Longitudinal control method and device of vehicle, storage medium and autonomous vehicle

Abstract

The disclosure provides a longitudinal control method and device of a vehicle, a storage medium and an automatic driving vehicle, relates to the technical field of computers, specifically relates to the field of intelligent transportation and the field of automatic driving and artificial intelligence technology, and the specific implementation scheme is as follows: when performing longitudinal control on the vehicle in automatic driving, in combination with the predicted longitudinal speed of the vehicle at each predicted time point in a predicted time domain after the current time, the predicted longitudinal control parameter of the model predictive controller of the vehicle at each predicted time point in the predicted time domain is determined, in combination with the longitudinal control parameter information, the longitudinal model in the model predictive controller and the expected trajectory of the vehicle, the longitudinal control amount at each predicted time point in the predicted time domain is determined, and the vehicle is controlled longitudinally based on the longitudinal control amount at the first predicted time point in the predicted time domain. Therefore, the accuracy and stability of the longitudinal control of the vehicle are improved, and the safety of the automatic driving of the vehicle is improved.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to the fields of intelligent transportation and autonomous driving, and other artificial intelligence technologies, particularly to longitudinal control methods, devices, storage media, and autonomous vehicles. Background Technology

[0002] With the development of technology, autonomous vehicles have become an important direction for the future development of automobiles. Autonomous vehicles can not only help improve people's travel convenience and experience, but also greatly improve the efficiency of people's travel.

[0003] In the process of longitudinal control of autonomous vehicles, related technologies typically rely on longitudinal control variables determined within the autonomous driving system. The accuracy of these longitudinal control variables is crucial for the safe operation of autonomous vehicles. Summary of the Invention

[0004] This disclosure provides a method, apparatus, storage medium, and autonomous vehicle for longitudinal control of a vehicle.

[0005] According to one aspect of this disclosure, a longitudinal control method for a vehicle is provided. The method includes: determining a predicted longitudinal velocity sequence of the vehicle in a predicted time domain after the current moment, wherein the predicted longitudinal velocity sequence includes predicted longitudinal velocities at each predicted time point; for each predicted time point, determining longitudinal control parameter information of a model predictive controller of the vehicle at the predicted time point based on the predicted longitudinal velocity at the predicted time point; determining a longitudinal control quantity sequence in the predicted time domain based on the longitudinal control parameter information, a longitudinal model in the model predictive controller, and the desired trajectory of the vehicle, wherein the longitudinal control quantity sequence includes longitudinal control quantities at each predicted time point; and performing longitudinal control of the vehicle for autonomous driving based on the longitudinal control quantity at the first predicted time point in the predicted time domain.

[0006] According to another aspect of this disclosure, a longitudinal control device for a vehicle is provided, the device comprising: a first determining module, configured to determine a predicted longitudinal velocity sequence of the vehicle in a predicted time domain after the current moment, wherein the predicted longitudinal velocity sequence includes: predicted longitudinal velocities at each predicted time point; a second determining module, configured to determine longitudinal control parameter information of a model predictive controller of the vehicle at each predicted time point based on the predicted longitudinal velocity at the predicted time point; a third determining module, configured to determine a longitudinal control quantity sequence in the predicted time domain based on the longitudinal control parameter information, the longitudinal model in the model predictive controller, and the desired trajectory of the vehicle, wherein the longitudinal control quantity sequence includes: longitudinal control quantities at each predicted time point; and a control module, configured to perform longitudinal control of the vehicle for autonomous driving based on the longitudinal control quantity at the first predicted time point in the predicted time domain.

[0007] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the longitudinal control method for a vehicle of this disclosure.

[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform a longitudinal control method for a vehicle disclosed in embodiments of this disclosure.

[0009] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the longitudinal control method for a vehicle of this disclosure.

[0010] According to another aspect of this disclosure, an autonomous driving vehicle is provided, which includes the electronic devices disclosed in embodiments of this disclosure.

[0011] One embodiment of the above application has the following advantages or beneficial effects:

[0012] When performing longitudinal control for autonomous driving, the predicted longitudinal velocities of the vehicle at various prediction time points within the prediction time domain after the current moment are combined to determine the predicted longitudinal control parameters of the vehicle's model predictive controller at each prediction time point within the prediction time domain. Furthermore, by combining the longitudinal control parameter information, the longitudinal model in the model predictive controller, and the vehicle's desired trajectory, the longitudinal control quantities at each prediction time point within the prediction time domain are determined. Finally, based on the longitudinal control quantity at the first prediction time point within the prediction time domain, longitudinal control of the vehicle is performed. Thus, by combining the predicted longitudinal velocities at each prediction time point within the prediction time domain, the longitudinal control quantities for longitudinal vehicle control are accurately determined, improving the accuracy and stability of longitudinal control and consequently enhancing the safety of autonomous driving.

