Longitudinal motion control method and device for a vehicle

Abstract

The application relates to the technical field of intelligent driving, in particular to a longitudinal motion control method and device for a vehicle, wherein the method comprises the following steps: in the case that it is detected that the vehicle enters a longitudinal motion control working condition, obtaining a desired driving route of the vehicle, confirming at least one dynamic comfort index parameter of the vehicle at a current time, obtaining a target speed change amount from the at least one dynamic comfort index parameter based on a performance index function of a preset single neuron network, and generating a desired longitudinal speed of the vehicle according to the target speed change amount, and controlling the vehicle to perform longitudinal motion by using the desired longitudinal speed. According to the application, the expected speed under the ideal position is output from the single neuron network based on the dynamic comfort index parameter of the vehicle and the vehicle ride comfort evaluation index function, so that the dependence of the longitudinal control on the vehicle dynamics model is reduced, the robustness and adaptability of the vehicle longitudinal speed motion control system are improved, and the vehicle longitudinal speed motion control system is more accurate.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, and in particular to a longitudinal motion control method and device for a vehicle. BACKGROUND

[0002] With the development of vehicle technology, the research direction of intelligent driving technology gradually enriches, and the automatic control of vehicle speed under high-speed driving conditions is an important content of intelligent driving vehicle research. As one of the automatic controls, longitudinal motion control can achieve tracking of the expected speed through joint control of driving and braking.

[0003] In related technologies, the longitudinal motion control of the vehicle can be achieved through optimal control theory, or the longitudinal speed of the vehicle is obtained based on a neural network algorithm to control the longitudinal motion of the vehicle, so as to ensure the accuracy of the longitudinal control.

[0004] However, in related technologies, due to the non-steady-state non-linear characteristics of tire mechanics under high-speed driving conditions of the vehicle, the vehicle chassis speed control established by the optimal control theory is only applicable to lower vehicle speeds, and it is difficult to meet the comprehensive needs of vehicle driving. The calculation of the longitudinal speed depends on the construction of the vehicle dynamics model, which increases the calculation complexity in the longitudinal motion control process, and the efficiency of the longitudinal control is insufficient, which needs to be solved urgently. SUMMARY

[0005] The present application provides a longitudinal motion control method and device for a vehicle to solve the problems in related technologies that due to the non-steady-state non-linear characteristics of tire mechanics under high-speed driving conditions of the vehicle, the vehicle chassis speed control established by the optimal control theory is only applicable to lower vehicle speeds, and it is difficult to meet the comprehensive needs of vehicle driving. The calculation of the longitudinal speed depends on the construction of the vehicle dynamics model, which increases the calculation complexity in the longitudinal motion control process, and the efficiency of the longitudinal control is insufficient.

[0006] The first aspect embodiment of the present application provides a longitudinal motion control method for a vehicle, comprising the following steps: in the case of detecting that the vehicle enters a longitudinal motion control condition, obtaining an expected driving route of the vehicle; based on the expected driving route, confirming at least one dynamic comfort index parameter of the vehicle at the current time; based on a performance index function of a preset single neuron network, obtaining a target speed change amount from the at least one dynamic comfort index parameter, and generating an expected speed longitudinal speed of the vehicle according to the target speed change amount, to control the vehicle to perform longitudinal motion by using the expected speed longitudinal speed.

[0007] By the technical solution, the expected speed in the ideal position can be output by the single neuron network based on the power comfort index parameter of the vehicle and the vehicle ride comfort evaluation index function, thereby reducing the dependence of the longitudinal control on the vehicle dynamics model, improving the robustness and adaptability of the vehicle longitudinal speed motion control system, and being more accurate.

[0008] Optionally, in an embodiment of the present application, the at least one power comfort index parameter of the vehicle at the current time is confirmed based on the expected driving route, including: generating an ideal longitudinal acceleration of the vehicle at the current time according to the expected driving route; calculating a current deviation of the ideal longitudinal acceleration and an actual longitudinal acceleration at the current time, and obtaining a speed change increment of the current time relative to a previous time.

