Vehicle system response delay estimation method, system, device and storage medium

Abstract

The invention provides a vehicle system response delay estimation method, system and device and a storage medium. The method comprises the steps that a control instruction and a chassis feedback signal are received and dynamically stored; constructing a regression matrix, wherein the regression matrix comprises a plurality of control instruction combination forms corresponding to the chassis feedback signals at a plurality of moments; performing QR decomposition on the regression matrix to obtain a QR decomposition result; calculating an ERR corresponding to each alternative decomposition item based on the chassis feedback signals at the multiple moments and the QR decomposition result; and selecting a dominant item in the QR decomposition result based on the ERR, and determining the response delay of the vehicle system according to the corresponding relationship between the dominant item and the control instruction combination form. According to the invention, on-line real-time accurate estimation of the response delay of the vehicle system is realized.

Description

Background Art

[0002] In autonomous driving control, there is a time difference between the autonomous driving command being issued by the autonomous driving system and the actual execution of the vehicle chassis system. This process is not completed instantly. Usually, there will be delays in the following aspects:

[0003] (1) Communication delay: The autonomous driving system usually needs to communicate with the vehicle chassis system through a wireless network or CAN (Controller Area Network) bus. Due to network transmission limitations or packet loss, communication may experience certain delays.

[0004] (2) Data processing delay: After the autonomous driving control command is issued by the control module of the autonomous driving system, it may go through other modules in the autonomous driving system for some data processing and format conversion, and finally be sent to the vehicle chassis system in the format specified by the communication protocol for data transmission. This part of the processing will also cause a certain delay.

[0005] (3) Chassis controller delay: When the vehicle chassis receives the autonomous driving control command, some processing and calculation are required to actually control the movement of the vehicle. The control of the vehicle chassis system is usually completed by the vehicle electronic control unit (ECU). The ECU integrates components such as processors, memory, interfaces and sensors to receive, process and send control signals to control various parts of the vehicle chassis system. The response speed and calculation efficiency of the ECU will also cause a certain delay.

[0006] (4) Actuator delay: After a long period of high-intensity operation, some large actuators (such as steering gear) may have insufficient pressure (hydraulic or pneumatic pressure) in the hardware, resulting in the subsequent execution being unable to reach the previous speed or accuracy, thus causing a certain delay.

[0007] (5) Sensor delay: Autonomous driving systems usually require the use of multiple sensors to obtain vehicle status and environmental information, such as cameras, lidar, millimeter-wave radar, etc. The sampling frequency and response speed of the sensor will also cause delay.

[0008] The delays in the above aspects will actually have a certain impact on the entire autonomous driving system. If they are not handled, they may cause some negative effects that are difficult to troubleshoot. The above time difference is more strictly and specifically defined, because generally this delay will have a relatively large impact on the autonomous driving control performance. At present, there is a lack of a relatively accurate estimation method for the above delays, especially the actuator delay. Although some existing literatures make rough estimates and add some strategies to the algorithm to compensate for the delay, there are some problems. For example, in one estimation method, the system state is directly deduced forward by a preset time step in the controller, and then the control quantity is calculated by delaying the state after one step, so as to compensate for the delay. In another estimation method, a fixed-length delay cache mechanism is used to buffer the calculated control quantity. The above two methods mainly only consider the calculation delay or data processing delay. The above two delay compensation methods have some common disadvantages: they can only handle a static fixed delay size scenario, and cannot perform dynamic compensation for variable delays. In actual situations, the actuator delay is always in a state of dynamic change. The delay generated by each actuator at each moment may be inconsistent. In addition, the actuator time-varying involves many factors and the change is nonlinear, making it difficult to model directly.

[0009] In summary, the disadvantages of the prior art are that it is difficult to comprehensively consider all actuator delays and it is impossible to accurately and real-timely estimate the actuator delays online.

[0010] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the invention

[0011] In response to the problems in the prior art, the purpose of the present application is to provide a vehicle system response delay estimation method, system, device and storage medium to achieve online real-time delay estimation with high accuracy and applicable to delay estimation of various different actuators.

