Abnormality detection method, device and terminal equipment of positioning sensor

Abstract

The present application is applicable to the field of autonomous driving technology, and provides a positioning sensor abnormality detection method, device and terminal device. The method is applied to autonomous driving equipment, on which multiple positioning sensors are arranged, and the method includes: obtaining the measurement data of each positioning sensor; fusing the measurement data of multiple positioning sensors to determine the motion state parameters of the autonomous driving equipment; if it is determined that there is an abnormal positioning sensor among the multiple positioning sensors according to the motion state parameters of the autonomous driving equipment, then for each positioning sensor, the measurement state parameters of the positioning sensor are determined using the measurement data of the positioning sensor, and it is determined whether the positioning sensor is abnormal according to the measurement state parameters of the positioning sensor. The above method can timely determine which specific positioning sensor is abnormal while judging that a positioning sensor is abnormal, and the abnormal autonomous driving equipment can be restored in a targeted manner later.

Description

Technical Field

[0001] The present application belongs to the field of autonomous driving technology, and in particular, relates to a method, device and terminal equipment for detecting anomalies of a positioning sensor. Background Art

[0002] With the rapid development of autonomous driving technology, more and more research is being done on autonomous driving equipment, such as autonomous cars, autonomous aircraft, and autonomous ships. The most common autonomous driving equipment is the driverless car. Currently, driverless food delivery vehicles and driverless taxis have begun to appear on public roads. In order to achieve autonomous driving without human control, driverless cars need to use on-board positioning sensors to sense the road environment during driving, analyze and process the acquired information, automatically plan the driving route, and navigate the vehicle to reach the predetermined destination.

[0003] Generally speaking, multiple positioning sensors are set up on autonomous driving equipment. The positioning sensors can not only obtain the relative position relationship between the equipment and the external environment, but also determine the absolute position of the equipment through equipment status perception. This also leads to the fact that once the positioning sensors are attacked and abnormalities occur, the autonomous driving equipment may exhibit abnormal behavior or even catastrophic accidents. Therefore, it is necessary to promptly detect whether the positioning sensors of the autonomous driving equipment are attacked, so as to take safety measures to avoid abnormal driving of the autonomous driving equipment.

[0004] In the prior art, convolutional neural networks are usually used to detect whether the vehicle-mounted positioning sensors are abnormal, or deep reinforcement learning algorithms are used to learn the optimal sensor fusion strategy for autonomous vehicles to prevent certain sensors from being attacked. However, the existing monitoring methods can only monitor whether the vehicle-mounted positioning sensors are abnormal, but it is difficult to locate the abnormal positioning sensors, that is, it is impossible to determine which specific positioning sensor has an abnormality, thus affecting the subsequent targeted recovery of the positioning sensors of the autonomous driving equipment. Summary of the invention

[0005] The embodiments of the present application provide a positioning sensor anomaly detection method, apparatus, terminal device and storage medium, which can solve the technical problem that the related technology is unable to locate the abnormal positioning sensor when performing anomaly detection on the positioning sensor on the autonomous driving equipment.

[0006] In a first aspect, an embodiment of the present application provides a positioning sensor abnormality detection method, which is applied to an autonomous driving device, wherein a plurality of positioning sensors are provided on the autonomous driving device, and the method is characterized in that it includes:

[0007] Acquiring measurement data of each of the positioning sensors;

[0008] fusing the measurement data of the plurality of positioning sensors to determine the motion state parameters of the autonomous driving device;

[0009] If it is determined that there is an abnormal positioning sensor among the multiple positioning sensors based on the motion state parameters of the automatic driving device, then for each positioning sensor, the measurement state parameters of the positioning sensor are determined using the measurement data of the positioning sensor, and it is determined whether the positioning sensor is abnormal based on the measurement state parameters of the positioning sensor.

[0010] Based on the above method, the motion state parameters of the autonomous driving device are first obtained based on the measurement data of multiple positioning sensors. When it is determined that there is an abnormal positioning sensor among the multiple positioning sensors based on the motion state parameters, each positioning sensor is analyzed to obtain the measurement state parameters corresponding to the positioning sensor, and whether the corresponding positioning sensor is abnormal is determined based on the measurement state parameters corresponding to each positioning sensor. Therefore, this method can timely determine which specific positioning sensor is abnormal while judging that there is an abnormal positioning sensor, so that the abnormal autonomous driving device can be restored in a targeted manner later.

[0011] In a possible implementation manner of the first aspect, the measurement data of the positioning sensor includes first measurement data of the positioning sensor at a first moment and second measurement data of the positioning sensor at a second moment, where the second moment is a next moment of the first moment in a time series; and fusing the measurement data of the plurality of positioning sensors to determine the motion state parameter of the autonomous driving device includes:

[0012] determining a motion state prediction parameter of the automatic driving device at the second moment according to the first measurement data of the plurality of positioning sensors;

[0013] determining a second motion state measurement parameter of the automatic driving device at the second moment according to the second measurement data of the plurality of positioning sensors;

[0014] Perform residual calculation on the second motion state measurement parameter and the motion state prediction parameter to obtain the motion state parameter of the automatic driving device at the second moment.

[0015] In a possible implementation manner of the first aspect, determining, according to the first measurement data of the plurality of positioning sensors, a motion state prediction parameter of the automatic driving device at the second moment includes:

[0016] Acquire first expected motion state parameters of the automatic driving device corresponding to the plurality of positioning sensors at the first moment, wherein the first expected motion state parameters are obtained by updating the motion state prediction parameters at the first moment using an extended Kalman filter algorithm;

[0017] The first measurement data and the first expected motion state parameter are input into a pre-established motion model for processing to obtain the motion state prediction parameter of the automatic driving device at the second moment.

[0018] Exemplarily, the method further includes: updating the motion state prediction parameters at the second moment based on an extended Kalman filter algorithm to obtain second expected motion state parameters of the autonomous driving device corresponding to the plurality of positioning sensors at the second moment.

[0019] Exemplarily, the determining, according to the motion state parameter of the automatic driving device, that there is an abnormal positioning sensor among the plurality of positioning sensors includes:

[0020] If the motion state parameter is not within the first preset range, it is determined that an abnormal positioning sensor exists among the plurality of positioning sensors.

[0021] In a possible implementation manner of the first aspect, determining, according to the motion state parameter of the automatic driving device, that there is an abnormal positioning sensor among the plurality of positioning sensors includes:

[0022] Acquire measurement data corresponding to each of the positioning sensors at each time in a target historical time period;

[0023] The measurement data of the plurality of positioning sensors at each moment are respectively fused and processed to determine the motion state parameters corresponding to each moment in the historical time period of the autonomous driving device and the target;

[0024] Accumulating and averaging the motion state parameters corresponding to each moment in the target historical time period and the autonomous driving device to obtain the average motion state parameter corresponding to the target historical time period;

[0025] If the average motion state parameter is not within the second preset range, it is determined that an abnormal positioning sensor exists among the plurality of positioning sensors.

[0026] In a possible implementation manner of the first aspect, the measurement data of the positioning sensor includes first measurement data of the positioning sensor at a first moment and second measurement data of the positioning sensor at a second moment, where the second moment is a next moment of the first moment in a time series; for each of the positioning sensors, determining a measurement state parameter of the positioning sensor by using the measurement data of the positioning sensor includes:

[0027] determining, according to the first measurement data of each of the positioning sensors, a state prediction parameter of the positioning sensor at the second moment;

[0028] Determining a second state measurement parameter of the positioning sensor at the second moment according to the second measurement data of each positioning sensor;

[0029] Residual calculation is performed on the second state measurement parameter and the state prediction parameter to obtain the measurement state parameter of each positioning sensor at the second moment.

[0030] Exemplarily, the determining, based on the first measurement data of each positioning sensor, the state prediction parameter of the positioning sensor at the second moment includes:

[0031] Acquire a first expected state parameter of each positioning sensor at the first moment, wherein the first expected state parameter is obtained by updating a state prediction parameter of the positioning sensor at the first moment using an extended Kalman filter algorithm;

[0032] The first measurement data and the first expected state parameter are input into a pre-established motion model for processing to obtain a state prediction parameter of each positioning sensor at the second moment.

[0033] In a second aspect, an embodiment of the present application provides an abnormality detection device for a positioning sensor, comprising:

[0034] A measurement data acquisition unit, used to acquire measurement data of each positioning sensor;

[0035] A motion state parameter acquisition unit, used to perform fusion processing on the measurement data of the plurality of positioning sensors to determine the motion state parameters of the autonomous driving device;

[0036] An abnormality judgment unit is used to determine, for each positioning sensor, a measurement state parameter of the positioning sensor using measurement data of the positioning sensor if it is determined that an abnormal positioning sensor exists among the plurality of positioning sensors according to the motion state parameters of the automatic driving device, and determine whether the positioning sensor has an abnormality according to the measurement state parameters of the positioning sensor.

[0037] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for detecting an abnormality of a positioning sensor described in any one of the first aspects when executing the computer program.

[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein when the computer program is executed by a processor, the method for detecting an abnormality of a positioning sensor described in any one of the first aspects is implemented.

[0039] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is executed on a terminal device, the terminal device executes the abnormality detection method for a positioning sensor described in any one of the first aspects above.

[0040] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 It is a flowchart of an abnormality detection method of a positioning sensor provided in an embodiment of the present application;

[0043] Figure 2 is a flowchart of a method for fusing the measurement data of a plurality of positioning sensors to determine the motion state parameters of the autonomous driving device in step S120 provided in an embodiment of the present application;

[0044] Figure 3 is a schematic diagram of a vehicle motion model provided by an embodiment of the present application;

[0045] Figure 4 This is a flowchart of the extended Kalman filter provided by an embodiment of the present application;

[0046] Figure 5 is a diagram showing the position measurement results of an autonomous driving car after a laser radar is attacked in an autonomous driving simulator experiment provided in an embodiment of the present application;

[0047] Figure 6It is a structural schematic diagram of an abnormality detection device for a positioning sensor provided in one embodiment of the present application;

[0048] Figure 7 It is a structural diagram of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0049] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0050] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0051] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0052] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0053] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0054] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0055] The present application is mainly aimed at detecting anomalies of positioning sensors on autonomous driving equipment. Autonomous driving vehicles are more common among autonomous driving equipment. For ease of understanding, the concept of the present application is described below using the detection of positioning sensors on autonomous driving vehicles as an example.

[0056] During the driving process of an autonomous vehicle, it is necessary to obtain the current positioning data of the vehicle, such as the vehicle position, driving speed and driving direction, through multiple positioning sensors installed on the vehicle. These positioning data are used to guide the vehicle's driving state at the next moment, such as whether the speed needs to be adjusted, whether the direction needs to be changed, etc. However, when the positioning sensor on the autonomous vehicle is abnormal due to attacks or other reasons, the positioning data obtained by the positioning sensor is often problematic, which will directly affect the driving state of the autonomous vehicle at the next moment, and is likely to cause a traffic accident.

[0057] To this end, the present application provides a positioning sensor anomaly detection method, which determines whether there is an abnormal positioning sensor among the multiple positioning sensors by fusing the measurement data of multiple positioning sensors; if there is an abnormal positioning sensor, the multiple positioning sensors are traversed, and the measurement data of each positioning sensor is used to determine whether each positioning sensor is abnormal, thereby solving the positioning problem of the abnormal sensor.

[0058] The following is an exemplary description of a positioning sensor abnormality detection method provided by the present application in conjunction with specific embodiments.

[0059] See also Figure 1 , a flowchart of an embodiment of a positioning sensor abnormality detection method is provided for an embodiment of the present application, which is applied to an autonomous driving device, and a plurality of the positioning sensors are arranged on the autonomous driving device; Figure 1 As shown, the method may include the following steps:

[0060] In step S110, measurement data of each positioning sensor is obtained.

[0061] In the embodiment, the autonomous driving device can obtain measurement data, such as the driving speed, position and driving direction of the autonomous driving vehicle, through multiple positioning sensors arranged thereon during the autonomous driving process. The autonomous driving device in the embodiment of the present application can be an autonomous driving car, an autonomous driving aircraft, an autonomous driving ship, etc.

[0062] In step S120, the measurement data of the plurality of positioning sensors are fused to determine the motion state parameters of the autonomous driving device.

[0063] In the embodiment of the present application, after obtaining the measurement data of each positioning sensor, the measurement data of multiple positioning sensors are fused to determine the motion state parameters of the autonomous driving device. The motion state parameters of the autonomous driving device are used to characterize whether the actual motion state of the autonomous driving device meets the expected motion state.

[0064] In step S130, if it is determined that there is an abnormal positioning sensor among the multiple positioning sensors based on the motion state parameters of the automatic driving device, for each positioning sensor, the measurement state parameters of the positioning sensor are determined using the measurement data of the positioning sensor, and whether the positioning sensor is abnormal is determined based on the measurement state parameters of the positioning sensor.

[0065] In the embodiment of the present application, both the motion state parameter and the measurement state parameter can be quantified values, and by comparing the quantifiable motion state parameter and the measurement state parameter with their respective corresponding preset thresholds, it is determined whether any positioning sensor is abnormal. When it is determined that a positioning sensor is abnormal, it is possible to sequentially check which positioning sensor is abnormal based on the measurement data of each positioning sensor.

[0066] In an embodiment, if it is determined based on the motion state parameters of the autonomous driving device that there is no abnormal positioning sensor among the multiple positioning sensors, steps S110 and S120 are repeated.

[0067] The positioning sensor abnormality detection method provided in the embodiment of the present application can not only detect that a positioning sensor among multiple positioning sensors on the autonomous driving equipment has an abnormality, but also promptly locate the specific positioning sensor with the abnormality, thereby improving the efficiency of positioning sensor legacy detection and making subsequent repair work on the positioning sensor more targeted.

[0068] Based on the above embodiment, in order to elaborate on the fusion processing of the measurement data of the plurality of positioning sensors in step S120 to determine the motion state parameters of the autonomous driving device, in another embodiment provided in the present application, the measurement data of the positioning sensor includes the first measurement data of the positioning sensor at the first moment and the second measurement data at the second moment, and the second moment is the next moment of the first moment in the time series; Figure 2 As shown, the method for determining the motion state parameters of the automatic driving device specifically includes:

[0069] Step S121, determining the motion state prediction parameters of the automatic driving device at a second moment based on the first measurement data of the plurality of positioning sensors at a first moment, wherein the second moment is the next moment of the first moment in the time series.

[0070] In an embodiment, the second moment may be the current moment when the anomaly detection is performed. The motion state at the second moment is predicted based on the first measurement data of the multiple positioning sensors at the previous moment, and the motion state prediction parameters of the autonomous driving device at the second moment are obtained. Taking an autonomous driving vehicle as an example, the motion state prediction parameters may be the predicted vehicle posture of the autonomous driving vehicle at the second moment, wherein the predicted vehicle posture specifically includes the predicted position coordinates and heading angle of the vehicle.

[0071] Step S122: Determine a second motion state measurement parameter of the automatic driving device at the second moment based on the second measurement data of the plurality of positioning sensors at the second moment.

[0072] In the embodiment, the second motion state measurement parameter is obtained based on the second measurement data of multiple positioning sensors at the second moment, and specifically, part of the data can be selected from the second measurement data to form the second motion state measurement parameter. Taking an autonomous driving vehicle as an example, the second motion state measurement parameter can be the measured vehicle posture of the autonomous driving device at the second moment, wherein the measured vehicle posture specifically includes the position coordinates and heading angle of the vehicle.

[0073] Step S123, performing residual calculation on the second motion state measurement parameter and the motion state prediction parameter to obtain the motion state parameter of the automatic driving device at the second moment.

[0074] In this embodiment, the motion state prediction parameters of the autonomous driving device at the second moment are predicted based on the first measurement data of multiple positioning sensors at the first moment, and the motion state parameters of the autonomous driving device at the second moment are obtained by performing residual calculation between the second motion state measurement parameters of the multiple positioning sensors at the second moment and the motion state prediction parameters. Subsequently, the motion state parameters are used to determine whether there is an abnormal positioning sensor among the multiple positioning sensors, specifically, by the calculated residual value. In this way, the motion state measurement parameters and motion state prediction parameters of multiple positioning sensors at a certain moment can be used to timely determine whether an abnormality has occurred, thereby avoiding the situation in the related technology where the judgment of the positioning sensor abnormality needs to be realized through the training model, and the situation that insufficient training samples may cause the inability to timely detect whether the equipment is abnormal.

[0075] Based on the above embodiment, in order to elaborate on step S121, determining the motion state prediction parameters of the autonomous driving device at the second moment according to the first measurement data of the plurality of positioning sensors, in another embodiment provided in the present application, the method for determining the motion state prediction parameters of the autonomous driving device at the second moment specifically includes:

[0076] Step S1211: Obtain first expected motion state parameters of the automatic driving device corresponding to the multiple positioning sensors at the first moment, wherein the first expected motion state parameters are obtained by updating the motion state prediction parameters at the first moment using an extended Kalman filter algorithm.

[0077] In the embodiment, the first expected motion state parameter is obtained by updating the motion state prediction parameter at the first moment by using an extended Kalman filter algorithm.

[0078] The extended Kalman filter algorithm combines the predicted value and the measured value. The specific filtering process will be introduced in detail later and will not be described here.

[0079] Step S1212: input the first measurement data and the first expected motion state parameter into a pre-established motion model for processing to obtain the motion state prediction parameter of the automatic driving device at the second moment.

[0080] The following is a detailed description of the motion model using an actual autonomous driving vehicle as an example. Specifically, the essence of an abnormality in the positioning sensor (such as being attacked) is that the positioning sensor data has undergone an abnormal change, and anomaly detection is to detect whether an abnormality has occurred in the positioning sensor data. Therefore, establishing a data model can make the impact of the positioning sensor abnormality on the autonomous driving device specific to the data, which can provide an analysis object for subsequent positioning sensor abnormality detection and abnormal positioning. In the embodiment, the data model of the positioning sensor is established based on the motion model of the vehicle.

[0081] The present application embodiment can use a bicycle motion model to model the vehicle motion state. The model assumes that the vehicle is a moving object on a two-dimensional plane, and the structure of the vehicle is the same as that of a bicycle, that is, the two front tires of the vehicle have the same angle and rotation speed, and the front tires control the turning angle of the vehicle. The vehicle motion scene on the two-dimensional plane can be obtained based on the assumption of the bicycle model. Figure 3 The vehicle motion model shown.

[0082] Figure 3 In the figure, assume that the wheelbase (the distance between the front and rear tires) of the autonomous vehicle is L, the heading angle in the world coordinate is θ, the angular velocity is w, the front wheel turning angle is δ, p = (a, b) is the position of the vehicle in the rectangular coordinate system, and v is the speed of the vehicle. From the kinematic principle, we can get:

[0083]

[0084] In the embodiment, the vehicle motion state is represented by the vehicle posture, specifically, the vehicle coordinates and heading angle. The first expected motion state parameter at time k-1 is x k-1 =[a k-1 , b k-1 ,θ k-1 ] T , the input vector μ of the autonomous vehicle motion model k-1 =[v k-1 , δ k-1 ] T , the output of the vehicle motion model is shown in formula (2):

[0085]

[0086] In formula (2), T s is the time interval between time k-1 and time k; x pre is the predicted parameter of the vehicle's motion state at time k; a k-1 and b k-1 is the expected position coordinate of the vehicle at time k-1, θ k-1 is the desired heading angle of the vehicle at time k-1, v k-1 is the speed of the vehicle measured at time k-1; ξ v，k-1 and δ，k-1 is the motion noise of the vehicle at time k-1, we define ω k =[ξ v，k ,ξ δ，k ] T , and ω kis an independent and identically distributed Gaussian random variable with a mean of 0 and a covariance of Q> 0. Therefore, the expression of the vehicle motion model in the embodiment of the present application is shown in formula (3):

[0087] x pre =f(x k-1 , μ k-1 ,ω k-1 ) (1)

[0088] In formula (3), f(·) is a nonlinear function.

[0089] In actual practice, the positioning sensor is often interfered by noise, so the observation model of the vehicle (that is, the actual motion state measurement parameters of the vehicle) is shown in formula (4):

[0090]

[0091] In formula (4), y k is the measured parameter of the vehicle's motion state at the kth moment, x k =[a k , b k ,θ k ] T is the initial motion state measurement parameter of the vehicle at the kth moment (at x k Directly obtained from the measurement data of the positioning sensor, Figure 4 The final desired motion state parameter x obtained after updating k has different meanings),∈ k =[∈ a，k ,∈ b，k ,∈ θ，k ] T represents the measurement noise vector, ∈ k With y k have the same dimension, and ∈ a，k ,∈ b，k ,∈ θ，k are independent random variables, ∈ k are independent and identically distributed Gaussian random variables with mean 0 and covariance Q>0.

[0092] In the observation model for obtaining the actual motion state measurement parameters of the vehicle, the obtained motion state measurement parameters are made more consistent with the actual motion state of the vehicle by introducing a measurement noise vector.

[0093] When the first measurement data of the vehicle positioning sensor at the first moment is obtained, the first motion state measurement parameters of the vehicle at the first moment can be obtained. By pre-establishing a vehicle motion model, the first measurement data at the first moment and the first expected motion state parameters can be used to predict the motion state prediction parameters of the vehicle at the second moment, and then the second measurement data at the second moment is obtained through the vehicle positioning sensor to obtain the second motion state measurement parameters of the vehicle at the second moment.

[0094] In one embodiment, after obtaining the motion state prediction parameters at the second moment, the motion state prediction parameters at the second moment may be updated based on the extended Kalman filter algorithm to obtain the second expected motion state parameters of the automatic driving device corresponding to the multiple positioning sensors at the second moment. The updated second expected motion state parameters are used as input values ​​of the motion model at the next moment of the second moment, thereby completing the recursive loop.

[0095] In a specific embodiment, the step of updating the motion state prediction parameters at the second moment based on the extended Kalman filter algorithm to obtain the second expected motion state parameters of the automatic driving device corresponding to the multiple positioning sensors at the second moment specifically includes:

[0096] Obtaining an estimated error covariance of the plurality of positioning sensors at the first moment, and obtaining a predicted error covariance of the plurality of positioning sensors at the second moment based on the estimated error covariance at the first moment, and obtaining a Kalman gain based on the predicted error covariance at the second moment;

[0097] The motion state prediction parameter at the second moment is updated based on the Kalman gain and the second motion state measurement parameter to obtain a second expected motion state parameter.

[0098] In the embodiment of the present application, the update of the motion state prediction parameters is obtained by recursive estimation using the Extended Kalman Filter (EKF) algorithm. The essence of the Extended Kalman Filter (EKF) algorithm is a parameterized Bayesian model.

