Vision-Based UAV Path Planning in GPS-Denied Areas

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Unmanned aerial vehicles face challenges in navigating in GPS-denied areas due to interference or spoofing of satellite signals, which can lead to inaccurate navigation and potential damage.

Innovation Solution

A navigation system on the aerial vehicle uses a camera to record images, applies a machine learning model to identify objects, matches these objects with an electronic map, and calculates the vehicle's location based on object coordinates to navigate to a target location.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If GPS navigation is used for autonomous navigation, then navigation capability is provided, but reliability deteriorates in GPS-denied areas due to signal interference and spoofing

Engineering Contradiction:

Improvenavigation capabilityVSAvoidnavigation accuracy

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent introduces an intermediary navigation system that uses visual landmarks and machine learning models as mediators between the aerial vehicle and the navigation task. Instead of directly relying on GPS signals, the system uses detected objects (landmarks) as intermediaries to determine position and navigate, thereby resolving the unreliability of GPS in denied areas while maintaining navigation capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical/electromagnetic GPS signal-based navigation system with a vision-based navigation system using cameras and machine learning models. This substitution eliminates dependency on satellite signals and enables reliable navigation in GPS-denied environments by using visual recognition and object matching algorithms instead of signal-based positioning.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If visual recognition system is added to enable navigation in GPS-denied areas, then reliability improves, but device complexity increases

Engineering Contradiction:

Improvenavigation accuracyVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies multi-functionality by using the same camera system for both visual recognition tasks and navigation functions. The machine learning model serves multiple purposes: object detection, location determination, and path planning. This universal approach enables the system to achieve reliable navigation in GPS-denied areas without proportionally increasing device complexity, as existing components are reused for multiple functions.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250232467A1Computer vision classifier defined path planning for unmanned aerial vehicles

Publication Date: 2025.07.17 TOMAHAWK ROBOTICS INC

AI summary

Methods and systems are described herein for enabling aerial vehicle navigation in GPS-denied areas. The system may use a camera to record images of terrain as the aerial vehicle is flying to a target location. The system may then detect (e.g., using a machine learning model) objects within those images and compare those objects with objects within an electronic map that was loaded onto the aerial vehicle. When the system finds one or more objects within the electronic map that match the objects detected within the recorded images, the system may retrieve locations (e.g., GPS coordinates) of the objects within the electronic map and calculate, based on the coordinates, the location of the aerial vehicle. Once the location of the aerial vehicle is determined, the system may navigate to a target location or otherwise adjust a flight path of the aerial vehicle.