[0009] By the technical solution, the power comfort index parameter of the vehicle at the current time can be obtained from the current deviation of the ideal longitudinal acceleration and the actual longitudinal acceleration at the current time, and the speed change increment of the current time relative to the previous time, thereby optimizing the comfort of the longitudinal control of the vehicle at the current time and improving the user experience.

[0010] Optionally, in an embodiment of the present application, after the vehicle is controlled to move longitudinally by using the expected speed, the method further includes: based on the target loss function, correcting the current connection weight value of the preset single neuron network in a target decreasing direction of the performance index function to obtain a corrected connection weight value; and based on the corrected connection weight value, iteratively updating the preset single neuron network to calculate a target speed change amount at a next time by using the updated preset single neuron network.

[0011] By the technical solution, the preset single neuron network can be updated, and the current power comfort index parameter can be input by using the updated single neuron network to calculate the target speed change amount at the next time in real time, and the output is closer to the actual demand by iteratively updating the network weight, thereby improving the calculation accuracy of the longitudinal speed.

[0012] Optionally, in an embodiment of the present application, the performance index function based on the preset single neuron network obtains a target speed change amount from the at least one power comfort index parameter, including: obtaining all input quantity components of the preset single neuron network based on the at least one power comfort index parameter; respectively obtaining learning rates of the all input quantity components, and calculating the target speed change amount based on the learning rates, the neuron proportion coefficient, and the all input quantity components.

[0013] By the technical solution, all input components of the preset single neuron network can be obtained based on at least one power comfort index parameter, learning rates of all input components are respectively obtained, a target speed change amount is calculated based on the learning rates, a neuron proportion coefficient and all input components, and the single neuron network can quickly process input data and output a control instruction, so that the vehicle can quickly respond to the demand for longitudinal motion control.

[0014] Optionally, in an embodiment of the present application, the generating the expected longitudinal speed of the vehicle according to the target speed change amount to control the vehicle to perform longitudinal motion by using the expected longitudinal speed includes: obtaining a historical expected longitudinal speed of the vehicle at a previous time and an expected position at a next time; obtaining the expected longitudinal speed according to the historical expected longitudinal speed and the target speed change amount, generating a related state variable of the vehicle based on the expected position and the expected longitudinal speed, and controlling the vehicle to move to the expected position by using the expected longitudinal speed and the related state variable.

[0015] By the technical solution, the historical expected longitudinal speed of the vehicle at a previous time and the expected position at a next time can be obtained, the expected longitudinal speed can be obtained according to the historical expected longitudinal speed and the target speed change amount, the related state variable of the vehicle can be generated based on the expected position and the expected longitudinal speed, and the vehicle can be controlled to move to the expected position by using the expected longitudinal speed and the related state variable. By accurately calculating the expected longitudinal speed and the related state variable, more smooth acceleration and deceleration can be realized, and the comfort of passengers can be improved.

[0016] The second aspect embodiment of the present application provides a longitudinal motion control device of a vehicle, including: an obtaining module, configured to obtain an expected driving route of the vehicle when it is detected that the vehicle enters a longitudinal motion control working condition; a confirming module, configured to confirm at least one power comfort index parameter of the vehicle at a current time based on the expected driving route; and a control module, configured to obtain a target speed change amount from the at least one power comfort index parameter based on a performance index function of a preset single neuron network, and generate an expected longitudinal speed of the vehicle according to the target speed change amount, so as to control the vehicle to perform longitudinal motion by using the expected longitudinal speed.

[0017] Optionally, in an embodiment of the present application, the confirming module includes: a generating unit, configured to generate an ideal longitudinal acceleration of the vehicle at the current time according to the expected driving route; and a first calculating unit, configured to calculate a current deviation of the ideal longitudinal acceleration and an actual longitudinal acceleration at the current time, and obtain a speed change increment of the current time relative to a previous time.

[0018] Optionally, in an embodiment of the present application, the device further comprises a correction module configured to correct the current connection weight value of the preset single neuron network in a target decreasing direction of the performance index function based on the target loss function after the vehicle is controlled to move longitudinally by using the expected longitudinal speed, to obtain a corrected connection weight value; and an update module configured to update the preset single neuron network iteratively based on the corrected connection weight value, so as to calculate the target speed variation at the next time by using the updated preset single neuron network.

