Vehicle parameter optimization method and device, computer device and storage medium

Abstract

The application relates to a vehicle parameter optimization method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining an optimization target; receiving vehicle state information uploaded by a target vehicle terminal and an optimization target value of a first loop; generating an optimization parameter index value according to a currently set first loop parameter index value, the vehicle state information and the optimization target value; and sending the optimization parameter index value to the target vehicle terminal, where the optimization parameter index value is used to instruct the target vehicle terminal to control the target vehicle. The method can optimize vehicle parameters to achieve an optimization target.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a vehicle parameter optimization method, apparatus, computer equipment, storage medium, and computer program product. Background Art

[0002] In related technologies, controller design methods can be implemented using expert systems, imitation learning, etc. Generally, expert systems are used to define and identify scenarios for controller design, while imitation learning requires studying and analyzing driving data from different drivers.

[0003] Different application scenarios often have other complex and advanced performance requirements. Because the definition and identification of scenario classes takes a long time, expert systems are inefficient in utilizing measurement data. Simulation learning, which replaces the driver's control of the vehicle's accelerator and brake pedals, interferes with the driver's normal driving and creates uncontrollable safety issues. Therefore, existing technologies are unable to solve the problem of optimizing vehicle controller parameters in complex scenarios. Summary of the Invention

[0004] Based on this, it is necessary to provide a vehicle parameter optimization method, device, computer equipment, computer-readable storage medium and computer program product that can optimize vehicle parameters to achieve optimization goals in response to the above technical problems.

[0005] In a first aspect, the present application provides a vehicle parameter optimization method applied to a server. The method comprises:

[0006] Get the optimization target;

[0007] Receive vehicle status information and the optimization target value of the first loop uploaded by the target vehicle terminal;

[0008] Generate an optimized parameter index value according to the currently set first loop parameter index value, vehicle state information and optimization target value;

[0009] The optimized parameter index value is sent to the target vehicle terminal, and the optimized parameter index value is used to instruct the target vehicle terminal to control the target vehicle.

[0010] In one embodiment, generating the optimized parameter index value based on the currently set first loop parameter index value, vehicle state information, and optimization target value includes:

[0011] Get the threshold value of parameter indicator value;

[0012] Generate initial parameters based on parameter index values, vehicle status information and optimization target values;

[0013] The initial parameter index value is corrected by the threshold to obtain the optimized parameter index value.

[0014] In one embodiment, the generating of the optimization parameter index value based on the first loop parameter index value according to the current setting, the vehicle state information and the optimization target value comprises:

[0015] obtaining a constraint condition of the parameter index value;

[0016] obtaining a pre-designed reward function and adding the constraint condition to the reward function;

[0017] generating the optimization parameter index value based on the parameter index value, the vehicle state information, the optimization target value and the reward function.

[0018] In a second aspect, a vehicle parameter optimization method applied to a vehicle terminal is provided, and the method comprises:

[0019] controlling the target vehicle through a first loop to obtain an optimization target value;

[0020] collecting vehicle information through a vehicle sensor and generating vehicle state information based on the vehicle information;

[0021] uploading the vehicle state information and the target optimization value to a server;

[0022] receiving an optimization parameter index value sent by the server and controlling the target vehicle based on the optimization parameter index value.

[0023] In one embodiment, the receiving of the optimization parameter index value sent by the server and the controlling of the target vehicle based on the optimization parameter index value comprises:

[0024] controlling the target vehicle based on the optimization parameter index value according to a vehicle type of the target vehicle.

[0025] In one embodiment, the controlling of the target vehicle based on the optimization parameter index value according to the vehicle type of the target vehicle comprises:

[0026] when the vehicle type does not include an intelligent driving system, controlling the target vehicle through a power domain controller based on the optimization parameter index value;

[0027] when the vehicle type includes the intelligent driving system, controlling the target vehicle through the power domain controller or an intelligent driving longitudinal controller based on the optimization parameter index value.

[0028] In a third aspect, the application further provides a vehicle parameter optimization device applied to a server, and the device comprises:

[0029] an optimization target obtaining module, configured to obtain an optimization target;

[0030] The vehicle status receiving module is used to receive the vehicle status information uploaded by the target vehicle terminal and the optimization target value of the first loop;

[0031] An optimization parameter generation module is used to generate an optimization parameter index value according to the currently set first loop parameter index value, vehicle state information and optimization target value;

[0032] The optimization parameter generation and sending module is used to send the optimization parameter index value to the target vehicle terminal, and the optimization parameter index value is used to instruct the target vehicle terminal to control the target vehicle.

