Vehicle positioning processing method, device, electronic equipment and storage medium

Abstract

The vehicle positioning processing method, device, electronic device and storage medium provided in the embodiment of the present application relate to the field of autonomous driving technology. The method can be applied to scenes such as ports, mines, trunk logistics, highways or urban transportation, and the method includes: obtaining the process variable at time k output in the process of estimating the vehicle error state at time k+1, determining the protection level of the vehicle at time k according to the process variable at time k, and estimating the positioning credibility of the vehicle at time k according to the protection level of the vehicle at time k. Through the process variables, the maximum positioning error of the vehicle positioning information can be determined, the credibility of the positioning information can be evaluated, and timely warnings can be issued in the event of positioning anomalies, which can improve the safety of vehicle driving.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a vehicle positioning processing method, device, electronic device and storage medium. Background Art

[0002] High-precision and reliable vehicle positioning is one of the key technologies for autonomous driving and an important prerequisite for the vehicle to correctly perform operations such as perception, planning and control.

[0003] In addition to the positioning information of the autonomous driving vehicle, the credibility of the positioning information is also an important indicator for performance evaluation. It is used by other functional modules of the autonomous driving to evaluate the confidence level of the positioning information, thereby ensuring the overall safety of the autonomous driving. Since the changing application scenarios of autonomous driving vehicles will limit the measurement capabilities of the positioning sensors, and unknown environmental changes will affect the measurement accuracy of the positioning sensors, the accurate and timely evaluation of the credibility of the positioning information has become a key issue that needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide a vehicle positioning processing method, device, electronic device and storage medium, which can improve the safety of vehicle driving by evaluating the positioning credibility.

[0005] In a first aspect, an embodiment of the present application provides a vehicle positioning processing method, comprising:

[0006] Obtaining a process variable at time k output during the process of determining the vehicle error state estimation at time k+1, wherein the process variable includes at least one of an innovation sequence, an innovation variance matrix, and a Kalman gain matrix;

[0007] Determine a protection level of the vehicle at time k according to the process variable at time k, wherein the protection level is used to characterize the maximum positioning error estimated for the vehicle at time k;

[0008] According to the protection level of the vehicle at time k, the positioning credibility of the vehicle at time k is warned. By evaluating the positioning credibility and issuing a warning in the event of positioning anomalies, the safety of vehicle driving can be improved.

[0009] Optionally, the providing an early warning on the positioning credibility of the vehicle according to the protection level of the vehicle at time k includes:

[0010] Obtaining the driving environment and motion state of the vehicle at time k;

[0011] According to the driving environment and motion state of the vehicle at the k moment, updating the initial alarm threshold of the vehicle to obtain the target alarm threshold of the vehicle at the k moment;

[0012] When the protection level of the vehicle at time k is greater than the target alarm threshold at time k, the positioning warning information of the vehicle at time k is output. By designing a positioning alarm threshold update strategy and combining the use scenario to adaptively adjust the threshold, the ability of automatic driving to issue an alarm in a timely manner can be improved.

[0013] Optionally, determining the vehicle error state estimate at time k+1 includes: acquiring first positioning information of the vehicle at time k according to first positioning sensor data of the vehicle, and acquiring second positioning information of the vehicle at time k according to second positioning sensor data of the vehicle;

[0014] Determine the measurement vector at the k moment according to the first positioning information at the k moment and the second positioning information at the k moment;

[0015] According to the measurement error at time k and the error state estimate at time k, the error state estimate at time k+1 is determined; the error state estimate at time k+1 is used to correct the first positioning information at time k+1 to obtain the target positioning information of the vehicle at time k+1. The above method can correct the cumulative error of the main sensor and improve the positioning accuracy of the vehicle.

[0016] Optionally, before determining the protection level of the vehicle at time k according to the process variable at time k, the method further includes:

[0017] Determine a fault statistic value of the second sensor data at time k according to the process variable at time k;

[0018] Determine whether the second sensor has a fault according to the fault statistics at the k moment. By determining whether the second sensor has a fault, the reliability of the positioning system fusion process can be improved.

[0019] Optionally, determining whether the second sensor has a fault according to the fault statistic value at the k moment includes:

[0020] If the fault statistic value at the k moment is greater than the first threshold, it is determined that the second sensor data has an error at the k moment;

[0021] updating the accumulated number of errors of the second sensor, and determining that the second sensor has a fault when the accumulated number of errors is greater than a second threshold;

[0022] If the fault statistic value at the k moment is less than or equal to the first threshold, the accumulated number of errors is reset.

[0023] Optionally, before determining the measurement vector at time k according to the first positioning information at time k and the second positioning information at time k, the method further includes:

[0024] The first positioning information at the k moment and the second positioning information at the k moment are converted into the same coordinate system.

[0025] Optionally, the vehicle includes at least one of the following candidate second sensors:

[0026] Global Satellite Navigation System GNSS receiver, wheel speed meter, lidar, camera;

[0027] When it is determined that the second sensor is faulty, the method further includes:

[0028] According to the preset strategy, the remaining candidate second sensors are used to replace the faulty second sensor. By setting multiple sensors to be redundant, the reliability is high, the configuration is flexible and changeable, and the versatility is strong.

[0029] In a second aspect, the present application provides a vehicle positioning processing device, comprising:

[0030] An acquisition module, used for acquiring a process variable at time k outputted in the process of determining the vehicle state error estimation at time k+1, wherein the process variable comprises at least one of an innovation sequence, an innovation variance matrix, and a Kalman gain matrix;

[0031] A determination module, used to determine a protection level of the vehicle at time k according to a process variable at time k, wherein the protection level is used to characterize a maximum positioning error estimated for the vehicle at time k;

[0032] The early warning module is used to issue an early warning on the positioning credibility of the vehicle according to the protection level of the vehicle at time k.

[0033] Optionally, the vehicle positioning processing device can execute the positioning processing method described in any one of the first aspects.