[0019] Optionally, in an embodiment of the present application, the control module comprises a confirmation unit configured to obtain all input components of the preset single neuron network based on the at least one power comfort index parameter; and a second calculation unit configured to obtain a learning rate of each of the input components, and calculate the target speed variation based on the learning rate, the neuron proportion coefficient and the input components.

[0020] Optionally, in an embodiment of the present application, the control module comprises an acquisition unit configured to acquire a historical expected longitudinal speed of the vehicle at the last time and an expected position at the next time; and a control unit configured to obtain the expected longitudinal speed according to the historical expected longitudinal speed and the target speed variation, generate a related state variable of the vehicle based on the expected position and the expected longitudinal speed, and control the vehicle to move to the expected position by using the expected longitudinal speed and the related state variable.

[0021] An embodiment of the third aspect of the present application provides a vehicle, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the longitudinal motion control method of the vehicle as described in the above embodiments.

[0022] An embodiment of the fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, wherein the program is executed by a processor to implement the longitudinal motion control method of the vehicle as described above.

[0023] An embodiment of the fifth aspect of the present application provides a computer program, which is executed to implement the longitudinal motion control method of the vehicle as described above.

[0024] The embodiment of the present application can output the expected speed in the ideal position based on the power comfort index parameter of the vehicle and the vehicle ride comfort evaluation index function, thereby reducing the dependence of the longitudinal control on the vehicle dynamics model, improving the robustness and adaptability of the vehicle longitudinal speed motion control system, and being more accurate. Thus, the problems in the related art that the optimal control theory established by the vehicle chassis speed control is only applicable to low vehicle speed and is difficult to meet the overall demand of vehicle driving due to the non-steady and nonlinear characteristics of tire mechanics under high-speed driving conditions of the automobile, the calculation of the longitudinal speed depends on the construction of the vehicle dynamics model, the calculation complexity in the longitudinal motion control process is increased, and the efficiency of the longitudinal control is insufficient are solved.

[0025] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0026] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which:

[0027] Figure 1 A flowchart of a vehicle longitudinal motion control method according to an embodiment of the present application;

[0028] Figure 2 A vehicle speed control logic diagram of a single neuron network of an embodiment of the present application;

[0029] Figure 3 A structural diagram of a vehicle longitudinal motion control device according to an embodiment of the present application;

[0030] Figure 4 A structural diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] The embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, in which the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application.

[0032] A method and device for longitudinal motion control of a vehicle are described below with reference to the accompanying drawings. In the related art mentioned in the background, due to the non-steady and non-linear characteristics of tire mechanics under high-speed driving conditions of a vehicle, the vehicle chassis speed control established by optimal control theory is only applicable to low vehicle speeds and cannot meet the overall demand for vehicle driving. The calculation of longitudinal speed relies on the construction of a vehicle dynamics model, which increases the computational complexity in the longitudinal motion control process and results in insufficient efficiency of longitudinal control. The present application provides a method for longitudinal motion control of a vehicle, in which the desired speed under ideal conditions can be output by a single neuron network based on a dynamic comfort index parameter of the vehicle and a vehicle ride comfort evaluation index function, thereby reducing the dependence of longitudinal control on the vehicle dynamics model, improving the robustness and adaptability of the vehicle longitudinal speed motion control system, and making it more accurate. Thus, the problems of insufficient efficiency of longitudinal control due to the non-steady and non-linear characteristics of tire mechanics under high-speed driving conditions of a vehicle, the vehicle chassis speed control established by optimal control theory being only applicable to low vehicle speeds and being difficult to meet the overall demand for vehicle driving, and the calculation of longitudinal speed relying on the construction of a vehicle dynamics model, which increases the computational complexity in the longitudinal motion control process, are solved.

[0033] Specifically, Figure 1 A flowchart of a method for longitudinal motion control of a vehicle is provided in the embodiments of the present application.

[0034] As Figure 1 shown, the method for longitudinal motion control of a vehicle includes the following steps:

[0035] In step S101, upon detection that the vehicle enters a longitudinal motion control condition, the desired driving route of the vehicle is obtained.