[0033] In a fourth aspect, the present application further provides a vehicle parameter optimization device applied to a vehicle terminal, the device comprising:

[0034] Optimization target acquisition module, used to obtain optimization target value;

[0035] The vehicle status receiving module is used to receive the vehicle status information and optimization target value uploaded by the target vehicle terminal;

[0036] An optimization parameter index value generation module, configured to generate an optimization parameter index value through a second loop according to the parameter index value, vehicle state information, and optimization target value;

[0037] The optimized parameter index value sending module is used to send the optimized parameter index value to the target vehicle terminal, and the optimized parameter index value is used to instruct the target vehicle terminal to control the target vehicle according to the optimized parameter index value.

[0038] In a fifth aspect, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in any one of the above embodiments when executing the computer program.

[0039] In a sixth aspect, the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, implements the steps of the method in any one of the above embodiments.

[0040] In a seventh aspect, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method in any one of the above embodiments.

[0041] In the above-mentioned vehicle parameter optimization method, device, computer equipment, storage medium and computer program product, the server first receives the optimization target and the vehicle status information and the optimization target value of the first loop sent by the target vehicle terminal, and then the server generates the optimization parameter index value based on the currently set first loop parameter index value, vehicle status information and optimization target value, and sends the optimization parameter index value to the target vehicle terminal. The target vehicle terminal controls the target vehicle according to the optimization parameter index value, so that the target vehicle can continuously improve the optimization target. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A diagram showing an application environment of a vehicle parameter optimization method according to an embodiment;

[0043] Figure 2 Schematic diagram of a process flow of a vehicle parameter optimization method according to one embodiment;

[0044] Figure 3 A schematic diagram of a system solution in one embodiment;

[0045] Figure 4 A schematic flow chart of a vehicle parameter optimization method according to another embodiment;

[0046] Figure 5 A schematic diagram of parameter optimization of a common vehicle in one embodiment;

[0047] Figure 6 is a schematic diagram of an intelligent driving system in one embodiment that does not include an intelligent driving longitudinal controller;

[0048] Figure 7 Schematic diagram of an intelligent driving system including an intelligent driving longitudinal controller in one embodiment;

[0049] Figure 8 is a structural block diagram of a vehicle parameter optimization device in one embodiment;

[0050] Figure 9 is a structural block diagram of a vehicle parameter optimization device in another embodiment;

[0051] Figure 10 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0053] The vehicle parameter optimization method provided in the embodiment of the present application can be applied toFigure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server first obtains the optimization target and receives the vehicle status information uploaded by the target vehicle terminal and the optimization target value of the first loop, and then generates the optimization parameter index value through the server 104 according to the currently set first loop parameter index value, vehicle status information and optimization target value, and finally sends the optimization parameter index value to the target vehicle terminal. The target vehicle terminal controls the target vehicle according to the optimization parameter index value to achieve the optimization target. Among them, the terminal 102 can be but is not limited to various intelligent vehicle-mounted devices, etc., and the server 104 can be implemented with an independent server or a server cluster composed of multiple servers.

[0054] In one embodiment, Figure 2 As shown, a vehicle parameter optimization method is provided, which is applied to Figure 1 Taking the server 104 in the example as an example, the following steps are included:

[0055] S202, obtaining an optimization target.

[0056] The optimization goal is to optimize the target vehicle, such as energy consumption, comfort, or safety, etc., which can be set according to the actual application scenario and is not specifically limited here.

[0057] Specifically, the server receives an optimization target, which can be set by a technician in this field according to the actual scenario. After receiving the optimization target, the server can optimize the parameters of the target vehicle according to the optimization target, such as the vehicle dynamics response characteristics of the target vehicle (such as torque accelerator pedal mapping table, acceleration response characteristic parameters, brake response characteristic parameters), electric energy storage management system control parameters (such as battery management system charging and discharging control parameters), vehicle air-conditioning control system parameters (such as air-conditioning controller control parameters), continuous or discrete control parameters in the motion planning module or decision module of the intelligent driving controller, etc., so that the target vehicle can achieve the optimization target, such as achieving the lowest energy consumption of the vehicle during driving.

[0058] S204: Receive vehicle status information uploaded by the target vehicle terminal and the optimization target value of the first loop.

[0059] The first loop refers to a conventional control loop in the target vehicle. The components of the first loop vary with the type of the target vehicle. For example, the first loop of a common vehicle without an intelligent driving system is composed of a throttle component, a brake component, a power domain controller, and a power system. The optimization target value of the first loop refers to the current state corresponding to the optimization target uploaded on the vehicle end. For example, if the optimization target is to optimize energy consumption, the optimization target value of the first loop is the current energy consumption state. In other embodiments, the optimization target value can be any value corresponding to the optimization target.

[0060] The vehicle state information refers to vehicle information collected by vehicle sensors in the target vehicle and uploaded to the server. For example, vehicle motion sensors such as a wheel speed sensor, an accelerometer, an inertial navigation system, etc. can be used to collect vehicle information such as vehicle speed, acceleration, and vehicle travel direction, and generate vehicle state information based on these vehicle information and upload it to the server.

[0061] S206, generating an optimization parameter index value according to the currently set first loop parameter index value, vehicle state information, and optimization target value.

