure 1
  • EP3353710B1 patent drawingFigure 2
  • EP3353710B1 patent drawingFigure 3A

AI summary

Described are systems and methods for surveying a destination as an unmanned aerial vehicle ("UAV") descends toward the destination. To confirm that the destination is clear of objects and includes a safe landing or delivery location, such as a substantially planar surface, the UAV may capture and process images at different altitudes during the descent. Feature points of a first image captured at a first altitude may be paired with feature points of a second image captured at a second, different altitude. A homography may be computed to confirm that the paired feature points lie in the same plane and then the two images may be registered based on the paired feature points. The registered images may then be processed to determine depth information and determine if descent of the UAV is to continue or be aborted.