[0036] It can be understood that in the embodiments of the present application, the vehicle can enter the longitudinal motion control condition after obtaining the longitudinal control instruction of the vehicle, such as the instruction to enter adaptive cruise control, and the desired driving route of the vehicle can be obtained according to the current position, destination and environmental model of the vehicle. Specifically, the vehicle can be set to travel in a straight line, and the control of the driver on the ideal expected driving trajectory of the vehicle is the control of the expected longitudinal speed of the vehicle. The driving speed of the vehicle is controlled according to the different target speeds required at each place on the desired driving route to achieve ideal longitudinal speed decision and follow-up control, and the change of speed corresponds to the longitudinal acceleration.

[0037] In step S102, at least one dynamic comfort index parameter of the vehicle at the current time is confirmed based on the desired driving route.

[0038] It can be understood that in the embodiments of the present application, the power comfort index parameter can be a performance index reflecting the comfort of the driver, which can be obtained by collecting the dynamic data of the vehicle in real time through vehicle-mounted sensors such as an accelerometer, a gyroscope, a vehicle speed sensor, etc., based on the expected driving route to obtain the power comfort index parameter.

[0039] Optionally, in an embodiment of the present application, based on the expected driving route, the at least one power comfort index parameter of the vehicle at the current time is confirmed, including: generating the ideal longitudinal acceleration of the vehicle at the current time according to the expected driving route; calculating the current deviation of the ideal longitudinal acceleration and the actual longitudinal acceleration at the current time, and obtaining the speed change increment of the current time relative to the last time.

[0040] In actual execution process, the error of the ideal longitudinal acceleration and the actual longitudinal acceleration at the current time and the speed change increment can be used as the performance index reflecting the comfort of the driver. The ideal longitudinal acceleration of the vehicle at the current time for the expected position is calculated by combining the expected driving route and the current traffic condition, the actual longitudinal acceleration of the vehicle is collected in real time by the vehicle-mounted sensor (such as a vehicle speed sensor, an accelerometer, etc.), the acceleration deviation at the current time is calculated, and the current speed change increment can be the speed increment to be executed at the current time relative to the last time, and its expression can be:

[0041]

[0042]

[0043] wherein J1 is the current deviation, J2 is the speed change increment, and is the expected longitudinal acceleration and the actual longitudinal acceleration of the vehicle at k time, v o (k) and v o (k-1) are the speeds of the vehicle at k and k-1 time.

[0044] The power comfort index parameter of the vehicle at the current time can be obtained from the current deviation of the ideal longitudinal acceleration and the actual longitudinal acceleration at the current time, and the speed change increment of the current time relative to the last time, so as to optimize the comfort of the longitudinal control of the vehicle at the current time, and improve the user experience.

[0045] In step S103, based on the performance index function of the preset single neuron network, the target speed change amount is obtained from the at least one power comfort index parameter, and the expected longitudinal speed of the vehicle is generated according to the target speed change amount, so as to control the vehicle to move longitudinally by using the expected longitudinal speed.

[0046] It should be noted that the preset single neuron network can be set by those skilled in the art according to actual conditions, and is not specifically limited here.

[0047] It can be understood that in the embodiments of the present application, the expression of the performance index function of the preset single neuron network can be:

[0048]

[0049] wherein J1 is the current deviation, J2 is the speed change increment, and are the expected longitudinal acceleration and the actual longitudinal acceleration of the vehicle at time k, v o (k) and v o (k-1) are the speeds of the vehicle at times k and k-1. The power comfort index parameter obtained in the above steps is input into the performance index function of the preset single neuron network, and the speed change amount at the current time is output, and the expected speed of the vehicle at the expected position is output according to the speed change amount, and the longitudinal speed of the vehicle is obtained according to the expected speed for longitudinal control.

[0050] Optionally, in one embodiment of the present application, after the vehicle is controlled to move longitudinally using the expected speed, it further comprises: based on the target loss function, correcting the current connection weight value of the preset single neuron network in the target reduction direction of the performance index function to obtain a corrected connection weight value; and iteratively updating the preset single neuron network based on the corrected connection weight value to calculate the target speed change amount at the next time using the updated preset single neuron network.