[0099] Figure 4 The extended Kalman filter workflow diagram shown in Figure 4 The extended Kalman filter (EKF) algorithm shown combines the prediction of the motion state at the current moment with the feedback obtained by measurement, and finally obtains the expected state at that moment (the expected state corresponds to the expected motion state parameter in the embodiment of the present application). The core idea is prediction + measurement feedback. For ease of understanding, the filtering operation is discussed below:

[0100] (a) Initialization. Assume that the initial motion state measurement parameter of the vehicle obtained by the observation model of equation (4) is y0. Assume that the motion state prediction parameter corresponding to the initial moment is x0=y0. In addition, the estimated error covariance of the motion state at the initial moment is P0, which is obtained according to the sensor manufacturer. After the algorithm is initialized, the k value is updated (k=1, 2, ...), and the following prediction and update steps will be recursively executed.

[0101] (b) Prediction. After updating the k value, the vehicle motion state prediction parameters corresponding to the time k = 1 are shown in formula (5):

[0102] x pre =f(x k-1 , μ k-1 ,0) (5)

[0103] And use Figure 4 The method in predicts the error covariance corresponding to the time k = 1, as shown in formula (6):

[0104] P pre =A k-1 P k-1 A k-1 T +B k-1 QB k-1 T (6)

[0105] A in the formula k-1 and B k-1 It is the partial derivative matrix obtained by the first-order approximation of the motion state model according to Taylor expansion. The specific expression is as follows:

[0106]

[0107] (c) Update. Figure 4 It can be seen that, specifically, the update of the motion state prediction parameters and the estimation error covariance at time k is as follows:

[0108] K k =P pre H k T (H k P pre H k T +R) -1

[0109] x k =x pre +K k (y k -x pre )

[0110] P k =P pre -K k H k P pre

[0111] In the embodiment, we designed a spatial domain detector and a temporal domain monitor, wherein the spatial domain detector fuses the measurement data of multiple positioning sensors to predict the motion state parameters of the autonomous driving device, and the detection result is to determine whether any of the multiple positioning sensors is attacked (abnormal). The temporal domain detector predicts the measurement state parameters of the corresponding positioning sensor for the measurement data of each positioning sensor on the premise that the spatial domain detector determines that a sensor is attacked, and the detection result is to determine whether the corresponding positioning sensor is attacked (abnormal).

[0112] The following is an expansion of the update step (c) for the spatial domain detector and the temporal domain detection domain respectively:

[0113] Before executing the update step, calculate the partial derivative matrix H obtained by the observation model according to the Taylor expansion in the first order approximation k , reference A k-1 and B k-1 , similarly we can get:

[0114]

[0115] For the spatial domain detector, multiple positioning sensors need to be detected. Therefore, the observation model (4) comes from the measurement data of multiple positioning sensors (assuming there are n positioning sensors), that is:

[0116]

[0117] Among them, y n，k represents the motion state measurement parameter of sensor n at time k; C is a 3n×3n unit matrix; where ∈ n，k is the measurement noise vector of sensor n at time k, and we can get R n，k represents the measurement noise covariance matrix of sensor n at time k, so we can get:

[0118] The update of the motion state prediction parameters and the estimation error covariance corresponding to time k is as follows:

[0119]

[0120] In the above formula, It is the identity matrix of order 3n×3n.

[0121] The expression of the residual value of multiple positioning sensors as a whole at time k is as follows:

[0122]

[0123] For the time domain detector, a single positioning sensor is detected, and y in the model (4) k Location data (a k , b k ,θ k ) are all derived from the measurement data of the same positioning sensor at time k.

[0124] For positioning sensor 1, the observation model (4) is modified as follows:

[0125]

[0126] Among them, y 1，k Represents the state measurement parameter of positioning sensor 1; ∈ 1，k represents the measurement noise of positioning sensor 1, and its covariance is R1. Therefore, the measurement update of the state prediction parameters and estimation error covariance of sensor 1 at time k is as follows:

[0127] K 1，k＝ P 1，pre H k T (H k P 1，pre H k T +R1) -1

[0128] x 1，k =x 1，pre +K 1，k (y 1，k -x 1，pre ) (11)

[0129] P 1，k =P 1，pre -K 1，k H k P 1，pre

[0130] The residual value expression of sensor 1 at time k is:

[0131] r 1，k =y 1，k -H k x 1，pre (12)

[0132] For positioning sensor 2, the observation model (4) is modified as follows:

[0133]

[0134] Among them, y 2，k Represents the state measurement parameter of positioning sensor 2; ∈ 2，k represents the measurement noise of positioning sensor 2, and its covariance is R2.

[0135] Therefore, the measurement update of the state prediction parameters and estimation error covariance of sensor 2 at time k is as follows:

[0136] K 2，k＝ P 2，pre H k T (H k P 2，pre H k T +R2) -1

[0137] x 2，k =x 2，pre +K 2，k (y 2，k -x 2，pre ) (14)

[0138] P 2，k =P 2，pre -K 2，k H k P 2，pre

[0139] The residual value expression of sensor 2 at time k is as follows:

[0140] r 2，k =y 2，k -H k x 2，pre (15)

[0141] In one embodiment, step S130 determines, based on the motion state parameters of the autonomous driving device, whether there is an abnormal positioning sensor among the multiple positioning sensors. Specifically, it may include: if the motion state parameters are not within a first preset range, determining whether there is an abnormal positioning sensor among the multiple positioning sensors.

[0142] In one embodiment, the method further includes: determining, based on the motion state parameters of the autonomous driving device, that there is no abnormal positioning sensor among the multiple positioning sensors, and specifically may include: if the motion state parameters are within a first preset range, determining that there is no abnormal positioning sensor among the multiple positioning sensors.

[0143] In one embodiment, the motion state parameter is a residual value r of the motion state prediction parameter and the second motion state measurement parameter. k , the specific expression is as described above.