[0013] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0014] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0015] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure;

[0016] Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure;

[0017] Figure 3 This is a schematic diagram according to the third embodiment of the present disclosure;

[0018] Figure 4 This is a schematic diagram according to the fourth embodiment of the present disclosure;

[0019] Figure 5 This is a schematic diagram according to the fifth embodiment of the present disclosure;

[0020] Figure 6 This is a schematic diagram according to the sixth embodiment of the present disclosure;

[0021] Figure 7 This is a schematic diagram according to the seventh embodiment of the present disclosure;

[0022] Figure 8 This is a block diagram of an electronic device used to implement the longitudinal control method for a vehicle according to embodiments of the present disclosure. Detailed Implementation

[0023] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0024] The following description, with reference to the accompanying drawings, describes a longitudinal control method, apparatus, storage medium, and autonomous vehicle according to embodiments of the present disclosure.

[0025] Figure 1 This is a schematic diagram based on a first embodiment of the present disclosure, which provides a method for longitudinal control of a vehicle.

[0026] like Figure 1 As shown, the longitudinal control method for this vehicle may include:

[0027] Step 101: Determine the predicted longitudinal velocity sequence of the vehicle in the predicted time domain after the current time, wherein the predicted longitudinal velocity sequence includes the predicted longitudinal velocity at each predicted time point.

[0028] In this embodiment, the vehicle longitudinal control method is executed by a vehicle longitudinal control device, which can be implemented by software and / or hardware. The vehicle longitudinal control device can be an electronic device or can be configured in an electronic device to achieve automatic driving control of the vehicle.

[0029] In some exemplary embodiments, the above-mentioned electronic device may be a terminal device or a server, etc., and this embodiment does not specifically limit it.

[0030] In some exemplary embodiments, the aforementioned terminal device can be a device that can be installed in any vehicle, such as an onboard controller or an onboard computer. In some examples, the longitudinal control device of the vehicle can be an onboard computer. It should be noted that the onboard computer in this example has autonomous driving capabilities, can plan routes for the vehicle, and can perform autonomous driving control of the vehicle. In other examples, the longitudinal control device of the vehicle can be a server, which can communicate with the vehicle and perform autonomous driving control of the vehicle.

[0031] In some embodiments of this disclosure, in order to accurately perform longitudinal control of the vehicle for autonomous driving and improve the safety and stability of the vehicle while it is in motion, the vehicle speed in the prediction time domain after the current moment can be predicted based on the current vehicle state at the current moment, so as to obtain the predicted longitudinal speed of the vehicle at each prediction time point in the prediction time domain after the current moment, and sort the predicted longitudinal speeds according to the time sequence of the prediction time points to obtain the predicted longitudinal speed sequence of the vehicle in the prediction time domain.

[0032] The prediction time domain refers to a period of time after the current moment, which may include N prediction time points, with a preset time interval between two adjacent prediction time points.

[0033] The aforementioned preset time interval is pre-set and its value can be adjusted according to actual needs. For example, the prediction time domain can include 25 prediction time points, with a time interval of 1 second between two adjacent prediction time points. Alternatively, the prediction time domain can include 10 prediction time points, with a time interval of 2 seconds between two adjacent prediction time points.

[0034] In some exemplary embodiments, in order to accurately control the vehicle longitudinally, the length of the prediction time domain and the value of the time interval between prediction time points can be determined by combining the vehicle's current speed at the current moment.

[0035] Step 102: For each prediction time point, determine the longitudinal control parameter information of the vehicle's model predictive controller at the prediction time point based on the predicted longitudinal velocity at the prediction time point.

[0036] In some other exemplary embodiments, after determining the predicted longitudinal velocity at each prediction time point, for each prediction time point, based on the pre-saved correspondence between longitudinal velocity and longitudinal control parameter information, the longitudinal control parameter information corresponding to the predicted longitudinal velocity at that prediction time point is determined, and the determined longitudinal control parameter information is used as the longitudinal control parameter information at that prediction time point.

[0037] The longitudinal control parameter information may include a first penalty weight applied to the state quantity error, a second penalty weight applied to the control quantity, and a second penalty weight applied to the control quantity increment.

[0038] Step 103: Based on the longitudinal control parameter information, the longitudinal model in the model predictive controller, and the vehicle's desired trajectory, determine the longitudinal control quantity sequence in the prediction time domain, wherein the longitudinal control quantity sequence includes the longitudinal control quantity at each prediction time point.

