A real-time trajectory prediction system and method for unmanned aerial vehicles

Abstract

The application discloses a kind of unmanned vehicle real-time trajectory prediction system and method, it is related to unmanned vehicle trajectory prediction technical field, system includes rotor speed monitoring module, flight attitude monitoring module, unmanned vehicle state judging module, control information acquisition module, flight attitude comparison module, attitude calibration module, trajectory prediction module;Rotor speed monitoring module is used to monitor the rotation speed of each rotor of unmanned vehicle respectively, obtains corresponding rotor speed;The unmanned vehicle real-time trajectory prediction system and method, by the relationship between unmanned vehicle rotor speed, flight attitude data and control information, whether unmanned vehicle and its flight attitude is abnormal is judged, and can adjust its rotor speed and flight attitude when unmanned vehicle or its flight attitude is abnormal, reduce the influence of interference factor on flight attitude, reduce the difficulty of trajectory prediction, to improve trajectory prediction precision.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle trajectory prediction, in particular to an unmanned aerial vehicle real-time trajectory prediction system and method. BACKGROUND

[0002] With the development of technology, the application field of unmanned aerial vehicles is also becoming more and more extensive, such as agriculture: used for precision agriculture, monitoring crop growth, fertilization and pesticide spraying; surveying and geographic information: conducting topographic surveying, land management, urban planning, etc.; logistics and transportation: used for express delivery, medical material transportation, etc., to improve logistics efficiency; environmental monitoring: monitoring air quality, water pollution, forest fires and other environmental changes; disaster relief: providing real-time monitoring and search and rescue support in natural disasters; construction and construction: monitoring, progress checking and safety evaluation of construction sites; entertainment and photography: used for aerial photography, video recording and entertainment activities, creating unique visual effects; military: used for reconnaissance, surveillance and target attack.

[0003] In order to ensure the quality of the unmanned aerial vehicle when performing tasks, it is necessary to predict the flight trajectory of the unmanned aerial vehicle to ensure that the trajectory of the unmanned aerial vehicle can smoothly complete the task on the predetermined trajectory. The prior art with publication number CN116627154A discloses a method for guiding and landing an unmanned aerial vehicle based on pose prediction and trajectory optimization, and an unmanned aerial vehicle. The specific steps of the method in the near-distance landing process are as follows: when the unmanned aerial vehicle reaches the landing threshold in the middle-distance tracking process, it enters the pre-landing state; the motion state of the current target landing object is obtained, and the motion state of the target landing object is predicted by a Kalman filter algorithm; the predicted motion process of the target landing object is compared with the set yaw motion angle to determine whether the motion state of the target landing object is stable and whether the unmanned aerial vehicle enters the landing state; after entering the landing state, the landing angle is kept unchanged for landing, and an initial landing trajectory is constructed according to the current attitude and dynamics structure; the initial landing curve is optimized by a Bezier curve to find the optimal landing trajectory; the unmanned aerial vehicle lands on the target landing object based on the optimal landing trajectory. The stability and accuracy of the multi-rotor unmanned aerial vehicle in visual guided landing are improved.

[0004] However, during the execution of the task, the unmanned aerial vehicle may have one or more rotors damaged, which changes the lift provided by the damaged rotors under the same conditions, thereby changing the flight trajectory of the unmanned aerial vehicle. Moreover, the change in the trajectory of the unmanned aerial vehicle due to damage to the unmanned aerial vehicle also affects the prediction accuracy of the trajectory prediction algorithm and the accuracy of the control of the trajectory of the unmanned aerial vehicle. SUMMARY

[0005] The purpose of the present application is to provide an unmanned aerial vehicle real-time trajectory prediction system and method to solve the above problems in the prior art.