[0062] The parameter index value of the first loop refers to the control parameter of the first loop, such as the torque pedal mapping table of the power domain controller or the PID control parameter of the auxiliary driving longitudinal controller.

[0063] Specifically, the server obtains the optimization parameter modification direction corresponding to the improved optimization target value based on the parameter index value, vehicle state information, and optimization target value, and generates a new optimization parameter index value by superimposing the original parameter index value on the optimization parameter change amount in the modification direction.

[0064] The optimization parameter modification direction refers to the gradient of the parameter index value corresponding to the improved optimization target direction generated by the server based on the parameter index value, vehicle state information, and optimization target value.

[0065] Specifically, the server dynamically adjusts the related parameters of the target vehicle according to the optimization target under the premise of meeting the control index of the first loop, i.e. under the premise of meeting the parameter index value, to generate the optimization parameter index value. For example, the torque acceleration pedal mapping table is adjusted. In other embodiments, any other adjustable controller parameter can also be adjusted.

[0066] In one embodiment, if the optimization target is to reduce energy consumption, the parameter change direction that can reduce energy consumption can be obtained by changing the control parameter of the first loop and observing the change in energy consumption. Then, the optimization parameter index value is obtained by superimposing the parameter change that can make the control target better on the original first loop parameter and sending it to the target vehicle terminal.

[0067] In an embodiment, the adjustment method of the server can be to adjust the relevant parameters of the target vehicle by using the method of reinforcement learning, i.e., to generate the optimization parameter index value.

[0068] It should be noted that the parameter index value and the vehicle state information required by the server to generate the optimization parameter index value are real-time uploaded by the target vehicle terminal, which are the current vehicle motion state and the optimization target value, and are not stored in the database of the server in advance.

[0069] In an embodiment, the server can store the vehicle state information uploaded by the target vehicle terminal each time to train the reinforcement learning model. In this way, the optimal control strategy can be extracted by using the big data generated by the use environment.

[0070] In an embodiment, the server can train the machine learning model by using the data stored in the server side as training data, and generate the optimization parameter index value by using the trained machine learning model. Optionally, the machine learning model can be a policy gradient method or a Q-learning method or a model-based reinforcement learning method. Since the reinforcement learning uses the optimization target, i.e., the reward signal, as the supervision signal, it can be used without labeling, which can save a large amount of labeling resources and costs. Secondly, since the training data used for training is the real data sent by the target vehicle terminal, the optimal control strategy can be extracted by using the big data generated by the use environment.

[0071] In an embodiment, if the scenario of the target vehicle does not change, the change of the optimization parameter index value will become smaller and smaller. In other embodiments, if the scenario changes, the dynamic gradient direction will make the server adapt to the new scenario.

[0072] S208, send the optimization parameter index value to the target vehicle terminal, and the optimization parameter index value is used to instruct the target vehicle terminal to control the target vehicle.

[0073] Specifically, after the server generates the optimization parameter index value, the server sends the optimization parameter index value to the target vehicle terminal. After the target vehicle terminal receives the optimization parameter index value, the target vehicle terminal controls the target vehicle according to the optimization parameter index value, so that the target vehicle can improve the optimization target value. It should be noted that the target vehicle refers to a vehicle that needs to be optimized, which can be any vehicle that needs to be optimized. It should be noted that the optimization target is continuously improved, and there is no fixed optimization target value. The server only calculates the parameter modification direction corresponding to the optimization improvement direction, and the improvement is continuous.

[0074] In one embodiment, after the target vehicle terminal receives the optimization parameter index value sent by the server, the target vehicle is controlled according to the vehicle type of the target vehicle type. For example, when the vehicle type of the target vehicle is a common vehicle without an intelligent driving system, the vehicle terminal can control the motor according to the optimization parameter index value through the power domain controller.

[0075] In one embodiment, specifically in combination with Figure 3 as shown, Figure 3 is a schematic diagram of the system scheme in one embodiment. The electric drive system controls the torque of the motor through the power controller. The actual physical system includes the real physical road where the vehicle is located and the vehicle itself as the controlled object. The input quantity is the control command issued by the controller, and the output quantity is the vehicle motion state and the voltage and current of the motor, which can be observed through the sensor. The cloud computing server is a server cluster deployed in the cloud for collecting data, training models and calculating optimal decisions. The data transmission system is a communication system responsible for collecting and uploading observation data and issuing dynamic optimal decisions. At the vehicle end, it is a TBox, and at the cloud end, it is a TSP system. The data needs to meet the following requirements: 1) observability, that is, it can reflect the influencing factors of energy consumption, such as vehicle motion state (vehicle speed) and throttle brake pedal state (driver's motion planning for the vehicle); 2) controllability, that is, it can effectively affect the data in the optimization space of energy consumption, such as the parameters of the electric power system controller.