[0034] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor;

[0035] The memory is used to store computer instructions; the processor is used to execute the computer instructions stored in the memory to implement any method in the first aspect.

[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement any one of the methods in the first aspect.

[0037] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements any method in the first aspect when executed by a processor.

[0038] In a sixth aspect, an embodiment of the present application provides a chip or a chip system, the chip or chip system includes at least one processor and a communication interface, the communication interface and the at least one processor are interconnected through a line, and the at least one processor is used to run a computer program or instruction to execute the vehicle positioning processing method described in the possible implementation method of the first aspect. Among them, the communication interface in the chip can be an input / output interface, a pin or a circuit, etc.

[0039] In a possible implementation, the chip or chip system described above in the present application further includes at least one memory, and instructions are stored in at least one memory. The memory may be a storage unit inside the chip, such as a register, a cache, etc., or a storage unit of the chip (e.g., a read-only memory, a random access memory, etc.).

[0040] The vehicle positioning processing method, device, electronic device and storage medium provided in the embodiment of the present application obtain the process variable at time k output in the process of determining the vehicle error state estimation at time k+1, determine the protection level of the vehicle at time k according to the process variable at time k, and issue an early warning for the positioning credibility of the vehicle at time k according to the protection level of the vehicle at time k. Through the process variable, the error range of the vehicle positioning estimation can be determined, the positioning reliability can be evaluated, and an early warning can be issued in the event of positioning abnormality, which can improve the safety of vehicle driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic diagram of a scenario provided for an embodiment of the present application;

[0042] Figure 2 Schematic diagram of the vehicle positioning processing method provided in the embodiment of the present application Figure 1 ;

[0043] Figure 3 Schematic diagram of the vehicle positioning processing method provided in the embodiment of the present application Figure 2 ;

[0044] Figure 4 Schematic diagram of the vehicle positioning processing method provided in the embodiment of the present application Figure 3 ;

[0045] Figure 5 A schematic diagram of determining whether a second sensor is faulty provided in an embodiment of the present application;

[0046] Figure 6 A schematic diagram of positioning warning provided in an embodiment of the present application;

[0047] Figure 7 A schematic diagram of the interaction between the positioning unit and the positioning credibility unit provided in an embodiment of the present application;

[0048] Figure 8 A schematic diagram of an early warning in an autonomous driving scenario provided in an embodiment of the present application;

[0049] Fig. 9 A schematic diagram of another warning in an autonomous driving scenario provided in an embodiment of the present application;

[0050] Fig.10 A schematic diagram of the structure of a vehicle positioning processing device provided in an embodiment of the present application;

[0051] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0053] In the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with substantially the same functions and effects, and do not limit their order. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0054] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0055] It should be noted that the “at…” in the embodiments of the present application may be the instant when a certain situation occurs, or may be a period of time after the occurrence of a certain situation, and the embodiments of the present application do not specifically limit this.

[0056] High-precision and reliable vehicle positioning is one of the key technologies for autonomous driving and an important prerequisite for the vehicle to correctly perform operations such as perception, planning and control.

[0057] The application scenarios of self-driving cars are varied. Factors such as sky obstructions, electromagnetic interference, bumpy roads, rainy and snowy weather will affect the performance of positioning sensors, causing deviations in positioning information. In addition, when self-driving cars are working for a long time, the performance degradation and failure of positioning sensors will also cause deviations in positioning information and affect driving safety. Therefore, in addition to the positioning information of self-driving vehicles, the credibility evaluation of positioning information is also an important indicator for evaluating the performance of self-driving cars. Therefore, how to accurately and timely evaluate the credibility of positioning information has become a key issue that needs to be urgently solved in the field of self-driving cars.

[0058] In view of this, an embodiment of the present application provides a vehicle positioning processing method, which determines the error range of the vehicle positioning information based on the process variables in the vehicle state estimation process, can evaluate the reliability of the positioning information, and issue an early warning in the event of positioning abnormalities, thereby improving the safety of vehicle driving.

[0059] The following specific embodiments are used to describe in detail the technical solution of the present application and how the technical solution of the present application solves the above technical problems. The following specific embodiments can be implemented independently or in combination with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0060] Figure 1 Schematic diagram of application scenarios of the embodiments of the present application, such as Figure 1 As shown, a vehicle 101 , a first positioning sensor 102 , and a second positioning sensor 103 are included.

[0061] The vehicle 101 may be a vehicle with an automatic driving function, and the first positioning sensor 102 and the second positioning sensor 103 may be sensors disposed in the vehicle 101. The first positioning sensor 102 and the second positioning sensor 103 are both used to provide a positioning function for the vehicle 101. The first positioning sensor 102 and the second positioning sensor 103 may communicate with the vehicle 101, respectively.

[0062] In the embodiment of the present application, during the driving process of the vehicle 101, the first positioning position of the vehicle 101 can be obtained through the positioning data collected by the first positioning sensor 102 and the second positioning position of the vehicle 101 can be obtained through the positioning data collected by the second positioning sensor 103. The vehicle 101 can comprehensively analyze the first positioning position and the second positioning position and output the final positioning information of the vehicle 101.

[0063] It is understandable that when the vehicle 101 performs positioning analysis, it can be the positioning unit of the vehicle 101. When the positioning unit obtains the final positioning information of the vehicle 101, it can output the final positioning information to the automatic driving unit of the vehicle 101. The automatic driving unit can perform automatic driving planning and control on the vehicle 101 according to the received positioning information. Among them, the positioning unit and the automatic driving unit can jointly constitute the automatic driving system of the vehicle, that is, the execution subject of the embodiment of the present application is the automatic driving system of the vehicle, and the vehicle will be used for replacement description later. Its functions can be implemented by software, and can also be implemented by a combination of software and hardware. The embodiment of the present application is not limited to this.

[0064] Optionally, in some embodiments, the first positioning sensor 102 and the second positioning sensor 103 may be located at the same position of the vehicle 101 , or may be located at different positions of the vehicle 101 , which is not limited in this embodiment of the present application.

