A dynamic feedback intelligent driving vehicle speed precision control method and device
The dynamic feedback intelligent driving speed precision control method addresses the lack of real-time adaptation in traditional systems by constructing a model with iterative and nonlinear mapping strategies, achieving precise and adaptive vehicle speed control.
Patent Information
- Application Number
- CN202411361265.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-27
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-27
AI Technical Summary
Traditional vehicle speed control methods in intelligent driving systems lack real-time dynamic adjustment capabilities, making them inadequate for complex and changing road environments.
A dynamic feedback intelligent driving speed precision control method that constructs a model with an operating lever state space, control parameter space, and reward function, optimizing the strategy through iterative objective functions and nonlinear mapping relationships to adjust vehicle speed in real-time based on environmental feedback.
Enables precise and adaptive vehicle speed control by dynamically adjusting to changing road conditions, improving safety, efficiency, and reducing energy consumption.
Smart Images

Figure CN118876975B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of vehicle speed control, and in particular to a method and device for precise control of vehicle speed of intelligent driving with dynamic feedback. Background Art
[0002] With the rapid development of science and technology and the continuous advancement of intelligent technology, intelligent driving has become a key direction in the field of modern transportation. Intelligent driving can not only greatly improve the safety and convenience of driving, but also effectively reduce the occurrence of traffic accidents, optimize traffic flow, and reduce environmental pollution. In the intelligent driving system, vehicle speed control, as one of its core technologies, plays a vital role. Accurate vehicle speed control is not only related to the stability and safety of the vehicle, but also directly affects the efficiency and energy consumption of the traffic system. Traditional vehicle speed control methods mainly rely on preset control algorithms and fixed parameter adjustments, lack the ability of real-time dynamic adjustment, and are difficult to adapt to the complex and changeable actual road environment. Summary of the invention
[0003] In view of this, the present invention provides a dynamic feedback intelligent driving speed precision control method and device, which dynamically adjusts the control strategy by obtaining feedback information on the vehicle's driving environment and status in real time to better cope with complex road conditions and changing driving environments.
[0004] To achieve the above object, the present invention provides a dynamic feedback intelligent driving vehicle speed precision control method, comprising the following steps:
[0005] S1: Construct an intelligent driving vehicle speed precision control model, where the intelligent driving vehicle speed precision control model includes an operating lever state space, an operating lever control parameter space and a reward function;
[0006] S2: Optimize the strategy of the constructed intelligent driving vehicle speed precision control model to obtain the intelligent driving vehicle speed precision control strategy;
[0007] S3: construct a nonlinear mapping relationship between vehicle speed and operating lever state;
[0008] S4: Determine the state of the operating lever according to the expected vehicle speed, use the intelligent driving vehicle speed precision control strategy to output the operating lever control parameters corresponding to the operating lever state, and control the operating lever according to the operating lever control parameters until the vehicle reaches the expected vehicle speed.
[0009] As a further improvement method of the present invention:
[0010] Optionally, constructing the intelligent driving vehicle speed precision control model in step S1 includes the following steps:
[0011] Construct an intelligent driving vehicle speed precision control model, where the intelligent driving vehicle speed precision control model includes an operating lever state space, an operating lever control parameter space and a reward function. The operating lever is used to control the vehicle speed. The operating lever state is the index information of the operating lever, where the index information of the operating lever includes the gear position, brake force and throttle force of the operating lever. The continuous state of the operating lever during vehicle driving constitutes the operating lever state space, where the state of the operating lever at any time is:
[0012] ;
[0013] in:
[0014] s indicates the state of the joystick;
[0015] Indicates the horizontal position of the joystick. Indicates the vertical position of the operating lever. represents the gear position in the operating lever state s;
[0016] Indicates the deformation of the brake controlled by the operating lever. represents the deformation of the throttle controlled by the operating lever, The brake force and throttle force corresponding to the joystick state s;
[0017] The joystick control parameter space includes all control parameters of the joystick, wherein the joystick control parameters include the joystick for the change action, including the change of gear, the change value of the brake pressure and the change value of the throttle pressure. The joystick control parameters are:
[0018] ;
[0019] in:
[0020] Indicates the control parameters of the joystick;
[0021] Indicates the horizontal position change of the operating lever. Indicates the vertical position change of the operating lever. They respectively represent the brake pressure change value and the throttle pressure change value of the operating lever.