[0076] In one embodiment, the server can send the optimization parameter index value to the target vehicle terminal through the TSP system, and the target vehicle terminal receives the optimization parameter index value sent by the server through the TBox system.

[0077] In the above vehicle parameter optimization method, the server first receives the optimization target and the vehicle state information sent by the target vehicle terminal and the optimization target value of the first loop, and then generates the optimization parameter index value according to the currently set first loop parameter index value, vehicle state information and optimization target value, and sends the optimization parameter index value to the target vehicle terminal. The target vehicle terminal controls the target vehicle according to the optimization parameter index value, so that the target vehicle can continuously improve the optimization target.

[0078] In one embodiment, the above generation of optimization parameter index value according to the currently set first loop parameter index value, vehicle state information and optimization target value includes: obtaining a threshold value of the parameter index value; generating an initial parameter according to the parameter index value, vehicle state information and optimization target value; and correcting the initial parameter index value through the threshold value to obtain the optimization parameter index value.

[0079] The threshold value of the parameter index value refers to a pre-set numerical value, which can be a value or a numerical range, for example, [100, 200], and the value can be set according to the actual use scenario, which is not specifically limited here.

[0080] The initial parameter is a parameter value generated by the server according to the current parameter index value, the current vehicle state, and the optimization target. The value is generated according to a pre-trained model. Since the parameter index value of the first loop needs to be satisfied in the vehicle parameter optimization process, it needs to be corrected subsequently. Optionally, the threshold value can be used for correction, or the reward function can be used for correction.

[0081] Specifically, the server first obtains the threshold value of the parameter index value, and then adds the threshold value to the process of generating the optimized parameter index value. Specifically, the server generates an initial parameter according to the parameter index value, the vehicle state information, and the optimization target through a pre-trained model, and then directly corrects the generated initial parameter according to the threshold value to obtain the optimized parameter index value. Optionally, when the initial parameter exceeds the pre-set maximum threshold value, it is reduced so that it can meet the threshold value; when the initial parameter is lower than the pre-set minimum threshold value, it is increased so that it can meet the threshold value.

[0082] In one embodiment, the server dynamically adjusts the power domain controller related parameters (such as the torque accelerator pedal mapping table) according to the optimization target, such as the goal of reducing energy consumption, under the premise of meeting the control index of the first loop. The control index of the first loop can be to add these constraints to the design of generating the optimized parameter index value, and to add the corresponding threshold and threshold limit after generating the initial parameter.

[0083] In the above embodiment, the threshold value of the parameter index value is directly corrected to the initial parameter generated by the server, and then the optimized parameter index value generated is ensured to meet the control index of the first loop.

[0084] In one embodiment, the above generating the optimized parameter index value according to the current set first loop parameter index value, vehicle state information, and optimization target value includes: obtaining a constraint condition of the parameter index value; obtaining a pre-designed reward function and adding the constraint condition to the reward function; and generating the optimized parameter index value according to the parameter index value, the vehicle state information, the optimization target, and the reward function.

[0085] The constraint condition refers to a pre-set constraint condition for generating the optimized parameter index value under the premise of meeting the index of the first loop. For example, the constraint condition can be an inequality, such as torque not exceeding 4000 Nm, which can be set according to the actual application scenario, and is not specifically limited in this embodiment.

[0086] Specifically, the server first acquires the constraint condition of the parameter index value and a pre-designed reward function, wherein the reward function is set according to the current use scenario, for example, to reduce energy consumption as the reward function, and then the server adds the pre-set constraint condition to the reward function, and generates the optimization parameter index value according to the current parameter index value, the current vehicle state information, the optimization target value and the reward function including the constraint condition, and through the pre-trained model. In other embodiments, the constraint condition can also not be included, that is, the constraint condition is not added to the reward function, but is directly fed back through the optimization target, for example, energy consumption.

[0087] In one embodiment, the constraint of the first loop control index, that is, the constraint condition, is included in the reward value, and the server adjusts the output optimization strategy through the feedback of the reward. For example, if the design of the reward function causes the violation of the constraint to result in the reduction of the reward value, the server increases the reward value by adjusting the parameter, and finally makes the system tend to meet the constraint.

[0088] In the above embodiment, the optimization parameter index value is generated according to the optimization target by designing the reward function to meet the first loop parameter index value.

[0089] In one embodiment, as shown in Figure 4 , a vehicle parameter optimization method is provided, which is applied to the target vehicle terminal 102 in Figure 1 for example, including the following steps:

[0090] S402, controlling the target vehicle through the first loop to obtain an optimization target value.

[0091] Specifically, the vehicle terminal controls the target vehicle through the first loop. For example, when the target vehicle is an ordinary vehicle without an intelligent driving system, the first loop (a conventional control vehicle loop) is specifically combined with Figure 5 , as shown in Figure 5 , which is an ordinary vehicle parameter optimization schematic diagram in one embodiment. The first loop (conventional control vehicle loop) is operated by the driver normally driving the vehicle pedal and brake pedal; the power domain controller receives the pedal and brake pedal signals, obtains the required request torque through calculation, and outputs to the power system, and the power system executes the instruction of the power domain controller to drive the vehicle. In this embodiment, the agent (also referred to as an intelligent decision module) is a server, wherein the agent and its input and output interface constitute the second loop, that is, the power domain controller parameter optimization loop.