[0006] In order to achieve the above object, the present application provides the following technical scheme: a real-time trajectory prediction system of unmanned aerial vehicle, comprising a rotor speed monitoring module, a flight attitude monitoring module, an unmanned aerial vehicle state judgment module, a control information acquisition module, a flight attitude comparison module, an attitude calibration module, and a trajectory prediction module.

[0007] The rotor speed monitoring module is used for monitoring the rotating speed of each rotor of the unmanned aerial vehicle respectively to obtain corresponding rotor speed, wherein the rotating speed of each rotor can be monitored by setting a rotating speed sensor on each rotor of the unmanned aerial vehicle.

[0008] The flight attitude monitoring module is used for monitoring the flight attitude of the unmanned aerial vehicle to obtain flight attitude data of the unmanned aerial vehicle, wherein the flight attitude data comprises a pitch angle, a yaw angle, a roll angle, a speed, an acceleration, a height, a position, and an attitude angular velocity, wherein the pitch angle is an angle of forward and backward inclination of the unmanned aerial vehicle, affecting upward and downward rising; the yaw angle is an angle of left and right rotation of the unmanned aerial vehicle, affecting the heading direction; the roll angle is an angle of side inclination of the unmanned aerial vehicle, affecting lateral movement; the attitude angular velocity of the unmanned aerial vehicle can be measured by a gyroscope, so as to calculate the pitch angle, the yaw angle, and the roll angle; the speed comprises a horizontal speed and a vertical speed, representing the flight speed of the unmanned aerial vehicle; the acceleration comprises acceleration data in each direction, which is helpful for evaluating the dynamic change of the unmanned aerial vehicle, and the acceleration can be measured by an acceleration sensor, and the speed and the position of the unmanned aerial vehicle can be calculated by acceleration change; the height is height information relative to the ground, which is usually obtained by an air pressure sensor or a GPS; the position is GPS positioning data, comprising longitude and latitude and relative height; the attitude angular velocity represents the angular velocity of the pitch, the yaw, and the roll, which is helpful for dynamically adjusting the flight attitude.

[0009] The unmanned aerial vehicle state judgment module is used for judging whether the flight attitude of the unmanned aerial vehicle matches the rotor speed of each rotor based on the rotor speed of each rotor and the flight attitude data.

[0010] The control information acquisition module is used for acquiring control information for controlling the unmanned aerial vehicle.

[0011] The flight attitude comparison module is used for judging whether the flight attitude of the unmanned aerial vehicle matches the control information based on comparison of the flight attitude data and the control information.

[0012] The attitude calibration module is used for re-matching the flight attitude and the rotor speed of each rotor to make the flight attitude match the control information when the judgment of the flight attitude comparison module is no.

[0013] The trajectory prediction module is configured to predict a flight trajectory of the unmanned aerial vehicle based on the flight attitude data after the attitude calibration module re-matches the flight attitude and the rotation speeds of the rotors, to obtain predicted trajectory coordinates. It is known in the art that the flight trajectory is predicted based on the flight attitude data, and no changes are made in this application. Therefore, this technical solution will not be described in detail, and it will not cause any problems in this field, such as using recurrent neural networks (RNN) and long short-term memory networks (LSTM).

[0014] Further, the unmanned aerial vehicle state judgment module is configured to judge whether the flight attitude of the unmanned aerial vehicle matches the rotation speeds of the rotors based on the rotation speeds of the rotors and the flight attitude data, including the following steps:

[0015] Obtain historical flight attitude data and corresponding rotation speeds of the rotors of the unmanned aerial vehicle when flying without external interference;

[0016] Based on the historical flight attitude data and the corresponding rotation speeds of the rotors, regression analysis is performed to obtain an attitude-speed relationship formula between the flight attitude data and the rotation speeds of the rotors, and a rotor attitude relationship between the flight attitude changes corresponding to the changes in the rotation speeds of the rotors, for example, the unmanned aerial vehicle has four rotors, which are 1, 2, 3 and 4 rotors arranged at the four corners of a rectangle, wherein the 1 and 3 rotors are diagonally arranged, and the 2 and 4 rotors are diagonally arranged. The rotor attitude relationship includes synchronously reducing the rotation speeds of the 1 and 3 rotors, and rotating the unmanned aerial vehicle around the central vertical line to the 2 rotation direction;