[0065] Optionally, in some embodiments, the second positioning sensor 103 may also be a device with a sensor function installed in the vehicle 101. For example, a user terminal with a sensor function. This embodiment of the present application does not limit this.

[0066] Optionally, in some embodiments, the location information of the vehicle 101 may be analyzed and processed by a cloud server connected to the vehicle 101. The vehicle 101 may upload the location data collected by the first location sensor 102 and the location data collected by the second location sensor 103 to the remote server, and receive the location information returned by the cloud server. The vehicle 101 may perform autonomous driving planning and control according to the location information returned by the cloud server.

[0067] Optionally, in some embodiments, autonomous driving planning and control of vehicle 101 may also be performed through a cloud server, which is not limited in this embodiment of the present application.

[0068] Optionally, the type of vehicle 101 may be a truck, a van, a car, etc. The embodiment of the present application does not limit the type of vehicle.

[0069] The above briefly introduces the application scenarios of the embodiments of the present application. Figure 1 Taking the vehicle in as an example, the vehicle positioning processing method provided in the embodiment of the present application is described in detail.

[0070] To facilitate understanding, the vehicle error state estimation process for determining the k+1 time provided in an embodiment of the present application is first introduced.

[0071] Autonomous driving vehicle positioning is usually a combination of an inertial measurement unit (IMU) and a global navigation satellite system (GNSS) receiver. The positioning data collected by the two sensors are fused through a fusion algorithm to output fused positioning information. Due to the characteristics of the sensor, the collected data will inevitably carry data errors. The fused positioning information is essentially a state estimation. During the vehicle's driving process, the continuous iteration of positioning data will amplify the impact of data errors on the positioning information, resulting in a decrease in the accuracy of vehicle positioning.

[0072] In the embodiment of the present application, when estimating the vehicle state error at time k+1, the positioning information deviation between the auxiliary positioning sensor and the main positioning sensor is used as the observation quantity for correcting the positioning information of the main sensor, and the error state is optimally estimated using a fusion filter. Then, the motion parameters of the main positioning sensor are corrected, so that the accumulated error of the main sensor can be corrected to ensure the positioning accuracy of the vehicle.

[0073] Figure 2 Schematic diagram of the vehicle positioning processing method provided in the embodiment of the present application Figure 1 ,like Figure 2 As shown, the following steps are included:

[0074] S201. Acquire first positioning information of the vehicle at time k according to first positioning sensor data of the vehicle, and acquire second positioning information of the vehicle at time k according to second positioning sensor data of the vehicle.

[0075] In the embodiment of the present application, the first positioning sensor may be a main positioning sensor of the vehicle, for example, the first positioning sensor may be an inertial measurement unit (IMU) for obtaining parameters such as angular velocity and acceleration of the vehicle. The second positioning sensor may be an auxiliary positioning sensor of the vehicle, for example, the second positioning sensor may be, but is not limited to, one or more of a GNSS receiver, a wheel speed meter, a laser radar, and a camera.

[0076] The first positioning information and the second positioning information may be fused positioning information including information such as the position, speed, and posture of the vehicle.

[0077] In the embodiment of the present application, the vehicle can obtain the first positioning information of the vehicle according to the data collected by the first positioning sensor. For example, the vehicle obtains the positioning information such as the position, speed and attitude of the vehicle according to the parameters such as the angular velocity and acceleration of the vehicle collected by the IMU and according to a preset algorithm, such as the strapdown inertial navigation algorithm.

[0078] The vehicle can obtain the second positioning information of the vehicle based on the data collected by the second positioning sensor. For example, when the second positioning sensor is a GNSS receiver, the vehicle can obtain the positioning message of the vehicle collected by the GNSS receiver, and parse the positioning message to obtain the positioning information such as the position, speed and posture of the vehicle. When the second positioning sensor is a wheel speed, the vehicle can calculate the positioning information such as the position, speed and posture of the vehicle based on the vehicle wheel speed pulse data collected by the speedometer. The way in which the vehicle obtains the second positioning information of the vehicle based on sensors such as laser radar and cameras can refer to various implementation methods in the prior art, and the embodiments of the present application will not be repeated here.

[0079] It is understandable that the first sensor and the second sensor collect vehicle data according to the frequency set by the sensors. For example, the frequency of the first sensor collecting vehicle data may be 0.1s, and the frequency of the second sensor collecting vehicle data may be 0.5s.

[0080] In an embodiment of the present application, if the first sensor and the second sensor have different frequencies for collecting vehicle data, for example, at time k, the first sensor reports the collected vehicle data, but the second sensor does not report the collected vehicle data. The vehicle can use the vehicle data last reported and collected by the second sensor as a reference, and according to the difference in reporting time offset and vehicle data collection frequency between the first sensor and the second sensor, use data interpolation and other methods to align the vehicle data last reported and collected by the second sensor to time k. Time alignment of vehicle data collected by the first sensor and the second sensor is achieved. The first positioning information and the second positioning information of the vehicle at time k are calculated respectively based on the aligned vehicle data.

[0081] S202 . Determine a measurement vector at time k according to the first positioning position at time k and the second positioning position at time k.

[0082] In the embodiment of the present application, the measurement vector may be the deviation between the first positioning information and the second positioning information at time k.

[0083] For example, taking the first sensor as an IMU and the second sensor as a GNSS receiver as an example, the measurement vector z at time k is k The following formula can be satisfied:

[0084] z k =[p IMU -p GNSS ,v IMU -v GNSS ] T

[0085] Among them, p IMU is the vehicle position obtained based on the data collected by IMU, p GNSSis the vehicle position obtained from the data collected by GNSS, v IMU is the vehicle speed obtained based on the data collected by IMU, v GNSS is the vehicle speed obtained from the data collected by GNSS.