[0092] In one embodiment, the control mode of the first loop of different types of target vehicles is different, combined with Figure 6 , as shown in Figure 6This is a schematic diagram of an intelligent driving system including an intelligent driving longitudinal controller in one embodiment. In the first loop, the intelligent driving longitudinal controller calculates the requested speed, acceleration signal, or deceleration signal value according to the motion planning algorithm and sends it to the power domain controller. After receiving the requested speed, acceleration, or deceleration signal, the power domain controller calculates the required requested torque and outputs it to the power system. The power system executes the instructions of the power domain controller to drive the vehicle. In this embodiment, the intelligent agent (also called an intelligent decision-making module) is a server, wherein the intelligent agent and its input and output interfaces constitute the second loop, namely the power domain controller parameter optimization loop. The control method of the intelligent driving controller is independent and not affected by the second loop. The goal is to achieve the optimization target S202 by optimizing the power domain control parameters.

[0093] In one embodiment, combined Figure 7 As shown, Figure 7 This is a schematic diagram of an intelligent driving system including an intelligent driving longitudinal controller in one embodiment. In the first loop, the intelligent driving longitudinal controller calculates a requested speed, acceleration signal, or deceleration signal value based on a motion planning algorithm and sends it to the power domain controller. The power domain controller calculates the requested speed, acceleration, or deceleration signal to obtain the required torque, which is output to the power system. The power system executes the power domain controller's instructions to drive the vehicle. The intelligent agent (also known as the intelligent decision-making module) is a server, and the intelligent agent and its input and output interfaces constitute the second loop, the intelligent driving longitudinal controller parameter optimization loop. The goal is to achieve optimization target S202 by optimizing the intelligent driving longitudinal controller parameters.

[0094] S404: Collect vehicle information through vehicle sensors and generate vehicle status information based on the vehicle information.

[0095] Vehicle information refers to information collected through vehicle sensors. This can be information collected through onboard motion sensors, such as wheel speedometers, accelerometers, and inertial navigation systems, to obtain vehicle motion status, such as speed, acceleration, and direction. It can also be information collected through onboard motion sensors, such as wheel speedometers, accelerometers, and inertial navigation systems, to obtain vehicle motion status, such as speed, acceleration, and direction. It can also be information collected through onboard energy storage systems, such as the voltage and current values ​​of battery packs and cells measured by voltage sensors and current sensors in power management systems. After the target vehicle terminal collects vehicle information through various vehicle sensors, it generates corresponding vehicle status information.

[0096] In one embodiment, after the target vehicle terminal collects vehicle information through various vehicle sensors in the target vehicle, it can generate vehicle status information according to a preset format. Optionally, the vehicle information can be filtered and then the vehicle status information can be generated, so as to ensure that the vehicle status information generated each time is valid.

[0097] S406, uploading the vehicle state information and the optimization target value to the server.

[0098] Specifically, the vehicle state information and the parameter index value are uploaded to the server by the system or device installed in the target vehicle, and optionally, the vehicle state information and the parameter index value can be uploaded to the server by the TBox system.

[0099] S408, receiving the optimization parameter index value sent by the server, and controlling the target vehicle according to the optimization parameter index value.

[0100] Specifically, after the target vehicle terminal receives the optimization parameter index value sent by the server, the target vehicle is controlled according to the optimization parameter index value, and optionally, the target vehicle can be controlled based on the vehicle type of the target vehicle. After judging the vehicle type of the target vehicle, the target vehicle can be controlled according to the vehicle type of the target vehicle, so as to accurately control the target vehicle, and avoid the failure of controlling the target vehicle due to the difference in vehicle type.

[0101] In the above embodiment, the target vehicle terminal first controls the target vehicle through the first loop to obtain the optimization target value and collects vehicle information through the vehicle sensor, generates vehicle state information according to the vehicle information, and then uploads the vehicle state information and the optimization target value to the server. The server calculates the gradient direction of improving the optimization parameter index according to the vehicle state information, the current parameter index value and the optimization target value, thereby generating the optimization parameter index value, and sends the optimization parameter index value to the vehicle terminal. The target vehicle terminal controls the target vehicle according to the optimization parameter index value, so that the target vehicle can continuously improve the optimization target value.

[0102] In one of the embodiments, the above receiving the optimization parameter sent by the server and controlling the target vehicle according to the optimization parameter index value comprises: controlling the target vehicle according to the optimization parameter index value based on the vehicle type of the target vehicle.

