Detection method and device

Abstract

The invention provides a detection method and device, and is applied to the field of automatic driving. The detection method comprises the steps that first measurement data and first reference data of a vehicle are obtained, the first measurement data comprise data collected by a positioning system of the vehicle at the first moment, and the first reference data comprise data of a reference track point of the vehicle at the first moment; and inputting the first measurement data and the first reference data into an adaptive Kalman filtering module to obtain a first reference difference, the first reference difference being a difference value between the optimized state estimation data at the first moment and the first reference data, and the optimized state estimation data at the first moment being obtained according to the first measurement data. And determining whether the positioning system is attacked according to the first reference difference. Therefore, the attack detection rate of the positioning system when the positioning system is subjected to the attack behavior can be improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving, and more particularly, to a detection method and device. Background Art

[0002] With the rapid development of autonomous driving, autonomous driving not only brings more convenience to drivers, but also reduces traffic accidents through precise control and cooperation between vehicles. Precise pose estimation is required for autonomous driving, but achieving reliable and robust navigation remains one of the main concerns in both the industrial and academic fields.

[0003] Currently, most vehicles can estimate the pose of the vehicle through three typical sensors: an inertial measurement unit (IMU), a positioning system, and a light detection and ranging (LiDAR). Among them, LiDAR can also be simply referred to as a lidar. For example, the positioning system can be a global positioning system (GPS), or it can be a Beidou system or other positioning systems.

[0004] Although the IMU is embedded in the vehicle and is usually not vulnerable to attacks, however, since civilian positioning systems are usually not encrypted and do not require authentication, civilian positioning systems are extremely vulnerable to malicious attacks. For example, there is currently a stealth manipulation attack on road navigation systems. By slightly modifying the GPS measurement results, 95% of the vehicles participating in the test can be navigated to the wrong destination.

[0005] Due to the power and concealment of fraud attacks on positioning systems, how to improve the detection rate of attacks on vehicle positioning systems is an urgent problem to be solved. Summary of the Invention

[0006] This application provides a detection method and device that can improve the detection rate of attacks on vehicle positioning systems.

[0007] In a first aspect, a detection method is provided. The method includes: obtaining first measurement data and first reference data of a vehicle. The first measurement data includes data collected by the positioning system of the vehicle at a first moment, and the first reference data includes data of a reference trajectory point of the vehicle at the first moment. Inputting the first measurement data and the first reference data into an adaptive Kalman filter module to obtain a first reference difference, where the first reference difference is the difference between the optimized state estimation data at the first moment and the first reference data, and the optimized state estimation data at the first moment is obtained according to the first measurement data. Determining whether the positioning system is attacked according to the first reference difference.

[0008] In the above technical solution, by estimating the reference difference between the estimated data and the reference data to detect whether the positioning system is under attack, compared with the residual-based detection method, it can better detect hidden attack behaviors. For example, if the attacker sets the attack signal small enough so that the difference between the measurement data and the estimated data of the sensors in the positioning system, that is, the residual, is close enough, it can avoid being detected. Therefore, the above technical solution can improve the attack detection rate of the positioning system when under attack. In addition, this solution can be implemented through simple programming languages, such as the C language, the scripting language of MATLAB, or the Python language, etc.

[0009] Combined with the first aspect, in some implementation manners of the first aspect, the method further includes: updating the measurement covariance of the adaptive Kalman filter module at the second moment according to the first reference difference and the first residual. The second moment is the next moment of the first moment. The first residual is the difference between the predicted state estimation data at the first moment and the first measurement data. The predicted state estimation data at the first moment includes the estimated data of the dynamic state parameters of the vehicle at the first moment. Obtain the second measurement data and the second reference data. The second measurement data includes the data collected by the positioning system at the second moment. The second reference data includes the data of the reference trajectory points of the vehicle at the second moment. Input the second measurement data and the second reference data into the updated adaptive Kalman filter module to obtain the second reference difference, where the second reference difference is the reference difference at the second moment. Determine whether the positioning system is under attack according to the second reference difference.

[0010] In this way, by using the residual and the reference difference to update the measurement covariance parameters in the adaptive Kalman filter module, the influence of the residual and the reference difference on the measurement covariance can be adjusted in real time, thereby improving the attack detection rate.

[0011] Combined with the first aspect, in some implementation manners of the first aspect, if the second reference difference is greater than the first reference difference, and / or the second residual is greater than the first residual, the measurement covariance at the second moment is greater than the measurement covariance at the first moment, where the second residual is the residual at the second moment.

[0012] In this way, the influence of the reference difference and the residual on the measurement covariance is synchronized. When the reference difference and / or the residual becomes larger, the measurement covariance becomes larger, and then the Kalman gain becomes smaller, thereby reducing the influence of the measurement data on the Kalman filter, making the adaptive Kalman filter module more dependent on the predicted value of the positioning system rather than the measurement value, and reducing the false detection rate caused by the false detection of the normal noise of the sensor data by the detection device.

[0013] Combined with the first aspect, in some implementation manners of the first aspect, the measurement covariance at the second moment is updated according to the first weight related to the first residual and the second weight related to the first reference difference.

[0014] In this way, the measurement covariance is updated by referring to the weights corresponding to the reference difference and the residual difference, making the detection method easier to implement and reducing the detection complexity.

[0015] In combination with the first aspect, in some implementation manners of the first aspect, the weight function corresponding to the first weight or the second weight is a piecewise linear function; or, the weight function corresponding to the first weight or the second weight is a piecewise polynomial function; or, the weight function corresponding to the first weight or the second weight is a piecewise exponential function.

[0016] In this way, there can be various weight functions for the different weights corresponding to the residual difference and the reference difference, so that for different scenarios, a more suitable weight function can be obtained, improving the flexibility of the detection method.

[0017] In combination with the first aspect, in some implementation manners of the first aspect, determining whether the positioning system is attacked according to the first reference difference includes: when the first reference difference is less than or equal to a preset value, determining that the positioning system is not attacked; or, when the first reference difference is greater than the preset value, determining that the positioning system is attacked.

[0018] In combination with the first aspect, in some implementation manners of the first aspect, the method further includes: when the positioning system is attacked, controlling a prompting device to issue a warning.

[0019] In a second aspect, a detection device is provided. The device includes a transceiver unit and a processing unit: The transceiver unit is configured to obtain first measurement data and first reference data of a vehicle. The first measurement data includes data collected by the positioning system of the vehicle at a first moment, and the first reference data includes data of a reference trajectory point of the vehicle at the first moment. The processing unit is configured to input the first measurement data and the first reference data into an adaptive Kalman filtering module to obtain a first reference difference, where the first reference difference is the difference between the optimized state estimation data at the first moment and the first reference data, and the optimized state estimation data at the first moment is obtained according to the first measurement data. The processing unit is configured to determine whether the positioning system is attacked according to the first reference difference.

[0020] It should be understood that the second aspect is the device corresponding to the first aspect. The beneficial effects brought by the solution of the second aspect can refer to the first aspect and will not be elaborated here.