[0086] S203. Determine the error state estimate at time k+1 based on the measurement vector at time k and the error state estimate at time k; the error state estimate at time k+1 is used to correct the first positioning information at time k+1 to obtain the target positioning information of the vehicle at time k+1.

[0087] In the embodiment of the present application, the positioning of the vehicle is essentially a state estimation problem, that is, to perform optimal estimation on the positioning information obtained based on the collected vehicle data.

[0088] In the embodiment of the present application, the optimal estimation of the positioning information can be achieved by using a standard Kalman filter, an extended Kalman filter, or other filters. Take the first sensor as an IMU, the second sensor as a GNSS receiver, and a standard Kalman filter as an example:

[0089] The system model of the vehicle's linear state equation and observation equation can be shown as follows:

[0090]

[0091] Among them, x k is the state vector of the vehicle at time k, x k+1 is the state vector of the vehicle at time k+1, z k is the observation vector at time k, F k ,G k ,H k is the parameter matrix of the model, w k The variance is Q k The process noise, The variance is R k of observation noise.

[0092] In the embodiment of the present application, the error state vector of the vehicle at time k can be shown as follows:

[0093]

[0094] Among them, δp, δv, are the position error, velocity error and attitude error vectors respectively, b g ,b a is the device error vector of the gyroscope and accelerometer.

[0095] In the embodiment of the present application, when a standard Kalman filter is used for state estimation, the initial error state vector x0 and position P0 are set, and the error state estimation at any k time can be obtained by iterative calculation.

[0096] The measurement error at time k is taken as the observed quantity, and the error state at time k is estimated Get the error state estimate at time k+1

[0097] The estimation process can be as follows:

[0098]

[0099]

[0100]

[0101]

[0102] P k =(IK k H k ) k+1|k

[0103] e k =z k -H k x k+1|k

[0104]

[0105] Among them, S k is the innovation variance matrix, e k is the new information sequence, K k is the Kalman gain matrix.

[0106] In an embodiment of the present application, when the vehicle determines the state error estimate at time k+1, when obtaining the first positioning information at time k+1, the first positioning information can be corrected. For example, the state error estimate at time k+1 is used as correction data for the first positioning position to obtain the target positioning information of the vehicle at time k+1.

[0107] The vehicle positioning processing method provided in the embodiment of the present application obtains the first positioning information of the vehicle at time k according to the first positioning sensor data of the vehicle, and obtains the second positioning information of the vehicle at time k according to the second positioning sensor data of the vehicle; determines the measurement vector at time k according to the first positioning position at time k and the second positioning position at time k; determines the error state estimate at time k+1 according to the measurement vector at time k and the error state estimate at time k; the error state estimate at time k+1 is used to correct the first positioning information at time k+1 to obtain the target positioning information of the vehicle at time k+1. By correcting the first positioning information through the deviation between the positioning information of the second positioning sensor and the positioning information of the first positioning sensor, the accumulated error of the first sensor can be corrected, thereby improving the accuracy of vehicle positioning.

[0108] Optionally, in some embodiments, the installation positions of the first sensor and the second sensor may be different, and there may be a lever arm error between the positioning information obtained from the data collected by the first sensor and the second sensor. Therefore, before determining the measurement vector at time k based on the first positioning information at time k and the second positioning information at time k, it is also necessary to align the first positioning information at time k with the second positioning information at time k.

[0109] Exemplarily, the first positioning information at time k and the second positioning information at time k are converted to positioning information in the same coordinate system. For example, the first positioning information at time k and the second positioning information at time k are converted to a coordinate system with the center of the vehicle as the origin, so as to achieve position alignment between the first sensor and the second sensor.

[0110] Optionally, in some embodiments, when the vehicle obtains the vehicle data reported by the second sensor, it may also perform a self-check on the collected vehicle data. For example, based on data such as the standard error, the number of available satellites, and the geometric distribution factor in the collected vehicle data, it may determine that the vehicle data reported by the second sensor can correctly represent the position of the vehicle.

[0111] Figure 3 Schematic diagram of the vehicle positioning processing method provided in the embodiment of the present application Figure 2 ,exist Figure 2 Based on the embodiment shown, the process of alarming the vehicle's location is introduced, such as Figure 3 As shown, including:

[0112] S301. Obtain a process variable at time k output during the process of determining the vehicle error state estimation at time k+1, where the process variable includes at least one of an innovation sequence, an innovation variance matrix, and a Kalman gain matrix.

[0113] In the present application examples, see Figure 2In the process of determining the vehicle error state estimation at time k+1 shown in S203 in the illustrated embodiment, the vehicle can obtain process variables. The process variables can be the innovation variance matrix S k 、New information sequence e k And the Kalman gain matrix K k One or more of .

[0114] S302. Determine the protection level of the vehicle at time k according to the process variable at time k.

[0115] In the embodiment of the present application, the protection level can be used to characterize the maximum positioning error estimated by the vehicle at time k, that is, the positioning reliability of the vehicle positioning system.

[0116] Exemplarily, the protection level of the vehicle at time k can be determined according to the process variable at time k and a preset positioning false alarm rate, wherein the preset positioning false alarm rate Pr md The maximum probability of a positioning error warning that can be estimated for the vehicle can be an empirical value.

[0117] For example, the vehicle's protection level HPL k The following formula can be satisfied:

[0118]

[0119] in, And f e (n) = [1, 0, 0, ..., 0], f n (n) = [0, 1, 0, ..., 0] corresponds to an n-dimensional row vector; CDF is the cumulative distribution function of the standard normal distribution; HS e , HS n All are calculated process quantities.

[0120] HS e and HS n The following formula can be satisfied:

[0121]

[0122]

[0123] S303 . Issue a warning on the positioning credibility of the vehicle at time k according to the protection level of the vehicle at time k.

[0124] In the embodiment of the present application, when positioning and warning the vehicle according to the protection level of the vehicle, it is necessary to determine the alarm threshold of the vehicle at the current moment. Whether the current positioning information is reliable is determined according to the relationship between the protection level and the alarm threshold. Among them, the alarm threshold is related to the driving environment and motion state of the vehicle.