[0017] Obtain the current rotation speeds of the rotors and the flight attitude data of the unmanned aerial vehicle, and substitute the rotation speeds of the rotors into the attitude-speed relationship formula to obtain theoretical flight attitude data;

[0018] Judge whether the theoretical flight attitude data matches the current flight attitude data;

[0019] If yes, the flight attitude is normal; if no, the flight attitude is the first abnormal, indicating that there is an abnormal reason for interference in the current flight, wherein the abnormal reason can include rotor damage affecting rotor lift, body affecting air resistance, encountering external wind force, etc.

[0020] Further, the flight attitude comparison module is configured to judge whether the flight attitude of the unmanned aerial vehicle matches the control information based on the comparison of the flight attitude data and the control information, including the following steps:

[0021] Obtain historical flight attitude data and corresponding control information, and associate the flight attitude data with the corresponding control information;

[0022] Obtain the current flight attitude data and the control information;

[0023] determine whether the current flight attitude data and the control information data are associated;

[0024] If yes, the flight attitude is normal; if no, the flight attitude is second abnormal.

[0025] Further, the attitude calibration module is configured to re-match the flight attitude and the rotation speed of each rotor when the flight attitude comparison module determines no, so that the flight attitude matches the control information, including the following steps:

[0026] determine whether the flight attitude is second abnormal;

[0027] If yes, obtain the flight attitude data associated with the current control information to obtain target flight attitude data;

[0028] calculate the difference between the current flight attitude data and the target flight attitude data to obtain flight attitude adjustment data;

[0029] obtain the required flight attitude change based on the flight attitude adjustment data, and obtain the required rotor speed change based on the rotor attitude relationship;

[0030] adjust the corresponding rotor speed based on the required rotor speed change until the current flight attitude data and the target flight attitude data are the same;

[0031] substitute the flight attitude data at this time into the attitude speed relationship formula to obtain the corresponding rotor speed, which is marked as the theoretical rotor speed;

[0032] obtain the actual rotor speed of each rotor at this time, calculate the difference between the actual rotor speed and the corresponding theoretical rotor speed to obtain the rotor correction speed, and associate the rotor correction speed with the flight attitude data at this time to obtain the rotor correction speed flight attitude relationship.

[0033] Further, the system further comprises a flight attitude abnormality reason judgment module, the flight attitude abnormality reason judgment module is configured to mark the abnormality reason corresponding to each rotor correction speed flight attitude relationship, train a machine learning model based on the rotor correction speed flight attitude relationship and the corresponding abnormality reason to obtain an abnormality reason prediction model, the abnormality reason prediction model is configured to output a predicted abnormality reason based on the input rotor correction speed flight attitude relationship, including the following steps:

[0034] obtain the rotor correction speed flight attitude relationship of a set continuous time length;

[0035] set a plurality of abnormality reason labels corresponding to the abnormality reason;

[0036] associate each rotor correction speed flight attitude relationship of a set continuous time length with the corresponding abnormality reason label;

[0037] The machine learning model is trained based on the rotor correction rotating speed flight attitude relationship of each setting continuous time length and the corresponding abnormal reason label, to obtain an abnormal reason prediction model, and the present application does not limit the specific machine learning model, which can be selected according to the needs during training, such as support vector machine (SVM), decision tree, random forest, convolutional neural network (CNN) and recurrent neural network (RNN) and the like; and during training, the rotor correction rotating speed in the rotor correction rotating speed flight attitude relationship of setting continuous time length and the corresponding flight attitude data are taken as input, the features of the input data are extracted, the features of the output data are output in the hidden layer, the features of the output data are associated with the corresponding abnormal reason label, and the abnormal reason label is taken as the output of the model;

[0038] The most recent rotor correction rotating speed flight attitude relationship of setting continuous time length is obtained, input into the abnormal reason prediction model, and the predicted abnormal reason label is obtained.