[0051] In actual execution process, the gradient descent method can be used to optimize the design of the established performance index function, so that the performance index function J tends to decrease, thereby realizing the correction of the connection weight value of the neuron. The gradient descent method is an iterative optimization algorithm for finding the minimum value of a certain performance index function, so that the connection weight value w i (k) of the neuron is corrected in the direction of decreasing the performance index function J, that is:

[0052]

[0053] wherein w i (k) is the connection weight value of the preset single neuron network at time k, Δw i (k-1) is the difference between the connection weight values of the preset single neuron network at times k and k-1. Specifically, the updating process can be represented as:

[0054]

[0055]

[0056]

[0057] wherein w P (k), w I (k), w D (k) are final connection weight values of the proportional component, the integral component and the differential component in the preset single neuron network at the kth moment, respectively, x P (k), x I (k), x D (k) are the proportional component, the integral component and the differential component at the kth moment, respectively, and are the expected longitudinal acceleration and the actual longitudinal acceleration of the vehicle at the kth moment, w′ P (k), w I ′(k), w′ D (k) are initial connection weight values of the proportional component, the integral component and the differential component in the preset single neuron network at the kth moment, T wx (k-1) is an intermediate quantity, η P , η I , η D are learning rates of the proportional component, the integral component and the differential component, respectively, P, Q, K are neuron proportionality coefficients, and b0 is an output response value of the control system at an initial state. The initial connection weight values are obtained according to the weight values at the previous moment, the final connection weight values are obtained according to the initial connection weight values, and the preset single neuron network is updated according to the final connection weight values, so as to obtain the current longitudinal speed of the vehicle.

[0058] The preset single neuron network can be updated, and the updated single neuron network is used to input the current power comfort index parameter, so as to calculate the target speed change amount at the next moment in real time. Through iterative updating of the network weight, the output is closer to the actual demand, and the calculation accuracy of the longitudinal speed is improved.

[0059] Optionally, in an embodiment of the present application, the target speed change amount is obtained from the at least one power comfort index parameter based on a performance index function of the preset single neuron network, including: obtaining all input components of the preset single neuron network based on the at least one power comfort index parameter; respectively obtaining learning rates of all input components, and calculating the target speed change amount based on the learning rates, neuron proportionality coefficients and all input components.

[0060] In actual execution, the current deviation and the current speed change increment can be input into the preset single neuron network to obtain the proportional component, the integral component and the differential component of the input, and the gain value of the output is obtained by calculating the learning rates and the neuron proportionality coefficients of the three components, respectively.

[0061] For example, as shown in FIG. 1, a vehicle speed control logic diagram of a single neuron network according to an embodiment of the present application is shown, in which the expected driving route is input into the longitudinal acceleration controller to obtain the ideal longitudinal acceleration, and the actual longitudinal acceleration is combined to obtain the proportional component X Figure 2 P , the integral component X I , and the differential component X D , which are then calculated and summed by their respective weight values W to obtain K as the gain value, △V as the calculated speed change, Z as the delay symbol for storing the expected speed value at the previous time, and V as the expected longitudinal speed.

[0062] The present application can obtain all input components of the preset single neuron network based on at least one power comfort index parameter, and obtain the learning rate of each input component. The target speed change is calculated based on the learning rate, the neuron proportion coefficient, and all input components. The single neuron network can quickly process input data and output control instructions, so that the vehicle can quickly respond to the demand for longitudinal motion control.

[0063] Optionally, in an embodiment of the present application, the expected longitudinal speed of the vehicle is generated according to the target speed change, so as to control the vehicle to move longitudinally by using the expected longitudinal speed, including: obtaining the historical expected longitudinal speed of the vehicle at the previous time and the expected position at the next time; obtaining the expected longitudinal speed according to the historical expected longitudinal speed and the target speed change, generating the related state variables of the vehicle based on the expected position and the expected longitudinal speed, and controlling the vehicle to move to the expected position by using the expected longitudinal speed and the related state variables.