[0039] Among them, the Model Predictive Control (MPC) uses the longitudinal model, desired trajectory, and longitudinal vehicle state parameters of the vehicle at the current moment in the model predictive controller to predict the longitudinal control quantity at each prediction time point in the prediction time domain, so as to perform autonomous driving control processing on the vehicle based on the longitudinal control quantity at the first prediction time point in the prediction time domain.

[0040] The model predictive controller employs an advanced process control strategy for prediction. For example, a control sequence is first randomly selected, and a predicted trajectory is determined based on this control sequence. Based on the predicted trajectory and the desired trajectory, the control sequence is adjusted once. This process is repeated until the difference between the predicted trajectory and the desired trajectory meets a specified condition.

[0041] It should be noted that the aforementioned longitudinal model can also be called the longitudinal state equation model. This longitudinal model is used to predict the longitudinal vehicle state parameters. Specifically, after inputting a first longitudinal vehicle state parameter and the corresponding longitudinal control quantity into this longitudinal model, the longitudinal model can predict the second longitudinal vehicle state parameters that the vehicle will enter after applying the longitudinal control quantity to the vehicle under the first longitudinal vehicle state parameters.

[0042] In this embodiment, the longitudinal vehicle state parameters may include longitudinal displacement, longitudinal velocity, longitudinal torque, etc.

[0043] In this embodiment, the longitudinal control quantity may include the drive control quantity and / or the braking control quantity.

[0044] The aforementioned state quantity error refers to the error between the expected state quantity and the predicted state quantity at the predicted time point.

[0045] The desired trajectory refers to the trajectory that the vehicle is expected to reach in the prediction time domain when planning the vehicle.

[0046] The predicted trajectory refers to the trajectory determined by predicting the vehicle's operating status at each predicted time point within the predicted time domain, based on the vehicle's actual operating status at the current moment and the predicted operating status at each predicted time point.

[0047] Step 104: Perform longitudinal control of the vehicle for autonomous driving based on the longitudinal control quantity at the first predicted time point in the prediction time domain.

[0048] In some exemplary embodiments of this disclosure, after determining the sequence of longitudinal control quantities of the vehicle in the prediction time domain, the longitudinal control quantity at the first prediction time point in the prediction time domain can be used as the longitudinal control quantity of the vehicle at the next time moment, and the vehicle can be longitudinally controlled at the next time moment based on the longitudinal control quantity.

[0049] In an exemplary embodiment of this disclosure, the prediction time points within the prediction time domain can be sorted in chronological order to obtain a sorting result, where the first prediction time point is the time point ranked first in the sorting result. For example, the sorting result is t1, t2, t3, t4, t5, where t1 is the first prediction time point.

[0050] In some exemplary embodiments, the time interval between the current time and the next time is the same as the time interval between adjacent prediction time points. When performing longitudinal control on the next time, since the next time is the first prediction time point in the prediction time domain,

[0051] Therefore, the longitudinal control quantity at the first prediction time point in the prediction time domain can be used as the longitudinal control quantity for longitudinal control of the vehicle at the next time point.

[0052] The longitudinal control method for a vehicle according to embodiments of this disclosure, when performing longitudinal control of an autonomous vehicle, determines the predicted longitudinal control parameters of the vehicle's model predictive controller at each predicted time point within the prediction time domain, based on the predicted longitudinal speed of the vehicle at each predicted time point after the current moment. Then, by combining the longitudinal control parameter information, the longitudinal model in the model predictive controller, and the vehicle's desired trajectory, the longitudinal control quantity at each predicted time point within the prediction time domain is determined. Finally, based on the longitudinal control quantity at the first predicted time point within the prediction time domain, longitudinal control of the vehicle is performed. Therefore, by combining the predicted longitudinal speed at each predicted time point within the prediction time domain, the longitudinal control quantity for longitudinal control of the vehicle is accurately determined, improving the accuracy and stability of the vehicle's longitudinal control, thereby enhancing the safety of autonomous driving.

[0053] In some embodiments, in order to accurately determine the longitudinal control parameter information at each prediction time point in the prediction time domain, one possible implementation of step 102 is as follows: Figure 2 As shown, it may include:

[0054] Step 201: Based on the predicted longitudinal velocity at the predicted time point, determine the first penalty weight of the state variable error of the vehicle's model predictive controller at the predicted time point.

[0055] In some example implementations, the aforementioned longitudinal control parameters may include a first penalty weight. This first penalty weight refers to the penalty weight applied by the vehicle's model predictive controller to the state variable error at the prediction time point when performing model predictive control on the longitudinal model.