[0039] Further, the abnormal reason label includes a self-abnormal label and an external force abnormal label, the self-abnormal label corresponds to an abnormal reason caused by damage of the unmanned aerial vehicle itself, such as rotor damage, body damage and the like, and the external force abnormal label corresponds to an abnormal reason caused by external force influence, such as wind influence.

[0040] Further, the flight attitude abnormal reason judgment module is further used to send a reminder to the user when the output abnormal reason is the senior abnormal label, and specifically, the user can be reminded through a pop-up window or information sending.

[0041] A real-time trajectory prediction method of an unmanned aerial vehicle, comprising the following steps:

[0042] Flight attitude data, rotating speeds of each rotor and control information of the unmanned aerial vehicle are monitored and obtained;

[0043] The flight attitude data and the rotating speeds of each rotor of the unmanned aerial vehicle in the state without external force interference are subjected to regression analysis, to obtain an attitude speed relationship formula of the flight attitude data and the rotating speeds of each rotor, and a rotor attitude relationship of flight attitude change corresponding to the rotating speed change of each rotor;

[0044] The flight attitude data are matched with the control information;

[0045] It is judged whether the control information matches the current flight attitude data:

[0046] If not, the corresponding rotor rotating speed is adjusted according to the rotor attitude relationship of flight attitude change corresponding to the rotating speed change of each rotor, until the control information matches the current flight attitude data;

[0047] Based on the matched flight attitude data, a flight trajectory of the unmanned aerial vehicle is predicted to obtain predicted trajectory coordinates.

[0048] 1. Compared with the prior art, the unmanned aerial vehicle real-time trajectory prediction system and method provided by the application can judge whether the unmanned aerial vehicle and its flight attitude are abnormal according to the relationship among the unmanned aerial vehicle rotor speed, flight attitude data and control information by setting a rotor speed monitoring module, a flight attitude monitoring module, an unmanned aerial vehicle state judgment module, a control information acquisition module and a flight attitude comparison module.

[0049] 2. Compared with the prior art, the unmanned aerial vehicle real-time trajectory prediction system and method provided by the application can reduce the influence of interference factors on the flight attitude and the difficulty of trajectory prediction by adjusting the rotor speed and flight attitude of the unmanned aerial vehicle when the unmanned aerial vehicle or its flight attitude is abnormal, thereby improving the trajectory prediction accuracy.

[0050] 3. Compared with the prior art, the unmanned aerial vehicle real-time trajectory prediction system and method provided by the application can predict the cause of the abnormal flight attitude of the unmanned aerial vehicle by analyzing the unmanned aerial vehicle rotor speed and flight attitude data before and after the flight attitude correction, and remind the user when the abnormal cause is self-damage, so as to maintain the unmanned aerial vehicle in time. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art according to these drawings.

[0052] Figure 1 The system structure block diagram provided for the embodiments of the present application;

[0053] Figure 2 The method step diagram provided for the embodiments of the present application. DETAILED DESCRIPTION

[0054] In order to make those skilled in the art better understand the technical solutions of the present application, the present application will be further described in detail with reference to the drawings.