[0012] The present application provides a method for estimating vehicle system response delay, comprising the following steps:

[0013] Receive and dynamically store control instructions and chassis feedback signals;

[0014] Constructing a regression matrix, wherein the regression matrix includes a plurality of control instruction combination forms corresponding to chassis feedback signals at a plurality of moments;

[0015] Performing QR decomposition on the regression matrix to obtain a QR decomposition result;

[0016] Calculating the ERR corresponding to each candidate decomposition item based on the chassis feedback signals at the multiple moments and the QR decomposition results;

[0017] A dominant term in the QR decomposition result is selected based on the ERR, and a vehicle system response delay is determined according to a corresponding relationship between the dominant term and the control instruction combination form.

[0018] In some embodiments, constructing a regression matrix comprises the following steps:

[0019] An m*a regression matrix is ​​constructed based on possible control instruction combinations corresponding to m chassis feedback signals, wherein a is the number of possible control instructions corresponding to the chassis feedback signals at each preset moment, and a is greater than 1. In the regression matrix, the data in the j-th row and the i-th column represent the i-th possible control instruction corresponding to the chassis feedback signal at the j-th moment, j∈[1,m], i∈[1,a], and the data in the i-th column represent the i-th control instruction combination corresponding to the m chassis feedback signals.

[0020] In some embodiments, the a possible control instructions corresponding to the chassis feedback signal at the j-th moment are respectively the control instructions at a moments before the j-th moment.

[0021] In some embodiments, the dynamic storage control instruction combination and chassis feedback signal comprises the following steps:

[0022] The control instructions and chassis feedback signals are dynamically stored based on a sliding window with a fixed size of n, where n is a positive integer greater than a, and m=na.

[0023] In some embodiments, performing QR decomposition on the regression matrix to obtain a QR decomposition result includes the following steps:

[0024] The regression matrix is ​​subjected to QR decomposition based on the classical Schmidt orthogonal algorithm to obtain a QR decomposition result.

[0025] In some embodiments, the candidate decomposition items in the QR decomposition result are orthogonal matrices; and calculating the ERR corresponding to each candidate decomposition item based on the chassis feedback signals at the multiple moments and the QR decomposition result comprises the following steps:

[0026] Construct an output matrix based on chassis signals at multiple moments;

[0027] The ERR corresponding to each orthogonal matrix is ​​calculated based on the output matrix and multiple orthogonal matrices in the QR decomposition result.

[0028] In some embodiments, the plurality of orthogonal matrices correspond to the control instruction combinations in one-to-one correspondence;

[0029] Selecting a dominant term in the QR decomposition result based on the ERR, and determining a vehicle system response delay according to a corresponding relationship between the dominant term and the control instruction combination form, comprising the following steps:

[0030] Selecting an optimal orthogonal matrix as the dominant term according to the ERR of each of the orthogonal matrices;

[0031] The control instruction combination form corresponding to the dominant item is determined, and the vehicle system response delay is determined according to the time difference between the moment corresponding to the control instruction combination form and the moment of the corresponding chassis feedback signal.

[0032] In some embodiments, the ERR corresponding to each orthogonal matrix is ​​calculated using the following formula:

[0033]

[0034]

[0035] Among them, w i represents the i-th orthogonal matrix, [error] i is the ERR corresponding to the i-th orthogonal matrix, z represents the output matrix, and <> represents the inner product;

[0036] Selecting a dominant term in the QR decomposition result based on the ERR includes: selecting an orthogonal matrix with the largest ERR as the dominant term in the QR decomposition result.

[0037] In some embodiments, before receiving and dynamically storing the control instruction and chassis feedback signal, the following steps are also included:

[0038] Determine whether the preset delay identification conditions are currently met;

[0039] If yes, receiving and dynamically storing the control command and chassis feedback signal;

[0040] If not, end the current process.

[0041] In some embodiments, the delayed identification condition includes that the current vehicle is in a driving state, and / or the current vehicle executes an execution action corresponding to the control instruction.

[0042] The embodiment of the present application further provides a vehicle system response delay estimation system, which is used to implement the vehicle system response delay estimation method, and the system includes:

[0043] A signal receiving module, used for receiving and dynamically storing a control instruction combination and a chassis feedback signal;

[0044] A matrix construction module, used to construct a regression matrix, wherein the regression matrix includes a plurality of possible control instruction combinations corresponding to the chassis feedback signal at each moment;

[0045] A matrix solving module, configured to perform QR decomposition on the regression matrix to obtain a QR decomposition result; and calculate the ERR corresponding to each candidate decomposition item based on the chassis feedback signals at the multiple moments and the QR decomposition result;

[0046] The delay estimation module is used to select the dominant item in the QR decomposition result based on the ERR, and determine the vehicle system response delay according to the corresponding relationship between the dominant item and the control instruction combination form.