[0022] The reward function:
[0023] The positive feedback of the control parameter on the vehicle speed control is used as the reward function value, where the reward function value corresponding to the state s and the control parameter a is:
[0024] ;
[0025] ;
[0026] ;
[0027] in:
[0028] Indicates state s, expected state The reward function value corresponding to the control parameter a, represents the reward function;
[0029] represents the L2 norm;
[0030] Indicates the expected state corresponding to the joystick state;
[0031] represents an exponential function with a natural constant as base;
[0032] Represents the mapping characteristics of state s and control parameter a, Indicates state s, expected state Mapping characteristics with control parameter a;
[0033] represents the state mapping matrix parameters, Represents the control parameter mapping matrix parameters;
[0034] Represents the convolution operator.
[0035] Optionally, in step S2, the strategy optimization of the constructed intelligent driving vehicle speed precision control model includes the following steps:
[0036] The constructed intelligent driving vehicle speed precision control model is optimized to obtain the intelligent driving vehicle speed precision control strategy, where the strategy optimization process is as follows:
[0037] S21: Obtain the operating lever states of K consecutive sections, where the operating lever state of the kth consecutive section is , ;
[0038] S22: Initialize and generate control strategy , set the current iteration number of the control strategy to t, the maximum iteration number to Max, and the initial value of t to 0, then the tth iteration result of the control strategy is ;
[0039] S23: Construct the iterative objective function of the control strategy:
[0040] ;
[0041] ;
[0042] in:
[0043] represents the iterative objective function of the control strategy, Indicates control strategy The iterative objective function value of ;
[0044] Indicates that the control strategy , Joystick status and expected status , the control parameters selected from the action space;
[0045] represents the action space, , a represents any control parameter in the action space;
[0046] Indicates control strategy The spatial mapping parameters in the control strategy The iteration of is the spatial mapping parameter Iterations;
[0047] Represents the reward function value threshold;
[0048] S24: Iterate the control strategy based on the iterative objective function to obtain the precise speed control strategy for intelligent driving .
[0049] Optionally, the step S24 of iterating the control strategy based on the iterative objective function comprises the following steps:
[0050] S241: Control strategy Perform multiple group strategy mapping to obtain control strategies There are H grouping strategies, where the multi-group strategy mapping formula is:
[0051] ;
[0052] in:
[0053] represents the h-th grouping strategy obtained by mapping, ;
[0054] represents a policy mapping control parameter; in the embodiment of the present invention, Set to 0.2;
[0055] represents a vector whose elements are all 1;
[0056] represents the smoothing control parameter, Set to 4;
[0057] S242: Taking H grouping strategies as iterative objective functions The input value of each grouping strategy is obtained, where the grouping strategy The iterative objective function value is ;
[0058] S243: Select the grouping strategy with the lowest iterative objective function value as the optimal grouping strategy ;
[0059] S244: Iterate H grouping strategies, where grouping strategy The iteration formula is:
[0060] ;
[0061] ;
[0062] in:
[0063] represents the iteration weight of the t+1th iteration;
[0064] Represents a random number between 0 and 1;
[0065] S245: Use the H grouping strategies obtained by iteration as the iteration objective function The input value of the iterative objective function is used as the control strategy. The iteration result ;
[0066] S246: Order , return to step S241 until the maximum number of iterations is reached, and the control strategy that reaches the maximum number of iterations is used as the intelligent driving vehicle speed precision control strategy .
[0067] Optionally, constructing a nonlinear mapping relationship between the vehicle speed and the state of the operating lever in step S3 includes the following steps:
[0068] A nonlinear mapping relationship between vehicle speed and operating lever state is constructed, wherein the construction process of the nonlinear mapping relationship is as follows:
[0069] S31: Obtain the vehicle speed of group D and the corresponding operating lever state as a calculation data set data for nonlinear mapping calculation:
[0070] ;
[0071] in:
[0072] Indicates the dth group of calculation data in the calculation data set data. Indicates the vehicle speed of the dth group obtained, Indicates vehicle speed The corresponding joystick status;
[0073] S32: Construct the loss function for calculating nonlinear mapping relationship:
[0074] ;
[0075] in:
[0076] Represents the loss function of nonlinear mapping relationship calculation, Represents a nonlinear mapping relationship The corresponding loss function value;
[0077] represents the L1 norm;
[0078] T stands for transpose;
[0079] S33: Initialize and generate a set of nonlinear mapping relationships , set the current number of iterations of the nonlinear mapping relationship to c, the maximum number of iterations to C, and the initial value of c to 0. Then the result of the cth iteration of the nonlinear mapping relationship is ;
[0080] S34: Iterate the nonlinear mapping relationship based on the loss function to construct a nonlinear mapping relationship between the vehicle speed and the operating lever state .
