CN113138399B - A method for tracking and identifying UAV tracks based on machine learning - Google Patents
A method for tracking and identifying UAV tracks based on machine learning Download PDFInfo
- Publication number
- CN113138399B CN113138399B CN202110434383.3A CN202110434383A CN113138399B CN 113138399 B CN113138399 B CN 113138399B CN 202110434383 A CN202110434383 A CN 202110434383A CN 113138399 B CN113138399 B CN 113138399B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- offset error
- uav
- satellite navigation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/21—Interference related issues ; Issues related to cross-correlation, spoofing or other methods of denial of service
- G01S19/215—Interference related issues ; Issues related to cross-correlation, spoofing or other methods of denial of service issues related to spoofing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/52—Determining velocity
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/53—Determining attitude
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Radar Systems Or Details Thereof (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention belongs to the field of navigation spoofing, and particularly discloses an unmanned aerial vehicle track tracking and identifying method based on machine learning. The method comprises the following steps: detecting whether an unmanned aerial vehicle exists or not and whether the unmanned aerial vehicle is in a straight-line flight state or not; step (2) transmitting satellite navigation deception signals to force the unmanned aerial vehicle to deviate from a planned route; step (3), recording the lateral offset error, the lateral offset error change rate and the unmanned aerial vehicle course angle information; step (4) taking a lateral offset error and a lateral offset error change rate as input, taking an unmanned plane course angle as output, and establishing an input-output mapping relation through machine learning methods such as a support vector machine and the like; and (5) predicting the course angle change of the unmanned aerial vehicle through satellite navigation deception signals based on a model established by machine learning, so as to realize the aim of navigation deception. The method is high in universality, can provide technical support for controlling the illegal unmanned aerial vehicle, and can effectively drive away and trap the illegal unmanned aerial vehicle to a designated place.
Description
Technical Field
The invention relates to the field of navigation spoofing, in particular to an unmanned aerial vehicle track tracking and identifying method based on machine learning.
Background
With the progress of satellite navigation technology and the opening of low-altitude airspace, unmanned aerial vehicle industry rapidly develops, and has been widely applied in the aspects of geological detection, disaster relief, traffic control, agricultural fertilization, pollution monitoring and the like. On the other hand, accidents caused by black flying or improper operation of the unmanned aerial vehicle are also common. Unmanned aerial vehicle effective management is at first to be urgent, and the main treatment means at present includes: the method has the advantages of suppressing interference, navigation spoofing, link hijacking and hard killing and destroying, wherein the navigation spoofing means has strong universality and good action effect, and can trap the unmanned aerial vehicle to a specified place at a fixed point to pay attention.
The invention starts from the real demand of handling illegal unmanned aerial vehicles, and aims to provide a novel method for controlling unmanned aerial vehicles by using navigation spoofing means, wherein the navigation spoofing method takes a lateral offset error and a lateral offset error change rate as input, takes a course angle of the unmanned aerial vehicle as output, obtains a mapping relation between satellite navigation spoofing signals and the course angle of the unmanned aerial vehicle based on machine learning, completes equivalent identification of a track tracking algorithm of the unmanned aerial vehicle, and further achieves the purpose of navigation spoofing.
Disclosure of Invention
The invention provides an unmanned aerial vehicle track tracking and identifying method based on machine learning, which forces an unmanned aerial vehicle to deviate from an original planning route through satellite navigation deception means, and utilizes information such as lateral offset errors, lateral offset error change rates, unmanned aerial vehicle course angles and the like generated by the deviation route to acquire a mapping relation between satellite navigation deception signals and unmanned aerial vehicle course angles based on machine learning so as to complete equivalent identification of an unmanned aerial vehicle track tracking algorithm. The method can be applied to the field of navigation spoofing and has high practical value.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
a machine learning-based unmanned aerial vehicle track tracking and identifying method comprises the following steps:
step (1): firstly, detecting the unmanned aerial vehicle by using the unmanned aerial vehicle or a third party detection device, acquiring position and speed information of the unmanned aerial vehicle, tracking the unmanned aerial vehicle, fitting extrapolation, determining whether the unmanned aerial vehicle is in a straight-line flight state, if not, continuously tracking, otherwise, executing the step (2);
step (2): when the unmanned aerial vehicle is in a stable straight-line flight state, satellite navigation deception signals are transmitted, so that the unmanned aerial vehicle-mounted satellite navigation receiver is ensured to receive false satellite signals and participate in self position, speed and gesture calculation;
step (3): judging whether the unmanned aerial vehicle deviates from the route under the action of the satellite navigation deception signal by controlling the satellite navigation deception signal and utilizing the unmanned aerial vehicle or a third party detection device, if not, closing the satellite navigation deception signal, returning to the step (2), otherwise, executing the step (4);
step (4): recording a lateral offset error, a lateral offset error change rate and unmanned aerial vehicle course angle information, and executing the step (5);
step (5): judging whether the acquired data volume is enough, if not, executing the step (3), otherwise, executing the step (6);
step (6): and taking the lateral offset error and the lateral offset error change rate as input, taking the course angle of the unmanned aerial vehicle as output, and establishing an input-output mapping relation through machine learning methods such as a support vector machine, a neural network and the like to finish the unmanned aerial vehicle track tracking and identifying method.