[0064] In actual execution, the speed of the vehicle moving to the expected position can be expressed as:

[0065] v o (k) = v o (k-1) + K(w P (k) x P (k) + w I (k) x I (k) + w D (k) x D (k),

[0066] wherein v o (k-1) is the historical expected longitudinal speed at the previous time, v o (k) is the expected longitudinal speed at the current time, K is the neuron proportion coefficient, and the related state variables of the vehicle power system are generated based on the expected longitudinal speed, x P (k), x I (k), and x D (k).(k) are the proportional, integral and derivative components at k time, w P (k), w I (k), w D (k) are the final connection weight values corresponding to the proportional, integral and derivative components in the preset single neuron network at k time.

[0067] The application can obtain the historical expected longitudinal speed of the vehicle at the previous time and the expected position at the next time, obtain the expected longitudinal speed according to the historical expected longitudinal speed and the target speed change, generate the related state variables of the vehicle based on the expected position and the expected longitudinal speed, control the vehicle motion to the expected position based on the expected longitudinal speed and the related state variables, and through the accurate calculation of the expected longitudinal speed and the related state variables, more smooth acceleration and deceleration can be realized, and the comfort of passengers can be improved.

[0068] According to the vehicle longitudinal motion control method provided by the embodiment of the application, the expected speed under the ideal position can be output by the single neuron network based on the dynamic comfort index parameter of the vehicle and the vehicle ride comfort evaluation index function, thereby reducing the dependence of the longitudinal control on the vehicle dynamics model, improving the robustness and adaptability of the vehicle longitudinal speed motion control system, and being more accurate. Therefore, the problems in the related art that the tire mechanical property under the high-speed driving condition of the automobile is non-stable and nonlinear, the vehicle chassis speed control established by the optimal control theory is only applicable to a low vehicle speed, and it is difficult to meet the comprehensive demand of the automobile driving, the calculation of the longitudinal speed depends on the construction of the vehicle dynamics model, the calculation complexity in the longitudinal motion control process is increased, and the efficiency of the longitudinal control is insufficient are solved.

[0069] Secondly, the vehicle longitudinal motion control device according to the embodiment of the application is described with reference to the accompanying drawings.

[0070] Figure 3 is a structural schematic diagram of the vehicle longitudinal motion control device according to the embodiment of the application.

[0071] As Figure 3 shown, the vehicle longitudinal motion control device 10 includes an acquisition module 100, a confirmation module 200 and a control module 300.

[0072] The acquisition module 100 is configured to acquire the expected driving route of the vehicle when it is detected that the vehicle enters the longitudinal motion control condition.

[0073] The confirmation module 200 is configured to confirm at least one dynamic comfort index parameter of the vehicle at the current time based on the expected driving route.

[0074] The control module 300 is configured to obtain a target speed variation based on a performance index function of a preset single neuron network and at least one power comfort index parameter, and generate a desired longitudinal speed of the vehicle according to the target speed variation, so as to control the vehicle to move longitudinally by using the desired longitudinal speed.

[0075] Optionally, in an embodiment of the present application, the confirmation module 200 comprises a first calculation unit and a generation unit.

[0076] The generation unit is configured to generate a desired longitudinal acceleration of the vehicle at the current time according to the desired driving route.

[0077] The first calculation unit is configured to calculate a current deviation of the desired longitudinal acceleration and an actual longitudinal acceleration at the current time, and obtain a speed variation increment of the current time relative to a previous time.

[0078] Optionally, in an embodiment of the present application, the device 10 further comprises a correction module and an update module.

[0079] The correction module is configured to correct a current connection weight value of the preset single neuron network in a target reduction direction of the performance index function based on a target loss function after the vehicle is controlled to move longitudinally by using the desired longitudinal speed, so as to obtain a corrected connection weight value.

[0080] The update module is configured to iteratively update the preset single neuron network based on the corrected connection weight value, so as to calculate a target speed variation of a next time by using an updated preset single neuron network.

[0081] Optionally, in an embodiment of the present application, the control module 300 comprises a second calculation unit and a confirmation unit.

[0082] The confirmation unit is configured to obtain all input quantity components of the preset single neuron network based on the at least one power comfort index parameter.

[0083] The second calculation unit is configured to respectively obtain a learning rate of all the input quantity components, and calculate the target speed variation based on the learning rate, a neuron proportion coefficient and all the input quantity components.