[0021] In combination with the second aspect, in certain implementations of the second aspect, the processing unit is further configured to update the measurement covariance of the adaptive Kalman filter module at the second moment according to the first reference difference and the first residual. The second moment is the next moment of the first moment. The first residual is the difference between the predicted state estimation data at the first moment and the first measurement data. The predicted state estimation data at the first moment includes the estimation data of the dynamic state parameters of the vehicle at the first moment. The transceiver unit is further configured to obtain the second measurement data and the second reference data. The second measurement data includes the data collected by the positioning system at the second moment. The second reference data includes the data of the reference trajectory point of the vehicle at the second moment. The processing unit is further configured to input the second measurement data and the second reference data into the updated adaptive Kalman filter module to obtain the second reference difference, where the second reference difference is the reference difference at the second moment. The processing unit is further configured to determine whether the positioning system is attacked according to the second reference difference.

[0022] In combination with the second aspect, in certain implementations of the second aspect, if the second reference difference is greater than the first reference difference, and / or the second residual is greater than the first residual, the measurement covariance at the second moment is greater than the measurement covariance at the first moment, where the second residual is the residual at the second moment.

[0023] In combination with the second aspect, in certain implementations of the second aspect, the measurement covariance at the second moment is updated according to the first weight related to the first residual and the second weight related to the first reference difference.

[0024] In combination with the second aspect, in certain implementations of the second aspect, the weight function corresponding to the first weight or the second weight is a piecewise linear function; or, the weight function corresponding to the first weight or the second weight is a piecewise polynomial function; or, the weight function corresponding to the first weight or the second weight is a piecewise exponential function.

[0025] In combination with the second aspect, in certain implementations of the second aspect, the processing unit is specifically configured to determine that the positioning system is not attacked when the first reference difference is less than or equal to a preset value; or, determine that the positioning system is attacked when the first reference difference is greater than the preset value.

[0026] In combination with the second aspect, in certain implementations of the second aspect, the processing unit is further configured to control the prompting device to issue a warning when the positioning system is attacked.

[0027] In a third aspect, a detection device is provided. The device includes: a memory for storing a program; a processor for executing the computer program code or instructions stored in the memory. When the computer program code or instructions stored in the memory are executed, the processor is used to execute the method provided in any one of the implementations of the first aspect above.

[0028] Fourthly, the present application provides a processor for executing the method provided by any implementation manner of the first aspect above. During the execution of these methods, the processes of sending the above information and obtaining / receiving the above information in the above methods can be understood as the process of the processor outputting the above information and the process of the processor receiving the input above information. When outputting the above information, the processor outputs the above information to the interface for transmission through the interface. After the above information is output by the processor, other processing may be required before it reaches the interface. Similarly, when the processor receives the input above information, the interface obtains / receives the above information and inputs it into the processor. Further, after the interface receives the above information, the above information may need to be processed otherwise before being input into the processor.

[0029] For operations such as transmission, sending, and obtaining / receiving involved, if there is no special description, or if it does not conflict with its actual function or internal logic in the relevant description, it can be understood as operations such as output, reception, and input, or can also be understood as operations of transmission, sending, and receiving performed by the radio frequency circuit and the antenna. The present application does not make any limitations in this regard.

[0030] During implementation, the above processor can be a processor dedicated to executing these methods, or a processor that executes the computer program code or instructions in the memory to execute these methods, such as a general-purpose processor. The above memory can be a non-transitory memory, such as a read-only memory (ROM), which can be integrated with the processor on the same chip or can be separately provided on different chips. The embodiments of the present application do not make any limitations on the type of the memory and the setting manner of the memory and the processor.

[0031] Fifthly, a computer-readable storage medium is provided, and the computer-readable medium stores program code or instructions for a device to execute, and the program code or instructions include those for executing the method provided by any implementation manner of the first aspect above.

[0032] Sixthly, a computer program product containing instructions is provided. When the computer program product runs on a computer, it causes the computer to execute the method provided by any implementation manner of the first aspect above.

[0033] Seventhly, a chip is provided. The chip includes a processor and a communication interface. The processor reads the instructions stored on the memory through the communication interface and executes the method provided by any implementation manner of the first aspect above.

[0034] Optionally, as an implementation, the chip may further include a memory in which computer program code or instructions are stored, and the processor is configured to execute the computer program code or instructions stored on the memory. When the computer program code or instructions are executed, the processor is configured to execute the method provided by any one of the implementations in the first aspect above.

[0035] In an eighth aspect, a mobile carrier is provided, and the mobile carrier includes any one of the possible devices in the second aspect.

[0036] In some possible implementations, the mobile carrier is a vehicle. Description of the Drawings

[0037] Figure 1 is a schematic functional block diagram of the mobile carrier provided by an embodiment of the present application;

[0038] Figure 2 is a schematic block diagram of the system architecture provided by an embodiment of the present application;

[0039] Figure 3 is a schematic diagram of a scenario where a positioning system provided by an embodiment of the present application is attacked;

[0040] Figure 4 is a schematic diagram for comparing trajectory tracking during a conventional trajectory tracking and spoofing attack provided by an embodiment of the present application;

[0041] Figure 5 is a schematic diagram of a detection system provided by an embodiment of the present application;

[0042] Figure 6 is a schematic flowchart of a detection method provided by an embodiment of the present application;

[0043] Figure 7 is a schematic diagram of different weight functions provided by an embodiment of the present application;

[0044] Figure 8 is a schematic diagram for comparing a residual-based detection method and a reference-difference-based detection method provided by an embodiment of the present application;

[0045] Figure 9 is a schematic diagram for comparing the trajectory tracking of a vehicle during conventional trajectory tracking and the trajectory tracking of detection based on a reference difference provided by an embodiment of the present application;

[0046] Figure 10 is another schematic diagram for comparing the trajectory tracking of a vehicle during conventional trajectory tracking and the trajectory tracking of detection based on a reference difference provided by an embodiment of the present application;

[0047] Figure 11 is a distribution diagram of a piecewise linear weight function provided by an embodiment of the present application;

[0048] Figure 12 is a distribution diagram of a piecewise exponential weight function provided in an embodiment of the present application;

[0049] Figure 13 is a schematic diagram of a detection device provided in an embodiment of the present application;

[0050] Figure 14 is a schematic structural diagram of a detection device provided in an embodiment of the present application;

[0051] Figure 15 is a schematic diagram of a chip system provided in an embodiment of the present application. Detailed implementation manners

[0052] Next, the technical solutions in the present application will be described with reference to the accompanying drawings.

[0053] First, in the present application, if there is no special description and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form a new embodiment according to their inherent logical relationships.

[0054] Second, in the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. In the text description of the present application, the character " / " generally represents an "or" relationship between the front and back associated objects. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b, and c can represent: a, or, b, or, c, or, a and b, or, a and c, or, b and c, or, a, b, and c. Where a, b, and c can be single or multiple respectively.

[0055] Third, in the present application, "first", "second", and various numerical numbers (for example, #1, #2, etc.) are used for distinction for the convenience of description and do not limit the scope of the embodiments of the present application. For example, to distinguish different reference differences, rather than for describing a specific order or sequence. It should be understood that the objects described in this way can be interchanged under appropriate circumstances so as to be able to describe the solutions other than the embodiments of the present application.

[0056] Fourth, in this application, descriptions such as "when...", "in the case of...", and "if" all refer to corresponding processing being carried out under certain objective circumstances, rather than limiting time. It does not require a judgment action to be necessarily made during implementation, nor does it mean the existence of other limitations. Additionally, it does not mean that the judgment action after these conditional conjunctions is the only condition for achieving the result, and other additional conditions may also be included to achieve the result.