[0103] Specifically, the target vehicle terminal controls the target vehicle based on the vehicle type of the target vehicle, because the vehicle types of different target vehicles are different, so the target vehicle terminal needs to judge the vehicle type first, and then control the target vehicle according to the vehicle type and the optimization parameter index value.

[0104] In the above embodiment, the target vehicle terminal controls the target vehicle based on the vehicle type of the target vehicle, so that the target vehicle can be accurately controlled according to the vehicle type of the target vehicle.

[0105] In one embodiment, the above-mentioned vehicle type based on the target vehicle is controlled according to the optimized parameter index value to achieve the S202 optimization target, including: when the vehicle type does not include an intelligent driving system, the target vehicle is controlled according to the parameter index value by optimizing the power domain controller; when the vehicle type includes an intelligent driving system, the target vehicle can also be controlled by optimizing the power domain controller parameter index value alone; when the vehicle type includes an intelligent driving system, the target vehicle is controlled according to the parameter index value by optimizing the intelligent driving longitudinal controller.

[0106] Specifically, when the vehicle type does not include an intelligent driving system, continue to combine Figure 5 As shown, the target vehicle terminal will control the target vehicle according to the optimization index value by optimizing the power domain controller.

[0107] Specifically, when the vehicle type includes an intelligent driving system, continue to combine Figure 6 As shown, after the target vehicle terminal receives the optimization parameter index value sent by the server, it will control the target vehicle according to the control parameter index value through the optimized power domain controller.

[0108] Specifically, when the vehicle type includes an intelligent driving system, continue to combine Figure 7 As shown, after the target vehicle terminal receives the optimization parameter index value sent by the server, it will control the target vehicle according to the control parameter index value by optimizing the intelligent driving longitudinal controller.

[0109] In the above embodiment, target vehicles of different vehicle types are controlled by optimizing parameter index values, thereby achieving precise control of target vehicles of different vehicle types, thereby achieving the optimization goal of S202.

[0110] In one embodiment, continue to combine Figure 5 As shown, the system consists of two loops, one is the conventional vehicle control loop (the first loop), and the other is the controller parameter optimization loop (the loop where the intelligent agent is located, the second loop, in this embodiment the intelligent agent is the server).

[0111] Among them, the conventional vehicle control loop is that the driver drives the vehicle normally by operating the accelerator pedal and brake pedal; the power domain controller receives the accelerator pedal and brake pedal signals, obtains the required requested torque through calculation, and outputs it to the power system. The power system executes the instructions of the power domain controller to drive the vehicle.

[0112] The controller parameter optimization loop is mainly composed of an intelligent agent (also referred to as an intelligent decision module) and its input and output interfaces. The intelligent agent obtains the vehicle motion state such as vehicle speed, acceleration and vehicle driving direction through vehicle-mounted motion sensors such as a wheel speed meter, an accelerometer, an inertial navigation system and the like, obtains the position state of the accelerator and brake pedals through pedal sensors, and obtains the voltage and current values of the battery and the battery core through sensors of the power management system. Then, the intelligent agent dynamically adjusts the relevant parameters (such as a torque accelerator pedal mapping table) of the power domain controller according to the vehicle motion state, the accelerator pedal and brake pedal state, and under the premise of meeting the control indicators of the conventional control loop, so as to achieve the optimal energy consumption reduction target. There are two ways to meet the control indicators of the conventional control loop. The first way is to add these constraints to the design of the parameter optimization loop, for example, to add corresponding threshold and threshold limits to the parameters optimized by the parameter optimization loop. The second way is to implicitly or explicitly design a reward function to incorporate the constraints of the conventional control loop control indicators into the reward value, and the intelligent agent adjusts the output optimization strategy through the feedback of the reward. For example, if the design of the reward function causes a decrease in the reward value when these constraints are violated, the intelligent agent will increase the reward value by adjusting the parameters, and ultimately the system will tend to meet these constraints. The parameter adjustment method of the parameter optimization link can be the current most advanced or typical reward-driven reinforcement learning method such as the policy gradient method, the Q-learning method or the model-based reinforcement learning method.

[0113] In the above embodiments, an intelligent decision module is added to the existing power system, intelligent decision is made by observing the motion state of the vehicle and the motion planning of the auxiliary driving system, so that the vehicle achieves the optimization target, and secondly, the control parameters of the power system or the auxiliary driving system are automatically dynamically adjusted as the reward function to reduce energy consumption.

[0114] It should be understood that although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0115] Based on the same inventive concept, the embodiments of the present application further provide a vehicle parameter optimization device for implementing the vehicle parameter optimization method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more vehicle parameter optimization device embodiments provided below can refer to the limitations of the vehicle parameter optimization method described above, which will not be repeated here.

[0116] In one embodiment, as shown in Figure 8 a vehicle parameter optimization device applied to a server is provided, comprising: an optimization target acquisition module 100, a vehicle state receiving module 200, an optimization parameter index value generation module 300, and an optimization parameter index value sending module 400, wherein:

[0117] The optimization target acquisition module 100 is configured to acquire an optimization target.