[0081] Optionally, the iterating of the nonlinear mapping relationship based on the loss function in step S34 includes the following steps:
[0082] S341: Calculate the gradient iteration coefficient of the c+1th iteration:
[0083] ;
[0084] in:
[0085] Represents the gradient iteration coefficient of the c+1th iteration;
[0086] Represents the loss function The gradient of The calculation method is: is the loss function for the variable Take the derivative and Substitute into the derivative result;
[0087] S342: Calculate the iteration step length of the c+1th iteration, where the iteration step length satisfies the following formula:
[0088] ;
[0089] in:
[0090] Indicates the iteration step size of the c+1th iteration;
[0091] S343: Nonlinear mapping relationship Perform iteration and weighted correction:
[0092] ;
[0093] S344: Order , return to step S341 until The gradient is less than the preset threshold value, and the nonlinear mapping relationship iteration result at this time is used as the nonlinear mapping relationship between the vehicle speed and the operating lever state. .
[0094] Optionally, in step S4, determining the state of the operating lever according to the expected vehicle speed, outputting the operating lever control parameters corresponding to the operating lever state using the intelligent driving vehicle speed precision control strategy, and controlling the operating lever according to the operating lever control parameters include the following steps:
[0095] The expected vehicle speeds on different road sections are obtained, and the vehicle speed is precisely controlled based on the nonlinear mapping relationship and the intelligent driving speed precision control strategy. The speed precision control process is as follows:
[0096] S41: Obtain the expected vehicle speed of the nth road segment , where the initial value of n is 1 and the maximum value is N, where N represents the total number of road sections traveled by the vehicle;
[0097] S42: Using the nonlinear mapping relationship between vehicle speed and lever state , the expected vehicle speeds of N road sections are mapped to the expected states of the operating lever, where the expected vehicle speed The mapping result is:
[0098] ;
[0099] in:
[0100] Indicates expected speed The mapping result is the expected state of the vehicle on the nth road segment;
[0101] T stands for transpose;
[0102] S43: Obtaining the current operating lever state of the vehicle at the nth road section , expected status , using intelligent driving speed precision control strategy to output the joystick status Corresponding joystick control parameters :
[0103] ;
[0104] S44: Control parameters according to joystick Control the operating lever to accurately control the vehicle's driving speed.
[0105] In order to solve the above problems, the present invention provides a dynamic feedback intelligent driving speed precision control device, characterized in that the device comprises:
[0106] The vehicle speed control strategy calculation module is used to construct an intelligent driving vehicle speed precision control model, optimize the strategy of the constructed intelligent driving vehicle speed precision control model, and obtain the intelligent driving vehicle speed precision control strategy;
[0107] The vehicle speed mapping module is used to construct a nonlinear mapping relationship between vehicle speed and operating lever state;
[0108] The vehicle speed control module is used to determine the state of the operating lever according to the expected vehicle speed, output the operating lever control parameters corresponding to the operating lever state using the intelligent driving vehicle speed precision control strategy, and control the operating lever according to the operating lever control parameters until the vehicle reaches the expected speed.
[0109] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:
[0110] A memory storing at least one instruction;
[0111] Communication interface, enabling electronic equipment to communicate; and
[0112] The processor executes the instructions stored in the memory to implement the above-mentioned dynamic feedback intelligent driving speed precision control method.
[0113] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned dynamic feedback intelligent driving vehicle speed precise control method.
[0114] Compared with the prior art, the present invention proposes a dynamic feedback intelligent driving vehicle speed precision control method, which has the following advantages:
[0115] First, this scheme proposes a method for calculating the vehicle speed control strategy, constructs an action space of an operating lever that represents the vehicle speed control, and uses the difference between the operating lever state and the expected state after the control parameters are taken, as well as the coherence between the mapping features of the current state and the expected state as the control parameter action feedback, to construct a reward function, where the higher the reward function value, the more it means that the action taken can obtain an operating lever state that is close to the expected state while ensuring the smoothness of the operating lever action. Based on the reward function, the iterative objective function of the control strategy is constructed, and the strategy is optimized in combination with the control strategy. In each iteration of the control strategy, a strategy mapping method is used to generate several groups of approximate strategies, and they are iterated synchronously to expand the search range of the control strategy and improve the accuracy of the control strategy, thereby constructing a precise speed control strategy for intelligent driving.