[0055] In the description of the present application, the terms "first", "second", "third", "fourth", "fifth", "sixth", "seventh" and "eighth" are used only for descriptive purposes and are not to be construed as indicating or implying relative importance or a specific number of the technical features indicated. Thus, features defined with "first", "second", "third", "fourth", "fifth", "sixth", "seventh" and "eighth" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "plurality" is two or more, unless otherwise explicitly and specifically limited. In addition, the terms "mount", "connect", "connection" should be broadly understood, for example, can be fixed connection, can also be detachable connection, or integral connection; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0056] In the following, example embodiments will be described more fully with reference to the accompanying drawings, in which example embodiments can be embodied in different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0057] In the case of no conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0058] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0059] Please refer to Figure 1 - Figure, a real-time trajectory prediction system of a UAV, comprising a rotor speed monitoring module, a flight attitude monitoring module, a UAV state judgment module, a control information acquisition module, a flight attitude comparison module, an attitude calibration module, a trajectory prediction module;

[0060] The rotor speed monitoring module is used to monitor the rotation speed of each rotor of the UAV respectively, and obtain the corresponding rotor speed, wherein the rotation speed of each rotor can be monitored by setting a rotation speed sensor on each rotor of the UAV;

[0061] The flight attitude monitoring module is configured to monitor the flight attitude of the unmanned aerial vehicle, and obtain flight attitude data of the unmanned aerial vehicle, wherein the flight attitude data comprises a pitch angle, a yaw angle, a roll angle, a speed, an acceleration, a height, a position, and an attitude angular velocity, the pitch angle is an angle of forward and backward inclination of the unmanned aerial vehicle, and affects upward and downward rising of the unmanned aerial vehicle, the yaw angle is an angle of left and right rotation of the unmanned aerial vehicle, and affects a heading direction of the unmanned aerial vehicle, the roll angle is an angle of side inclination of the unmanned aerial vehicle, and affects lateral movement of the unmanned aerial vehicle, the angular velocity of the unmanned aerial vehicle can be measured by a gyroscope, so as to calculate the pitch angle, the yaw angle, and the roll angle, the speed comprises a horizontal speed and a vertical speed, and indicates a flight speed of the unmanned aerial vehicle, the acceleration comprises acceleration data in each direction, and is helpful to evaluate dynamic changes of the unmanned aerial vehicle, the acceleration can be measured by an acceleration sensor, and the speed and the position of the unmanned aerial vehicle can be calculated according to the acceleration changes, the height is height information relative to the ground, and is usually obtained by an air pressure sensor or a GPS, the position is GPS positioning data, and comprises longitude and latitude and relative height, and the attitude angular velocity indicates angular velocities of the pitch, the yaw, and the roll, and is helpful to dynamically adjust the flight attitude.

[0062] The unmanned aerial vehicle state judgment module is configured to judge whether the flight attitude of the unmanned aerial vehicle matches the rotation speed of each rotor based on the rotation speed of each rotor and the flight attitude data, and comprises the following steps.

[0063] A1. Obtain historical flight attitude data and corresponding rotation speeds of each rotor of the unmanned aerial vehicle when the unmanned aerial vehicle flies in a state without external interference.

[0064] A2. Perform regression analysis based on the historical flight attitude data and the corresponding rotation speeds of each rotor, to obtain an attitude-rotation speed relationship formula of the flight attitude data and the rotation speed of each rotor, and a rotor attitude relationship of flight attitude changes corresponding to changes in the rotation speed of each rotor, for example, the unmanned aerial vehicle has four rotors, which are a No. 1 rotor, a No. 2 rotor, a No. 3 rotor, and a No. 4 rotor arranged at four corners of a split rectangle, the No. 1 rotor and the No. 3 rotor are arranged in a diagonal line, the No. 2 rotor and the No. 4 rotor are arranged in a diagonal line, and the rotor attitude relationship comprises synchronously reducing the rotation speed of the No. 1 rotor and the No. 3 rotor, and rotating the unmanned aerial vehicle around a central vertical line to a direction of the No. 2 rotor.

[0065] A3. Obtain the current rotation speed of each rotor and the flight attitude data of the unmanned aerial vehicle, and substitute the rotation speed of each rotor into the attitude-rotation speed relationship formula to obtain theoretical flight attitude data.

[0066] A4. Judge whether the theoretical flight attitude data matches the current flight attitude data.