[0056] In related technologies, the penalty weights applied by model predictive controllers to the state variable errors at each prediction time point are usually fixed. However, since longitudinal models are typically linear, the longitudinal velocity corresponding to the prediction time point during optimization may be negative. In reality, regardless of the vehicle's longitudinal control quantity (e.g., braking force), the vehicle's longitudinal velocity cannot be negative. This is a limitation of linear models. If the vehicle's model predictive controller strictly limits the longitudinal velocity to non-negative values ​​during the optimization process, it may lead to solution failure. To ensure accurate determination of the longitudinal control quantity and improve the safety of autonomous driving control, in some embodiments, for each prediction time point, it can be determined whether the predicted longitudinal velocity of the vehicle at the prediction time point is greater than zero. If the predicted longitudinal velocity at that prediction time point is greater than or equal to zero, the penalty weight of the state variable error at the prediction time point is greater than zero. In some examples, the penalty weight of the state variable error at the prediction time point can be set to a preset value greater than zero, where the preset value is an empirical value obtained from multiple experiments.

[0057] In other embodiments, when the predicted longitudinal velocity at the prediction time point is less than zero, the penalty weight for the state variable error at the prediction time point is equal to zero.

[0058] Step 202: Obtain the second penalty weight that is pre-set for the longitudinal control quantity at the prediction time point, wherein the second penalty weight is the same at different prediction time points.

[0059] Step 203: Obtain the third penalty weight that is pre-set for the control increment at the prediction time point, wherein the third penalty weight is the same at different prediction time points.

[0060] Step 204: Generate longitudinal control parameter information of the vehicle's model predictive controller at the prediction time point based on the first penalty weight, the second penalty weight, and the third penalty weight.

[0061] In some exemplary embodiments, in order to accurately determine the predicted longitudinal velocity sequence of the vehicle in the prediction time domain, one possible implementation of step 101 above is as follows: Figure 3 As shown, it may include:

[0062] Step 301: Obtain the vehicle's current longitudinal velocity at the current moment.

[0063] Step 302: Obtain the expected longitudinal acceleration sequence of the vehicle in the prediction time domain, wherein the expected longitudinal acceleration sequence includes the expected longitudinal acceleration at each prediction time point.

[0064] Step 303: Determine the predicted longitudinal velocity sequence of the vehicle in the prediction time domain based on the current longitudinal velocity and the expected longitudinal acceleration sequence.

[0065] In some exemplary implementations, the current longitudinal speed and the desired longitudinal speed sequence can be input into a longitudinal speed prediction model to obtain a predicted longitudinal speed sequence of the vehicle in the prediction time domain.

[0066] In some exemplary implementations, in order to accurately determine the predicted longitudinal velocity sequence within the prediction time domain, another possible implementation of determining the predicted longitudinal velocity sequence of the vehicle within the prediction time domain based on the current longitudinal velocity and the desired longitudinal acceleration sequence is as follows: Figure 4 As shown, it may include:

[0067] Step 401: For the i-th prediction time point, determine the predicted longitudinal velocity at the i-th prediction time point based on the expected longitudinal acceleration and the current longitudinal velocity at the i-th prediction time point, where the initial value of i is 1.

[0068] Here, the i-th prediction time point refers to the i-th prediction time point among multiple prediction time points arranged in chronological order in the prediction time domain.

[0069] Step 402: Increment i by 1.

[0070] Step 403: If i is less than or equal to N, determine the predicted longitudinal velocity at the i-th prediction time point based on the expected longitudinal acceleration at the i-th prediction time point and the predicted longitudinal velocity at the (i-1)-th prediction time point, and then jump to step 402, where N is the total number of prediction time points in the prediction time domain.

[0071] In some exemplary embodiments, the above calculation of the predicted longitudinal velocity V at the i-th prediction time... i The calculation formula is as follows:

[0072]

[0073] Where, in the formula, a r This represents the expected acceleration at the r-th prediction time point, where r ranges from 1 to i, and v in the formula... cur This represents the current longitudinal velocity, where t in the formula represents the time interval between prediction time points.

[0074] For example, when the time interval t between prediction time points is 1 second, the formula for calculating the predicted longitudinal velocity at the i-th prediction time can be expressed as:

[0075]

[0076] Here, the predicted longitudinal speed at the i-th prediction time refers to the longitudinal speed obtained by the vehicle when it travels at the expected longitudinal speed corresponding to the previous i prediction time points, at the current longitudinal speed.

[0077] It is understandable that if i is greater than N, the process ends directly.

[0078] In some embodiments of this disclosure, in order to accurately determine the longitudinal control quantity sequence in the prediction time domain, one possible implementation of step 104 is as follows: Figure 5 As shown, it may include:

[0079] Step 501: Determine the longitudinal vehicle state parameters of the vehicle at the current moment, and determine the initial longitudinal control quantities of the vehicle at each predicted time point.

[0080] In some exemplary embodiments, the initial longitudinal control parameters of the vehicle at each predicted time point can be determined based on the vehicle's longitudinal vehicle state parameters at the current moment.