[0118] The vehicle state receiving module 200 is configured to receive vehicle state information uploaded by a target vehicle terminal and an optimization target value of a first loop.

[0119] The optimization parameter index value generation module 300 is configured to generate an optimization parameter index value according to a currently set first loop parameter index value, vehicle state information, and the optimization target value.

[0120] The optimization parameter index value sending module 400 is configured to send the optimization parameter index value to the target vehicle terminal, and the optimization parameter index value is used to instruct the target vehicle terminal to control a target vehicle.

[0121] In one embodiment, the optimization parameter generation module 300 described above comprises:

[0122] A threshold acquisition unit is configured to acquire a threshold of the parameter index value.

[0123] An initial parameter index value generation unit is configured to generate an initial parameter index value according to the parameter index value, the vehicle state information, and the optimization target value.

[0124] A first optimization parameter index value correction unit is configured to correct the initial parameter index value by the threshold to obtain the optimization parameter index value.

[0125] In one embodiment, the optimization parameter generation module 300 described above comprises:

[0126] A constraint condition acquisition unit is configured to acquire a constraint condition of the parameter index value.

[0127] A reward function acquisition unit is configured to acquire a pre-designed reward function and add the constraint condition to the reward function.

[0128] The second optimization parameter index value correction unit is configured to generate the optimization parameter index value according to the parameter index value, the vehicle state information, the optimization target value, and the reward function.

[0129] In one embodiment, as shown in Figure 9 A vehicle parameter optimization apparatus applied to a vehicle terminal is provided, which comprises a vehicle state information generation module 500, a parameter index acquisition module 600, an information uploading module 700, and a vehicle control module 800.

[0130] The parameter index acquisition module 600 is configured to control the target vehicle through a first loop to obtain the optimization target value.

[0131] The vehicle state information generation module 500 is configured to collect vehicle information through a vehicle sensor and generate vehicle state information according to the vehicle information.

[0132] The information uploading module 700 is configured to upload the vehicle state information and the optimization target value to a server.

[0133] The vehicle control module 800 is configured to receive the optimization parameter index value sent by the server and control the target vehicle according to the optimization parameter index value.

[0134] In one embodiment, the above-mentioned parameter optimization module 800 comprises:

[0135] The vehicle type optimization unit is configured to control the target vehicle according to the optimization parameter index value based on the vehicle type of the target vehicle.

[0136] In one embodiment, the above-mentioned vehicle type optimization unit comprises:

[0137] The first vehicle type optimization sub-unit is configured to control the target vehicle according to the optimization parameter index value through a power domain controller when the vehicle type does not include an intelligent driving system.

[0138] The second vehicle type optimization sub-unit is configured to control the target vehicle according to the optimization parameter index value through a power domain controller or an intelligent driving longitudinal controller when the vehicle type includes an intelligent driving system.

[0139] The above-mentioned various modules in the vehicle parameter optimization apparatus can be realized by software, hardware, and combinations thereof in whole or in part. The above-mentioned various modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform the operations corresponding to the above-mentioned various modules.

[0140] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram thereof can be as shown in Figure 10As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is used to store vehicle state information data. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to implement a vehicle parameter optimization method.

[0141] Those skilled in the art can understand that, Figure 10 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or less components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0142] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the above method embodiments.

[0143] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps in the above method embodiments.

[0144] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps in the above method embodiments.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0146] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0147] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be noted that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method of optimizing parameters of a vehicle, characterized in that, The method applied to a server comprises: obtaining an optimization target; receiving vehicle state information uploaded by a target vehicle terminal and an optimization target value of a first loop; generating an optimization parameter index value according to a currently set first loop parameter index value, the vehicle state information and the optimization target value; sending the optimization parameter index value to the target vehicle terminal, the optimization parameter index value being used to instruct the target vehicle terminal to control a target vehicle; judging a vehicle type of the target vehicle; when the vehicle type of the target vehicle does not include an intelligent driving system, a driver normally drives the vehicle to operate an accelerator pedal and a brake pedal; after a power domain controller receives signals of the accelerator pedal and the brake pedal, the power domain controller calculates a first request torque and outputs the first request torque to a power system, the power system drives the target vehicle according to an instruction of the power domain controller; and the server sends the optimization parameter index value to the power domain controller of the target vehicle terminal; when the vehicle type of the target vehicle includes the intelligent driving system, an intelligent driving longitudinal controller calculates a speed or acceleration signal or deceleration signal request value according to a motion planning algorithm and sends the speed or acceleration signal or deceleration signal request value to the power domain controller; after the power domain controller receives the speed or acceleration signal or deceleration signal request value, the power domain controller calculates a second request torque and outputs the second request torque to the power system, the power system drives the target vehicle according to the instruction of the power domain controller; and the server sends the optimization parameter index value to the power domain controller or the intelligent driving longitudinal controller of the target vehicle terminal.