[0116] At the same time, this scheme constructs a nonlinear mapping relationship loss function that characterizes the vehicle speed and the state of the operating lever, and constructs the gradient iteration coefficient and iteration step of the nonlinear mapping relationship in combination with the gradient change value. The nonlinear mapping relationship is gradient iterated to obtain the expected vehicle speed in different sections. Based on the nonlinear mapping relationship and the intelligent driving speed precision control strategy, the intelligent driving speed precision control strategy is used to output the operating lever control parameters corresponding to the operating lever state, and the operating lever is controlled according to the operating lever control parameters until the vehicle reaches the expected speed, thereby realizing intelligent and precise speed control of the vehicle in different sections. BRIEF DESCRIPTION OF THE DRAWINGS
[0117] Figure 1 A schematic flow chart of a method for precise speed control of intelligent driving with dynamic feedback provided by an embodiment of the present invention;
[0118] Figure 2 A functional module diagram of a dynamic feedback intelligent driving vehicle speed precision control device provided by an embodiment of the present invention;
[0119] Figure 2 Middle: 100 dynamic feedback intelligent driving speed precision control device, 101 speed control strategy calculation module, 102 speed mapping module, 103 speed control module;
[0120] Figure 3 A schematic diagram of the structure of an electronic device for implementing a smart driving vehicle speed precision control method with dynamic feedback provided by an embodiment of the present invention;
[0121] Figure 3 In: 1 electronic device, 10 processor, 11 memory, 12 program, 13 communication interface.
[0122] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0123] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0124] The embodiment of the present application provides a method for precise control of vehicle speed of intelligent driving with dynamic feedback. The execution subject of the method for precise control of vehicle speed of intelligent driving with dynamic feedback includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for precise control of vehicle speed of intelligent driving with dynamic feedback can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.
[0125] S1: Construct an intelligent driving vehicle speed precision control model, where the intelligent driving vehicle speed precision control model includes an operating lever state space, an operating lever control parameter space and a reward function.
[0126] The intelligent driving vehicle speed precision control model is constructed in step S1, including the following steps:
[0127] Construct an intelligent driving vehicle speed precision control model, where the intelligent driving vehicle speed precision control model includes an operating lever state space, an operating lever control parameter space and a reward function. The operating lever is used to control the vehicle speed. The operating lever state is the index information of the operating lever, where the index information of the operating lever includes the gear position, brake force and throttle force of the operating lever. The continuous state of the operating lever during vehicle driving constitutes the operating lever state space, where the state of the operating lever at any time is:
[0128] ;
[0129] in:
[0130] s indicates the state of the joystick;
[0131] Indicates the horizontal position of the joystick. Indicates the vertical position of the operating lever. represents the gear position in the operating lever state s;
[0132] Indicates the deformation of the brake controlled by the operating lever. represents the deformation of the throttle controlled by the operating lever, The brake force and throttle force corresponding to the joystick state s;
[0133] The joystick control parameter space includes all control parameters of the joystick, wherein the joystick control parameters include the joystick for the change action, including the change of gear, the change value of the brake pressure and the change value of the throttle pressure. The joystick control parameters are:
[0134] ;
[0135] in:
[0136] Indicates the control parameters of the joystick;
[0137] Indicates the horizontal position change of the operating lever. Indicates the vertical position change of the operating lever. They respectively represent the brake pressure change value and the throttle pressure change value of the operating lever.
[0138] The positive feedback of the control parameter on the vehicle speed control is used as the reward function value, where the reward function value corresponding to the state s and the control parameter a is:
[0139] ;
[0140] ;
[0141] ;
[0142] in:
[0143] Indicates state s, expected state The reward function value corresponding to the control parameter a, represents the reward function;
[0144] represents the L2 norm;
[0145] Indicates the expected state corresponding to the joystick state;
[0146] represents an exponential function with a natural constant as base;
[0147] Represents the mapping characteristics of state s and control parameter a, Indicates state s, expected state Mapping characteristics with control parameter a;
[0148] represents the state mapping matrix parameters, Represents the control parameter mapping matrix parameters;
[0149] Represents the convolution operator.