The invention has the beneficial effects that:
the universality is strong: the invention can utilize machine learning based on navigation deception means for unmanned aerial vehicle using satellite navigation system to participate in navigation positioning, and has certain regression and ability of predicting unmanned aerial vehicle course angle change;
technical support is provided for the management and control illegal unmanned aerial vehicle: can effectively drive away and decoy the illegal unmanned aerial vehicle to the appointed place.
Drawings
FIG. 1 is a flow chart of an unmanned aerial vehicle track tracking and identifying method and implementation based on machine learning designed by the invention;
FIG. 2 is a diagram of physical quantities such as lateral offset, lateral offset error change rate and unmanned aerial vehicle course angle;
fig. 3 is a view showing the effect of the unmanned aerial vehicle in the cruising flight state according to the present invention;
FIG. 4 is a graph of unmanned navigation spoofing effect in accordance with the present invention;
FIG. 5 is a graph of a lateral offset error log in accordance with the present invention;
FIG. 6 is a graph of a side offset error rate of change record in accordance with the present invention;
FIG. 7 is a chart of unmanned aerial vehicle course angle recordings in accordance with the present invention;
fig. 8 is a diagram of the effect of predicting a heading angle of a drone using machine learning in accordance with the present invention.
Detailed Description
The following detailed description of the invention is provided with the understanding that the present disclosure is to be considered as an exemplification of the invention and is not intended to limit the invention to that as illustrated.
A flow chart of navigation spoofing signal generation and implementation is shown in fig. 1.
FIG. 2 is a diagram showing the physical quantities of lateral offset, the error rate of lateral offset, the heading angle of unmanned aerial vehicle, and the like, wherein x and y respectively represent the x axis and the y axis of a rectangular coordinate system, W i W i+1 Representing a planned track (straight line), wherein A is the current position of the unmanned aerial vehicle, psi is the angle between the flight direction and the x-axis of the unmanned aerial vehicle, namely the heading angle of the unmanned aerial vehicle, AB T W i W i+1 D=ab, d is the lateral offset,is the change rate of the lateral offset;
the technical scheme adopted by the invention is as follows:
a machine learning-based unmanned aerial vehicle track tracking and identifying method comprises the following steps:
step (1): firstly, detecting the unmanned aerial vehicle by using the unmanned aerial vehicle or a third party detection device, acquiring position and speed information of the unmanned aerial vehicle, tracking the unmanned aerial vehicle, fitting extrapolation, determining whether the unmanned aerial vehicle is in a straight-line flight state, if not, continuously tracking, otherwise, executing the step (2);
step (2): when the unmanned aerial vehicle is in a stable straight-line flight state, satellite navigation deception signals are transmitted, so that the unmanned aerial vehicle-mounted satellite navigation receiver is ensured to receive false satellite signals and participate in self position, speed and gesture calculation;
step (3): judging whether the unmanned aerial vehicle deviates from the route under the action of the satellite navigation deception signal by controlling the satellite navigation deception signal and utilizing the unmanned aerial vehicle or a third party detection device, if not, closing the satellite navigation deception signal, returning to the step (2), otherwise, executing the step (4);
step (4): recording a lateral offset error, a lateral offset error change rate and unmanned aerial vehicle course angle information, and executing the step (5);
step (5): judging whether the acquired data volume is enough, if not, executing the step (3), otherwise, executing the step (6);
step (6): and taking the lateral offset error and the lateral offset error change rate as input, taking the course angle of the unmanned aerial vehicle as output, and establishing an input-output mapping relation through machine learning algorithms such as a support vector machine, a neural network and the like to finish the unmanned aerial vehicle track tracking and identifying method.