[0144] Based on the above embodiment, in order to improve the efficiency of the abnormality detection method, in another embodiment provided by the present application, the step of determining that there is an abnormal positioning sensor among multiple positioning sensors according to the motion state parameters of the automatic driving device may further include the following steps:

[0145] Acquire the measurement data corresponding to each of the positioning sensors at each moment in the target historical time period.

[0146] The measurement data of the plurality of positioning sensors at each moment are fused and processed respectively to determine the motion state parameters corresponding to each moment in the target historical time period of the autonomous driving device.

[0147] The motion state parameters corresponding to each moment in the target historical time period of the automatic driving device are accumulated and averaged to obtain the average motion state parameters corresponding to the target historical time period.

[0148] If the average motion state parameter is not within the second preset range, it is determined that an abnormal positioning sensor exists among the plurality of positioning sensors.

[0149] In one embodiment, if the average motion state parameter is within a second preset range, it is determined that there is no abnormal positioning sensor among the plurality of positioning sensors.

[0150] The above embodiments mainly provide a detailed description of the method for determining whether an abnormal positioning sensor exists among multiple positioning sensors. The above method for determining whether an abnormal positioning sensor exists among multiple positioning sensors is also applicable to determining whether each positioning sensor on the autonomous driving device is abnormal. The following is a brief description of the method for determining whether an abnormal positioning sensor exists on the autonomous driving device.

[0151] In step S130, for each positioning sensor, the measurement state parameter of the positioning sensor is determined using the measurement data of the positioning sensor, including:

[0152] determining, according to the first measurement data of each of the positioning sensors, a state prediction parameter of the positioning sensor at the second moment;

[0153] Determining a second state measurement parameter of the positioning sensor at the second moment according to the second measurement data of each positioning sensor;

[0154] Residual calculation is performed on the state prediction parameter and the second state measurement parameter to obtain the measurement state parameter of each positioning sensor at the second moment.

[0155] In one embodiment, the step of determining the state prediction parameter of the positioning sensor at the second moment according to the first measurement data of each positioning sensor includes:

[0156] Acquire a first expected state parameter of each positioning sensor at the first moment, wherein the first expected state parameter is obtained by updating a state prediction parameter of the positioning sensor at the first moment using an extended Kalman filter algorithm;

[0157] Inputting the first measurement data and the first expected state parameter into a pre-established motion model for processing to obtain a state prediction parameter of each positioning sensor at the second moment;

[0158] In one embodiment, the method for determining whether each positioning sensor is abnormal further includes:

[0159] The state prediction parameters of each positioning sensor at the second moment are updated based on the extended Kalman filter algorithm to obtain the second expected state parameters of each positioning sensor at the second moment.

[0160] In one embodiment, the step of determining whether the positioning sensor is abnormal according to the measurement state parameter of the positioning sensor includes:

[0161] If the measurement state parameter of the positioning sensor is not within the third preset range, it is determined that the positioning sensor is abnormal.

[0162] In one embodiment, the step of determining whether the positioning sensor is abnormal according to the measurement state parameter of the positioning sensor includes:

[0163] If the measurement state parameter of the positioning sensor is within a third preset range, it is determined that an abnormality occurs in the positioning sensor.

[0164] In one embodiment, for each positioning sensor, the step of determining whether the positioning sensor is abnormal according to the measurement state parameter of the positioning sensor includes:

[0165] Acquire measurement data corresponding to each of the positioning sensors at each time in a target historical time period;

[0166] For each of the measurement data of the positioning sensor at each of the moments, determining the measurement state parameters of the positioning sensor corresponding to each moment in the target historical time period;

[0167] Accumulate and average the measured state parameters corresponding to each moment in the target historical time period of the positioning sensor to obtain the average state parameter corresponding to the target historical time period;

[0168] If the average state parameter is not within the fourth preset range, it is determined that the positioning sensor is abnormal.

[0169] In one embodiment, if the average state parameter is within a fourth preset range, it is determined that the positioning sensor is not abnormal.

[0170] In order to avoid too much elaboration, the specific steps of the method for determining whether each positioning sensor on the autonomous driving equipment has an abnormality will not be expanded.

[0171] For example, usually the residual value r k The default range (including the first default range, the second default range, the third default range and the fourth default range) is a confidence interval corresponding to the confidence level. The default range is determined as follows:

[0172] The residual value of the positioning sensor under normal conditions is used as a sample to establish the residual value r k The normal distribution of is shown in formula (16):

[0173] r k ~N(ε,σ 2 ) (16)

[0174] If we want to judge that the sensor is normal with a 99% confidence level, the corresponding confidence interval M satisfies the following conditions:

[0175]

[0176] That is, if the subsequent It means that the sensor is considered normal at a confidence level of 99%, otherwise it is considered abnormal. n represents the number of samples. The higher the required confidence level, the narrower the judgment interval of normal situation.

[0177] For ease of understanding, the following is a specific interpretation of the discrimination results of the spatial domain detector and the time domain detector in the embodiment of the present application. The attack positioning scheme based on the following Table 1 is used to identify the attacked positioning sensor. Table 1 takes the attack positioning scheme for detecting two positioning sensors as an example, where the time domain detector 1 is for GPS and the time domain detector 2 is for LiDAR. The specific description is as follows:

[0178] Table 1 Attack location scheme

[0179] Condition Spatial Domain Detector Time Domain Detector 1 Time Domain Detector 2 result 1 No abnormality No abnormality No abnormality No attack 2 abnormal No abnormality No abnormality Uncertain Attack 3 abnormal abnormal No abnormality GPS Hacked 4 abnormal No abnormality abnormal LiDAR is under attack 5 abnormal abnormal abnormal Both GPS and LiDAR are attacked

[0180] Case 1: In this case, the spatial domain detector, the temporal domain detector 1, and the temporal domain detector 2 do not raise an alarm, which means that in each attack detector, the sensor measurement value is consistent with the predicted value obtained from the vehicle motion model. So both positioning sensors are normal.

