Unmanned aerial vehicle sensor fault safe flight control method and system

Abstract

The invention relates to the field of unmanned aerial vehicle control, in particular to an unmanned aerial vehicle sensor fault safety flight control method and system.The method comprises the steps that relative displacement changes of wings and three-axis data of a sensor are obtained when an unmanned aerial vehicle flies, and the relative displacement changes comprise vertical height changes and tendency changes; calculating a mutation index of the unmanned aerial vehicle according to the vertical height change of the wings, and judging whether the fuselage of the unmanned aerial vehicle is abnormal or not so as to construct a fluctuation interval of the unmanned aerial vehicle; according to historical flight data, an abnormal interval is determined by calculating similarity and applying an Otsu threshold method. Meanwhile, the three-axis data synchronization coefficients of the current sensor and the historical sensor are compared to identify sensor faults, and when the optimal synchronization coefficient is lower than a preset threshold value, PID control homeward voyage is triggered to ensure flight safety. By calculating the synchronization coefficient of the sensor, the capability of detecting the sensor fault of the unmanned aerial vehicle is improved, so that the safe flight of the unmanned aerial vehicle is ensured.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle control, and more specifically to a method and system for unmanned aerial vehicle sensor failure-safe flight control. Background Art

[0002] A drone, or unmanned aerial vehicle (UAV), is an aircraft that does not require a human pilot to operate it. It flies autonomously through remote control or preset programs. With the advancement of technology, especially breakthroughs in avionics, communications, sensors and artificial intelligence, drones have become an important tool in many fields such as military reconnaissance, surveillance, target strikes, as well as agricultural monitoring, logistics distribution, environmental research, film and television production, emergency rescue and infrastructure inspection in the civilian field, which has led to more attention to the flight safety of drones; drone sensors are key components in drone systems, used to collect and process drone flight status and environmental information, thereby protecting drone flights.

[0003] The existing Chinese patent application document with publication number CN115167508A discloses a multi-rotor UAV sensor fault safety flight control system and method, including: a sensor module, used to detect the current first flight state information of the UAV; a fault monitoring module, used to monitor the operating state information of each sensor in the sensor module, and determine whether each sensor has an abnormality; a control module, used to obtain the visual data of the UAV after an abnormality occurs in the sensor module, and control the flight of the UAV based on the first flight state information and visual data.

[0004] The application document uses the first flight status information and visual data to determine the status of the drone, provide accurate flight control, and ensure flight safety in the event of a sensor failure. Currently, sensors play a vital role in the flight of drones. However, sensor failure may cause the drone to be unable to obtain accurate flight data, thereby affecting flight safety. If the drone's real-time data feedback system fails to identify and report sensor failures in a timely manner, the control terminal may not be able to issue an effective warning, and if the drone continues to fly, there is a risk of an accident. Summary of the invention

[0005] In order to solve the problem that the real-time data feedback system of the drone fails to identify and report sensor failure in time, the control terminal may not be able to issue an effective warning, and if the drone continues to fly, there is a risk of an accident, the present invention provides solutions in the following aspects.

[0006] In a first aspect, a method for safe flight control of a drone sensor failure comprises: obtaining a relative displacement change of a wing and three-axis data of a sensor when the drone is flying, wherein the relative displacement change comprises: a vertical height change and a tilt change; calculating a mutation index of the drone according to a vertical height change of the wing from the time when the drone takes off to the current moment, determining whether an abnormality occurs to the drone fuselage, and constructing a fluctuation interval of the drone; traversing historical flight data of the same model as the current drone, taking a data interval of the same period in the historical flight data as an interval to be matched, calculating a similarity between the fluctuation interval and the interval to be matched, obtaining a plurality of height difference similarities, forming a set of the height difference similarities in descending order, using the Otsu threshold method to perform binary classification on the set, obtaining two groups, and taking a maximum mean of the group as an abnormal interval to be determined; calculating a three-axis data synchronization coefficient between a sensor of the current drone and a corresponding sensor of the drone in the historical data, taking the maximum value of the synchronization coefficient of the corresponding sensors of all the abnormal intervals to be determined as an optimal synchronization coefficient, and in response to the optimal synchronization coefficient being less than a preset synchronization threshold, indicating that a sensor of the current drone fails, and using PID to control the drone to return.

[0007] The effect is as follows: by real-time monitoring of the relative displacement changes of the drone's wings and the three-axis data of the sensor, calculating the mutation index and constructing the fluctuation range, it is beneficial to timely discover abnormal conditions of the drone body; by comparing with the historical flight data of the same model of drone, calculating the similarity between the fluctuation range and the interval to be matched, and using the Otsu threshold method for binary classification, the abnormal interval can be effectively identified, the monitoring of the drone status can be enhanced, and the accuracy of fault detection can be improved. It can significantly improve the safety and reliability of the drone during flight and reduce the risk of accidents caused by sensor failures.