[0057] Fifth, in this application, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that comprises a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0058] Sixth, in this application, "for indicating" may include direct indication and indirect indication. When describing that a certain indication information is used to indicate A, it may include the indication information directly indicating A or indirectly indicating A, and it does not necessarily mean that A is carried in the indication information.

[0059] The indication methods involved in the embodiments of this application should be understood to cover various methods that can enable the party to be indicated to obtain the indication information. The indication information can be sent as a whole or divided into multiple sub-information and sent separately. Moreover, the sending periods and / or sending timings of these sub-information can be the same or different, and this application does not limit the specific sending method.

[0060] The "indication information" in the embodiments of this application can be explicit indication, that is, directly indicated by a signaling, or obtained by combining other rules or other parameters or through derivation according to the parameters indicated by the signaling. It can also be implicit indication, that is, obtained according to rules or relationships, or according to other parameters, or through derivation. This application does not make specific limitations on this.

[0061] Seventh, in this application, "store" may refer to being stored in one or more memories. The one or more memories can be set separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partly set separately and partly integrated in a decoder, a processor, or a communication device. The type of memory can be any form of storage medium, and this application does not limit this.

[0062] Figure 1It is a schematic functional block diagram of a mobile vehicle provided by an embodiment of the present application. The mobile vehicle may include a sensing system 120, a prompting device 130, and a computing platform 150. Among them, the sensing system 120 may include several sensors for sensing information about the environment around the mobile vehicle. For example, the sensing system 120 may include a positioning system, which may be a Global Positioning System (GPS), or a Beidou system, or other positioning systems, an Inertial Measurement Unit (IMU), a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device, or one or more of them. The prompting device 130 may include a display device, a speaker, a seat belt tightening device, or other devices that can provide sensory prompts to the user.

[0063] Some or all functions of the mobile vehicle may be controlled by the computing platform 150. The computing platform 150 may include processors 151 to 15n (n is a positive integer). A processor is a circuit with signal processing capabilities. In one implementation, the processor may be a circuit with the ability to read and execute instructions, such as a Central Processing Unit (CPU), a microprocessor, a Graphics Processing Unit (GPU) (which can be understood as a type of microprocessor), or a Digital Signal Processor (DSP), etc.; in another implementation, the processor may achieve certain functions through the logical relationship of a hardware circuit, and the logical relationship of this hardware circuit is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an Application-Specific Integrated Circuit (ASIC) or a Programmable Logic Device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it may also be a hardware circuit designed for artificial intelligence, which can be understood as a type of ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), a Deep Learning Processing Unit (DPU), etc. In addition, the computing platform 150 may also include a memory for storing instructions, and some or all of the processors 151 to 15n may call the instructions in the memory and execute the instructions to achieve corresponding functions.

[0064] In this application, the mobile carrier in this application may include land vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, the mobile carrier may be a vehicle, which is a vehicle in a broad sense and can be a transportation vehicle (such as a commercial vehicle, a passenger vehicle, a motorcycle, a flying car, a train, etc.), an industrial vehicle (such as a forklift, a trailer, a tractor, etc.), an engineering vehicle (such as an excavator, a bulldozer, a crane, etc.), agricultural equipment (such as a lawn mower, a harvester, etc.), a recreational equipment, a toy vehicle, etc. The embodiments of this application do not make specific limitations on the type of the mobile carrier.

[0065] It should be understood that the sensors involved in the embodiments of this application mainly include a positioning system and an IMU.

[0066] Figure 2 is a schematic block diagram of the system architecture provided by the embodiments of this application. As Figure 2 shown, the system includes sensors and a detection device. Exemplarily, the sensors may include Figure 1 the positioning system and the IMU in the perception system 120. The detection device may be deployed on Figure 1 the computing platform 150 shown, and the detection is performed through the in-vehicle computing platform 150, or may be deployed on a cloud server, and the detection is performed through the cloud server, and the detection result is transmitted to the computing platform 150.

[0067] Currently, the attacks on the positioning system are generally divided into two categories, namely jamming and spoofing. Among them, the jamming attack refers to an external device interfering with the signal frequency of the positioning system, causing the receiver of the positioning system to lose position information. Since the signal of the positioning system needs to travel a long distance from the satellite to the receiver, the power of the signal of the positioning system is low and is easily interfered intentionally. The jamming attack is also easy to be detected. Compared with the jamming attack, the spoofing attack affects the receiver of the positioning system through a forged positioning signal, so that the receiver of the positioning system cannot distinguish between the real satellite signal and the forged signal.

[0068] Figure 3 is a schematic diagram of a scenario where a positioning system is attacked provided by the embodiments of this application.

[0069] As Figure 3As shown in (a) of , a vehicle may include a computing platform 310, an IMU 320, a positioning system receiver 330, and an actuator 340. Under normal non - attack conditions, the positioning system receiver 330 receives signal ① sent from a conventional signal transmitter. Subsequently, the computing platform 310 estimates the vehicle dynamics estimate based on the vehicle dynamics data collected by the IMU 320 and the positioning measurement result of signal ①, obtains the vehicle acceleration result, and sends the signal to the actuator 340. Accordingly, the vehicle travels straight along trajectory ① according to the correct signal, as Figure 3 shown in (b) of . However, when the signal ② sent by the attacker is received by the positioning system receiver 330, as Figure 3 shown in (a) of . The attacker manipulates the vehicle trajectory by tampering with the measurement result of the positioning system. At this time, the vehicle does not travel straight along the original trajectory ①, but turns right along trajectory ② as shown in Figure 3 . Therefore, if the situation of the positioning system being attacked cannot be detected in time, it will affect the driving safety of the vehicle.

[0070] Currently, it can be roughly divided into two detection methods. One detection method mainly depends on the processing of the received positioning signal. For example, by monitoring the signal strength and identification code, etc. Also, for example, position estimation is carried out through redundant information of other satellites or other resources. This detection method only detects whether the positioning system is attacked based on the received positioning signal, which is limited to the physical signal level. The positioning signal can only provide limited information. If the attack signal designed by the attacker is clever enough, the detection rate of this detection method for attack events is relatively low.

[0071] Another detection method is based on control science. For example, a detector based on the cumulative sum of residuals, which detects the cumulative sum of the residuals of the sensor. The residual is the difference between the measured value and the estimated value of the sensor. Among them, the measured value of the sensor can be the measurement result that fuses GPS, LiDAR, and IMU. Under non - attacked conditions, the cumulative sum of the residuals should theoretically be close to 0. If the value of the cumulative sum of the residuals is greater than a threshold, then this indicates that the estimated pose and the measurement result of the vehicle are inconsistent, and it can be concluded that the positioning system or the lidar has been attacked. Also, for example, a state estimation algorithm for autonomous vehicles. When the residual value of the sensor is large, the corresponding covariance will increase. Therefore, state estimation is achieved by assigning a lower weight to the sensor with a large residual. This scheme first detects the attacked situation of the sensor based on the residual, and secondly, this method highly depends on the choice of noise distribution and weight.

[0072] The above two exemplary detection methods in control science are both residual-based detection methods. Such detection methods cannot handle the situation where the attack signal is relatively concealed. For example, the weight for the residual in the attack signal can be artificially set very low. At this time, it will be very difficult to detect that the sensor has been attacked through the residual-based detection method. In addition, the second example in the detection method of control science may occur when there is no attacker but it affects the normal operation of the vehicle. Since there is noise in the positioning system during normal operation, the residual obtained by the residual-based detection method may not be an ideal value close to 0. If the threshold related to the residual is not designed reasonably, even if the positioning system is not attacked, false alarms may occur. In fact, this kind of false alarm will affect the subsequent normal operation of the vehicle.

[0073] Regarding the detection method based on control science, the vehicle dynamics model and the attacker model will be described in detail below.

[0074] The vehicle dynamics model is as follows: First, assume that the vehicle is a point. According to Newton's second law of motion, the vehicle dynamics equation can be shown as formula (1).

[0075]

[0076] Among them, formula (1) can also be called the system state equation corresponding to vehicle dynamics. Among them, x(k) is the system state value at time k, r(k) and v(k) respectively represent the position state value and speed state value of the vehicle at time k, b(k) is the acceleration deviation at time k, where, a m (k) = a(k) - b(k), a(k) is the actual acceleration of the IMU at time k, a m (k) is the measured acceleration at time k. x(k + 1) is the system state at time k + 1, δ is the sampling time, n x (k) is a zero-mean Gaussian white noise with covariance Q, and can also be called process noise.

[0077] Formula (1) can also be simplified as x(k + 1) = Ax(k) + Ba m (k) + n x (k).

[0078] Secondly, the measurement equation of the positioning system is shown as formula (2).

[0079]

[0080] Among them, y(k) is the measurement data at time k, y r (k) and y v (k) are the position measurement data and speed measurement data of the vehicle at time k respectively, n y(k) is zero-mean Gaussian white noise with covariance R, which can also be called measurement noise.

[0081] Equation (2) can also be simplified as y(k) = Cx(k) + n y (k).

[0082] According to equations (1) and (2), the minimum mean-square error estimate of the system state given by the Kalman filter can be achieved through equations (3) and (4).

[0083]

[0084] Among them, represents the predicted state estimate data at time k obtained based on the optimized state estimate data at time k - 1 (optimal state estimate).

[0085]

[0086] Among them, is the optimized state estimate data at time k. Specifically, it is obtained from the predicted state estimate data at time k in equation (3) and the measurement data y(k) at time k. Among them, the optimized state estimate data at time k can be the initial condition of L(k) is the Kalman gain, which can be specifically updated through equations (5) and (6).

[0087]

[0088] P(k|k - 1) = AP(k|k - 1)A T + Q - AP(k|k - 1)C T (CP(k|k - 1)C T + R) -1 CP(k|k - 1)A T (6)

[0089] Among them, the initial value of P(k|k - 1) is P(0|-1) = Q.

[0090] To track the reference trajectory, a control algorithm can be applied to the vehicle. The control algorithm can be, for example, a proportion differentiation (PD) control algorithm. Specifically, a(k) is the acceleration at time k, as shown in equation (7).

[0091]

[0092] Among them, is a preset reference position, is a preset reference speed, K = [K p K d is the gain matrix for balancing the closed-loop system, where K p is the proportional gain, K d is the differential gain.

[0093] It should be understood that the algorithm for tracking the reference trajectory can also be other algorithms, which are not limited in the embodiments of the present application. Here, the PD control algorithm is taken as an example for illustration.

[0094] The attack model is as follows: It is assumed that the attacker can measure the vehicle dynamics through formulas (8) and (9).

[0095]

[0096]

[0097] Among them, formula (8) can be simplified to Among them, y s (k) is the measured position and measured speed of the attacker at time k, is the measured acceleration of the attacker at time k.

[0098] It should be understood that is zero-mean Gaussian white noise with covariance R s , and can also be called the first measurement noise. This first measurement noise is the measurement noise for position and speed. is zero-mean Gaussian white noise with covariance σ, and can also be called the second measurement noise. This second measurement noise is the measurement noise for acceleration.

[0099] Since the spoofing attack on the positioning system is usually carried out remotely, the attacker cannot attack the IMU. Therefore, the covariance σ corresponding to the zero-mean Gaussian white noise in formula (9) is greater than the value corresponding to the acceleration parameter in the covariance Q of the zero-mean Gaussian white noise in formula (1), that is, Q 3,3 .

[0100] Through Kalman filtering, the attacker can obtain the attack state estimation data at time k According to the attack state estimation data, the attacker can obtain the desired acceleration through formula (10).

[0101]

[0102] Among them, a*(k) is the attack acceleration, The measured acceleration of the attacker at time k is the reference data that the attacker expects the vehicle to travel, K s is the gain matrix designed by the attacker.

[0103] Assume that the attacker tampers with the measurement data of the positioning system at time k from y(k) to y*(k). According to the relationship between position, velocity, and acceleration, the tampered measurement data y*(k + 1) at time k + 1 can be obtained through Equation (11).

[0104]

[0105] Among them, the initial value of the tampered measurement data at time k can be K s is not only the gain matrix of the attacker but also used to indicate the balance between attack performance and attack concealment.

[0106] When the positioning system is under a spoofing attack, only the vehicle acceleration data from the IMU measurement is correct. If the attack strategy designed by the attacker is good enough, for example, setting K s small enough, that is, the attack acceleration a*(k) at time k is approximately equal to the measured acceleration of the attacker at time k That is Furthermore, the tampered measurement data designed by the attacker is sufficiently concealed and can avoid the usual detection algorithms.

[0107] As mentioned above, the detection methods in control science are all residual-based detection methods. The residual is the difference between the measurement data and the estimated data of the detection sensor. If the attacker sets K s small enough, for example, Ks = [0.01; 0.1], the vehicle may follow the attacker's reference trajectory. However, the measurement data and the estimated data obtained by the vehicle are still related to the vehicle's own reference trajectory. Therefore, the residual-based detection method cannot cope with the attacker's concealed attack, such as the concealed attack Figure 4 shown.

[0108] Figure 4 is a schematic diagram comparing the trajectory tracking during normal trajectory tracking and spoofing attack provided by an embodiment of the present application.

[0109] Figure 4 is a comparison chart of normal trajectory tracking and trajectory tracking under spoofing attack in a simulation environment. Figure 4 In (a) of Figure 4 is the trajectory result without attack. As Figure 4The result of (b) is the trajectory result when under a spoofing attack. From Figure 4 As can be seen from (b) of Figure 4 , the reference trajectory presents a rectangular trajectory, and the attacker's trajectory presents a line segment trajectory different from the rectangular trajectory. If the attack signal is designed ingeniously, for example, the weight of the attack signal for the residual is set low enough, the estimated result and the measurement result still coincide and are consistent with the reference trajectory. However, the real result has deviated far from the reference trajectory. Therefore, the residual-based detection method cannot cope with the attack method shown in

[0110] To solve the above problems, the embodiments of the present application provide a detection method and device, which will be described in detail below in conjunction with Figures 5 to 15 in detail.

[0111] Figure 5 is a schematic diagram of a detection system provided by the embodiments of the present application.

[0112] As Figure 5 shown, the sensor data and the reference data are input into the adaptive Kalman filter module 510 to output a reference difference, and the reference difference is input into the detection unit 520 for detection to obtain a detection result. In addition, the predicted state estimation data of the position and speed of the vehicle output after passing through the adaptive Kalman filter module 510 can also be input into the trajectory tracking unit 530.

[0113] Figure 6 is a schematic flowchart of a detection method provided by the embodiments of the present application.

[0114] S610, obtain the first measurement parameter and the first reference data of the vehicle. Among them, the first measurement data includes the data collected by the positioning system of the vehicle at the first moment, and the first reference data includes the data of the reference trajectory point of the vehicle at the first moment.

[0115] Exemplarily, the first measurement data may include the position measurement data and the speed measurement data of the vehicle at time k, which is hereinafter represented by y(k), where k is a natural number. The first reference data may include the vehicle position reference data and the speed reference data at time k, in the form of

[0116] Specifically, the first measurement data of the vehicle is obtained from the sensor. The specific sensor has been described in detail above and will not be elaborated here.

[0117] S620, input the first measurement data and the first reference data into the adaptive Kalman filter module to obtain a first reference difference.

[0118] Among them, the first reference difference is the difference between the optimized state estimation data at the first moment and the first reference data, and the optimized state estimation data at the first moment is obtained according to the first measurement data.

[0119] Exemplarily, the first reference difference is denoted as d(k), and the first reference difference d(k) at the k-th moment represents the optimized state estimation data at the k-th moment and the difference between the first reference data at the k-th moment.

[0120] It should be understood that the optimized state estimation data at the k-th moment can be obtained through formula (4).

[0121] As a possible implementation, the measurement covariance in the adaptive Kalman filter module can be adjusted in real time.

[0122] In some possible implementations, according to the first reference difference and the first residual, update the measurement covariance of the adaptive Kalman filter module at the second moment, where the second moment is the next moment of the first moment. Among them, the first residual is the difference between the predicted state estimation data at the first moment and the first measurement data, and the predicted state estimation data at the first moment includes the estimated data of the vehicle's dynamic state parameters at the first moment.

[0123] In other words, the measurement covariance in the adaptive Kalman filter module at the second moment (for example, the k + 1 moment) is related to the first reference difference and the first residual. Among them, the first residual is the difference between the predicted state estimation data at the first moment (for example, the k moment) and the first measurement data, and the predicted state estimation data at the first moment (for example, the k moment) includes the estimated data of the vehicle's dynamic state parameters at the k moment.

[0124] Exemplarily, the first residual is denoted as c(k), and the first residual c(k) at the k-th moment represents the first measurement data y(k) at the k-th moment and the predicted state estimation data at the k-th moment the difference between

[0125] It should be understood that can be obtained according to formula (3). The difference is that the predicted state estimation data at the k-th moment here is two-dimensional data, the predicted state estimation position data and the predicted state estimation speed data.

[0126] As a possible implementation, obtain the second measurement data and the second reference data. The second measurement data includes the data collected by the positioning system at the second moment, and the second reference data includes the data of the reference trajectory points of the vehicle at the second moment. Input the second measurement data and the second reference data into the updated adaptive Kalman filter module to obtain the second reference difference, where the second reference difference is the reference difference at the second moment.

[0127] In other words, the measurement data and reference data at time k + 1 are used, through the updated Kalman filter module, to obtain the reference difference at time k + 1, so as to further determine whether the positioning system at time k + 1 is under attack.

[0128] As a possible implementation, the first residual c(k) is represented by the first residual parameter q(k), as shown in Equation (12).

[0129] q(k) = c(k) T S(k) -1 c(k) (12)

[0130] where S(k) = CP(k|k - 1)C T + R is the covariance matrix of the first residual c(k). It should be understood that the first residual parameter may also have other forms, and the embodiments of the present application do not limit this.

[0131] As a possible implementation, the reference difference d(k) is represented by the first reference difference parameter p(k), as shown in Equation (13).

[0132] p(k) = ||d(k)|| (13)

[0133] where p(k) is the two-norm of the reference difference d(k). It should be understood that although p(k) is calculated step by step based on the reference trajectory, the reference trajectory can be time-varying.

[0134] As a possible implementation, the measurement covariance at the second time is determined according to the first weight related to the first residual and the second weight related to the first reference difference. It should be understood that the first reference difference parameter may also have other forms, and the embodiments of the present application do not limit this.

[0135] It should be understood that the first weight related to the first residual may be the first weight of the first residual itself, or it may also be the first weight of the first residual parameter. The second weight related to the first reference difference may be the second weight of the first reference difference itself, or it may also be the second weight of the first reference difference parameter.

[0136] As a possible implementation, if the first reference difference is greater than the second reference difference, and / or the first residual is greater than the second residual, the measurement covariance at the second time is greater than the measurement covariance at the first time. Wherein, the second reference difference is the reference difference at the second time, and the second residual is the residual at the second time.

[0137] In other words, when the first residual c(k) at time k and / or the first reference difference d(k) at time k are relatively large, it is necessary to increase the measurement covariance R at time k + 1.

[0138] It should be understood that there are various ways to associate the measurement covariance R at time k+1 with the first residual and the first reference difference. When the first residual and / or the first reference difference is relatively large, the measurement covariance R at time k+1 can be increased.

[0139] Exemplarily, the total weight ω of the first weight (denoted as ω q ) and the second weight (denoted as ω p ) can be ω = ω q ω p , where ω q represents the weight of the first residual parameter, and ω p represents the weight of the first reference difference parameter.

[0140] Among them, the weight ω q of the residual parameter and ω p of the reference difference parameter can be represented by piecewise functions respectively.

[0141] As a possible implementation, the weight functions corresponding to the first weight of the first residual parameter and the second weight of the first reference difference parameter can be piecewise linear weight functions. For example, the first weight of the first residual parameter can be The second weight of the first reference difference parameter can be The piecewise linear weight function includes two thresholds, and the specific form can be as shown in formula (14).

[0142]

[0143] As a possible implementation, the weight functions corresponding to the first weight of the first residual parameter and the second weight of the first reference difference parameter can also be piecewise polynomial weight functions.

[0144] Exemplarily, the piecewise polynomial weight function can also be as shown in formula (15).

[0145]

[0146] As a possible implementation, the weight functions corresponding to the first weight of the first residual parameter and the second weight of the first reference difference parameter can also be piecewise exponential weight functions.

[0147] Exemplarily, the piecewise exponential weight function can also be as shown in formula (16).

[0148]

[0149] Among them, α and β are hyperparameters to be tuned in formula (15) and formula (16) respectively.

[0150] Specifically, according to the total weight ω, formulas (5) and (6) can be modified to formulas (17) and (18) respectively.

[0151]

[0152]

[0153] It should be understood that ω q the first weight of the first residual parameter and ω p the value ranges of the second weight of the first reference difference parameter are both [0.1, 1], and the total weight ω ≤ 1. The value range of the total weight ω is [0.01, 1]. Since the total weight ω ≤ 1, when both the first residual and the second reference difference are large, the measurement covariance of formulas (5) and (6) changes from R to R / ω, and the Kalman gain will become smaller, and the influence of the measurement data on the Kalman filter is smaller. Furthermore, the Kalman filter depends more on the predicted value of the positioning system rather than the measurement data.

[0154] In this way, compared with simply fusing the predicted value and the estimated data through a linear combination, the detection method in the embodiment of the present application is based on an adaptive Kalman filter and is more interpretable at the statistical level.

[0155] As a possible implementation, it can be continuously tested through experiments, and a value that meets the requirements of the detection accuracy rate and the false detection rate indicators is selected from multiple test values as the target value of η.

[0156] In this way, different from the residual-based detection method, by selecting the value of η, the influence of the method in the embodiment of the present application on the tracking performance during the normal operation of the original system will be greatly reduced in the absence of an attacker.

[0157] Figure 7 is a schematic diagram of a different weight function provided by the embodiment of the present application. As Figure 7 shown, the embodiment of the present application gives 5 weight functions by way of example, which are the piecewise linear weight function of formula (14), the piecewise exponential weight function of formula (16) with the hyperparameter β = -1, the piecewise exponential weight function of formula (16) with the hyperparameter β = 1, the piecewise exponential weight function of formula (15) with the hyperparameter α = -5, and the piecewise exponential weight function of formula (15) with the hyperparameter α = 5.

[0158] S630. Determine whether the positioning system is attacked according to the first reference difference.

[0159] As a possible implementation, compare the first reference difference with a preset value to determine whether the positioning system is attacked.

[0160] Exemplarily, Δ is a preset value. When the value of the first reference difference parameter is less than or equal to the preset value, the null hypothesis H0 holds, and it is determined that the positioning system is not under attack, that is, the system is operating normally, i.e., the system is not attacked. When the value of the first reference difference parameter is greater than the preset value, the alternative hypothesis H1 holds, and it is determined that the positioning system is under attack, that is, the system cannot operate normally, i.e., the system is attacked. The specific detection form is shown in formula (19).

[0161]

[0162] Among them, the preset value Δ is used to balance the detection success rate and the false alarm rate. The preset value Δ can be obtained according to the rule of thumb under 10 minutes of normal operation.

[0163] It should be understood that the preset value can be a specific value or a value range, and the embodiments of the present application do not limit this.

[0164] Exemplarily, when the value of the first reference difference parameter is less than the preset value, it is determined that the positioning system is not under attack. When the value of the first reference difference parameter is greater than or equal to the preset value, it is determined that the positioning system is under attack.

[0165] It should be understood that the embodiments of the present application do not limit the result of whether the positioning system is under attack or not when the value of the first reference difference parameter is equal to the preset value or within the preset value range.

[0166] Optionally, S640, when the positioning system is under attack, control the prompting device to issue a warning.

[0167] Specifically, when the positioning system is under attack, control the display device to issue a warning display message. Or, when the positioning system is under attack, control the speaker to issue a warning reminder. Or when the positioning system is under attack, control the seat belt to tighten to issue a warning.

[0168] In the above technical solution, by detecting the reference difference between the estimated data and the reference data to detect whether the positioning system is under attack, compared with the residual-based detection method, it can better detect hidden attack behaviors. For example, the attacker sets the gain matrix in the attack acceleration small enough, so that the difference between the measurement data and the estimated data of the sensor in the positioning system, that is, the residual, is close enough. Therefore, the above technical solution can improve the attack detection rate of the positioning system when under attack.

[0169] Next, in combination with Figures 8 to 12 , the simulation detection effect of the method of the embodiments of the present application will be described in detail.

[0170] First, the relevant simulation parameters are described. Table 1 shows the simulation parameters in one dimension, where one dimension here can be understood as the simulation in the embodiments of the present application only considering one direction. This does not limit that the detection method proposed in the embodiments of the present application can be applied to two-dimensional cases. In two-dimensional cases, the simulation parameters can be obtained through the Kronecker product (denoted as kron(·; I2)).

[0171] Table 1

[0172]

[0173] It should be understood that the formulas corresponding to the attacker-related parameters in Table 1 may include Formulas (8) to (11), where the state equation of the attacker is shown in Formula (20).

[0174]

[0175] Among them, is the process noise of the attacker, and the covariance of The estimated data of the attacker's attack state at time k can be obtained through Formula (21).

[0176]

[0177] Among them, and are the steady-state Kalman gains. Where P * satisfies Formula (22).

[0178]

[0179] Among them, the simulation duration is set to 160 seconds. Exemplarily, the preset reference trajectory of the vehicle in the simulation is achieved through Formula (23).

[0180]

[0181] More specifically, the reference trajectory is in the shape of a 100-meter square. On each side of the square reference trajectory, the vehicle accelerates to a vehicle speed of 2 m / s with a fixed acceleration of 0.25 m / s 2 and then decelerates to 0 m / s with a fixed deceleration of -0.25 m / s 2 as shown in Formula (23) specifically.

[0182] Assume that the attacker attacks the measurement data of the positioning system, and the attacker expects the vehicle to move in a fixed direction at a constant vehicle speed of 2 m / s.

[0183] Figure 8It is a comparison schematic diagram provided by an embodiment of the present application based on a residual detection method and a reference difference detection method. Figure 8 (a) is the detection method based on residuals detection, Figure 8 (b) is the detection method based on the reference difference. As can be seen from Figure 8 it, in the face of a stealth attack, for example, the gain matrix K designed by the attacker s is small enough, the detection rate of the residual-based detection method is 15%, and the detection rate of the reference difference-based detection method is 48.75%. The attack detection rate of the detection method proposed by the embodiment of the present application is much higher than that of the residual-based detection method.

[0184] Figure 9 It is a comparison schematic diagram of the conventional trajectory tracking of a vehicle and the trajectory tracking based on the reference difference provided by an embodiment of the present application. Among them, the weight function in the reference difference-based detection method is a piecewise linear weight function. Figure 9 (a) is the trajectory result without attack. As shown in Figure 9 (a), the reference trajectory presents a rectangular trajectory. When there is no spoofing attack, the estimated result, the true result, and the measurement result of the trajectory are all consistent. Figure 9 (b) is the trajectory result when under a spoofing attack. As can be seen from Figure 9 (b), the reference trajectory presents a rectangular trajectory, and the attacker's trajectory presents a line segment trajectory different from the rectangular trajectory. Through the reference difference-based detection method, when the true result deviates, the obtained estimated result and measurement result also change greatly. Compared with Figure 4 (b), for the residual-based detection method, Figure 4 the estimated result and measurement result shown in (b) still coincide with the reference trajectory, but the true result of the vehicle has deviated from the reference trajectory. Therefore, the reference difference-based detection method is more likely to detect the situation where the positioning system is attacked.

[0185] Figure 10 It is another comparison schematic diagram of the conventional trajectory tracking of a vehicle and the trajectory tracking based on the reference difference provided by an embodiment of the present application. Among them, the weight function in the reference difference-based detection method is a piecewise exponential weight function, and the hyperparameter is β = -1. Similar to Figure 9 (a), Figure 10 (a) is also the trajectory result without being attacked. Figure 10 (b) is the trajectory result when under attack. As can be seen from Figure 10 (b), the estimated result and the measurement result deviate significantly from the reference trajectory. Similarly, compared with the residual-based detection method, the reference difference-based detection method is more likely to detect the situation where the positioning system is attacked.