[0081] In some other exemplary implementations, an initial longitudinal control quantity pre-set for the vehicle at each predicted time point can be obtained.

[0082] It is understood that the initial longitudinal control values ​​at each prediction time point may be the same, different, or partially the same. This embodiment does not impose specific limitations on this, and the actual situation shall prevail.

[0083] Step 502: Determine the predicted longitudinal vehicle state parameters at each predicted time point based on the longitudinal vehicle state parameters, the initial longitudinal control variables at each predicted time point, and the longitudinal model.

[0084] In some exemplary implementations, one possible way to determine the predicted longitudinal vehicle state parameters at each prediction time point based on the longitudinal vehicle state parameters, the initial longitudinal control quantity at each prediction time point, and the longitudinal model is as follows: For the i-th prediction time point, based on the longitudinal model, using the initial longitudinal control quantity at the i-th prediction time point and the current longitudinal vehicle state parameters, determine the predicted longitudinal vehicle state parameters at the i-th prediction time point, where the initial value of i is 1; increment i by 1; if i is less than or equal to N, determine the predicted longitudinal vehicle state parameters at the i-th prediction time point based on the expected longitudinal acceleration at the i-th prediction time point and the predicted longitudinal vehicle state parameters at the (i-1)-th prediction time point, and jump to the step of incrementing i by 1, where N is the total number of prediction time points in the prediction time domain.

[0085] Step 503: Construct an objective function based on the predicted longitudinal vehicle state parameters at each prediction time point, the expected longitudinal vehicle state parameters at each prediction time point in the expected trajectory, and the longitudinal control parameter information.

[0086] The formula for the objective function J is shown below:

[0087]

[0088] Where, Y in the formula i Y represents the predicted longitudinal vehicle state parameter at the i-th prediction time point; ri Q represents the expected longitudinal vehicle state parameter at the i-th prediction time point; i U represents the first penalty weight corresponding to the state variable error at the i-th prediction time point; i ΔU represents the initial longitudinal control quantity at the i-th prediction time point; i R1 represents the control increment at the i-th prediction time point; R2 represents the second penalty weight; R3 represents the third penalty weight; T represents the transpose; N represents the total number of prediction time points in the prediction time domain.

[0089] Step 504: Adjust the initial longitudinal control quantity at each prediction time point according to the value of the objective function to obtain the longitudinal control quantity at each prediction time point.

[0090] In other words, after determining the objective function, the optimal solution of the objective function can be obtained through rolling optimization to obtain the longitudinal control quantity at each prediction time point.

[0091] Step 505: Determine the sequence of longitudinal control quantities based on the longitudinal control quantities at each predicted time point.

[0092] In one embodiment of this disclosure, after obtaining the longitudinal control quantities at each prediction time point, the longitudinal control quantities can be sorted according to the chronological order of the prediction time points to obtain a longitudinal control quantity sequence.

[0093] To implement the above embodiments, this disclosure also provides a longitudinal control device for a vehicle.

[0094] Figure 6 This is a schematic diagram according to the sixth embodiment of the present disclosure, which provides a longitudinal control device for a vehicle.

[0095] like Figure 6 As shown, the longitudinal control device 600 of the vehicle may include a first determining module 601, a second determining module 602, a third determining module 603, and a control module 604, wherein:

[0096] The first determining module 601 is used to determine the predicted longitudinal velocity sequence of the vehicle in the predicted time domain after the current moment, wherein the predicted longitudinal velocity sequence includes the predicted longitudinal velocity at each predicted time point.

[0097] The second determining module 602 is used to determine the longitudinal control parameter information of the vehicle's model predictive controller at each prediction time point based on the predicted longitudinal speed at that prediction time point.

[0098] The third determining module 603 is used to determine the longitudinal control quantity sequence in the prediction time domain based on the longitudinal control parameter information, the longitudinal model in the model predictive controller, and the vehicle's expected trajectory. The longitudinal control quantity sequence includes the longitudinal control quantity at each prediction time point.

[0099] The control module 604 is used to perform longitudinal control of the vehicle for autonomous driving based on the longitudinal control quantity at the first prediction time point in the prediction time domain.

[0100] The longitudinal control method for a vehicle according to embodiments of this disclosure, when performing longitudinal control of an autonomous vehicle, determines the predicted longitudinal control parameters of the vehicle's model predictive controller at each predicted time point within the prediction time domain, based on the predicted longitudinal speed of the vehicle at each predicted time point after the current moment. Then, by combining the longitudinal control parameter information, the longitudinal model in the model predictive controller, and the vehicle's desired trajectory, the longitudinal control quantity at each predicted time point within the prediction time domain is determined. Finally, based on the longitudinal control quantity at the first predicted time point within the prediction time domain, longitudinal control of the vehicle is performed. Therefore, by combining the predicted longitudinal speed at each predicted time point within the prediction time domain, the longitudinal control quantity for longitudinal control of the vehicle is accurately determined, improving the accuracy and stability of the vehicle's longitudinal control, thereby enhancing the safety of autonomous driving.