[0047] The embodiment of the present application further provides a vehicle system response delay estimation device, comprising:

[0048] processor;

[0049] a memory storing executable instructions of the processor;

[0050] Wherein, the processor is configured to perform the steps of the vehicle system response delay estimation method by executing the executable instructions.

[0051] An embodiment of the present application also provides a computer-readable storage medium for storing a program, which, when executed by a processor, implements the steps of the vehicle system response delay estimation method.

[0052] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0053] The vehicle system response delay estimation method, system, device and storage medium of the present application have the following beneficial effects:

[0054] By adopting the vehicle system response delay estimation method of the present application, collecting control instructions and chassis feedback signals, and establishing and solving a regression matrix, an online real-time and accurate estimation of the vehicle system response delay is achieved. The method can be applied to different actuators, and the control instructions and chassis feedback signals of different actuators can be processed separately, which has high versatility. The present application adopts QR decomposition, which is more accurate and has a small amount of calculation, thereby improving the accuracy and real-time performance of the vehicle system response delay estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings.

[0056] Figure 1is a flow chart of a vehicle system response delay estimation method according to an embodiment of the present application;

[0057] Figure 2 is a flow chart of calculating ERR in one embodiment of the present application;

[0058] Figure 3 is a flow chart of determining a vehicle system response delay according to an embodiment of the present application;

[0059] Figure 4 is a structural diagram of a vehicle system response delay estimation system according to an embodiment of the present application;

[0060] Figure 5 is a structural schematic diagram of a vehicle system response delay estimation device according to an embodiment of the present application;

[0061] Figure 6 It is a schematic diagram of the structure of a computer-readable storage medium according to an embodiment of the present application. DETAILED DESCRIPTION

[0062] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0063] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated descriptions will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices. Although "first" or "second" etc. are used in this specification to represent certain features, they are only used to represent the function and are not used as a limitation on the number and importance of specific features.

[0064] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the steps. For example, some steps may be decomposed, while some steps may be combined or partially combined. Therefore, the actual execution order may be changed according to the actual situation.

[0065] like Figure 1 As shown, the embodiment of the present application provides a vehicle system response delay estimation method, comprising the following steps:

[0066] S100: receiving and dynamically storing control instructions and chassis feedback signals;

[0067] Here, the control command and the chassis feedback signal correspond to the same actuator, that is, in order to estimate the system response delay of an actuator, the control command is the control command issued by the vehicle control system (such as the automatic driving system) to the actuator, and the chassis feedback signal is the feedback signal of the chassis after the actuator performs a specific action in response to the control command, that is, it corresponds to the actual execution result of the actuator;

[0068] S200: constructing a regression matrix, wherein the regression matrix includes a plurality of control instruction combination forms corresponding to chassis feedback signals at a plurality of moments;

[0069] S300: Perform QR decomposition on the regression matrix to obtain a QR decomposition result;

[0070] QR decomposition is the orthogonal triangular decomposition method, which is used to decompose a matrix into the product of an orthogonal matrix Q and an upper triangular matrix R, that is, A = QR;

[0071] S400: Calculating the ERR corresponding to each candidate decomposition item based on the chassis feedback signals at the multiple moments and the QR decomposition results;

[0072] In this embodiment, the orthogonal matrix Q after QR decomposition is used as an alternative decomposition item, that is, the ERR (Error Reduction Ratio) corresponding to each orthogonal matrix Q is calculated based on the chassis feedback signals at the multiple moments, and the ERR can reflect the error between the orthogonal matrix Q and the chassis feedback signal;

[0073] S500: Selecting a dominant term in the QR decomposition result based on the ERR, and determining a vehicle system response delay according to a corresponding relationship between the dominant term and a combination form of the control instructions.

[0074] By adopting the vehicle system response delay estimation method of the present application, collecting control instructions and chassis feedback signals, and establishing and solving a regression matrix, an online real-time and accurate estimation of the vehicle system response delay is achieved. This method can be applied to different actuators, and the control instructions and chassis feedback signals of different actuators can be processed separately, and it has high versatility. The present application adopts QR decomposition, which is more accurate than LU decomposition and singular value decomposition, and has a small amount of calculation, thereby improving the accuracy and real-time performance of vehicle system response delay estimation.