[0008] Preferably, the mutation index includes: Get the vertical height difference between any two wings of the drone, take the maximum vertical height difference as the height difference of the drone's fuselage, and get the height difference sequence of the drone's fuselage from the take-off time to the current time. The ratio of the fuselage height difference of the drone between the current moment and the previous moment in the fuselage height difference sequence is used as the height change factor of the drone at the current moment, and the complement of the ratio between the height change factor and the average of the fuselage height difference ratios of the drone from the take-off moment to the moment before the current moment is calculated to obtain the mutation index of the fuselage height difference at the current moment.

[0009] The effect is: by comparing the vertical height difference between any two wings of the drone, the vertical changes of the drone fuselage can be accurately captured, which helps to identify abnormal postures that may occur in the drone during flight. The amplitude of the drone state change is obtained through the ratio of the fuselage height difference between the current moment and the previous moment, which reflects the mutation index of the drone state. The flight route is adjusted or the return procedure is executed according to the mutation index to ensure the safety of the drone.

[0010] Preferably, the mutation index further includes: The absolute value of the difference between the height difference ratio of the drone at the current moment and the previous moment is taken as the change amplitude of the height difference of the drone at the current moment; The average of the absolute values ​​of the height difference ratios between the moment when the drone takes off and the moment before the current moment is taken as the average amplitude of the drone; The ratio between the change amplitude of the fuselage height difference at the current moment and the average amplitude of the UAV is taken as the mutation index of the UAV at the current moment.

[0011] Preferably, the step of constructing the fluctuation range of the drone includes: In response to the mutation index being greater than the mutation threshold, the fuselage of the UAV is abnormal, and the flight data of the UAV from the take-off time to the current time is used to construct a fluctuation range.

[0012] The effect is: by constructing a fluctuation range, analyzing whether the flight status of the drone deviates from the normal range, further analyzing and confirming abnormal situations, and improving the flight safety of the drone.

[0013] Preferably, the height difference similarity includes: The Pearson correlation coefficient between the fluctuation interval to be determined and the interval to be matched is calculated to obtain the height difference similarity.

[0014] Preferably, the height difference similarity also includes: Calculate the Pearson correlation coefficient between the pending fluctuation interval and the interval to be matched, and calculate the dynamic time warping distance between the pending fluctuation interval and the interval to be matched; The ratio between the Pearson correlation coefficient and the dynamic time warping distance is taken as the height difference similarity.

[0015] The effect is that by calculating the ratio between the Pearson correlation coefficient and the DTW distance as the height difference similarity, the abnormal patterns in the UAV flight data can be more accurately identified. This method can capture the subtle differences between the data and improve the accuracy of anomaly detection. Among them, the Pearson correlation coefficient is more sensitive to outliers, while the DTW distance can better handle the local deformation of the time series and enhance the robustness of anomaly detection.

[0016] Preferably, the synchronization coefficient satisfies the following polynomial: ; ; In the formula, represents the synchronization coefficient of the sensor, represents the three-axis vector of the sensor, Indicates that the sensor is around The rotation speed of the shaft, Indicates that the sensor is around The rotation speed of the shaft, Indicates that the sensor is around The rotation speed of the shaft, Indicates that the drone is The first flight The three-axis vector of the sensor at the moment, Indicates that the drone is The first flight The three-axis vector of the sensor at the moment, Indicates the time interval, represents the starting point of any pending abnormal interval, Represents cosine similarity.

[0017] The effect is that by monitoring the synchronization coefficient in real time, the control parameters can be dynamically adjusted to adapt to changes in sensor data, thereby improving flight stability and safety. A high synchronization coefficient indicates that the sensor data is highly consistent at different time points or between different drones. If the synchronization coefficient is significantly lower than normal, this may indicate a sensor failure or data anomaly.

[0018] In a second aspect, a drone sensor failure safety flight control system includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned drone sensor failure safety flight control method is implemented.

[0019] The present invention has the following effects: 1. The present invention compares the similarity between historical flight data and current flight data and uses the Otsu threshold method for binary classification to effectively identify the abnormal fluctuation range in UAV flight. By calculating the sensor synchronization coefficient and then analyzing the consistency between the current sensor data and the historical data, the detection capability of UAV sensor failure is further enhanced.