[0101] In one embodiment of this disclosure, such as Figure 7 As shown, the longitudinal control device 700 of the vehicle may include: a first determining module 701, a second determining module 702, a third determining module 703 and a control module 704, wherein the first determining module 701 may include: a first acquiring unit 7011, a second acquiring unit 7012 and a determining unit 7013.

[0102] It should be noted that a detailed description of the control module 704 can be found above. Figure 6 The description of the control module 604 is omitted here.

[0103] In one embodiment of this disclosure, the second determining module 702 is specifically configured to: determine a first penalty weight for the state quantity error of the vehicle's model predictive controller at the prediction time point based on the predicted longitudinal velocity at the prediction time point; obtain a second penalty weight pre-set for the longitudinal control quantity at the prediction time point, wherein the second penalty weight is the same at different prediction time points; obtain a third penalty weight pre-set for the control quantity increment at the prediction time point, wherein the third penalty weight is the same at different prediction time points; and generate longitudinal control parameter information of the vehicle's model predictive controller at the prediction time point based on the first penalty weight, the second penalty weight, and the third penalty weight.

[0104] In one embodiment of this disclosure, when the predicted longitudinal velocity at the prediction time point is greater than or equal to zero, the penalty weight of the state variable error at the prediction time point is greater than zero; when the predicted longitudinal velocity at the prediction time point is less than zero, the penalty weight of the state variable error at the prediction time point is equal to zero.

[0105] In one embodiment of this disclosure, the first determining module 701 includes:

[0106] The first acquisition unit 7011 is used to acquire the current longitudinal speed of the vehicle at the current moment.

[0107] The second acquisition unit 7012 is used to acquire the expected longitudinal acceleration sequence of the vehicle in the prediction time domain, wherein the expected longitudinal acceleration sequence includes the expected longitudinal acceleration at each prediction time point.

[0108] Determining unit 7013 is used to determine the predicted longitudinal velocity sequence of the vehicle in the prediction time domain based on the current longitudinal velocity and the desired longitudinal acceleration sequence.

[0109] In one embodiment of this disclosure, the determining unit 7013 is specifically configured to: for the i-th prediction time point, determine the predicted longitudinal velocity at the i-th prediction time point based on the expected longitudinal acceleration and the current longitudinal velocity at the i-th prediction time point, wherein the initial value of i is 1; increment i by 1; if i is less than or equal to N, determine the predicted longitudinal velocity at the i-th prediction time point based on the expected longitudinal acceleration and the predicted longitudinal velocity at the (i-1)-th prediction time point, and proceed to the step of incrementing i by 1, wherein N is the total number of prediction time points in the prediction time domain.

[0110] In one embodiment of this disclosure, the third determining module 703 is specifically used for: determining the longitudinal vehicle state parameters of the vehicle at the current moment, and determining the initial longitudinal control quantity of the vehicle at each predicted time point; determining the predicted longitudinal vehicle state parameters at each predicted time point based on the longitudinal vehicle state parameters, the initial longitudinal control quantity at each predicted time point, and the longitudinal model; constructing an objective function based on the predicted longitudinal vehicle state parameters at each predicted time point, the expected longitudinal vehicle state parameters at each predicted time point in the expected trajectory, and the longitudinal control parameter information; adjusting the initial longitudinal control quantity at each predicted time point based on the value of the objective function to obtain the longitudinal control quantity at each predicted time point; and determining the longitudinal control quantity sequence based on the longitudinal control quantity at each predicted time point.

[0111] It should be noted that the above explanation of the longitudinal control method for vehicles also applies to the longitudinal control device of the vehicle in this embodiment, and this embodiment will not repeat the above.

[0112] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0113] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0114] like Figure 8As shown, the electronic device 800 may include a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. The RAM 803 may also store various programs and data required for the operation of the device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0115] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0116] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the longitudinal control method for a vehicle. For example, in some embodiments, the longitudinal control method for a vehicle may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the longitudinal control method for a vehicle described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the longitudinal control method for a vehicle by any other suitable means (e.g., by means of firmware).

[0117] Various embodiments of the apparatuses and techniques described above herein can be implemented in digital electronic circuit devices, integrated circuit devices, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), device-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable device including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage device, at least one input device, and at least one output device, and transmitting data and instructions to the storage device, the at least one input device, and the at least one output device.

[0118] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0119] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution apparatus, device, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor device, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0120] To provide interaction with a user, the apparatus and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of apparatus can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0121] The apparatus and techniques described herein can be implemented in computing devices that include backend components (e.g., as a data server), or computing devices that include middleware components (e.g., an application server), or computing devices that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the apparatus and techniques described herein), or computing devices that include any combination of such backend, middleware, or frontend components. The components of the apparatus can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0122] Computer devices can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system, addressing the shortcomings of traditional physical hosts and VPS services ("Virtual Private Server," or simply "VPS") in terms of management difficulty and weak business scalability. A server can be a cloud server, a distributed server, or a server incorporating blockchain technology.

[0123] In one embodiment of this disclosure, an autonomous vehicle is also provided, including... Figure 8 The exemplary electronic device.

[0124] It should be noted that the electronic device is used to execute the longitudinal control method of the vehicle according to the embodiments of this disclosure. It should be understood that the various processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and no limitation is imposed herein.

[0125] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for longitudinal control of a vehicle, comprising: Determine the predicted longitudinal velocity sequence of the vehicle in the predicted time domain after the current time, wherein the predicted longitudinal velocity sequence includes: the predicted longitudinal velocity at each predicted time point; For each of the predicted time points, the longitudinal control parameter information of the vehicle's model predictive controller at the predicted time point is determined based on the predicted longitudinal velocity at the predicted time point. Based on the longitudinal control parameter information, the longitudinal model in the model predictive controller, and the vehicle's desired trajectory, the longitudinal control quantity sequence in the prediction time domain is determined, wherein the longitudinal control quantity sequence includes: the longitudinal control quantity at each prediction time point; Based on the longitudinal control quantity at the first predicted time point within the predicted time domain, the vehicle is subjected to longitudinal control for autonomous driving. The step of determining the longitudinal control quantity sequence in the prediction time domain based on the longitudinal control parameter information, the longitudinal model in the model predictive controller, and the vehicle's desired trajectory includes: Determine the longitudinal vehicle state parameters of the vehicle at the current time, and determine the initial longitudinal control quantity of the vehicle at each of the predicted time points; Based on the longitudinal vehicle state parameters, the initial longitudinal control quantity at each of the prediction time points, and the longitudinal model, the predicted longitudinal vehicle state parameters at each of the prediction time points are determined. Based on the predicted longitudinal vehicle state parameters at each predicted time point, the expected longitudinal vehicle state parameters at each predicted time point in the expected trajectory, and the longitudinal control parameter information, an objective function is constructed. Based on the value of the objective function, the initial longitudinal control quantity at each of the prediction time points is adjusted to obtain the longitudinal control quantity at each of the prediction time points. The longitudinal control quantity sequence is determined based on the longitudinal control quantity at each of the predicted time points.

2. The method according to claim 1, wherein, The step of determining the longitudinal control parameter information of the vehicle's model predictive controller at the predicted longitudinal velocity at the predicted time point includes: Based on the predicted longitudinal velocity at the predicted time point, determine the first penalty weight of the state quantity error of the vehicle's model predictive controller at the predicted time point; Obtain a second penalty weight pre-set for the longitudinal control quantity at the predicted time point, wherein the second penalty weight is the same at different predicted time points; Obtain the third penalty weight that is pre-set for the control quantity increment at the predicted time point, wherein the third penalty weight is the same at different predicted time points; Based on the first penalty weight, the second penalty weight, and the third penalty weight, the longitudinal control parameter information of the vehicle's model predictive controller at the prediction time point is generated; wherein, when the predicted longitudinal velocity at the prediction time point is greater than or equal to zero, the penalty weight of the state variable error at the prediction time point is greater than zero, and when the predicted longitudinal velocity at the prediction time point is less than zero, the penalty weight of the state variable error at the prediction time point is equal to zero.

3. The method according to claim 1, wherein, Determining the predicted longitudinal velocity sequence of the vehicle in the predicted time domain after the current moment includes: Obtain the current longitudinal speed of the vehicle at the current moment; Obtain the desired longitudinal acceleration sequence of the vehicle in the prediction time domain, wherein the desired longitudinal acceleration sequence includes: the desired longitudinal acceleration at each of the prediction time points; Based on the current longitudinal velocity and the expected longitudinal acceleration sequence, the predicted longitudinal velocity sequence of the vehicle in the prediction time domain is determined; Wherein, determining the predicted longitudinal velocity sequence of the vehicle in the prediction time domain based on the current longitudinal velocity and the expected longitudinal acceleration sequence includes: For the i-th prediction time point, the predicted longitudinal velocity at the i-th prediction time point is determined based on the expected longitudinal acceleration at the i-th prediction time point and the current longitudinal velocity, where the initial value of i is 1; Increment i by 1; When i is less than or equal to N, the predicted longitudinal velocity at the i-th prediction time point is determined based on the expected longitudinal acceleration at the i-th prediction time point and the predicted longitudinal velocity at the (i-1)-th prediction time point. Proceed to the step of incrementing i by 1, and repeat the step of determining the predicted longitudinal velocity at the i-th prediction time point based on the expected longitudinal acceleration at the i-th prediction time point and the predicted longitudinal velocity at the (i-1)-th prediction time point when i is less than or equal to N, until i is greater than N, where N is the total number of prediction time points in the prediction time domain.