[0075] The present application can be applied to delay estimation of various actuators. For example, when the actuator is a steering mechanism, the method can estimate the steering delay, the control instruction is the wheel deflection angle issued by the vehicle control system, and the chassis feedback signal is the wheel deflection angle fed back by the chassis; when the actuator is a braking mechanism, the method can estimate the braking delay, the control instruction is the braking torque issued by the vehicle control system, and the chassis feedback signal is the actual braking torque fed back by the chassis; when the actuator is a throttle mechanism, the method can estimate the throttle delay, the control instruction is the throttle opening issued by the vehicle control system, and the chassis feedback signal is the actual throttle opening fed back by the chassis.

[0076] The following takes the estimation of steering delay as an example to illustrate the specific implementation of the vehicle system response delay estimation method, but it can be understood that the following description is only an example. When applied to the delay estimation of other actuators, the corresponding control instructions and chassis feedback signals can be replaced. Steering delay refers to the time from the vehicle control system issuing a lateral control instruction to the vehicle chassis actuator actually starting to execute the lateral control instruction and the steering feedback signal being received by the vehicle control system. This steering delay is very important for autonomous driving lateral control, because there will be a phase difference between the control signal and the actual chassis feedback signal. If the steering delay is not considered to compensate for this phase difference, the controller adjustment will be inaccurate or delayed, resulting in poor control performance. In severe cases, it may directly cause the entire control system to oscillate or diverge. In addition, the impact of this delay on the control system will become more serious as the above-mentioned delay times increase.

[0077] As described above, when the actuator is a steering mechanism, the control command is the wheel deflection angle issued by the vehicle control system, and the chassis feedback signal is the wheel deflection angle fed back by the chassis. This application classifies delay identification as steering delay system identification. System identification is different from parameter identification. The system to be identified is a black box. There is no known polynomial or model to describe the system. Therefore, this application constructs all possible polynomials as the expression form of this steering delay system.

[0078] In this application, these polynomials are collectively referred to as regression terms. In this application, the control command is used as the input term, and the chassis feedback signal is used as the output term, that is, the steering delay system can be regarded as a single-input single-output system. For the delay identification of the single-input single-output system, each term that constitutes this system can be regarded as a regression term of the current input. Permutations and combinations are performed here according to the complexity of the modeling required. For all regression terms, they can be permuted and combined singly, or multiple terms can be arithmetically combined or powers can be added to perform nonlinear combinations. In this embodiment, in order to simplify the problem, the degree of nonlinear combination is set to 1. And this application only needs to find an optimal possibility when solving, so it can be achieved with a combination degree of 1. Therefore, in this embodiment, the steering delay system is regarded as a system composed of single factors, the process of permutations and combinations is greatly simplified, and the key issue is focused on the decomposition algorithm.

[0079] In this embodiment, a set of simple coding rules is pre-set to facilitate the formation of the final regression matrix. The C matrix is ​​defined to store all possible forms of permutations and combinations of regression items. The C matrix is ​​an a*b dimensional matrix, where a is the number of possible control instructions corresponding to the chassis feedback signal at each preset moment, representing a total of a possible combination forms, and b represents b different items. When the nonlinear combination degree is 1, a=b. If the nonlinear combination degree is greater than 1, then a>b. For example, when the nonlinear combination degree is 1, the sum of each row of the C matrix must be equal to 1. When the nonlinear combination degree is 2, the sum of each row of the C matrix must be equal to 2. Assuming a=b=3, then There are three different possible combinations of the steering delay system, namely u(k-1), u(k-2), and u(k-3). Among them, u represents the input wheel deflection angle command. Therefore, it can be seen that based on the assumption that the nonlinear combination degree is 1, the permutation combination matrix C must be a unit matrix.

[0080] In this embodiment, the step S100: dynamically storing the control instruction combination and the chassis feedback signal, comprises the following steps:

[0081] The control instructions and chassis feedback signals are dynamically stored based on a sliding window of fixed size n, where n is a positive integer greater than a. Among them, the control instructions and chassis feedback signals are stored using two sliding windows respectively. The size n of the sliding window is an adjustable parameter that can be set by the user, and the appropriate n value can be selected based on the trade-off between recognition accuracy and recognition speed. The larger n is, the more sampled data is solved each time, the higher the recognition accuracy is, and the longer the recognition time is. Conversely, the smaller n is, the less sampled data is solved each time, the lower the recognition accuracy is, and the lower the time is.