[0020] 2. The present invention monitors the relative displacement changes of the drone's wings and the three-axis data of the sensor in real time to promptly detect abnormal states of the drone's sensors. By calculating the mutation index and fluctuation range, the system can identify abnormal behavior of the drone's fuselage and respond in a timely manner, thereby improving the flight safety of the drone. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a method flow chart of steps S1 to S4 in a method for safe flight control of a drone sensor failure according to an embodiment of the present invention.

[0022] Figure 2 The present invention is a structural block diagram of a UAV sensor failure safety flight control system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] Specific implementation scenario: When the drone is in flight, Reference Figure 1 , a drone sensor failure safe flight control method includes steps S1 to S4, which are as follows: S1: Obtain the relative displacement change of the wing and the three-axis data of the sensor during the flight of the UAV, wherein the relative displacement change includes: vertical height change and inclination change.

[0026] Exemplarily, an infrared position detection is installed at the bottom of each wing of the drone, and the infrared position detection can obtain the relative position height between each wing.

[0027] In this embodiment, the sensor is a gyroscope, which monitors the angular velocity of the drone around each axis, maintains the stability of the drone and prevents shaking, so as to avoid accidents caused by failure of the gyroscope and inability to fly safely.

[0028] It should be noted that in the initial stage of the drone's takeoff, if the environmental wind is small, the vertical height relative position of the four rotor axes should remain stable with limited fluctuations. However, the actual situation may be affected by many factors, such as wind speed and propeller power changes. In order to ensure the safe flight of the drone, it is necessary to set a reasonable limit on the fluctuation range of the vertical height relative position of the four rotor axes. When the relative height of the drone's wings changes significantly, it means that the drone's flight state is unstable. Therefore, the vertical height change of the drone is further analyzed to obtain the mutation index of the drone. The specific steps are as follows: S2: According to the vertical height change of the drone's wing from takeoff to the current moment, the mutation index of the drone is calculated, and it is determined whether the drone fuselage has any abnormality, and the fluctuation range of the drone is constructed.

[0029] The steps to obtain the mutation index include: Get the vertical height difference between any two wings of the drone, take the maximum vertical height difference as the height difference of the drone's fuselage, and get the height difference sequence of the drone's fuselage from the take-off time to the current time. The ratio of the fuselage height difference of the drone between the current moment and the previous moment in the fuselage height difference sequence is taken as the height change factor of the drone at the current moment. The complement of the ratio between the height change factor and the mean of the fuselage height difference ratio from the take-off moment to the moment before the current moment is calculated to obtain the mutation index of the fuselage height difference at the current moment.

[0030] Specifically, the mutation index satisfies the following polynomial: ; ; In the formula, Indicates The mutation index of the drone at the moment, Indicates Flight No. The height difference ratio of the drone’s fuselage at the moment, Indicates Flight No. The height difference of the drone fuselage at each moment, Indicates Flight No. The height difference of the drone fuselage at each moment, Indicates Flight No. The height difference ratio of the drone’s fuselage at the moment, Indicates Flight No. The height difference ratio of the drone’s fuselage at the moment, represents the mean function.

[0031] That is to say, Indicates The change speed of the height difference of the drone fuselage at the moment When the speed of change at a moment is greater than the previous average speed, the mutation index When it is greater than 1, it means that the fuselage of the drone has undergone a sudden change, that is, a sudden tilt.

[0032] In addition, another embodiment further includes: The absolute value of the difference between the height difference ratio of the drone at the current moment and the previous moment is taken as the change amplitude of the height difference of the drone at the current moment; The average of the absolute values ​​of the height difference ratios between the moment when the drone takes off and the moment before the current moment is taken as the average amplitude of the drone; The ratio between the change amplitude of the fuselage height difference at the current moment and the average amplitude of the UAV is taken as the mutation index of the UAV at the current moment.

[0033] Specifically, the mutation index satisfies the following relationship: ; In the formula, Indicates The mutation index of the drone at the moment, Indicates Flight No. The height difference ratio of the drone’s fuselage at the moment, Indicates Flight No. The height difference ratio of the drone's fuselage at the moment, Indicates Flight No. The height difference ratio of the drone's fuselage at the moment, Indicates Flight No. The height difference ratio of the drone's fuselage at the moment, No. Flight No. The height difference ratio of the drone's fuselage at the moment, represents the mean function.

[0034] That is to say, Indicates Flight No. The height difference ratio of the drone's fuselage at the moment is calculated by comparing the drone's current vertical height with its vertical height at a previous moment. It is used to measure the rate at which the drone's height changes. It reflects the drastic degree of the altitude change of the drone between two adjacent moments. If it is greater than 1, the drone's wings fluctuate and tilt during flight. The tilt may be due to sensor failure or external influences, making the drone unable to fly normally.