The method is explained below in connection with a real flight test. The test was carried out in the 13×32 square kilometer field composed of the east longitude 112.93 ° and the north latitude 28.23 ° in the 6 th 2017 Beijing time, two planned tracks are defined, namely a path1 and a path2, wherein the starting point of the path1 isEndpoint +.>Path2 starts from->Endpoint +.>Only considering a two-dimensional flight plane, the following steps are described according to the technical scheme:
step (1): firstly, acquiring position and speed information of an unmanned aerial vehicle by utilizing a GPS (global positioning system) and a Beidou receiver, determining whether the unmanned aerial vehicle is in a straight-line flight state or not through fitting extrapolation, and if not, continuously observing if the unmanned aerial vehicle is in the straight-line flight state, as shown in fig. 3, and otherwise, executing the step (2);
step (2): when the unmanned aerial vehicle is in a stable straight-line flight state, transmitting GPS satellite navigation deception signals, ensuring that an unmanned aerial vehicle airborne satellite navigation receiver receives false satellite signals and participates in position, speed and gesture resolving, wherein in the test, only the GPS participates in the unmanned aerial vehicle position, speed and gesture resolving, and an airborne Beidou receiver does not participate in resolving, so that the real flight path of the unmanned aerial vehicle is reflected;
step (3): judging whether the unmanned aerial vehicle deviates from the route under the action of the GPS satellite navigation deception signal or not by controlling the GPS satellite navigation deception signal and utilizing an onboard Beidou receiver to acquire data in real time, returning to the step (2) if the satellite navigation deception signal is not closed as shown in fig. 4, and executing the step (4) if the satellite navigation deception signal is not closed;
step (4): recording a lateral offset error, a lateral offset error change rate and unmanned aerial vehicle course angle information, respectively shown in figures 5-7, and executing a step (5);
step (5): judging whether the acquired data volume is enough, if not, executing the step (3), otherwise, executing the step (6);
step (6): the unmanned aerial vehicle course angle is used as output by taking the lateral offset error and the lateral offset error change rate as input, the test uses a support vector machine method for learning, an input-output mapping relation is established, and the unmanned aerial vehicle course tracking and identifying method is completed.
And (3) using the learned model, verifying by taking a section of new unmanned aerial vehicle navigation spoofing data as a test set, comparing with the real course angle of the unmanned aerial vehicle displayed by the airborne Beidou receiver, verifying the correctness of the algorithm, and ending as shown in fig. 8.
While illustrative embodiments of the invention have been described above and true flight data is presented so that those skilled in the art can understand the invention, the invention is not limited to the details but rather by the claims and any inventions made using the inventive concepts will be protected by those skilled in the art so long as they come within the spirit and scope of the invention.
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110434383.3A CN113138399B (en) | 2021-04-22 | 2021-04-22 | A method for tracking and identifying UAV tracks based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110434383.3A CN113138399B (en) | 2021-04-22 | 2021-04-22 | A method for tracking and identifying UAV tracks based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113138399A CN113138399A (en) | 2021-07-20 |
| CN113138399B true CN113138399B (en) | 2023-09-22 |
Family
ID=76813270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110434383.3A Active CN113138399B (en) | 2021-04-22 | 2021-04-22 | A method for tracking and identifying UAV tracks based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113138399B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114120712B (en) * | 2021-11-22 | 2022-11-29 | 四川九洲电器集团有限责任公司 | Aerospace ball-borne AIS early warning method and device |
| CN115267867A (en) * | 2022-07-31 | 2022-11-01 | 郑州轻工业大学 | Network space positioning detection method based on graph neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9643722B1 (en) * | 2014-02-28 | 2017-05-09 | Lucas J. Myslinski | Drone device security system |
| CN110646814A (en) * | 2019-09-16 | 2020-01-03 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle deception method under combined navigation mode |
| CN111026152A (en) * | 2019-11-29 | 2020-04-17 | 北京自动化控制设备研究所 | A UAV navigation decoy device and method based on flight destination prediction |