[0150] S2: Optimize the strategy of the constructed intelligent driving vehicle speed precision control model to obtain the intelligent driving vehicle speed precision control strategy.
[0151] In the step S2, the strategy optimization of the constructed intelligent driving vehicle speed precision control model is performed, including the following steps:
[0152] The constructed intelligent driving vehicle speed precision control model is optimized to obtain the intelligent driving vehicle speed precision control strategy, where the strategy optimization process is as follows:
[0153] S21: Obtain the operating lever states of K consecutive sections, where the operating lever state of the kth consecutive section is , ;
[0154] S22: Initialize and generate control strategy , set the current iteration number of the control strategy to t, the maximum iteration number to Max, and the initial value of t to 0, then the tth iteration result of the control strategy is ;
[0155] S23: Construct the iterative objective function of the control strategy:
[0156] ;
[0157] ;
[0158] in:
[0159] represents the iterative objective function of the control strategy, Indicates control strategy The iterative objective function value of ;
[0160] Indicates that the control strategy , Joystick status and expected status , the control parameters selected from the action space;
[0161] represents the action space, , a represents any control parameter in the action space;
[0162] Indicates control strategy The spatial mapping parameters in the control strategy The iteration of is the spatial mapping parameter Iterations;
[0163] Represents the reward function value threshold;
[0164] S24: Iterate the control strategy based on the iterative objective function to obtain the precise speed control strategy for intelligent driving .
[0165] In the step S24, the control strategy is iterated based on the iterative objective function, including the following steps:
[0166] S241: Control strategy Perform multiple group strategy mapping to obtain control strategies There are H grouping strategies, where the multi-group strategy mapping formula is:
[0167] ;
[0168] in:
[0169] represents the h-th grouping strategy obtained by mapping, ;
[0170] represents a policy mapping control parameter; in the embodiment of the present invention, Set to 0.2;
[0171] represents a vector whose elements are all 1;
[0172] represents the smoothing control parameter, Set to 4;
[0173] S242: Taking H grouping strategies as iterative objective functions The input value of each grouping strategy is obtained, where the grouping strategy The iterative objective function value is ;
[0174] S243: Select the grouping strategy with the lowest iterative objective function value as the optimal grouping strategy ;
[0175] S244: Iterate H grouping strategies, where grouping strategy The iteration formula is:
[0176] ;
[0177] ;
[0178] in:
[0179] represents the iteration weight of the t+1th iteration;
[0180] Represents a random number between 0 and 1;
[0181] S245: Use the H grouping strategies obtained by iteration as the iteration objective function The input value of the iterative objective function is used as the control strategy. The iteration result ;
[0182] S246: Order , return to step S241 until the maximum number of iterations is reached, and the control strategy that reaches the maximum number of iterations is used as the intelligent driving vehicle speed precision control strategy .
[0183] S3: Construct a nonlinear mapping relationship between vehicle speed and operating lever state.
[0184] The nonlinear mapping relationship between the vehicle speed and the state of the operating lever is constructed in step S3, including the following steps:
[0185] A nonlinear mapping relationship between vehicle speed and operating lever state is constructed, wherein the construction process of the nonlinear mapping relationship is as follows:
[0186] S31: Obtain the vehicle speed of group D and the corresponding operating lever state as a calculation data set data for nonlinear mapping calculation:
[0187] ;
[0188] in:
[0189] Indicates the dth group of calculation data in the calculation data set data. Indicates the vehicle speed of the dth group obtained, Indicates vehicle speed The corresponding joystick status;
[0190] S32: Construct the loss function for calculating nonlinear mapping relationship:
[0191] ;
[0192] in:
[0193] Represents the loss function of nonlinear mapping relationship calculation, Represents a nonlinear mapping relationship The corresponding loss function value;
[0194] represents the L1 norm;
[0195] T stands for transpose;
[0196] S33: Initialize and generate a set of nonlinear mapping relationships , set the current number of iterations of the nonlinear mapping relationship to c, the maximum number of iterations to C, and the initial value of c to 0. Then the result of the cth iteration of the nonlinear mapping relationship is ;
[0197] S34: Iterate the nonlinear mapping relationship based on the loss function to construct a nonlinear mapping relationship between the vehicle speed and the operating lever state .
[0198] In the step S34, the nonlinear mapping relationship is iterated based on the loss function, including the following steps:
[0199] S341: Calculate the gradient iteration coefficient of the c+1th iteration:
[0200] ;
[0201] in:
[0202] Represents the gradient iteration coefficient of the c+1th iteration;
[0203] Represents the loss function The gradient of The calculation method is: is the loss function for the variable Take the derivative and Substitute into the derivative result;
[0204] S342: Calculate the iteration step length of the c+1th iteration, where the iteration step length satisfies the following formula:
[0205] ;
[0206] in:
[0207] Indicates the iteration step size of the c+1th iteration;
[0208] S343: Nonlinear mapping relationship Perform iteration and weighted correction:
[0209] ;
[0210] S344: Order , return to step S341 until The gradient is less than the preset threshold value, and the nonlinear mapping relationship iteration result at this time is used as the nonlinear mapping relationship between the vehicle speed and the operating lever state. .
[0211] S4: Determine the state of the operating lever according to the expected vehicle speed, use the intelligent driving vehicle speed precision control strategy to output the operating lever control parameters corresponding to the operating lever state, and control the operating lever according to the operating lever control parameters until the vehicle reaches the expected vehicle speed.
[0212] In the step S4, the state of the operating lever is determined according to the expected vehicle speed, the intelligent driving vehicle speed precision control strategy is used to output the operating lever control parameters corresponding to the state of the operating lever, and the operating lever is controlled according to the operating lever control parameters, including the following steps:
[0213] The expected vehicle speeds on different road sections are obtained, and the vehicle speed is precisely controlled based on the nonlinear mapping relationship and the intelligent driving speed precision control strategy. The speed precision control process is as follows:
[0214] S41: Obtain the expected vehicle speed of the nth road segment , where the initial value of n is 1 and the maximum value is N, where N represents the total number of road sections traveled by the vehicle;
[0215] S42: Using the nonlinear mapping relationship between vehicle speed and lever state , the expected vehicle speeds of N road sections are mapped to the expected states of the operating lever, where the expected vehicle speed The mapping result is:
[0216] ;
[0217] in:
[0218] Indicates expected speed The mapping result is the expected state of the vehicle on the nth road section;
[0219] T stands for transpose;
[0220] S43: Obtaining the current operating lever state of the vehicle at the nth road section , expected status , using intelligent driving speed precision control strategy to output the joystick status Corresponding joystick control parameters :
[0221] ;
[0222] S44: Control parameters according to joystick Control the operating lever to accurately control the vehicle's driving speed.
[0223] like Figure 2 , is a functional module diagram of a smart driving vehicle speed precision control device with dynamic feedback provided by an embodiment of the present invention, which can implement the smart driving vehicle speed precision control method with dynamic feedback in Example 1.
[0224] The dynamic feedback intelligent driving speed precision control device 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the dynamic feedback intelligent driving speed precision control device can include a speed control strategy calculation module 101, a speed mapping module 102 and a speed control module 103. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0225] The vehicle speed control strategy calculation module 101 is used to construct an intelligent driving vehicle speed precision control model, optimize the strategy of the constructed intelligent driving vehicle speed precision control model, and obtain the intelligent driving vehicle speed precision control strategy;
[0226] A vehicle speed mapping module 102, used to construct a nonlinear mapping relationship between vehicle speed and operating lever state;
[0227] The vehicle speed control module 103 is used to determine the state of the operating lever according to the expected vehicle speed, output the operating lever control parameters corresponding to the operating lever state using the intelligent driving vehicle speed precision control strategy, and control the operating lever according to the operating lever control parameters until the vehicle reaches the expected vehicle speed.
[0228] In detail, each module in the dynamic feedback intelligent driving speed precision control device 100 in the embodiment of the present invention is used in the same manner as above. Figure 1 The technical means are the same as the dynamic feedback intelligent driving speed precise control method described in, and can produce the same technical effects, so I will not go into details here.
[0229] like Figure 3 , which is a schematic diagram of the structure of an electronic device for implementing a smart driving vehicle speed precision control method with dynamic feedback provided by an embodiment of the present invention.
[0230] The electronic device 1 may include a processor 10 , a memory 11 , a communication interface 13 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as a program 12 .
[0231] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 may not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the program 12, etc., but also be used to temporarily store data that has been output or is to be output.
[0232] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as the program 12 for realizing precise speed control of intelligent driving with dynamic feedback), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.
[0233] The communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices, and to achieve connection and communication between internal components of the electronic device.
[0234] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.
[0235] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.
[0236] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
[0237] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.
[0238] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.
[0239] The program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:
[0240] Build a precise speed control model for intelligent driving;
[0241] Optimize the strategy of the constructed intelligent driving vehicle speed precision control model to obtain the intelligent driving vehicle speed precision control strategy;
[0242] Construct a nonlinear mapping relationship between vehicle speed and operating lever state;
[0243] The state of the operating lever is determined according to the expected vehicle speed, and the intelligent driving speed precision control strategy is used to output the operating lever control parameters corresponding to the operating lever state, and the operating lever is controlled according to the operating lever control parameters until the vehicle reaches the expected speed.
[0244] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.
[0245] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.
[0246] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0247] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A dynamic feedback intelligent driving vehicle speed precision control method, characterized in that: The method comprises the following steps: S1: Construct an intelligent driving vehicle speed precision control model, where the intelligent driving vehicle speed precision control model includes an operating lever state space, an operating lever control parameter space and a reward function; Construct an intelligent driving vehicle speed precision control model, wherein the intelligent driving vehicle speed precision control model includes an operating lever state space, an operating lever control parameter space, and a reward function. The operating lever is used to control the vehicle speed. The operating lever state is the indicator information of the operating lever, wherein the indicator information of the operating lever includes the gear position, brake force, and throttle force of the operating lever. The joystick control parameter space includes all control parameters of the joystick, wherein the control parameters of the joystick include the joystick for the change action, including the change of gear, the change value of the brake pressure and the change value of the throttle pressure; The reward function: The positive feedback of the control parameter on the vehicle speed control is used as the reward function value, where the reward function value corresponding to the state s and the control parameter a is: ; ; ; in: Indicates state s, expected state The reward function value corresponding to the control parameter a, represents the reward function; represents the L2 norm; Indicates the expected state corresponding to the joystick state; represents an exponential function with a natural constant as base; Represents the mapping characteristics of state s and control parameter a, Indicates state s, expected state Mapping characteristics with control parameter a; represents the state mapping matrix parameters, Represents the control parameter mapping matrix parameters; represents the convolution operator; S2: Optimize the strategy of the constructed intelligent driving vehicle speed precision control model to obtain the intelligent driving vehicle speed precision control strategy; S3: construct a nonlinear mapping relationship between vehicle speed and operating lever state; S4: Determine the state of the operating lever according to the expected vehicle speed, use the intelligent driving vehicle speed precision control strategy to output the operating lever control parameters corresponding to the operating lever state, and control the operating lever according to the operating lever control parameters until the vehicle reaches the expected vehicle speed.
2. The method for precise control of vehicle speed with dynamic feedback of intelligent driving according to claim 1, characterized in that: In the step S2, the strategy optimization of the constructed intelligent driving vehicle speed precision control model is performed, including the following steps: The constructed intelligent driving vehicle speed precision control model is optimized to obtain the intelligent driving vehicle speed precision control strategy, where the strategy optimization process is as follows: S21: Obtaining the operating lever states of K consecutive road sections; S22: Initialize and generate a control strategy, and set the current number of iterations and the maximum number of iterations of the control strategy; S23: Construct the iterative objective function of the control strategy: ; in: represents the iterative objective function of the control strategy, Indicates control strategy The iterative objective function value of ; Indicates that the control strategy , Joystick status and expected status , the control parameters selected from the action space; Represents the reward function value threshold; Indicates status , expected status and control parameters The corresponding reward function value; S24: Iterate the control strategy based on the iterative objective function to obtain the precise speed control strategy for intelligent driving .
3. The method for precise control of vehicle speed with dynamic feedback of intelligent driving as claimed in claim 2, characterized in that: In the step S24, the control strategy is iterated based on the iterative objective function, including the following steps: S241: mapping the control strategy into multiple group strategies to obtain a group strategy of the control strategy; S242: using the grouping strategy as an input value of the iterative objective function to obtain an iterative objective function value of each grouping strategy; S243: Selecting the grouping strategy with the lowest iterative objective function value as the optimal grouping strategy; S244: iteratively updating the grouping strategy; S245: using the grouping strategy obtained by iteration as the input value of the iteration objective function, and using the grouping strategy with the highest iteration objective function value as the iteration result of the control strategy; S246: Return to step S241 and iterate until the maximum number of iterations is reached, and use the control strategy that reaches the maximum number of iterations as the intelligent driving vehicle speed precision control strategy.