[0125] For example, when the weather is bad and the vehicle speed is high, the vehicle's alarm threshold will be lower than the alarm threshold when the weather is good and the vehicle speed is low. When there are many pedestrians around the vehicle path, the alarm threshold will be lower than the alarm threshold when there are few pedestrians around the vehicle path.

[0126] When the current alarm threshold is determined according to the driving environment and motion state of the vehicle, if the protection level HPL k If it is greater than the alarm threshold, it can be determined that there is a serious deviation in the current positioning information of the vehicle, the positioning reliability is low, and a safety positioning alarm needs to be issued.

[0127] The vehicle positioning processing method provided in the embodiment of the present application obtains the process variable at time k output in the process of determining the vehicle error state estimation at time k+1, determines the protection level of the vehicle at time k according to the process variable at time k, and issues an early warning for the positioning credibility of the vehicle at time k according to the protection level of the vehicle at time k. Through the process variable, the error range of the vehicle positioning information can be determined, the reliability of the positioning information can be evaluated, and an early warning can be issued in the event of positioning abnormalities, thereby improving the safety of vehicle driving.

[0128] Figure 4 Schematic diagram of the vehicle positioning processing method provided in the embodiment of the present application Figure 3 ,exist Figure 3 Based on the embodiment shown, the process of early warning of the vehicle positioning information is further described. Figure 4 As shown, the following steps are included:

[0129] S401. Obtain process variables for determining the error state estimation process of the vehicle at time k+1.

[0130] S402: Determine whether the second sensor has a fault according to the process variable.

[0131] In the embodiment of the present application, the vehicle can construct a statistical value of fault detection based on the process variable, which can also be called a statistic, and determine whether the second sensor has a fault based on the statistical value of the fault detection.

[0132] Exemplarily, in the process of determining the estimation error at time k+1, the process variable at time k is output; based on the process variable at time k, the fault statistic value of the second sensor data at time k is determined; and based on the fault statistic value at time k, it is determined whether the second sensor has a fault.

[0133] For example, the fault statistic value GT of the second sensor data at time k is k The following formula can be satisfied:

[0134]

[0135] In the embodiment of the present application, the vehicle can be k The relationship between the magnitude and the preset threshold value is used to determine whether the second sensor is faulty.

[0136] Exemplary: if the fault statistic value at the time k is greater than a first threshold, it is determined that there is an error in the second sensor data at the time k; the number of accumulated errors of the second sensor is updated, and when the accumulated number of errors is greater than a second threshold, it is determined that there is a fault in the second sensor; if the fault statistic value at the time k is less than or equal to the first threshold, the accumulated number of errors is reset.

[0137] For example, Figure 5 As shown in the figure, when the vehicle obtains the process variables of state estimation, the fault statistics value GT can be determined according to the process variables. k , if GT k If the value is greater than the first threshold Thres1, it can be determined that the vehicle data collected by the second sensor at time k is erroneous, and the accumulated number of errors of the second sensor recorded by the current vehicle is updated. f That is, when it is determined that the second sensor has an error, the number of accumulated errors of the second sensor N f Increased 1 time.

[0138] When updating the error accumulation number N of the second sensor f After that, the vehicle can accumulate the number of times N for the current error f Make a judgment, if the number of errors accumulated is N f If the value is greater than the second threshold Thres2, it can be determined that the second sensor is faulty.

[0139] If GT k If the error count N of the second sensor is smaller than or equal to the first threshold Thres1, the error count N of the second sensor is reset. f That is, the error accumulation number N of the second sensor f The value of is set to 0. The process of calculating the vehicle protection level is executed.

[0140] Optional, in determining GT k When the error is greater than the first threshold Thres1, it can be considered that the second sensor has a single data collection failure, and a single data failure warning can be output. When receiving a fault alarm, the vehicle can pause the step of correcting the first positioning position according to the second positioning position corresponding to the second sensor data and wait for the next second sensor data. f When it is less than or equal to the second threshold Thres2, the next second sensor data may also be waited for.

[0141] Optionally, when it is determined that the second sensor is faulty, corresponding alarm information may be output.

[0142] S403: When the second sensor is faulty, use a candidate second sensor to replace the faulty second sensor.

[0143] In the embodiment of the present application, the vehicle may have a plurality of candidate second sensors. When a currently used second sensor fails, the candidate second sensor may be used to replace the failed second sensor.

[0144] Exemplarily, the candidate second sensors of the vehicle may include a GNSS receiver, a wheel speed meter, a laser radar, and a camera. When it is determined that the second sensor is faulty, the remaining candidate second sensors are used to replace the faulty second sensor according to a preset strategy.

[0145] Taking the case where the second sensor currently used by the vehicle is a GNSS receiver, if it is determined that the GNSS receiver is faulty, the remaining candidate second sensors can be used to replace the GNSS receiver according to the preset strategy. The preset strategy can be a sequential replacement strategy or a designated replacement strategy, etc., which is not limited in the embodiments of the present application.

[0146] S404: When there is no fault in the second sensor, determine the protection level of the vehicle according to the process variable.

[0147] In the embodiment of the present application, the protection level is used to characterize the maximum positioning error estimated by the vehicle at any time, that is, the reliability of the positioning information output by the vehicle.

[0148] When it is determined that the second sensor does not have a fault, the protection level of the vehicle at time k can be determined according to the process variable at time k. Figure 3 The implementation of S302 in the illustrated embodiment is similar and will not be described in detail here.

[0149] S405: Position and warn the vehicle according to the protection level of the vehicle.

[0150] In the embodiment of the present application, when positioning and warning the vehicle according to the protection level of the vehicle, it is necessary to determine the alarm threshold of the vehicle at the current moment. Whether the current positioning information is reliable is determined according to the relationship between the protection level and the alarm threshold.