| CN111381604A (en) * | 2020-04-30 | 2020-07-07 | 北京无线电计量测试研究所 | Deception trajectory generation method and system for intercepting autonomous flight low-speed small target |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018135522A1 (en) * | 2017-01-19 | 2018-07-26 | 日本電気株式会社 | Mobile body control system, mobile body control device, mobile body control method, and recording medium |
| WO2020014122A1 (en) * | 2018-07-09 | 2020-01-16 | Noblis, Inc. | Systems and methods for optimizing cooperative actions among heterogeneous autonomous connected machines |
-
2021
- 2021-04-22 CN CN202110434383.3A patent/CN113138399B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9643722B1 (en) * | 2014-02-28 | 2017-05-09 | Lucas J. Myslinski | Drone device security system |
| CN110646814A (en) * | 2019-09-16 | 2020-01-03 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle deception method under combined navigation mode |
| CN111026152A (en) * | 2019-11-29 | 2020-04-17 | 北京自动化控制设备研究所 | A UAV navigation decoy device and method based on flight destination prediction |
| CN111381604A (en) * | 2020-04-30 | 2020-07-07 | 北京无线电计量测试研究所 | Deception trajectory generation method and system for intercepting autonomous flight low-speed small target |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113138399A (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7174063B2 (en) | Obstacle avoidance method and device for driverless vehicle | |
| CN111492202B (en) | Location determination of vehicle operation | |
| US10809735B2 (en) | System and method for a framework of robust and safe reinforcement learning application in real world autonomous vehicle application | |
| CN104854639B (en) | Vehicle position estimation device and vehicle position estimation method | |
| US20200005645A1 (en) | Orientation-Adjust Actions for Autonomous Vehicle Operational Management | |
| CN112868031B (en) | Autonomous vehicle operations management with visual saliency perception control | |
| CN111275969B (en) | A Vehicle Trajectory Filling Method Based on Intelligent Recognition of Road Environment | |
| US20240298205A1 (en) | Systems and methods for selecting locations to validate automated vehicle data transmission | |
| CN115140096A (en) | Spline curve and polynomial curve-based automatic driving track planning method | |
| CN111902782A (en) | Centralized shared autonomous vehicle operation management | |
| CN113138399B (en) | A method for tracking and identifying UAV tracks based on machine learning | |
| US11408739B2 (en) | Location correction utilizing vehicle communication networks | |
| CN112419792B (en) | Aircraft flight conflict detection method, system, device and medium | |
| CN110617815A (en) | Method and device for automatic driving monitoring alarm | |
| CN114590276A (en) | Remote monitoring unmanned system | |
| CN115061176B (en) | Vehicle GPS enhanced positioning method based on V2V instantaneous data exchange | |
| CN113085868A (en) | Method, device and storage medium for operating an automated vehicle | |
| JP2025520096A (en) | On-line state space refinement for competence recognition systems | |
| CN103678925A (en) | Flight path classification method based on auxiliary information source | |
| CN110728309A (en) | A traffic trajectory clustering method based on railway signal and Beidou positioning | |
| Eiermann et al. | Driver Assistance for Safe and Comfortable On-Ramp Merging Using Environment Models Extended through V2X Communication and Role-Based Behavior Predictions | |
| CN115683125A (en) | Method, system and computer program product for automatically locating a vehicle | |
| CN110109159A (en) | Travel management method, device, electronic equipment and storage medium | |
| Chipka et al. | Autonomous urban localization and navigation with limited information | |
| Nayak et al. | The Role of Integrity Monitoring in Connected and Automated Vehicles: Current State of Practice and Future Directions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220314 Address after: 410031 Hunan Science and technology building, 233 Yuelu Avenue, Changsha City, Hunan Province Applicant after: Hunan Industrial Technology Cooperative Innovation Research Institute Address before: 410073 Hunan province Changsha Kaifu District, Deya Road No. 109 Applicant before: National University of Defense Technology |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220406 Address after: 410000 Room 301, third floor, building 16, phase I, Changsha Zhongdian Software Park, No. 39, Jianshan Road, high tech Development Zone, Changsha, Hunan Applicant after: Hunan Navigation Instrument Engineering Research Center Co.,Ltd. Address before: 410031 Hunan Science and technology building, 233 Yuelu Avenue, Changsha City, Hunan Province Applicant before: Hunan Industrial Technology Cooperative Innovation Research Institute |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |