Artificial Point of View for UAV Navigation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Operating unmanned aerial vehicles in challenging environments, such as forests, under bridges, or inside buildings, is difficult due to limited situational awareness provided by current camera systems, which often lack sufficient information about obstacles and clearance, making it hard for operators to navigate safely.

Innovation Solution

A method and apparatus that processes video information by selecting prior images to display a model of the vehicle in its current position relative to objects, with size and orientation based on actual proportions, and includes an arrow indicating direction and speed, even when the vehicle is hidden from view, providing an artificial point of view to enhance operator control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If real-time video feeds from the vehicle are used to provide operator view, then the operator can see the current position of the vehicle, but the operator cannot see the vehicle when it is hidden from view by obstacles such as trees or buildings

Engineering Contradiction:
Improvevisibility of vehicle positionVSAvoidoperator situational awareness
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The system stores a sequence of historical images captured by the vehicle's camera at different positions along its flight path. When the current view is blocked by obstacles, the operator can access previously captured images that show the vehicle's position relative to environmental features, effectively providing advance visual information about areas currently obscured from direct view.

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If the vehicle flies at lower altitudes to navigate through challenging environments like forests or under bridges, then the vehicle can access areas of interest, but the operator's ability to see and track the vehicle is reduced

Engineering Contradiction:
Improvevehicle access to environmentsVSAvoidvehicle position information
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

Instead of relying solely on the current 2D video feed, the system creates a temporal dimension by storing and displaying multiple historical images at different time points. This allows the operator to view the vehicle's position at previous locations along its path, effectively adding a time-based dimension to compensate for the loss of spatial visibility at low altitudes.

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

3Productivity

If the vehicle moves quickly through an area to capture images, then productivity is improved, but the operator has less time to process and understand the environment

Engineering Contradiction:
Improveimage capture speedVSAvoidoperator decision time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system pre-captures and stores multiple images at different positions along the vehicle's path before the operator needs to make navigation decisions. This preliminary capture of environmental information allows the operator to review multiple frames showing the vehicle's progression through the area, effectively compensating for the reduced decision time caused by faster vehicle movement.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2523062B1Time phased imagery for an artificial point of view
Publication Date: 2019.08.21 THE BOEING CO
  • EP2523062B1 patent drawingFigure 1
  • EP2523062B1 patent drawingFigure 2
  • EP2523062B1 patent drawingFigure 3

AI summary

A method and apparatus for processing video information for a vehicle. A number of prior images is selected from images generated by the vehicle. An object is seen in the number of prior images. A model of the vehicle is displayed in the number of prior images in a current position of the vehicle and with a size that is based on the current position of the vehicle relative to the object in the number of prior images.