[0151] Exemplary: obtaining the driving environment and motion state of the vehicle at time k; updating the initial alarm threshold of the vehicle according to the driving environment and motion state of the vehicle at time k to obtain the target alarm threshold of the vehicle at time k; when the protection level of the vehicle at time k is greater than the target alarm threshold at time k, outputting the warning information of the positioning position of the vehicle at time k.

[0152] In the embodiment of the present application, the alarm threshold of the vehicle is related to the driving environment and motion state of the vehicle. When the vehicle is driving in different driving environments and in different motion states, the alarm threshold of the vehicle may be different.

[0153] For example, the factors affecting the alarm threshold are as follows:

[0154]

[0155] As shown in the above table, the driving environment and motion state of the vehicle can affect the vehicle's alarm threshold. Therefore, the calculation of the vehicle's alarm threshold at the current moment needs to comprehensively consider the vehicle's driving environment and motion state.

[0156] Taking the vehicle sensor as a GNSS / IMU combination mode as an example, according to the influence of various influencing factors on the vehicle alarm threshold in this combination mode, the comparison table of influencing factors is shown below:

[0157] Influencing Factor A 9 7 5 3 1 3 5 7 9 Influencing Factor B weather √ Road conditions and surrounding environment interference weather √ Motor vehicle traffic conditions weather √ Pedestrian traffic conditions weather √ Vehicle's own motion weather √ Special Areas Road conditions and surrounding environment interference √ Motor vehicle traffic conditions Road conditions and surrounding environment interference √ Pedestrian traffic conditions Road conditions and surrounding environment interference √ Vehicle's own motion Road conditions and surrounding environment interference √ Special Areas Motor vehicle traffic conditions √ Pedestrian traffic conditions Motor vehicle traffic conditions √ Vehicle's own motion Motor vehicle traffic conditions √ Special Areas Pedestrian traffic conditions √ Vehicle's own motion Pedestrian traffic conditions √ Special Areas Vehicle's own motion √ Special Areas

[0158] Among them, a total of five measurement values ​​[1 3 5 7 9] are used to represent the bias when the influencing factors are compared pairwise, 1 represents no bias, 3 represents slight bias, 5 represents bias, 7 represents obvious bias, and 9 represents strong bias.

[0159] Taking weather factors and motor vehicle traffic congestion as an example, it can be seen from the above table that compared with weather factors, motor vehicle traffic congestion obviously has a greater impact on the safe driving alarm threshold, so the comparison between the two tends to favor the latter.

[0160] When determining the relative bias of each factor on the alarm threshold, the analytic hierarchy process (AHP) can be used to analyze each influencing factor and obtain the weight σ of each influencing factor that passes the consistency test. i (i=1,…,6), and the sum of all weight values ​​is 1.

[0161] For example, Figure 6 As shown, when the weights of various influencing factors are determined, the initial alarm threshold of the vehicle can be updated according to the weights to obtain the target alarm threshold of the vehicle at time k. The initial alarm threshold can be an empirical value.

[0162] The target warning threshold of the vehicle satisfies the following formula:

[0163]

[0164] Among them, HAL k is the target alarm threshold at time k, and the initial alarm threshold of HAL0.

[0165] From the above formula, we can see that when the factors listed in the table have no effect, HAL k Equal to HAL0; when one or more factors have an impact, the weight and The existence of HAL k Compared with HAL0, it becomes smaller, which means the alarm threshold is reduced and the alarm probability is increased.

[0166] Determine the protection level HPL of the vehicle at time k k and target alarm threshold HAL k If the protection level HPL k and target alarm threshold HAL k The following formula is not satisfied:

[0167] HPL k <HAL k

[0168] It can be determined that the current positioning information of the vehicle has serious deviations, and a safety positioning alarm is issued. When the vehicle receives a safety positioning alarm, it may need to change the current autonomous driving strategy, such as parking or requesting manual access. If the above formula is satisfied, the positioning credibility of the vehicle is output.

[0169] It is understandable that the embodiment of the present application uses six conventional influencing factors as examples when calculating the alarm threshold of the vehicle, and the embodiment of the present application does not limit the types of influencing factors.

[0170] The vehicle positioning method provided in the embodiment of the present application obtains the alarm threshold and protection level of the vehicle by correcting the process variables output during the vehicle positioning information process and combining the vehicle's driving environment and form status. The credibility of the vehicle positioning information is analyzed according to the alarm threshold and protection level of the vehicle. When the credibility is low, the positioning is warned, which can improve the ability of automatic driving to give timely alarms and improve the positioning safety performance.

[0171] In summary, the vehicle positioning processing method provided in the embodiment of the present application includes a process of correcting the positioning of the vehicle and a process of analyzing the reliability of the positioning of the vehicle, which can be executed by the vehicle positioning unit and the positioning reliability unit respectively.

[0172] like Figure 7 As shown, the vehicle positioning unit may include a primary and secondary positioning calculation module, a sensor device selection module, a data alignment module, and a fusion estimator module. The positioning credibility unit may include a fault diagnosis module, a protection level calculation module, and a multi-level positioning alarm module.

[0173] Through data interaction between the vehicle positioning unit and the positioning credibility unit, a fusion positioning system for autonomous driving vehicles is jointly formed, which outputs positioning information, positioning credibility and safety alarm messages. The vehicle positioning unit is responsible for processing the data of each positioning sensor, implementing the fusion positioning algorithm, outputting fusion positioning information, transmitting process quantities to the positioning credibility unit, and receiving fault alarm information. The positioning credibility unit is used to monitor the working status of each sensor online, detect single-frame data or sensor failures in a timely manner, calculate the error range of the fusion positioning information, determine the alarm threshold according to the vehicle driving environment, and broadcast positioning safety alarms in a timely manner.

[0174] The vehicle positioning processing method provided in the embodiment of the present application is based on IMU: good real-time performance and high update frequency; based on Kalman filter: simple algorithm and low computing power consumption; multiple sensors are redundant: high reliability, flexible configuration and strong versatility. Design a two-level fault diagnosis strategy to more effectively eliminate various device failures and meet the requirements of vehicle positioning for missed reports and false alarm ratios; design a protection level calculation algorithm to achieve effective and accurate estimation of the positioning confidence; design a positioning alarm threshold update strategy to adaptively adjust the threshold value in combination with the usage scenario.

[0175] Figure 8 and Fig. 9 These are the protection levels of the fused positioning information of the autonomous driving vehicle in two typical autonomous driving scenarios. The scenarios are open roads without safety factors ( Figure 7 corresponding scene), and a road with partial sky obstruction containing two safety factors ( Figure 8 Corresponding scene). Set the initial value of the alarm threshold HAL0 to 0.85m.

[0176] like Figure 8 As shown in the figure, in the open road scenario, the main factor affecting the system positioning performance is the GNSS positioning accuracy, which is determined by Figure 8 The results show that, except for the period of 300 seconds when the protection level exceeded the set threshold due to the degradation of GNSS positioning performance, triggering a positioning alarm, the positioning reliability remained stably below 0.6 m at other times.

[0177] like Fig. 9As shown in the figure, in the presence of sky obstructions, the overall positioning performance of GNSS decreases, which is manifested as an increase in the protection level value from the perspective of positioning credibility. If the factors affecting vehicle driving safety are not considered, the time period for triggering the positioning alarm is mainly 350-450s; if one influencing factor is considered, the alarm threshold drops to 0.842m, and the number of alarms triggered increases; if two factors are considered, the alarm threshold drops to 0.83m, and the number of alarms increases significantly throughout the entire period. This shows that the more safety influencing factors are added, the more significantly the alarm threshold is lowered, which is manifested as an increase in positioning credibility alarms at the system level, indicating that the tolerance for positioning errors is lower in driving safety-sensitive areas, and there are timely alarm prompts for situations that may trigger positioning errors, thereby proving that the positioning safety of autonomous vehicles has been effectively improved.

[0178] The embodiment of the present application also provides a vehicle positioning processing device.

[0179] Fig.10 The schematic diagram of the structure of the vehicle positioning processing device 100 provided in the embodiment of the present application is as follows: Fig.10 As shown, including:

[0180] An acquisition module 1001 is used to acquire a process variable at time k output during the process of determining the vehicle error state estimation at time k+1, wherein the process variable includes at least one of an innovation sequence, an innovation variance matrix, and a Kalman gain matrix;

[0181] A determination module 1002 is used to determine a protection level of the vehicle at time k according to a process variable at time k, wherein the protection level is used to characterize a maximum positioning error estimated for the vehicle at time k;

[0182] The early warning module 1003 is used to issue an early warning on the positioning credibility of the vehicle according to the protection level of the vehicle at time k.

[0183] Optionally, the early warning module 1003 is also used to obtain the driving environment and motion state of the vehicle at time k; update the initial alarm threshold of the vehicle according to the driving environment and motion state of the vehicle at time k, and obtain the target alarm threshold of the vehicle at time k; when the protection level of the vehicle at time k is greater than the target alarm threshold at time k, output the early warning information of the positioning position of the vehicle at time k.

[0184] Optionally, the determination module 1002 is further used to determine a fault statistic value of the second sensor data at time k according to the process variable at time k; and determine whether the second sensor has a fault according to the fault statistic value at time k.

[0185] Optionally, the determination module 1002 is also used to determine that there is an error in the second sensor data at time k if the fault statistical value at the k moment is greater than a first threshold; update the number of accumulated errors of the second sensor, and determine that there is a fault in the second sensor when the accumulated number of errors is greater than a second threshold; if the fault statistical value at the k moment is less than or equal to the first threshold, reset the accumulated number of errors.

[0186] Optionally, the determination module 1002 is further configured to convert the first positioning information at the k moment and the second positioning information at the k moment into the same coordinate system.

[0187] Optionally, the acquisition module 1001 is also used to acquire the first positioning information of the vehicle at time k based on the first positioning sensor data of the vehicle, and to acquire the second positioning information of the vehicle at time k based on the second positioning sensor data of the vehicle; determine the measurement vector at time k based on the first positioning position at time k and the second positioning position at time k; determine the error state estimate at time k+1 based on the measurement vector at time k and the error state estimate at time k; the error state estimate at time k+1 is used to correct the first positioning information at time k+1 to obtain the target positioning information of the vehicle at time k+1.

[0188] The vehicle positioning processing device provided in the embodiment of the present application can execute the technical solution of the vehicle positioning processing method provided in any of the above embodiments, and its principles and technical effects are similar, which will not be repeated here.

[0189] Fig.11 This is a schematic diagram of the structure of an electronic device provided in this application. Fig.11 As shown, the electronic device 110 may include: at least one processor 1101 , a memory 1102 , and a communication interface 1103 .

[0190] The memory 1102 is used to store programs. Specifically, the programs may include program codes, and the program codes include computer operation instructions.

[0191] The memory 1102 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0192] The processor 1101 is used to execute the computer-executable instructions stored in the memory 1102 to implement the vehicle positioning processing method described in the aforementioned method embodiment. The processor 1101 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0193] In specific implementation, if the communication interface 1103, the memory 1102 and the processor 1101 are implemented independently, the communication interface 1103, the memory 1102 and the processor 1101 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0194] Optionally, the processor 1101 may also be connected to an external positioning sensor via the communication interface 1103 to obtain vehicle positioning data collected by the positioning sensor.

[0195] Optionally, the electronic device may further include a display device 1104 . The display device 1104 may be coupled to the processor 1101 . The processor 1101 controls the display device 1104 to display the warning information sent by the processor 1101 .

[0196] Optionally, in a specific implementation, if the communication interface 1103, the memory 1102 and the processor 1101 are integrated on a chip, the communication interface 1103, the memory 1102 and the processor 1101 can communicate through an internal interface.