[0186] Figure 11 It is a distribution diagram of a piecewise linear weight function provided by an embodiment of the present application. It can be seen from the solid line broken line and the warning area that the false detection rate of the detection method based on this piecewise linear weight function is relatively small. As shown in the figure, the false detection rate is 0.625%. In addition, from the warning area, the non-warning area, and the attack, the detection rate can be obtained. As shown in the figure, the detection rate is 72.5%.

[0187] Figure 12 It is a distribution diagram of a piecewise exponential weight function provided by an embodiment of the present application. It can be seen from the solid line broken line and the warning area that the false detection rate of the detection method based on this piecewise exponential weight function is relatively small. As shown in the figure, the false detection rate is 0%. In addition, from the warning area, the non-warning area, and the attack, the detection rate can be obtained. As shown in the figure, the detection rate is 76.25%. The detection rate of the detection method based on the piecewise exponential weight function has been further improved compared to the detection rate of the detection method based on the piecewise linear weight function.

[0188] In addition to the above simulation result diagrams, Table 2 shows the detection rates and false detection rates of different algorithms provided by an embodiment of the present application. Among them, the detection rates and false detection rates in Table 2 are the averages of 1000 independent experimental results, and the control algorithm used in the results of Table 2 is the PD control algorithm.

[0189] Table 2

[0190]

[0191] It can be seen from Table 2 that the detection rate of the detection method based on the reference difference has been significantly improved compared to the detection rate of the detection method based on the residual.

[0192] If the above PD control algorithm is replaced with a PID control algorithm for simulation, the detection rates and false detection rates of different detection methods are obtained, as shown in Table 3. Among them, the detection rates and false detection rates in Table 3 are the averages of 1000 independent test results.

[0193] Among them, formula (7) of the above PD algorithm can be replaced by formula (24) of the PID control algorithm.

[0194]

[0195] Among them, K i is the integral gain.

[0196] Table 3

[0197]

[0198] As can be seen from Table 3, the detection rate of the detection method based on the reference difference has been significantly improved compared to the detection rate of the detection method based on the residual.

[0199] Above, in combination with Figures 5 to 12 The detection method provided by the embodiments of the present application has been described in detail. It can be understood that, in order to implement the above functions, it includes the corresponding hardware structure and / or software module for executing each function.

[0200] Those skilled in the art should be able to realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for a specific application, but such implementation should not be considered to exceed the scope of the present application.

[0201] Next, in combination with Figures 13 to 15 The detection device provided by the embodiments of the present application will be described in detail. It should be understood that the description of the device embodiments corresponds to the description of the method embodiments. Therefore, for the content not described in detail, reference can be made to the above method embodiments. For the sake of brevity, some content will not be repeated.

[0202] Figure 13 FIG. is a schematic diagram of a detection device provided by an embodiment of the present application. The device may include a processing unit 1320, and the processing unit 1320 is used for data processing. The device may further include a transceiver unit 1310. The transceiver unit 1310 can implement the corresponding communication function, and the transceiver unit 1310 may also be referred to as a communication interface or a communication unit or an interface unit. It should be understood that for operations such as sending and receiving involved in the present application, if there is no special description, or if it does not conflict with its actual role or internal logic in the relevant description, it can be more generally understood as operations such as output and input, rather than the sending and receiving operations directly performed by the radio frequency circuit and the antenna.

[0203] Optionally, the device may further include a storage unit, and the storage unit can be used to store instructions and / or data. The processing unit 1320 can read the instructions and / or data in the storage unit to enable the device to implement the foregoing method embodiments.

[0204] The device can be used to execute the actions in the above method embodiments. The transceiver unit 1310 is used to execute the operations related to acquisition in the above method embodiments, and the processing unit 1320 is used to execute the operations related to processing in the above method embodiments.

[0205] As a design, the device is used to execute the above Figure 5 andFigure 6 The operations of the method embodiments shown. The executing entity may be a chip, a chip system, or a processor that supports the detection device to implement the corresponding method, or may also be a logic module or software that can implement all or part of the functions of the detection device.

[0206] Specifically, the transceiver unit 1310 is configured to obtain first measurement data and first reference data of the vehicle. The first measurement data includes data collected by the positioning system of the vehicle at a first moment, and the first reference data includes data of the reference trajectory points of the vehicle at the first moment.

[0207] The processing unit 1320 is configured to input the first measurement data and the first reference data into an adaptive Kalman filter module to obtain a first reference difference. The first reference difference is the difference between the optimized state estimation data at the first moment and the first reference data, and the optimized state estimation data at the first moment is obtained according to the first measurement data. Determine whether the positioning system is attacked according to the first reference difference.

[0208] For details not described in detail, reference may be made to the above method embodiments.

[0209] It should be understood that the specific processes of each unit executing the above corresponding steps have been described in detail in the above method embodiments. For the sake of brevity, they will not be repeated here.

[0210] The processing unit 1320 in the above embodiments may be implemented by at least one processor or processor-related circuit. The transceiver unit 1310 may be implemented by a transceiver or transceiver-related circuit. The storage unit may be implemented by at least one memory.

[0211] Figure 14 It is a schematic structural diagram of a detection device provided by an embodiment of the present application.

[0212] As Figure 14 shown, an embodiment of the present application further provides a detection device. The device includes a processor 1410. Optionally, the device further includes a memory 1420. The processor 1410 is coupled to the memory 1420. The memory 1420 is used to store computer programs or instructions and / or data. The processor 1410 is used to execute the computer programs or instructions and / or data stored in the memory 1420, so that the method in the above method embodiments is executed.

[0213] Optionally, the processor 1410 included in the device is one or more.

[0214] Optionally, as Figure 14 shown, the device may further include a memory 1420.

[0215] Optionally, the memory 1420 included in the device may be one or more.

[0216] Optionally, the memory 1420 may be integrated with the processor 1410 or separately provided.

[0217] Optionally, as Figure 14 shown, the apparatus may further include a transceiver 1430 for receiving and / or transmitting signals. For example, the processor 1410 is configured to control the transceiver 1430 to receive and / or transmit signals.

[0218] As a solution, the apparatus is configured to implement the operations performed by the detection apparatus in the foregoing method embodiments.

[0219] For example, the processor 1410 is configured to implement the operations related to processing performed by the detection apparatus in the foregoing method embodiments, and the transceiver 1430 is configured to implement the operations related to receiving and transmitting performed by the detection apparatus in the foregoing method embodiments.

[0220] Figure 15 is a schematic diagram of a chip system provided by an embodiment of the present application, as Figure 15 shown. The chip system (or may also be referred to as a processing system) includes a logic circuit 1510 and an input / output interface 1520. The logic circuit is used to couple with the input interface and transmit data parameters through the input / output interface to execute the method in the foregoing method embodiments. The device installed with the chip system can implement the method and functions of the embodiments of the present application. For example, the logic circuit 1510 may be a processing circuit in the chip system to implement the control of the device installed with the chip system, and may also be coupled to a storage unit to call instructions in the storage unit, so that the device can implement the method and functions of the embodiments of the present application. The input / output interface 1520 may be an input / output circuit in the chip system to output the information processed by the chip system or input the data or signaling information to be processed into the chip system for processing.