[0035] In response to the mutation index being greater than the mutation threshold, the fuselage of the UAV is abnormal, and the flight data of the UAV from the take-off time to the current time is used to construct a fluctuation range.

[0036] To further explain, in order to further determine whether the current tilt is normal or abnormal, the system will search for data segments similar to the current fuselage height difference change in the historical database, thereby calculating the similarity between the fuselage height difference sequence of the current flight and the fuselage height difference sequence of the historical flight.

[0037] S3: Traverse the historical flight data of the same model as the current drone, and take the data interval of the same period in the historical flight data as the interval to be matched. Calculate the similarity between the fluctuation interval and the interval to be matched to obtain multiple height difference similarities, and organize the height difference similarities into a set in descending order. Use the Otsu threshold method to classify the set into two groups, and take the maximum mean of the group as the abnormal interval to be determined.

[0038] The steps for obtaining height difference similarity include: The Pearson correlation coefficient between the fluctuation interval to be determined and the interval to be matched is calculated to obtain the height difference similarity.

[0039] Specifically, the height difference similarity satisfies the following relationship: ; In the formula, Indicates Time to The similarity of the height difference of the drone at the moment, Indicates that the drone is The first flight Time to The height difference of the fuselage at the moment, Indicates that the drone is The first flight Time to The height difference of the fuselage at the moment, represents the Pearson correlation coefficient, Indicates a time interval.

[0040] That is to say, The closer the value is to 1, the stronger the linear relationship between the two sequences is, that is, the change in fuselage height difference in the current flight is similar to the change in fuselage height difference in historical flights.

[0041] In addition, another embodiment further includes: Calculate the Pearson correlation coefficient between the pending fluctuation interval and the interval to be matched, and calculate the dynamic time warping distance between the pending fluctuation interval and the interval to be matched; The ratio between the Pearson correlation coefficient and the dynamic time warping distance is taken as the height difference similarity.

[0042] Specifically, the height difference similarity satisfies the following relationship: ; In the formula, Indicates Time to The similarity of the height difference of the drone at the moment, Indicates that the drone is The first flight Time to The height difference of the fuselage at the moment, Indicates that the drone is The first flight Time to The height difference of the fuselage at the moment, represents the dynamic time warping algorithm value, represents the Pearson correlation coefficient, Indicates a time interval.

[0043] In other words, the greater the similarity of the height difference of the drone, the more similar the drone is in flight. Time to The height difference of the fuselage at the moment and at The first flight Time to The more similar the height differences of the fuselage at different moments are, the more likely it is that the sensor data will change synchronously.

[0044] Further analysis, the synchronization coefficient between the corresponding sensors of the drone in the undetermined abnormal interval and the corresponding sensors of the drone in the historical data is calculated in order to analyze the similarity between the sensors of the current flight and the sensors of the historical flight data, and then identify significant deviations, which may be caused by sensor failure. The specific steps are as follows: S4: Calculate the three-axis data synchronization coefficient between the sensor of the current drone and the corresponding sensor of the historical data drone, and take the maximum value of the synchronization coefficient of the sensors corresponding to all pending abnormal intervals as the optimal synchronization coefficient. When the optimal synchronization coefficient is less than the preset synchronization threshold, the sensor of the current drone fails, and the drone is controlled to return using PID.

[0045] Specifically, the synchronization coefficient satisfies the following polynomial: ; ; In the formula, represents the synchronization coefficient of the sensor, represents the three-axis vector of the sensor, Indicates that the sensor is around The rotation speed of the shaft, Indicates that the sensor is around The rotation speed of the shaft, Indicates that the sensor is around The rotation speed of the shaft, Indicates that the drone is The first flight The three-axis vector of the sensor at the moment, Indicates that the drone is The first flight The three-axis vector of the sensor at the moment, Indicates the time interval, represents the starting point of any pending abnormal interval, Represents cosine similarity.

[0046] That is to say, the degree of similarity is reflected by calculating the cosine similarity, where the value range of cosine similarity is When the synchronization coefficient of the sensor approaches When , it means that the current data is more similar to the historical data in direction, otherwise it tends to , it means completely dissimilar.

[0047] In addition, another embodiment further includes: The synchronization coefficient satisfies the following polynomial: ; ; In the formula, represents the synchronization coefficient of the sensor, Indicates that the drone is The first flight and The Euclidean distance between the three-axis vectors of the sensor at the corresponding time in the flight, Indicates Sensors at all times The rotation speed of the shaft, Indicates Sensors at all times The rotation speed of the shaft, Indicates Sensors at all times The rotation speed of the shaft, Indicates Sensors at all times The rotation speed of the shaft, Indicates Sensors at all times The rotation speed of the shaft, Indicates Sensors at all times The rotation speed of the shaft, Indicates a time interval.