4. A longitudinal control device for a vehicle, comprising: The first determining module is used to determine the predicted longitudinal velocity sequence of the vehicle in the predicted time domain after the current time, wherein the predicted longitudinal velocity sequence includes: the predicted longitudinal velocity at each predicted time point; The second determining module is used to determine the longitudinal control parameter information of the vehicle's model predictive controller at each predicted time point based on the predicted longitudinal speed at the predicted time point. The third determining module is used to determine the longitudinal control quantity sequence in the prediction time domain based on the longitudinal control parameter information, the longitudinal model in the model prediction controller, and the vehicle's expected trajectory, wherein the longitudinal control quantity sequence includes: the longitudinal control quantity at each prediction time point; The control module is used to perform longitudinal control of the vehicle for autonomous driving based on the longitudinal control quantity at the first prediction time point in the prediction time domain. The third determining module is specifically used for: Determine the longitudinal vehicle state parameters of the vehicle at the current time, and determine the initial longitudinal control quantity of the vehicle at each of the predicted time points; Based on the longitudinal vehicle state parameters, the initial longitudinal control quantity at each of the prediction time points, and the longitudinal model, the predicted longitudinal vehicle state parameters at each of the prediction time points are determined. Based on the predicted longitudinal vehicle state parameters at each predicted time point, the expected longitudinal vehicle state parameters at each predicted time point in the expected trajectory, and the longitudinal control parameter information, an objective function is constructed. Based on the value of the objective function, the initial longitudinal control quantity at each of the prediction time points is adjusted to obtain the longitudinal control quantity at each of the prediction time points. The longitudinal control quantity sequence is determined based on the longitudinal control quantity at each of the predicted time points.

5. The apparatus according to claim 4, wherein, The second determining module is specifically used for: Based on the predicted longitudinal velocity at the predicted time point, determine the first penalty weight of the state quantity error of the vehicle's model predictive controller at the predicted time point; Obtain a second penalty weight pre-set for the longitudinal control quantity at the predicted time point, wherein the second penalty weight is the same at different predicted time points; Obtain the third penalty weight that is pre-set for the control quantity increment at the predicted time point, wherein the third penalty weight is the same at different predicted time points; Based on the first penalty weight, the second penalty weight, and the third penalty weight, the longitudinal control parameter information of the vehicle's model predictive controller at the prediction time point is generated; Wherein, if the predicted longitudinal velocity at the prediction time point is greater than or equal to zero, the penalty weight of the state variable error at the prediction time point is greater than zero; if the predicted longitudinal velocity at the prediction time point is less than zero, the penalty weight of the state variable error at the prediction time point is equal to zero.

6. The apparatus according to claim 4, wherein, The first determining module includes: The first acquisition unit is used to acquire the current longitudinal speed of the vehicle at the current moment; The second acquisition unit is used to acquire the expected longitudinal acceleration sequence of the vehicle in the prediction time domain, wherein the expected longitudinal acceleration sequence includes: the expected longitudinal acceleration at each of the prediction time points; A determining unit is configured to determine a predicted longitudinal velocity sequence of the vehicle in the prediction time domain based on the current longitudinal velocity and the desired longitudinal acceleration sequence; The determining unit is specifically used for: For the i-th prediction time point, the predicted longitudinal velocity at the i-th prediction time point is determined based on the expected longitudinal acceleration at the i-th prediction time point and the current longitudinal velocity, where the initial value of i is 1; Increment i by 1; If i is less than or equal to N, the predicted longitudinal velocity at the i-th prediction time point is determined based on the expected longitudinal acceleration at the i-th prediction time point and the predicted longitudinal velocity at the (i-1)-th prediction time point; then proceed to the step of incrementing i by 1, and repeat the step of determining the predicted longitudinal velocity at the i-th prediction time point based on the expected longitudinal acceleration at the i-th prediction time point and the predicted longitudinal velocity at the (i-1)-th prediction time point when i is less than or equal to N, until i is greater than N, where N is the total number of prediction time points in the prediction time domain.

7. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-3.

9. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-3.

10. An autonomous vehicle, comprising: The electronic device as claimed in claim 7.

Images