[0067] A5. If yes, the flight attitude is normal; if no, the flight attitude is first abnormal, indicating that there is an abnormal reason for interference in the current flight, wherein the abnormal reason can comprise rotor damage affecting rotor lift, a body affecting air resistance, encountering external wind force, and the like.

[0068] The control information acquisition module is configured to acquire control information for controlling the UAV.

[0069] The flight attitude comparison module is configured to determine whether the flight attitude of the UAV matches the control information based on a comparison of the flight attitude data and the control information, including the following steps:

[0070] B1, acquire historical flight attitude data and corresponding control information, and associate the flight attitude data with the corresponding control information;

[0071] B2, acquire current flight attitude data and control information;

[0072] B3, determine whether the current flight attitude data and the control information data are associated;

[0073] B4, if yes, the flight attitude is normal; if no, the flight attitude is second abnormal.

[0074] The attitude calibration module is configured to re-match the flight attitude and the rotation speed of each rotor when the flight attitude comparison module determines no, so that the flight attitude matches the control information, including the following steps:

[0075] C1, determine whether the flight attitude is second abnormal;

[0076] C2, if yes, acquire flight attitude data associated with the current control information to obtain target flight attitude data;

[0077] C3, calculate the difference between the current flight attitude data and the target flight attitude data to obtain flight attitude adjustment data;

[0078] C4, obtain the required flight attitude change based on the flight attitude adjustment data, and obtain the required rotor speed change according to the rotor attitude relationship;

[0079] C5, adjust the corresponding rotor speed based on the required rotor speed change until the current flight attitude data and the target flight attitude data are the same;

[0080] C6, substitute the flight attitude data at this time into the attitude speed relationship formula to obtain the corresponding rotor speed, which is marked as the theoretical rotor speed;

[0081] C7, acquire the actual rotor speed of each rotor at this time, calculate the difference between the actual rotor speed and the corresponding theoretical rotor speed to obtain the rotor correction speed, and associate the rotor correction speed with the flight attitude data at this time to obtain the rotor correction speed flight attitude relationship

[0082] The trajectory prediction module is configured to predict the flight trajectory of the unmanned aerial vehicle based on the flight attitude data after the attitude calibration module re-matches the flight attitude and the rotation speed of each rotor, to obtain predicted trajectory coordinates. It is known in the prior art to predict the flight trajectory based on flight attitude data, and this is directly applied without change in this technical solution, so it will not be described in detail in this technical solution, and it will not cause any problems in the field. For example, recurrent neural networks (RNN) and long short-term memory networks (LSTM) can be used.

[0083] The system also includes a flight attitude anomaly cause judgment module, which is configured to label the abnormal causes corresponding to the rotor correction speed flight attitude relationship, train a machine learning model based on the rotor correction speed flight attitude relationship and the corresponding abnormal causes, and obtain an abnormal cause prediction model. The abnormal cause prediction model is configured to output a predicted abnormal cause based on the input rotor correction speed flight attitude relationship, including the following steps:

[0084] D1, obtain a rotor correction speed flight attitude relationship with a continuous time length;

[0085] D2, set a plurality of abnormal cause labels corresponding to abnormal causes. Further, the abnormal cause labels include a self-abnormal label and an external force abnormal label. The abnormal cause corresponding to the self-abnormal label is an abnormality caused by damage to the unmanned aerial vehicle itself, such as rotor damage or body damage. The abnormal cause corresponding to the external force abnormal label is an abnormality caused by external force, such as wind force.

[0086] D3, associate each rotor correction speed flight attitude relationship with a continuous time length with the corresponding abnormal cause label;

[0087] D4, train a machine learning model based on each rotor correction speed flight attitude relationship with a continuous time length and the corresponding abnormal cause label, to obtain an abnormal cause prediction model. The present application does not limit the specific machine learning model, which can be selected according to the needs during training, such as support vector machines (SVM), decision trees, random forests, convolutional neural networks (CNN), and recurrent neural networks (RNN). During training, the rotor correction speed and the corresponding flight attitude data in the rotor correction speed flight attitude relationship with a continuous time length are input, the features of the input data are extracted, the features of the input data are output in the hidden layer, the features of the output data are associated with the corresponding abnormal cause label, and the abnormal cause label is output as the model.