4. The method for precise control of vehicle speed with dynamic feedback of intelligent driving according to claim 1, characterized in that: The nonlinear mapping relationship between the vehicle speed and the state of the operating lever is constructed in step S3, including the following steps: A nonlinear mapping relationship between vehicle speed and operating lever state is constructed, wherein the construction process of the nonlinear mapping relationship is as follows: S31: Obtain the vehicle speed of group D and the corresponding operating lever state as a calculation data set data for nonlinear mapping calculation: ; in: Indicates the dth group of calculation data in the calculation data set data. Indicates the vehicle speed of the dth group obtained, Indicates vehicle speed The corresponding joystick status; S32: Construct loss function for calculating nonlinear mapping relationship; S33: Initialize and generate a set of nonlinear mapping relationships , set the current number of iterations of the nonlinear mapping relationship to c, the maximum number of iterations to C, and the initial value of c to 0. Then the result of the cth iteration of the nonlinear mapping relationship is ; S34: Iterating the nonlinear mapping relationship based on the loss function to construct a nonlinear mapping relationship between the vehicle speed and the state of the operating lever.
5. The method for precise control of vehicle speed with intelligent driving based on dynamic feedback as claimed in claim 4, characterized in that: In the step S34, the nonlinear mapping relationship is iterated based on the loss function, including the following steps: S341: Calculate the gradient iteration coefficient of the c+1th iteration: ; in: Represents the gradient iteration coefficient of the c+1th iteration; Represents the loss function The gradient of The calculation method is: is the loss function for the variable pair Take the derivative and Substitute into the derivative result; S342: Calculate the iteration step length of the c+1th iteration, where the iteration step length satisfies the following formula: ; in: Indicates the iteration step size of the c+1th iteration; S343: Nonlinear mapping relationship Perform iteration and weighted correction: ; S344: Order , return to step S341 until The gradient is less than the preset threshold value, and the nonlinear mapping relationship iteration result at this time is used as the nonlinear mapping relationship between the vehicle speed and the operating lever state. .
6. The method for precise speed control of intelligent driving with dynamic feedback according to claim 1, characterized in that: In the step S4, the state of the operating lever is determined according to the expected vehicle speed, the intelligent driving vehicle speed precision control strategy is used to output the operating lever control parameters corresponding to the state of the operating lever, and the operating lever is controlled according to the operating lever control parameters, including the following steps: The expected vehicle speeds on different road sections are obtained, and the vehicle speed is precisely controlled based on the nonlinear mapping relationship and the intelligent driving speed precision control strategy. The speed precision control process is as follows: S41: Obtain the expected vehicle speed of the nth road segment , where the initial value of n is 1 and the maximum value is N, where N represents the total number of road sections traveled by the vehicle; S42: Mapping the expected vehicle speeds of the N road sections into the expected states of the operating lever using the nonlinear mapping relationship between the vehicle speed and the state of the operating lever; S43: obtaining the current operating lever state and expected state of the vehicle on the nth road section, and outputting the operating lever control parameters corresponding to the operating lever state using the intelligent driving vehicle speed precision control strategy; S44: Control the operating lever according to the operating lever control parameter to accurately control the driving speed of the vehicle.
7. A dynamic feedback intelligent driving speed precision control device, characterized in that: The device comprises: The vehicle speed control strategy calculation module is used to construct an intelligent driving vehicle speed precision control model, optimize the strategy of the constructed intelligent driving vehicle speed precision control model, and obtain the intelligent driving vehicle speed precision control strategy; The vehicle speed mapping module is used to construct a nonlinear mapping relationship between vehicle speed and operating lever state; A vehicle speed control module is used to determine the state of the operating lever according to the expected vehicle speed, output the operating lever control parameters corresponding to the operating lever state using the intelligent driving vehicle speed precision control strategy, and control the operating lever according to the operating lever control parameters until the vehicle reaches the expected vehicle speed, so as to realize a dynamic feedback intelligent driving vehicle speed precision control method as described in any one of claims 1-6.