[0082] In this embodiment, the chassis feedback signal at the jth moment is the control instruction at a moment before the jth moment corresponding to the a possible control instruction. For example, when a=3, the a possible control instructions corresponding to the chassis feedback signal at the i-th moment are the control instruction at the i-th moment (the first possible control instruction), the control instruction at the i-1-th moment (the second possible control instruction), and the control instruction at the i-2-th moment (the third possible control instruction). Therefore, for n chassis feedback signals, only m=na chassis feedback signals can obtain the complete corresponding possible a control instructions, that is, when solving the problem later, m chassis feedback signals and the a control instructions corresponding to each chassis feedback signal are actually used. Taking a=3 as an example, the above u(k-1) is the combination of the first possible control instructions of the m chassis feedback signals, that is, the first possible control instruction combination form. u(k-2) is the combination of the second possible control instructions of the m chassis feedback signals, that is, the second possible control instruction combination form. u(k-3) is the third possible combination of control instructions of the m chassis feedback signals, that is, the third possible combination form of control instructions.

[0083] In this embodiment, the step S200: constructing a regression matrix includes the following steps:

[0084] Based on the possible control command combinations corresponding to the m chassis feedback signals, an m*a regression matrix Φ is constructed. Φ represents the matrix of each possible combination of the steering delay system within a continuous sampling time, that is, each candidate steering delay system model within a continuous sampling time.

[0085] Wherein, a is the number of possible control instructions corresponding to the chassis feedback signal at each preset moment, and a is greater than 1, and a is also the number of all possible control instruction combinations, m is the number of sampled output data, and the output data includes chassis feedback signals at m moments. In the regression matrix, each row represents all possible control instructions corresponding to the chassis feedback moment at a moment, and each column represents a possible control instruction combination of the m chassis feedback signals. The data in the jth row and the i-th column represent the i-th possible control instruction corresponding to the chassis feedback signal at the j-th moment, j∈[1,m], i∈[1,a]. The data in the i-th column represent the i-th control instruction combination corresponding to the m chassis feedback signals. The data in the jth row represent all possible control instructions corresponding to the chassis feedback moment at the j-th moment.

[0086] The subsequent solution process is to find which input wheel angle command the actual wheel deflection angle feedback from the vehicle chassis can correspond to, and then estimate the steering delay based on the issuance time of the input wheel deflection angle command and the time when the feedback of the actual wheel deflection angle is received. That is, find a wheel deflection angle command combination that is closest to the m actual wheel deflection angle combinations from a possible control command combination. Assuming that the final wheel deflection angle command combination u(k-2) is closest to the actual wheel deflection angle combination, the estimated steering delay is 2 cycles. Assuming that the final wheel deflection angle command combination u(k-3) is closest to the actual wheel deflection angle combination, the estimated steering delay is 3 cycles. The present application is to select the most dominant one among a possible control command combinations through the QR decomposition algorithm, that is, the one that is closest to the chassis feedback signal.

[0087] The problem of finding the most dominant control instruction combination form is converted into a mathematical problem of solving Φθ=Z, where θ is a coefficient matrix and Z is an output matrix composed of m chassis feedback signals. In this embodiment, for delay estimation, it is not necessary to finally solve the coefficient matrix, but only to decompose the regression matrix Φ and then select the most dominant one according to a specific standard.

[0088] In this embodiment, the regression matrix is ​​subjected to QR decomposition based on the classical Schmidt orthogonal algorithm to obtain a QR decomposition result.

[0089] like Figure 2 As shown, the step S400: calculating the ERR corresponding to each candidate decomposition item based on the chassis feedback signals at the multiple moments and the QR decomposition results, comprises the following steps:

[0090] S410: constructing an output matrix based on chassis signals at multiple moments; the output matrix is ​​defined as a Z matrix;

[0091] S420: Calculate the ERR corresponding to each orthogonal matrix based on the output matrix and multiple orthogonal matrices in the QR decomposition result.

[0092] In this embodiment, the step S300: performing QR decomposition on the regression matrix to obtain the QR decomposition result, assuming that Φ=WA, W is a partial term of Φ and is an orthogonal matrix, and A is an upper triangular matrix, so WAθ=Z. Let g=Aθ=W - 1 Z=(W T W) -1 W T Z, so the g matrix can be calculated from W and Z. For each orthogonal matrix w i , the corresponding g i for: In the formula, <> represents the inner product of the vector. From a mathematical point of view, g i Represents the output vector Z and each orthogonal vector w i The cosine value of the angle between the output matrix Z and the output matrix Z on the orthogonal matrix is ​​the smallest.

[0093] In this embodiment, the residual ε=Z-Φθ=Z-Wg is defined. For each orthogonal matrix w i , and its corresponding residual ε i =Zw i *g i . Combining the mathematical meaning of g mentioned above, here w i *g i What it actually means is that Z is in w i The projection on this orthogonal vector, and the next goal is to find a set of orthogonal vectors so that the projection of Z on it can restore Z to the greatest extent.

[0094] In this embodiment, the dominant term can be directly selected from the orthogonal matrix based on the minimum residual, that is, the residual is directly used as the ERR, and the orthogonal matrix with the minimum ERR is used as the dominant term. In another alternative implementation, in order to eliminate the influence of different residual directions, the ERR is further calculated based on the residual, so that a group of orthogonal matrices with the largest ERR are used as the dominant term. In this implementation, the following formula is used to calculate the ERR corresponding to each orthogonal matrix:

[0095]

[0096]

[0097] Among them, w i represents the i-th orthogonal matrix, [error] i is the ERR corresponding to the i-th orthogonal matrix, z represents the output matrix, and <> represents the inner product.

[0098] The calculated ERR is always less than 1, and the closer the ERR is to 1, the more the corresponding projection can restore the output matrix. Therefore, in step S500, selecting the dominant term in the QR decomposition result based on the ERR includes: selecting the orthogonal matrix with the largest ERR as the dominant term in the QR decomposition result.

[0099] like Figure 3As shown, the step S500: selecting the dominant item in the QR decomposition result based on the ERR, and determining the vehicle system response delay according to the corresponding relationship between the dominant item and the control instruction combination form, includes the following steps:

[0100] S510: Selecting the optimal orthogonal matrix as the dominant term according to the ERR of each of the orthogonal matrices; that is, selecting the orthogonal matrix with the smallest residual or the largest ERR as the dominant term;

[0101] S520: Determine the control instruction combination form corresponding to the dominant item;

[0102] S530: Determine the vehicle system response delay according to the time difference between the moment corresponding to the control command combination and the moment of the corresponding chassis feedback signal. For example, if the control command combination u(k-2) is the closest to the chassis feedback signal, the estimated steering delay is 2 cycles. If the control command combination u(k-3) is the closest to the chassis feedback signal, the estimated steering delay is 3 cycles.

[0103] In this embodiment, the vehicle system response delay estimation method can be turned on only at a specific time and does not need to be turned on all the time, thereby avoiding occupying too many computing resources. Before the step S100: receiving and dynamically storing the control command and chassis feedback signal, the following steps are also included:

[0104] Determine whether the preset delay identification conditions are currently met;

[0105] In this embodiment, the delayed identification condition includes that the current vehicle is in a driving state, and / or the current vehicle executes an execution action corresponding to the control instruction;

[0106] For example, it is preset that the delay identification condition is satisfied only when the vehicle is in a driving state (vehicle acceleration is greater than 0 and / or vehicle speed is greater than 0), or it is preset that the vehicle needs to execute an execution action of a control instruction, and the delay identification condition is satisfied. Taking the actuator as a steering mechanism as an example, it is set that the delay identification condition is satisfied only when the vehicle is in a turning section. For the automatic driving system, it can be judged according to the path navigation that when the vehicle is about to enter a turning section, the delay identification condition is satisfied, and the delay identification of the steering delay system is started;

[0107] If yes, continue with steps S100 to S500 to complete the vehicle system response delay estimation and obtain the vehicle system response delay finally outputted in step S500.

[0108] If not, end the current process.

[0109] like Figure 4As shown, the embodiment of the present application also provides a vehicle system response delay estimation system, which is used to implement the vehicle system response delay estimation method, and the system includes:

[0110] The signal receiving module M100 is used to receive and dynamically store the control instruction combination and chassis feedback signal;

[0111] The matrix construction module M200 is used to construct a regression matrix, wherein the regression matrix includes a plurality of possible control instruction combinations corresponding to the chassis feedback signal at each moment;

[0112] The matrix solving module M300 is used to perform QR decomposition on the regression matrix to obtain a QR decomposition result; and calculate the ERR corresponding to each candidate decomposition item based on the chassis feedback signals at the multiple moments and the QR decomposition result;

[0113] The delay estimation module M400 is used to select the dominant item in the QR decomposition result based on the ERR, and determine the vehicle system response delay according to the corresponding relationship between the dominant item and the control instruction combination form.

[0114] By adopting the vehicle system response delay estimation system of the present application, collecting control instructions and chassis feedback signals, and establishing and solving a regression matrix, an online real-time and accurate estimation of the vehicle system response delay is achieved. The system can be applied to different actuators, and can process the control instructions and chassis feedback signals of different actuators respectively, and has high versatility. The present application adopts QR decomposition, which is more accurate than LU decomposition and singular value decomposition, and has a small amount of calculation, thereby improving the accuracy and real-time performance of vehicle system response delay estimation.

[0115] In the vehicle system response delay estimation system of the present application, the functions of each module can be implemented by using the specific implementation of the vehicle system response delay estimation method as described above, which will not be described in detail here.

[0116] An embodiment of the present application also provides a vehicle system response delay estimation device, comprising a processor; a memory, in which executable instructions of the processor are stored; wherein the processor is configured to execute the steps of the vehicle system response delay estimation method by executing the executable instructions.

[0117] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "platform" herein.

[0118] Refer to the following Figure 5 The electronic device 600 according to this embodiment of the present application is described. Figure 5 The electronic device 600 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0119] like Figure 5 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0120] The storage unit stores a program code, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps of various exemplary embodiments of the present application described in the vehicle system response delay estimation method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 Follow the steps shown in .

[0121] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0122] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0123] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0124] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0125] In the vehicle system response delay estimation device, the program in the memory implements the steps of the vehicle system response delay estimation method when executed by the processor. Therefore, the device can also obtain the technical effect of the above-mentioned vehicle system response delay estimation method.

[0126] The embodiment of the present application also provides a computer-readable storage medium for storing a program, which implements the steps of the vehicle system response delay estimation method when executed by a processor. In some possible implementations, various aspects of the present application can also be implemented in the form of a program product, which includes a program code. When the program product is executed on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present application described in the vehicle system response delay estimation method section of this specification.

[0127] refer to Figure 6 As shown, a program product 800 for implementing the above method according to an embodiment of the present application is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be executed on a terminal device, such as a personal computer. However, the program product of the present application is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0128] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0129] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0130] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0131] When the program in the computer storage medium is executed by the processor, the steps of the vehicle system response delay estimation method are implemented. Therefore, the computer storage medium can also obtain the technical effect of the above-mentioned vehicle system response delay estimation method.

[0132] The above content is a further detailed description of the present application in combination with specific preferred implementation methods, and it cannot be determined that the specific implementation of the present application is limited to these descriptions. For ordinary technicians in the technical field to which the present application belongs, several simple deductions or substitutions can be made without departing from the concept of the present application, which should be deemed to fall within the scope of protection of the present application.

Claims

1. A vehicle system response delay estimation method, characterized in that: The steps include: Receive and dynamically store control instructions and chassis feedback signals; Constructing a regression matrix, wherein the regression matrix includes a plurality of control instruction combination forms corresponding to chassis feedback signals at a plurality of moments; Performing QR decomposition on the regression matrix to obtain a QR decomposition result; Calculating the ERR corresponding to each candidate decomposition item based on the chassis feedback signals at the multiple moments and the QR decomposition results; A dominant term in the QR decomposition result is selected based on the ERR, and a vehicle system response delay is determined according to a corresponding relationship between the dominant term and the control instruction combination form.

2. The vehicle system response delay estimation method according to claim 1, characterized in that: The step of constructing a regression matrix comprises the following steps: An m*a regression matrix is ​​constructed based on possible control instruction combinations corresponding to m chassis feedback signals, wherein a is the number of possible control instructions corresponding to the chassis feedback signals at each preset moment, and a is greater than 1. In the regression matrix, the data in the j-th row and the i-th column represent the i-th possible control instruction corresponding to the chassis feedback signal at the j-th moment, j∈[1,m], i∈[1,a], and the data in the i-th column represent the i-th control instruction combination corresponding to the m chassis feedback signals.

3. The vehicle system response delay estimation method according to claim 2, characterized in that: The a possible control instructions corresponding to the chassis feedback signal at the j-th moment are respectively the control instructions at a moments before the j-th moment.

4. The vehicle system response delay estimation method according to claim 2, characterized in that: The dynamic storage control instruction combination and chassis feedback signal comprises the following steps: The control instructions and chassis feedback signals are dynamically stored based on a sliding window with a fixed size of n, where n is a positive integer greater than a, and m=na.

5. The vehicle system response delay estimation method according to claim 1, characterized in that: Performing QR decomposition on the regression matrix to obtain a QR decomposition result includes the following steps: The regression matrix is ​​subjected to QR decomposition based on the classical Schmidt orthogonal algorithm to obtain a QR decomposition result.

6. The vehicle system response delay estimation method according to claim 1, characterized in that: The candidate decomposition items in the QR decomposition result are orthogonal matrices; and the ERR corresponding to each candidate decomposition item is calculated based on the chassis feedback signals at the multiple moments and the QR decomposition result, including the following steps: Construct an output matrix based on chassis signals at multiple moments; The ERR corresponding to each orthogonal matrix is ​​calculated based on the output matrix and multiple orthogonal matrices in the QR decomposition result.

7. The vehicle system response delay estimation method according to claim 6, characterized in that: The multiple orthogonal matrices correspond to the control instruction combination forms one by one; Selecting a dominant term in the QR decomposition result based on the ERR, and determining a vehicle system response delay according to a corresponding relationship between the dominant term and the control instruction combination form, comprising the following steps: Selecting an optimal orthogonal matrix as the dominant term according to the ERR of each of the orthogonal matrices; The control instruction combination form corresponding to the dominant item is determined, and the vehicle system response delay is determined according to the time difference between the moment corresponding to the control instruction combination form and the moment of the corresponding chassis feedback signal.

8. The vehicle system response delay estimation method according to claim 6, characterized in that: The ERR corresponding to each orthogonal matrix is ​​calculated using the following formula: Among them, w i represents the i-th orthogonal matrix, [error] i is the ERR corresponding to the i-th orthogonal matrix, z represents the output matrix, and <> represents the inner product; Selecting a dominant term in the QR decomposition result based on the ERR includes: selecting an orthogonal matrix with the largest ERR as the dominant term in the QR decomposition result.

9. The vehicle system response delay estimation method according to claim 1, characterized in that: Before receiving and dynamically storing the control instruction and chassis feedback signal, the following steps are also included: Determine whether the preset delay identification conditions are currently met; If yes, receiving and dynamically storing the control command and chassis feedback signal; If not, end the current process.

10. The vehicle system response delay estimation method according to claim 9, characterized in that: The delayed identification condition includes that the current vehicle is in a driving state, and / or the current vehicle executes an execution action corresponding to the control instruction.

11. A vehicle system response delay estimation system, characterized in that: The method for estimating the response delay of a vehicle system according to any one of claims 1 to 10 is implemented, the system comprising: A signal receiving module, used for receiving and dynamically storing a control instruction combination and a chassis feedback signal; A matrix construction module, used to construct a regression matrix, wherein the regression matrix includes a plurality of possible control instruction combinations corresponding to the chassis feedback signal at each moment; A matrix solving module, configured to perform QR decomposition on the regression matrix to obtain a QR decomposition result; and calculate the ERR corresponding to each candidate decomposition item based on the chassis feedback signals at the multiple moments and the QR decomposition result; The delay estimation module is used to select the dominant item in the QR decomposition result based on the ERR, and determine the vehicle system response delay according to the corresponding relationship between the dominant item and the control instruction combination form.

12. A vehicle system response delay estimation device, characterized in that: include: processor; a memory storing executable instructions of the processor; The processor is configured to execute the steps of the vehicle system response delay estimation method according to any one of claims 1 to 10 by executing the executable instructions.

13. A computer-readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps of the vehicle system response delay estimation method according to any one of claims 1 to 10 are implemented.

Images