[0088] D5, obtain the most recent rotor correction speed flight attitude relationship with a continuous time length, input the abnormal cause prediction model, and obtain the predicted abnormal cause label;

[0089] The D6, flight attitude abnormality reason judging module is further configured to issue a prompt to the user when the output abnormality reason is the senior abnormality label, and specifically, the user can be prompted through a pop-up window or by sending a message.

[0090] A real-time trajectory prediction method for a UAV, comprising the following steps:

[0091] Flight attitude data, rotor speeds and control information of the UAV are monitored and acquired.

[0092] Regression analysis is performed on the flight attitude data and the rotor speeds of the UAV in a state without external force interference, to obtain a relationship formula between the flight attitude data and the rotor speeds, and a rotor attitude relationship between changes in the rotor speeds and changes in the flight attitude.

[0093] The flight attitude data are matched with the control information.

[0094] It is judged whether the control information matches the current flight attitude data.

[0095] If not, the corresponding rotor speed is adjusted according to the rotor attitude relationship between changes in the rotor speeds and changes in the flight attitude, until the control information matches the current flight attitude data.

[0096] Based on the matched flight attitude data, the flight trajectory of the UAV is predicted to obtain a predicted trajectory coordinate.

[0097] The foregoing merely describes some exemplary embodiments of the present application by way of illustration, and it is needless to say that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present application. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present application.

Claims

1. A real-time trajectory prediction system for unmanned aerial vehicles (UAVs), characterized in that: It includes a rotor speed monitoring module, a flight attitude monitoring module, a UAV status judgment module, a control information acquisition module, a flight attitude comparison module, an attitude calibration module, and a trajectory prediction module; The rotor speed monitoring module is used to monitor the rotation speed of each rotor of the UAV and obtain the corresponding rotor speed. The flight attitude monitoring module is used to monitor the flight attitude of the UAV and obtain the flight attitude data of the UAV. The UAV status judgment module is used to determine whether the UAV's flight attitude matches the rotational speed and flight attitude data of each rotor. The control information acquisition module is used to acquire control information for controlling the UAV; The flight attitude comparison module is used to determine whether the UAV's flight attitude and control information match based on the comparison between flight attitude data and control information. The attitude calibration module is used to re-match the flight attitude with the rotational speed of each rotor when the flight attitude comparison module determines that the flight attitude is negative, so that the flight attitude matches the control information. The trajectory prediction module is used to predict the flight trajectory of the UAV based on the flight attitude data after the attitude calibration module rematches the flight attitude with the rotation speed of each rotor, and obtain the predicted trajectory coordinates. The UAV status judgment module is used to determine whether the UAV's flight attitude matches the rotational speed of each rotor based on the rotor speed and flight attitude data of each rotor. The module includes the following steps: obtaining the historical flight attitude data of the UAV when it is flying in a state without external interference and the corresponding rotor speed of each rotor. Based on historical flight attitude data and the corresponding rotor speeds of each rotor, regression analysis was performed to obtain the formula for the relationship between flight attitude data and the attitude speed of each rotor, and the rotor attitude relationship between changes in flight attitude and changes in rotor speed. Obtain the current rotor speed and flight attitude data of the UAV, substitute the rotor speed into the attitude speed relationship formula, and obtain the theoretical flight attitude data; Determine whether the theoretical flight attitude data matches the current flight attitude data; If yes, the flight attitude is normal; if no, the flight attitude is abnormal. The flight attitude comparison module is used to determine whether the flight attitude of the UAV matches the control information based on the comparison of flight attitude data and control information. It includes the following steps: acquiring historical flight attitude data and corresponding control information, and associating the flight attitude data with the corresponding control information. Acquire current flight attitude data and control information; Determine whether the current flight attitude data and control information data are correlated; If yes, the flight attitude is normal; if no, the flight attitude is the second abnormality. The attitude calibration module is used to re-match the flight attitude with the rotational speed of each rotor when the flight attitude comparison module determines that it is not, so that the flight attitude matches the control information. The steps include: determining whether it is a second abnormality of flight attitude. If so, then obtain the flight attitude data associated with the current control information to obtain the target flight attitude data; Calculate the difference between the current flight attitude data and the target flight attitude data to obtain the flight attitude adjustment data; Based on the flight attitude adjustment data, the required flight attitude change is obtained, and based on the rotor attitude relationship, the required rotor speed change is obtained. Adjust the corresponding rotor speed based on the required rotor speed change until the current flight attitude data is the same as the target flight attitude data; Substitute the flight attitude data at this time into the attitude speed relationship formula to obtain the corresponding rotor speed, which is marked as the theoretical rotor speed. The actual rotor speed is obtained by acquiring the rotational speed of each rotor at this time. The difference between the actual rotor speed and the corresponding theoretical rotor speed is calculated to obtain the rotor correction speed. The rotor correction speed is then associated with the flight attitude data at this time to obtain the rotor correction speed-flight attitude relationship. The system also includes a flight attitude anomaly cause judgment module. The flight attitude anomaly cause judgment module is used to mark the anomaly causes corresponding to the flight attitude relationship of each rotor correction speed. Based on the rotor correction speed flight attitude relationship and the corresponding anomaly causes, a machine learning model is trained to obtain an anomaly cause prediction model. The anomaly cause prediction model is used to output the predicted anomaly causes based on the input rotor correction speed flight attitude relationship. The system includes the following steps: obtaining the rotor correction speed flight attitude relationship with a set continuous duration. Set multiple exception reason labels corresponding to the exception reasons; Associate the relationship between the rotor correction speed and flight attitude for each set continuous duration with the corresponding anomaly cause label; Based on the relationship between rotor correction speed and flight attitude for each continuous duration and the corresponding abnormal cause label, a machine learning model is trained to obtain an abnormal cause prediction model. Obtain the most recent rotor correction speed and flight attitude relationship with a long continuous setting time, input it into the anomaly cause prediction model, and obtain the predicted anomaly cause label; The abnormality cause labels include self-abnormality labels and external force abnormality labels. The abnormality cause corresponding to the self-abnormality label is the abnormality caused by damage to the UAV itself, and the abnormality cause corresponding to the external force abnormality label is the abnormality caused by external force.

2. The real-time trajectory prediction system for unmanned aerial vehicles according to claim 1, characterized in that: The flight attitude abnormality cause judgment module is also used to issue a reminder to the user when the output abnormality cause is a senior-level abnormality label.

3. A method for real-time trajectory prediction of unmanned aerial vehicles (UAVs), applicable to the real-time trajectory prediction system for UAVs as described in any one of claims 1-2, characterized in that: Includes the following steps: Monitor and acquire flight attitude data, rotor speed and control information of the UAV; Regression analysis was performed on the flight attitude data and rotor speed of the UAV under the condition of no external interference to obtain the attitude speed relationship formula between the flight attitude data and the rotor speed, and the rotor attitude relationship between the flight attitude change and the change of rotor speed. Match flight attitude data with control information; Determine if the control information matches the current flight attitude data: If not, adjust the corresponding rotor speed according to the rotor attitude relationship of the flight attitude change corresponding to the change of each rotor speed until the control information matches the current flight attitude data. Based on the matched flight attitude data, the flight trajectory of the UAV is predicted, and the predicted trajectory coordinates are obtained.

Images