[0197] A computer-readable storage medium is also provided in an embodiment of the present application, on which a computer program is stored. When the computer program is executed by a processor, the technical solution of the above-mentioned vehicle positioning processing method embodiment is implemented. The implementation principle and technical effect are similar and will not be repeated here.

[0198] In one possible implementation, a computer-readable medium may include a random access memory (RAM), a read-only memory (ROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage or other magnetic storage device, or any other medium that is intended to carry or store the required program code in the form of instructions or data structures and can be accessed by a computer. Moreover, any connection is appropriately referred to as a computer-readable medium. For example, if the software is transmitted from a website, server or other remote source using a coaxial cable, a fiber optic cable, a twisted pair, a digital subscriber line (DSL) or wireless technologies such as infrared, radio and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, radio and microwave are included in the definition of the medium. Disks and optical disks as used herein include optical disks, laser disks, optical disks, digital versatile disks (DVDs), floppy disks and Blu-ray disks, where disks usually reproduce data magnetically, while optical disks reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0199] A computer program product is also provided in an embodiment of the present application, including a computer program. When the computer program is executed by a processor, the technical solution of the above-mentioned vehicle positioning processing method embodiment is implemented. The implementation principle and technical effect are similar and will not be repeated here.

[0200] In the specific implementation of the above-mentioned terminal device or server, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0201] Those skilled in the art will appreciate that all or part of the steps of any of the above method embodiments may be completed by hardware associated with program instructions. The aforementioned program may be stored in a computer-readable storage medium, and when the program is executed, all or part of the steps of the above method embodiments are executed.

[0202] If the technical solution of the present application is implemented in the form of software and sold or used as a product, it can be stored in a computer-readable storage medium. Based on such an understanding, all or part of the technical solution of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a computer program or several instructions. The computer software product enables a computer device (which can be a personal computer, a server, a network device, or a similar electronic device) to perform all or part of the steps of the method described in the embodiment of the present application.

[0203] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle positioning processing method, characterized in that: include: Obtaining a process variable at time k output during the process of determining the vehicle error state estimation at time k+1, wherein the process variable includes at least one of an innovation sequence, an innovation variance matrix, and a Kalman gain matrix; Determine a protection level of the vehicle at time k according to the process variable at time k, wherein the protection level is used to characterize the maximum positioning error estimated for the vehicle at time k; Providing an early warning on the positioning credibility of the vehicle at time k according to the protection level of the vehicle at time k; Determining the vehicle error state estimate at time k+1 includes: Acquire first positioning information of the vehicle at time k according to first positioning sensor data of the vehicle, and acquire second positioning information of the vehicle at time k according to second positioning sensor data of the vehicle; Determine the measurement vector at the k moment according to the first positioning information at the k moment and the second positioning information at the k moment; The error state estimate at time k+1 is determined based on the measurement vector at time k and the error state estimate at time k; the error state estimate at time k+1 is used to correct the first positioning information at time k+1 to obtain the target positioning information of the vehicle at time k+1.

2. The method according to claim 1, characterized in that The step of providing an early warning on the reliability of the positioning of the vehicle at time k according to the protection level of the vehicle at time k includes: Obtaining the driving environment and motion state of the vehicle at time k; According to the driving environment and motion state of the vehicle at the k moment, updating the initial alarm threshold of the vehicle to obtain the target alarm threshold of the vehicle at the k moment; When the protection level of the vehicle at time k is greater than the target alarm threshold at time k, the positioning warning information of the vehicle at time k is output.

3. The method according to claim 2, characterized in that Before determining the protection level of the vehicle at time k according to the process variable at time k, the method further includes: Determine a fault statistic value of the second sensor data at time k according to the process variable at time k; Determine whether the second sensor has a fault according to the fault statistics value at the k moment.

4. The method according to claim 3, characterized in that The determining whether the second sensor has a fault according to the fault statistics at the k moment includes: If the fault statistic value at the k moment is greater than the first threshold, it is determined that the second sensor data has an error at the k moment; updating the accumulated number of errors of the second sensor, and determining that the second sensor has a fault when the accumulated number of errors is greater than a second threshold; If the fault statistic value at the k moment is less than or equal to the first threshold, the accumulated number of errors is reset.

5. The method according to claim 1, characterized in that: Before determining the measurement vector at time k according to the first positioning information at time k and the second positioning information at time k, the method further includes: The first positioning information at the k moment and the second positioning information at the k moment are converted into the same coordinate system.

6. The method according to claim 4, characterized in that The vehicle includes at least one of the following candidate second sensors: Global Satellite Navigation System GNSS receiver, wheel speed meter, lidar, camera; When it is determined that the second sensor has a fault, the method further includes: According to a preset strategy, the remaining candidate second sensors are used to replace the faulty second sensor.

7. A vehicle positioning processing device, characterized in that: include: An acquisition module, used for acquiring a process variable at time k outputted in the process of determining the vehicle error state estimation at time k+1, wherein the process variable comprises at least one of an innovation sequence, an innovation variance matrix, and a Kalman gain matrix; A determination module, used to determine a protection level of the vehicle at time k according to a process variable at time k, wherein the protection level is used to characterize a maximum positioning error estimated for the vehicle at time k; An early warning module, used for issuing an early warning on the positioning credibility of the vehicle according to the protection level of the vehicle at time k; The acquisition module is specifically used for: Acquire first positioning information of the vehicle at time k according to first positioning sensor data of the vehicle, and acquire second positioning information of the vehicle at time k according to second positioning sensor data of the vehicle; Determine the measurement vector at the k moment according to the first positioning information at the k moment and the second positioning information at the k moment; The error state estimate at time k+1 is determined based on the measurement vector at time k and the error state estimate at time k; the error state estimate at time k+1 is used to correct the first positioning information at time k+1 to obtain the target positioning information of the vehicle at time k+1.

8. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program to implement the method according to any one of claims 1 to 6.

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

10. A computer program product, characterized in that A computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

Images