2. The method of claim 1, wherein, The method of generating the optimization parameter index value according to the currently set first loop parameter index value, the vehicle state information and the optimization target value comprises: obtaining a threshold value of the parameter index value; generating an initial parameter index value according to the parameter index value, the vehicle state information and the optimization target value; correcting the initial parameter index value by the threshold value to obtain the optimization parameter index value.

3. The method of claim 1, wherein, The method of generating the optimization parameter index value according to the currently set first loop parameter index value, the vehicle state information and the optimization target value comprises: obtaining a constraint condition of the parameter index value; obtaining a pre-designed reward function and adding the constraint condition to the reward function; generating the optimization parameter index value according to the parameter index value, the vehicle state information, the optimization target value and the reward function.

4. A method of optimizing vehicle parameters, characterized by The method applied to a vehicle terminal comprises: controlling a target vehicle through a first loop to obtain an optimization target value; collecting vehicle information through a vehicle sensor and generating vehicle state information according to the vehicle information; uploading the vehicle state information and the optimization target value to a server; receiving an optimization parameter index value sent by the server and controlling the target vehicle according to the optimization parameter index value; judging a vehicle type of the target vehicle; When the vehicle type of the target vehicle does not include an intelligent driving system, the first loop is operated by a driver normally driving a vehicle to operate an accelerator pedal and a brake pedal; after the power domain controller receives signals of the accelerator pedal and the brake pedal, the first request torque is calculated and output to a power system, and the power system drives the target vehicle according to the instruction of the power domain controller; the server sends the optimization parameter index value to the power domain controller of the target vehicle terminal; When the vehicle type of the target vehicle includes an intelligent driving system, the first loop is operated by an intelligent driving longitudinal controller to calculate a speed or acceleration signal or deceleration signal request value and send the value to a power domain controller; after the power domain controller receives the speed or the acceleration signal or the deceleration signal request value, the second request torque is calculated and output to a power system, and the power system drives the target vehicle according to the instruction of the power domain controller; the server sends the optimization parameter index value to the power domain controller or the intelligent driving longitudinal controller of the target vehicle terminal.

5. The method of claim 4, wherein, The receiving server sends the optimization parameter index value, and controls the target vehicle according to the optimization parameter index value, including: Based on the vehicle type of the target vehicle, the target vehicle is controlled according to the optimization parameter index value.

6. The method of claim 5, wherein, The control based on the vehicle type of the target vehicle according to the optimization parameter index value includes: When the vehicle type does not include an intelligent driving system, the target vehicle is controlled by the power domain controller according to the optimization parameter index value; When the vehicle type includes an intelligent driving system, the target vehicle is controlled by the power domain controller or the intelligent driving longitudinal controller according to the optimization parameter index value.

7. A vehicle parameter optimization apparatus characterized by comprising: The application is applied to a server, and the device includes: An optimization target acquisition module is configured to acquire an optimization target value; A vehicle state receiving module is configured to receive vehicle state information uploaded by a target vehicle terminal and an optimization target value of a first loop; An optimization parameter index value generation module is configured to generate an optimization parameter index value according to a currently set first loop parameter index value, the vehicle state information and the optimization target value. The optimization parameter index value sending module is configured to send the optimization parameter index value to the target vehicle terminal, and the optimization parameter index value is used to instruct the target vehicle terminal to control the target vehicle.

8. A vehicle parameter optimization apparatus characterized by comprising: The vehicle state information generation module is configured to collect vehicle information through a vehicle sensor and generate vehicle state information according to the vehicle information. The parameter index acquisition module is configured to control a target vehicle through a first loop according to the vehicle state information to obtain an optimization target value. The information uploading module is configured to upload the vehicle state information and the optimization target value to a server. The vehicle control module is configured to receive an optimization parameter index value sent by the server and control the target vehicle according to the optimization parameter index value, judge a vehicle type of the target vehicle, when the vehicle type of the target vehicle does not include an intelligent driving system, a driver normally drives the vehicle to operate a throttle pedal and a brake pedal, a power domain controller receives signals of the throttle pedal and the brake pedal, calculates a first request torque, and outputs the first request torque to a power system, the power system drives the vehicle according to an instruction of the power domain controller, when the vehicle type of the target vehicle includes the intelligent driving system, an intelligent driving longitudinal controller calculates a request speed or an acceleration signal or a deceleration signal request value according to a motion planning algorithm and sends the request value to the power domain controller, the power domain controller receives the request speed or the acceleration signal or the deceleration signal, calculates a second request torque, and outputs the second request torque to the power system, and the power system drives the vehicle according to the instruction of the power domain controller. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 3 or 4 to 6. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 3 or 4 to 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, ​ 11. A computer program product comprising a computer program, characterized in that, The computer program, which when executed by the processor, implements the steps of the method of any one of claims 1 to 3 or 4 to 6.

Images