[0084] Optionally, in an embodiment of the present application, the control module 300 comprises an acquisition unit and a control unit.

[0085] The acquisition unit is configured to acquire a historical desired longitudinal speed of the vehicle at a previous time and a desired position at a next time.

[0086] The control unit is configured to obtain a desired longitudinal speed according to a historical desired longitudinal speed and a target speed variation amount, generate a relevant state variable of the vehicle based on a desired position and the desired longitudinal speed, and control a movement of the vehicle to the desired position based on the desired longitudinal speed and the relevant state variable.

[0087] It should be noted that the above description of the embodiment of the vehicle longitudinal motion control method is also applicable to the vehicle longitudinal motion control device of the embodiment, which will not be described here.

[0088] The vehicle longitudinal motion control device provided by the embodiment of the present application can output the desired speed at the ideal position based on the single neuron network according to the power comfort index parameter of the vehicle and the vehicle ride comfort evaluation index function, thereby reducing the dependence of the longitudinal control on the vehicle dynamics model, improving the robustness and adaptability of the vehicle longitudinal speed motion control system, and being more accurate. Therefore, the problems in the related art that the optimal control theory established by the vehicle chassis speed control is only applicable to low vehicle speed due to the non-steady and nonlinear characteristics of the tire mechanics characteristics in the high-speed driving condition of the automobile, and the calculation of the longitudinal speed depends on the construction of the vehicle dynamics model, thereby increasing the calculation complexity in the longitudinal motion control process and causing the insufficient efficiency of the longitudinal control are solved.

[0089] Figure 4 The vehicle provided by the embodiment of the present application is shown in the structural schematic diagram. The vehicle can include:

[0090] The memory 401, the processor 402, and the computer program stored in the memory 401 and executable on the processor 402.

[0091] The processor 402 implements the vehicle longitudinal motion control method provided in the above embodiments when executing the program.

[0092] Further, the vehicle further includes:

[0093] The communication interface 403 is configured to communicate between the memory 401 and the processor 402.

[0094] The memory 401 is configured to store the computer program executable on the processor 402.

[0095] The memory 401 can include a high-speed RAM memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0096] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected with each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 4 Only one thick line is used to represent the bus in the figure, but it does not mean that there is only one bus or only one type of bus.

[0097] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can complete communication between each other through an internal interface.

[0098] The processor 402 can be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the present application.

[0099] The embodiment further provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the vehicle longitudinal motion control method.

[0100] The embodiment further provides a computer program. The computer program is executed to implement the vehicle longitudinal motion control method.

[0101] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0102] Furthermore, the terms "first", "second", etc. are used herein only to describe different instances, and do not imply or suggest relative importance or a number of the indicated technical features. Thus, the features defined with "first", "second" can include at least one of the features explicitly or implicitly. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise explicitly and specifically limited.

[0103] Any process or method descriptions or descriptions of the flow diagrams herein, or otherwise described herein, can be understood as representing the steps of a method implemented by a computer or a processor, or otherwise embodied in computer-readable or computer-usable code instructions, and the scope of the preferred embodiments of the present application includes additional implementation involving other computer-readable or computer-usable code instructions, where the order of the steps can be different, including substantially simultaneous execution of the steps or the steps in reverse order, as will be understood by those skilled in the art of the field of the embodiments of the present application.

[0104] The logic and / or steps represented in the flow diagrams, or otherwise described herein, for example, can be considered as a list of executable instructions for implementing the logic function, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor- based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or a combination of the above. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical apparatus), a portable computer diskette (magnetic apparatus), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber (optical apparatus), and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via the optical scan of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in the computer memory.

[0105] It should be understood that portions of the application can be realized with a combination of hardware, software, firmware, or their combination. In the above-described embodiments, the N steps or methods can be realized with software or firmware stored in a memory and executed by a suitable instruction execution system. As in another embodiment, if realized with hardware, any one or their combination of the following technologies known in the art can be used: discrete logic circuit with logic gate circuit for implementing logic functions on data signals, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA), etc.