[0181] Case 2: In this case, only the spatial domain detector raises an alarm, while the temporal domain detector 1 and the temporal domain detector 2 do not find any anomalies. This is a special case because even if the measurement value of the positioning sensor 1 or the positioning sensor 2 matches the expected value in the temporal domain detector 1 and the temporal domain detector 2, a mismatch is still found in the spatial domain detector. The silence of the temporal domain detector 1 and the temporal domain detector 2 may be because the intensity of the attack is so small that it is suppressed by the process and measurement noise. However, over time, the inconsistency between the two measurements will increase, resulting in an alarm in the spatial domain detector. Therefore, in this case, it can be determined that there is an attack, but the source of the attack is unknown.

[0182] Case 3: In this case, the spatial domain detector and the temporal domain detector 1 detect anomalies, while the temporal domain detector 2 remains silent, which means that the positioning sensor 1 is attacked and the positioning sensor 2 is working normally. Therefore, the measurements of the positioning sensor 1 and the positioning sensor 2 are inconsistent, which triggers an alarm in the spatial domain detector.

[0183] Case 4: In this case, anomalies are detected in the spatial domain detector and the temporal domain detector 2, while the detector 1 remains silent. Similar to the analysis of case 3, it can be concluded that the positioning sensor 2 is attacked.

[0184] Case 5: In this case, all three detectors detect anomalies, which can easily lead to the conclusion that both localization sensor 1 and localization sensor 2 are affected. Anomalies in spatial domain detectors are due to inconsistent measurements.

[0185] In the embodiment of the present application, a spatial domain detector and a temporal domain detector are designed based on the correlation of positioning sensors. Compared with the traditional model-based method, the main novelty of this attack detection scheme is that the positioning sensors with spatial correlation are first detected to determine whether any sensor is attacked, and then the single positioning sensor is judged based on the temporal correlation to determine which sensor is attacked, thereby improving the detection speed.

[0186] In addition, the spatial domain detector in the embodiment analyzes the complementary differences between different sensor data from the spatial dimension, and the time domain detector analyzes the temporal continuity differences of the same sensor data from the temporal dimension. Both detectors reduce the delay in real-time attack detection requirements, making the autonomous driving car safer during driving.

[0187] In order to explain the problem more clearly, the embodiment of the present application was experimented in an autonomous driving simulator. The specific experimental process and results are as follows:

[0188] In the autonomous driving simulator, the autonomous vehicle was driven on a pre-planned path, and a series of data collected were used for experiments. By recording rosbag, all available data including perception, planning, and control are stored. This experiment focuses on the detection and identification of positioning sensor attacks (anomalies), so the position data of the positioning sensors GPS and LiDAR in the stored data and the controller command data including speed and steering angle are used.

[0189] Table 2 shows the data format in the stored data, where x and y in the position coordinates correspond to the position coordinates a and b, yaw in the vehicle's attitude data corresponds to the heading angle θ, and the vehicle speed v and front wheel steering angle v at different times are obtained from the stored data in the controller command. During the data collection process, the autonomous vehicle moves on the autonomous driving simulation platform, and the positioning sensor attack detection experiment is carried out by attacking the laser radar. After the laser radar is attacked, the position measurement values ​​collected in real time are all wrong and can further mislead the vehicle. Specifically, in the experiment, we make the laser radar position measurement gradually biased towards the adjacent lane. The position measurement results are as follows: Figure 5 As shown in Figure 2. The attack time is randomly determined, and the lateral offset from the vehicle's actual lane caused by the attack is also randomly generated from [3.5, 7] ∪ [-7, -3.5] meters, which means the adjacent lanes on the left and right sides of the vehicle's current lane with a lane width of 3.5 meters. In the test, the lidar attack occurred at 43.07 seconds, and the lateral offset was equal to 5.342 meters, which means that the lidar system position measurement data has become the adjacent lane on the left, while the orientation measurement data remains unaffected.

[0190] Table 2

[0191]

[0192]

[0193] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0194] Corresponding to the abnormality detection method of the positioning sensor described in the above embodiment, Figure 6 A structural block diagram of an abnormality detection device for a positioning sensor provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0195] Reference Figure 6 , the abnormality detection device 6 of the positioning sensor includes:

[0196] A measurement data acquisition unit 61, used to acquire measurement data of each positioning sensor;

[0197] A motion state parameter acquisition unit 62, configured to perform fusion processing on the measurement data of the plurality of positioning sensors to determine the motion state parameters of the autonomous driving device;

[0198] The abnormality judgment unit 63 is used to determine, for each positioning sensor, the measurement state parameters of the positioning sensor using the measurement data of the positioning sensor if it is determined that there is an abnormal positioning sensor among the multiple positioning sensors according to the motion state parameters of the automatic driving device, and determine whether the positioning sensor has an abnormality according to the measurement state parameters of the positioning sensor.

[0199] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0200] in addition, Figure 6 The device shown may be a software unit, a hardware unit, or a combination of software and hardware, which is built into an existing terminal device, or may be integrated into the terminal device as an independent accessory, or may exist as an independent terminal device.

[0201] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0202] Figure 7 This is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application. Figure 7 As shown, the terminal device 7 of this embodiment includes: at least one processor 70 ( Figure 7Only one processor is shown in the figure), a memory 71, and a computer program 72 stored in the memory 71 and executable on the at least one processor 70, wherein the processor 70 implements the steps in any of the above-mentioned method embodiments when executing the computer program 72.

[0203] The terminal device 7 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will appreciate that Figure 7 It is only an example of the terminal device 7 and does not constitute a limitation on the terminal device 7. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0204] The processor 70 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0205] In some embodiments, the memory 71 may be an internal storage unit of the terminal device 7, such as a hard disk or memory of the terminal device 7. In other embodiments, the memory 71 may also be an external storage device of the terminal device 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 7. Further, the memory 71 may also include both an internal storage unit and an external storage device of the terminal device 7. The memory 71 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 71 may also be used to temporarily store data that has been output or is to be output.