[0048] The present invention also provides a UAV sensor failure safe flight control system. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for safe flight control of a sensor failure of an unmanned aerial vehicle according to the first aspect of the present invention is implemented.

[0049] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0050] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0051] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0052] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for controlling unmanned aerial vehicle sensor failure-safe flight, characterized in that: include: Acquire the relative displacement change of the wing and the three-axis data of the sensor during the flight of the UAV, wherein the relative displacement change includes: vertical height change and inclination change; According to the vertical height change of the drone's wing from takeoff to the current moment, the mutation index of the drone is calculated, and it is determined whether the drone fuselage has any abnormality, and the fluctuation range of the drone is constructed; Traverse the historical flight data of the same model as the current drone, take the data interval of the same period in the historical flight data as the interval to be matched, calculate the similarity between the fluctuation interval and the interval to be matched, obtain multiple height difference similarities, organize the height difference similarities into a set in descending order, use the Otsu threshold method to classify the set into two groups, and take the maximum mean of the group as the abnormal interval to be determined; Calculate the three-axis data synchronization coefficient between the sensor of the current drone and the corresponding sensor of the historical data drone, and take the maximum value of the synchronization coefficient of the sensors corresponding to all pending abnormal intervals as the optimal synchronization coefficient. When the optimal synchronization coefficient is less than the preset synchronization threshold, the sensor of the current drone fails, and the drone is controlled to return using PID.

2. The method for controlling a drone sensor failure-safe flight according to claim 1, characterized in that: The mutation index includes: Get the vertical height difference between any two wings of the drone, take the maximum vertical height difference as the height difference of the drone's fuselage, and get the height difference sequence of the drone's fuselage from the take-off moment to the current moment. The ratio of the fuselage height difference of the drone between the current moment and the previous moment in the fuselage height difference sequence is used as the height change factor of the drone at the current moment, and the complement of the ratio between the height change factor and the average of the fuselage height difference ratios of the drone from the take-off moment to the moment before the current moment is calculated to obtain the mutation index of the fuselage height difference at the current moment.

3. The method for controlling a drone sensor failure-safe flight according to claim 1, characterized in that: The mutation index also includes: The absolute value of the difference between the height difference ratio of the drone at the current moment and the previous moment is taken as the change amplitude of the height difference of the drone at the current moment; The average of the absolute values ​​of the height difference ratios between the moment when the drone takes off and the moment before the current moment is taken as the average amplitude of the drone; The ratio between the change amplitude of the fuselage height difference at the current moment and the average amplitude of the UAV is taken as the mutation index of the UAV at the current moment.

4. The method for controlling a drone sensor failure-safe flight according to claim 1, characterized in that: The construction of the fluctuation range of the drone includes: In response to the mutation index being greater than the mutation threshold, the fuselage of the UAV is abnormal, and the flight data of the UAV from the take-off time to the current time is used to construct a fluctuation range.

5. The method for controlling a drone sensor failure-safe flight according to claim 1, characterized in that: The height difference similarity includes: The Pearson correlation coefficient between the fluctuation interval to be determined and the interval to be matched is calculated to obtain the height difference similarity.

6. The method for controlling a drone sensor failure-safe flight according to claim 1, characterized in that: The height difference similarity also includes: Calculate the Pearson correlation coefficient between the pending fluctuation interval and the interval to be matched, and calculate the dynamic time warping distance between the pending fluctuation interval and the interval to be matched; The ratio between the Pearson correlation coefficient and the dynamic time warping distance is taken as the height difference similarity.

7. The method for controlling a drone sensor failure-safe flight according to claim 1, characterized in that: The synchronization coefficient satisfies the following polynomial: ； ； In the formula, represents the synchronization coefficient of the sensor, represents the three-axis vector of the sensor, Indicates that the sensor is around The rotation speed of the shaft, Indicates that the sensor is around The rotation speed of the shaft, Indicates that the sensor is around The rotation speed of the shaft, Indicates that the drone is The first flight The three-axis vector of the sensor at the moment, Indicates that the drone is The first flight The three-axis vector of the sensor at the moment, Indicates the time interval, represents the starting point of any pending abnormal interval, Represents cosine similarity.

8. A UAV sensor failure safe flight control system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the unmanned aerial vehicle sensor failure safety flight control method according to any one of claims 1 to 7 is implemented.

Images