[0221] As a solution, the chip system is configured to implement the operations performed by the detection apparatus in the foregoing method embodiments.

[0222] For example, the logic circuit 1510 is configured to implement the operations related to processing in the foregoing method embodiments, and the input / output interface 1520 is configured to implement the operations related to obtaining in the foregoing method embodiments.

[0223] The embodiment of the present application further provides a computer-readable storage medium, on which computer instructions for implementing the method performed by the detection apparatus in the foregoing method embodiments are stored.

[0224] For example, when the computer program is executed by a computer, the computer can implement the method performed by the detection apparatus in the foregoing method embodiments.

[0225] An embodiment of the present application also provides a computer program product including instructions, which, when executed by a computer, cause the computer to implement the method executed by the detection device in the above method embodiment.

[0226] An embodiment of the present application also provides a mobile carrier, which may include the above detection device.

[0227] Optionally, the mobile carrier may be a vehicle.

[0228] An embodiment of the present application also provides a cloud server, which may include the above detection device.

[0229] For the explanations and beneficial effects of the relevant content in any of the above provided devices, reference may be made to the corresponding method embodiments provided above, and details are not described herein again.

[0230] It should be understood that the processor mentioned in the embodiments of the present application may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0231] It should also be understood that the memory mentioned in the embodiments of the present application may be a volatile memory and / or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM). For example, the RAM may be used as an external cache. By way of example and not limitation, the RAM may include the following various forms: static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0232] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, the memory (storage module) may be integrated in the processor.

[0233] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0234] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0235] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0236] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0237] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0238] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0239] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory ROM, random access memory RAM, magnetic disks, or optical discs that can store program codes.

[0240] As described above, the above are only the specific implementation manners of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A detection method, characterized in that, Including: Obtain the first measurement data and the first reference data of the vehicle, where the first measurement data includes the data collected by the positioning system of the vehicle at the first moment, and the first reference data includes the data of the reference trajectory points of the vehicle at the first moment; Input the first measurement data and the first reference data into the adaptive Kalman filter module to obtain a first reference difference, where the first reference difference is the difference between the optimized state estimation data at the first moment and the first reference data, and the optimized state estimation data at the first moment is obtained based on the first measurement data; Determine whether the positioning system is attacked according to the first reference difference.

2. The method according to claim 1, wherein The method further includes: Update the measurement covariance of the adaptive Kalman filter module at the second moment according to the first reference difference and the first residual, where the second moment is the next moment of the first moment, and the first residual is the difference between the predicted state estimation data at the first moment and the first measurement data, and the predicted state estimation data at the first moment includes the estimated data of the dynamic state parameters of the vehicle at the first moment; Obtain the second measurement data and the second reference data, where the second measurement data includes the data collected by the positioning system at the second moment, and the second reference data includes the data of the reference trajectory points of the vehicle at the second moment; Input the second measurement data and the second reference data into the updated adaptive Kalman filter module to obtain a second reference difference, and the second reference difference is the reference difference at the second moment; Determine whether the positioning system is attacked according to the second reference difference.

3. The method according to claim 2, wherein If the second reference difference is greater than the first reference difference, and / or the second residual is greater than the first residual, the measurement covariance at the second moment is greater than the measurement covariance at the first moment, and the second residual is the residual at the second moment.

4. The method according to claim 2 or 3, characterized in that The measurement covariance at the second moment is updated according to the first weight related to the first residual and the second weight related to the first reference difference.

5. The method according to claim 4, wherein The weight function corresponding to the first weight or the second weight is a piecewise linear function; or, the weight function corresponding to the first weight or the second weight is a piecewise polynomial function; or, the weight function corresponding to the first weight or the second weight is a piecewise exponential function.

6. The method according to any one of claims 1 to 5, characterized in that, The determining whether the positioning system is attacked according to the first reference difference includes: When the first reference difference is less than or equal to a preset value, determine that the positioning system is not attacked; or, When the first reference difference is greater than the preset value, determine that the positioning system is attacked.

7. The method according to any one of claims 1 to 6, characterized in that The method further includes: When the positioning system is attacked, control the prompting device to issue a warning.

8. A detection device, characterized in that, The device includes a transceiver unit and a processing unit: The transceiver unit is used to obtain the first measurement data and the first reference data of the vehicle, where the first measurement data includes the data collected by the positioning system of the vehicle at the first moment, and the first reference data includes the data of the reference trajectory points of the vehicle at the first moment; The processing unit is configured to input the first measurement data and the first reference data into an adaptive Kalman filter module to obtain a first reference difference, where the first reference difference is the difference between the optimized state estimation data at the first moment and the first reference data, and the optimized state estimation data at the first moment is obtained according to the first measurement data; The processing unit is configured to determine whether the positioning system is attacked according to the first reference difference.

9. The device according to claim 8, wherein The processing unit is further configured to update the measurement covariance of the adaptive Kalman filter module at the second moment according to the first reference difference and the first residual, where the second moment is the next moment of the first moment, and the first residual is the difference between the predicted state estimation data at the first moment and the first measurement data, and the predicted state estimation data at the first moment includes the estimated data of the dynamic state parameters of the vehicle at the first moment; The transceiver unit is further configured to obtain second measurement data and second reference data, where the second measurement data includes the data collected by the positioning system at the second moment, and the second reference data includes the data of the reference trajectory points of the vehicle at the second moment; The processing unit is further configured to input the second measurement data and the second reference data into the updated adaptive Kalman filter module to obtain a second reference difference, where the second reference difference is the reference difference at the second moment; The processing unit is further configured to determine whether the positioning system is attacked according to the second reference difference.

10. The device according to claim 9, characterized in that, If the second reference difference is greater than the first reference difference, and / or the second residual is greater than the first residual, the measurement covariance at the second moment is greater than the measurement covariance at the first moment, and the second residual is the residual at the second moment.

11. The device according to claim 9 or 10, characterized in that, The measurement covariance at the second moment is updated according to a first weight related to the first residual and a second weight related to the first reference difference.

12. The device according to claim 11, wherein, The weight function corresponding to the first weight or the second weight is a piecewise linear function; or, the weight function corresponding to the first weight or the second weight is a piecewise polynomial function; or, the weight function corresponding to the first weight or the second weight is a piecewise exponential function.

13. The device according to any one of claims 8 to 12, characterized in that, The processing unit is specifically configured to When the first reference difference is less than or equal to a preset value, determine that the positioning system is not attacked; or, When the first reference difference is greater than the preset value, determine that the positioning system is attacked.

14. The device according to any one of claims 8 to 13, characterized in that, The processing unit is further configured to When the positioning system is attacked, control the prompting device to issue a warning.

15. A detection device, characterized in that, It includes a processor, the processor is coupled with a memory, the memory is used to store computer program code or instructions, and the processor is used to execute the computer program code or instructions in the memory, so that the device executes the method according to any one of claims 1 to 7.

16. A mobile carrier, characterized in that, The mobile carrier includes the detection device according to any one of claims 8 to 15.

17. A computer-readable storage medium, characterized in that, Computer program code or instructions are stored on the computer-readable storage medium, and when the computer program code or instructions run on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

18. A chip, characterized in that, The chip is coupled to the memory and is configured to read and execute program instructions stored in the memory to implement the method according to any one of claims 1 to 7.

Images