[0206] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the above-mentioned method embodiments when executing the computer program.

[0207] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0208] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0209] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the abnormality detection device / terminal device of the positioning sensor, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0210] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0211] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0212] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0213] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0214] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting abnormality of a positioning sensor, applied to an autonomous driving device, wherein a plurality of positioning sensors are arranged on the autonomous driving device, characterized in that: include: Acquiring measurement data of each of the positioning sensors; fusing the measurement data of the plurality of positioning sensors to determine the motion state parameters of the autonomous driving device; If it is determined that an abnormal positioning sensor exists among the plurality of positioning sensors according to the motion state parameters of the automatic driving device, then for each positioning sensor, a measurement state parameter of the positioning sensor is determined using the measurement data of the positioning sensor, and whether the positioning sensor is abnormal is determined according to the measurement state parameters of the positioning sensor; The measurement data of the positioning sensor includes first measurement data of the positioning sensor at a first moment and second measurement data at a second moment, wherein the second moment is a next moment of the first moment in the time series; The fusing and processing the measurement data of the plurality of positioning sensors to determine the motion state parameters of the automatic driving device includes: determining a motion state prediction parameter of the automatic driving device at the second moment according to the first measurement data of the plurality of positioning sensors; determining a second motion state measurement parameter of the automatic driving device at the second moment according to the second measurement data of the plurality of positioning sensors; Perform residual calculation on the second motion state measurement parameter and the motion state prediction parameter to obtain the motion state parameter of the automatic driving device at the second moment.

2. The method according to claim 1, characterized in that The step of determining the motion state prediction parameter of the automatic driving device at the second moment according to the first measurement data of the plurality of positioning sensors includes: Acquire first expected motion state parameters of the automatic driving device corresponding to the plurality of positioning sensors at the first moment, wherein the first expected motion state parameters are obtained by updating the motion state prediction parameters at the first moment using an extended Kalman filter algorithm; The first measurement data and the first expected motion state parameter are input into a pre-established motion model for processing to obtain the motion state prediction parameter of the automatic driving device at the second moment.

3. The method according to claim 1, characterized in that The step of determining, based on the motion state parameter of the automatic driving device, that an abnormal positioning sensor exists among the plurality of positioning sensors comprises: If the motion state parameter is not within the first preset range, it is determined that an abnormal positioning sensor exists among the plurality of positioning sensors.

4. The method according to claim 1, characterized in that The step of determining, based on the motion state parameter of the automatic driving device, that an abnormal positioning sensor exists among the plurality of positioning sensors comprises: Acquire measurement data corresponding to each of the positioning sensors at each time in a target historical time period; The measurement data of the plurality of positioning sensors at each moment are respectively fused and processed to determine the motion state parameters corresponding to each moment in the historical time period of the autonomous driving device and the target; Accumulating and averaging the motion state parameters corresponding to each moment in the target historical time period of the automatic driving device to obtain the average motion state parameter corresponding to the target historical time period; If the average motion state parameter is not within the second preset range, it is determined that an abnormal positioning sensor exists among the plurality of positioning sensors.

5. The method according to any one of claims 1 to 4, characterized in that: The measurement data of the positioning sensor includes first measurement data of the positioning sensor at a first moment and second measurement data at a second moment, wherein the second moment is a next moment of the first moment in the time series; The method of determining the measurement state parameter of each positioning sensor by using the measurement data of the positioning sensor comprises: determining, according to the first measurement data of each of the positioning sensors, a state prediction parameter of the positioning sensor at the second moment; Determining a second state measurement parameter of the positioning sensor at the second moment according to the second measurement data of each positioning sensor; Residual calculation is performed on the second state measurement parameter and the state prediction parameter to obtain the measurement state parameter of each positioning sensor at the second moment.

6. The method according to claim 5, characterized in that The step of determining the state prediction parameter of the positioning sensor at the second moment according to the first measurement data of each positioning sensor comprises: Acquire a first expected state parameter of each positioning sensor at the first moment, wherein the first expected state parameter is obtained by updating a state prediction parameter of the positioning sensor at the first moment using an extended Kalman filter algorithm; The first measurement data and the first expected state parameter are input into a pre-established motion model for processing to obtain a state prediction parameter of each positioning sensor at the second moment.

7. A positioning sensor abnormality detection device, applied to an automatic driving device, wherein a plurality of positioning sensors are provided on the automatic driving device, characterized in that: include: A measurement data acquisition unit, used to acquire measurement data of each positioning sensor; A motion state parameter acquisition unit, used to perform fusion processing on the measurement data of the plurality of positioning sensors to determine the motion state parameters of the autonomous driving device; an abnormality judgment unit, configured to determine, for each of the positioning sensors, a measurement state parameter of the positioning sensor using measurement data of the positioning sensor if it is determined that an abnormal positioning sensor exists among the plurality of positioning sensors according to the motion state parameter of the automatic driving device, and determine whether the positioning sensor has an abnormality according to the measurement state parameter of the positioning sensor; The measurement data of the positioning sensor includes first measurement data of the positioning sensor at a first moment and second measurement data at a second moment, wherein the second moment is a next moment of the first moment in the time series; The motion state parameter acquisition unit is used to perform fusion processing on the measurement data of the plurality of positioning sensors to determine the motion state parameters of the automatic driving device, including: determining a motion state prediction parameter of the automatic driving device at the second moment according to the first measurement data of the plurality of positioning sensors; determining a second motion state measurement parameter of the automatic driving device at the second moment according to the second measurement data of the plurality of positioning sensors; Perform residual calculation on the second motion state measurement parameter and the motion state prediction parameter to obtain the motion state parameter of the automatic driving device at the second moment.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images