UAV Neural Network Control Against Spoofing and Jamming
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned aerial vehicles (UAVs) are vulnerable to electronic attacks such as GPS spoofing, RF blocking, and laser attacks, which can disrupt their navigation and control systems, making it difficult to detect and counter these threats in real-time.
Innovation Solution
The implementation of a neural network-based system, known as the Drone Inspection Neural Network (DINN), which analyzes real-time data from onboard sensors and communicates with terrestrial and satellite-based communication networks to detect and respond to electronic attacks, ensuring safe and efficient drone operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS navigation is used for drone operation, then navigation accuracy is improved, but vulnerability to GPS spoofing attacks increases
Solution Approach 1:
The patent introduces an intermediary detection system that acts as a mediator between the GPS receiver and the navigation controller. This intermediary layer analyzes GPS signal characteristics, detects spoofing attempts, and prevents compromised signals from affecting navigation, thus maintaining navigation accuracy while reducing vulnerability to spoofing attacks
Solution Approach 2:
The system implements feedback mechanisms where the detection system continuously monitors GPS signals and provides real-time information about signal integrity to the navigation system. This feedback loop enables dynamic adjustment of navigation operations based on detected threats, maintaining accuracy while protecting against spoofing
2Reliability
If real-time attack detection systems are implemented, then security against electronic attacks is improved, but device complexity increases
Solution Approach 1:
The detection system is segmented into modular functional blocks including signal acquisition, signal processing, anomaly detection, and response generation modules. Each module performs a specific function and can be independently configured or replaced, reducing overall system complexity while maintaining comprehensive security
Solution Approach 2:
The detection system is designed to detect multiple types of electronic attacks (GPS spoofing, RF blocking, laser attacks) using a unified architecture. This multi-functional approach avoids the need for separate specialized systems for each threat type, thereby reducing device complexity while improving reliability
3Reliability
If multiple sensor data streams are analyzed in real-time, then attack detection capability is improved, but energy consumption increases
Solution Approach 1:
The system processes sensor data streams selectively based on operational context and detected threat levels. During normal operation, only essential data streams are analyzed at full resolution, while less critical streams are sampled at lower rates. When threats are detected, the system temporarily increases processing intensity for relevant streams, balancing detection capability with energy consumption
Data Source
AI summary
An unmanned aerial vehicle (UAV) or “drone” executes a neural network to assist with detecting and responding to attacks. The neural network may monitor, in real time, the data stream from a plurality of onboard sensors during navigation and may communicate with a high-altitude pseudosatellite (“HAPS”) platform For example, if the neural network detects a cyber-attack but determines that it does not interfere with external communications, it may shift navigation control of the drone to the HAPS.