[0106] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by a program instructing the relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0107] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0108] The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. A method of longitudinal motion control of a vehicle, characterized by, The method comprises the following steps: obtaining a desired driving route of the vehicle when it is detected that the vehicle enters a longitudinal motion control working condition; confirming at least one power comfort index parameter of the vehicle at a current time based on the desired driving route; obtaining a target speed change amount from the at least one power comfort index parameter based on a performance index function of a preset single neuron network, and generating a desired longitudinal speed of the vehicle according to the target speed change amount, so as to control the vehicle to move longitudinally by using the desired longitudinal speed; the performance index function of the preset single neuron network, the target speed change amount is obtained from the at least one power comfort index parameter, and comprises: obtaining all input components of the preset single neuron network based on the at least one power comfort index parameter; respectively obtaining learning rates of the all input components, and calculating the target speed change amount based on the learning rates, a neuron proportion coefficient and the all input components; the desired longitudinal speed of the vehicle is generated according to the target speed change amount, so as to control the vehicle to move longitudinally by using the desired longitudinal speed, and comprises: obtaining a historical desired longitudinal speed of the vehicle at a previous time and a desired position at a next time; obtaining the desired longitudinal speed according to the historical desired longitudinal speed and the target speed change amount, generating a related state variable of the vehicle based on the desired position and the desired longitudinal speed, and controlling the vehicle to move to the desired position according to the desired longitudinal speed and the related state variable.

2. The method of claim 1, wherein, the at least one power comfort index parameter of the vehicle at the current time is confirmed based on the desired driving route, and comprises: generating an ideal longitudinal acceleration of the vehicle at the current time according to the desired driving route; calculating a current deviation of the ideal longitudinal acceleration and an actual longitudinal acceleration at the current time, and obtaining a speed change increment of the current time relative to a previous time.

3. The method of claim 1, wherein, after the vehicle is controlled to move longitudinally by using the desired longitudinal speed, the method further comprises: based on a target loss function, correcting a current connection weight value of the preset single neuron network in a target reduction direction of the performance index function to obtain a corrected connection weight value; iteratively updating the preset single neuron network based on the corrected connection weight value, so as to calculate a target speed change amount at a next time by using an updated preset single neuron network.

4. A longitudinal motion control device for a vehicle, characterized by comprising: comprise: an obtaining module, configured to obtain a desired driving route of the vehicle when it is detected that the vehicle enters a longitudinal motion control working condition; a confirming module, configured to confirm at least one power comfort index parameter of the vehicle at a current time based on the desired driving route; a control module, configured to obtain a target speed change amount from the at least one power comfort index parameter based on a performance index function of a preset single neuron network, and generate a desired longitudinal speed of the vehicle according to the target speed change amount, so as to control the vehicle to move longitudinally by using the desired longitudinal speed; the control module comprises: The confirming unit is configured to obtain all input components of the preset single neuron network based on the at least one power comfort index parameter; The second calculating unit is configured to obtain learning rates of the all input components respectively, and calculate the target speed variation based on the learning rates, a neuron proportion coefficient and the all input components; The obtaining unit is configured to obtain a historical expected longitudinal speed of the vehicle at a previous time and an expected position at a next time; The control unit is configured to obtain the expected longitudinal speed according to the historical expected longitudinal speed and the target speed variation, generate relevant state variables of the vehicle based on the expected position and the expected longitudinal speed, and control the vehicle to move to the expected position based on the expected longitudinal speed and the relevant state variables.

5. The apparatus of claim 4, wherein, The confirming module comprises: The generating unit is configured to generate an ideal longitudinal acceleration of the vehicle at the current time according to the expected driving route; The first calculating unit is configured to calculate a current deviation of the ideal longitudinal acceleration and an actual longitudinal acceleration at the current time, and obtain a speed variation increment of the current time relative to a previous time.

6. A vehicle characterized by comprising: The computer program is stored in the memory and executable on the processor, and the processor executes the program to implement the longitudinal motion control method of the vehicle according to any one of claims 1-3. The program is executed by the processor to implement the longitudinal motion control method of the vehicle according to any one of claims 1-3.

7. A computer readable storage medium having stored thereon a computer program, characterized in that, ​

Images