Method for drone detection and for determining the distance to its remote control, computer program and detection device for carrying out the method
Machine learning models analyze drone signals to reliably detect and determine distance from remote controls, addressing inaccuracies in existing methods and enabling precise drone localization for effective repulsion.
Patent Information
- Application Number
- DE102024003181
- Authority / Receiving Office
- DE · DE
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-04-19
- Publication Date
- 2025-07-31
- Estimated Expiration
- 2044-04-19
AI Technical Summary
Existing methods for drone detection and distance determination from their remote controls are inaccurate and unreliable due to encrypted signals, making it difficult to identify drones and implement effective repulsion mechanisms, especially in air-traffic zones and military operations, and are susceptible to signal spoofing.
Utilizing machine learning models, particularly support vector machines (SVMs) and random forest models, to analyze drone signals without decryption, detecting and classifying drone presence and determining distance based on quadrature amplitude modulation (QAM) order and triangulation of radio signals.
Enables reliable drone detection and distance measurement from their remote controls, even in the presence of encrypted signals and signal spoofing, allowing for precise localization and effective repulsion strategies.
Smart Images

Figure 00000000_0000_ABST
Abstract
Claims
[1] A method for detecting drones and determining the distance to their remote control (114), comprising the steps of: - detecting a plurality of wirelessly transmitted radio signals (200) over the air using a detection device; - checking for the presence of at least one drone (100) within the range of the detection device by analyzing the radio signals (200); - detecting or determining an order of quadrature amplitude modulation used in the transmission of the radio signals (200) of the drone (100); and - Determining the distance of the drone (100) to its associated remote control (114) based on the order of the quadrature amplitude modulation. [2] Method according to claim 1, characterized by that the distance is determined using a previously empirically recorded characteristic curve. [3] Method according to claim 1 or 2, characterized bythat the distance is determined using a previously empirically recorded characteristic map, which also takes into account the number or quantity of non-drone-specific interference signals. [4] Method according to one of claims 1 to 3, characterized by that the distance of the detection device to the drone (100) is determined by means of a triangulation of the radio signals (200) in order to draw conclusions also about the distance of the detection device to the remote control (114). [5] Method according to one of claims 1 to 4, characterized by that there is a trained AI model (400) which is configured to classify the order of the quadrature amplitude modulation in order to subsequently determine the distance of the drone (100) from its associated remote control (114). [6] Method according to claim 5, characterized by that the AI model (400) is trained on the basis of images to recognize the signals of the drone (100) in a frequency spectrum (202). [7] Method according to claim 5 or 6, characterized by that the AI model (400) is based on a support vector machine (SVM) which is configured to classify the signals in the time domain at least with regard to the bandwidth and / or with regard to the signal duration and / or with regard to the frequency band. [8] Method according to claim 5 or 6, characterized by that the AI model (400) is based on a support vector machine (SVM) which is configured to classify the signals in the frequency domain at least with regard to the bandwidth and / or with regard to the signal duration and / or with regard to the frequency band. [9] Computer program with program code for carrying out all method steps according to one of claims 1 to 8, when the computer program is executed in a computer. [10] A detection device comprising a computer adapted to effect a method according to any one of claims 1 to 8.
Citation Information
Patent Citations
Hyper-precise positioning and communications system and network
US20200260225A1
Phase-accurate vehicle positioning systems and devices
US20200319330A1
Systems, methods, and devices for unmanned vehicle detection
US20240121499A1