Vehicle control method and device, system, vehicle controller, and storage medium

Abstract

The present application provides a vehicle control method and device, system, vehicle controller, and storage medium, which relate to the field of vehicle control technology. The method includes: obtaining the current vehicle state information of the vehicle, the driving condition information of the current driving condition of the vehicle, and the driving habit information of the user driving the vehicle. The predicted motion information of the vehicle at the next driving moment under the current driving condition is predicted through the current vehicle state information and driving habit information. The driving information of the vehicle is determined through the current vehicle state information, driving condition information, and predicted motion information. The vehicle is controlled to drive according to the driving information at the next driving moment. The vehicle driving information can be adjusted to adapt to the constantly changing current vehicle state information, driving condition information, and driving habit information, so as to realize the refined management of vehicle energy, effectively reduce unnecessary energy consumption, and improve the vehicle's cruising range.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle control method and device, system, vehicle controller, and storage medium. Background Art

[0002] At present, pure electric buses usually rely on the driver to send pedal opening information to the vehicle control system of the pure electric bus through the accelerator pedal of the pure electric bus. The vehicle control system directly adjusts the motor torque according to the pedal opening information of the accelerator pedal, thereby controlling the acceleration or deceleration of the pure electric bus.

[0003] However, the driver's uneven driving operations near bus stops (e.g., sudden acceleration or sudden braking) will significantly increase the energy consumption of the pure electric bus, reduce the cruising range of the pure electric bus, and affect the operating efficiency of the pure electric bus.

[0004] Based on this, the present application provides a vehicle control method to improve the energy-saving efficiency of electric buses. Summary of the invention

[0005] The purpose of the present application is to provide a vehicle control method and device, system, vehicle controller, and storage medium to solve the problem of low energy-saving efficiency of current vehicle control systems.

[0006] In a first aspect, the present application provides a vehicle control method, which is applied to a vehicle, and the method includes: obtaining current vehicle state information of the vehicle, driving condition information of the current driving condition of the vehicle, and driving habit information of the user driving the vehicle. Predicted motion information of the vehicle at the next driving moment under the current driving condition is predicted based on the current vehicle state information and driving habit information. Determine the driving information of the vehicle based on the current vehicle state information, driving condition information, and predicted motion information. Control the vehicle to drive according to the driving information at the next driving moment.

[0007] The vehicle control method provided in the embodiment of the present application obtains the current vehicle state information of the vehicle, the driving condition information of the current driving condition of the vehicle, and the driving habit information of the user driving the vehicle, and predicts the predicted motion information of the vehicle at the next driving moment under the current driving condition by utilizing the current vehicle state information and driving habit information. The driving information of the vehicle is determined by the current vehicle state information, the driving condition information, and the predicted motion information, and finally the vehicle is controlled to travel according to the driving information at the next driving moment. The method can adapt to the constantly changing current vehicle state information, driving condition information, and driving habit information to adjust the vehicle driving information, realize the refined management of vehicle energy, effectively reduce unnecessary energy consumption, and improve the vehicle's cruising range.

[0008] In one possible implementation, the predicted motion information of the vehicle at the next driving moment under the current driving condition is predicted based on the current vehicle state information and driving habit information, including: inputting the current vehicle state information, driving condition information and driving habit information into a trained reinforcement learning model to obtain predicted motion information.

[0009] In this possible implementation, the current vehicle state information, driving condition information and driving habit information are input into the trained reinforcement learning model to obtain predicted motion information. By continuously interacting with the driving condition information, the optimal predicted motion information can be found according to the reward value in the reinforcement learning model.

[0010] In a possible implementation, the training process of the reinforcement learning model includes: obtaining first state information and second state information of the vehicle. The first state information is used to indicate historical state information of the first state of the vehicle. The second state information is used to indicate state information of the vehicle switching from the first state to the second state according to the first action information. Using the first state information, the second state information and the first action information, the vehicle operation parameters of the vehicle switching from the first state to the second state are calculated. The loss function of the reinforcement learning model is generated according to the vehicle operation parameters. The model parameters of the reinforcement learning model are adjusted using a preset adjustment algorithm to make the loss function converge.

[0011] In a possible implementation, the first state information, the second state information and the first action information are used to calculate the vehicle operation parameters when the vehicle switches from the first state to the second state, including: using the first state information, the second state information and the first action information, the energy efficiency, the driving time and the smoothness of the vehicle switching from the first state to the second state are calculated. The smoothness is used to represent the acceleration change rate of the vehicle switching from the first state to the second state. The energy efficiency, the driving time and the smoothness are input into the reward function to calculate the vehicle operation parameters.

[0012] In this possible implementation method, the present application uses the first state information, the second state information and the first action information to calculate the energy efficiency, driving time and smoothness of the vehicle when switching from the first state to the second state, and comprehensively calculates the vehicle operating parameters from the perspectives of energy efficiency, driving time and smoothness, so that the vehicle operating parameters are more accurate, and the refined management of vehicle energy is achieved to improve energy-saving efficiency.

[0013] In a possible implementation, the vehicle control method provided by the present application further includes: receiving feedback information from a user of the vehicle. The feedback information is the evaluation information of the comfort of the vehicle by the user of the vehicle. The user includes the driver and / or the passenger of the vehicle. The model parameters are adjusted using the feedback information.

[0014] In this possible implementation, the present application receives feedback from users and uses the feedback to adjust model parameters, thereby being able to learn and adapt to user feedback in real time and making vehicle operating parameters more accurate.

[0015] In one possible implementation, the driving information includes the motor torque parameters of the vehicle; the driving information of the vehicle is determined through the current vehicle state information, driving condition information and predicted motion information, including: performing fuzzy reasoning through the current vehicle state information, driving condition information and predicted motion information to obtain the motor torque parameters.

[0016] In this possible implementation method, the present application performs fuzzy reasoning through the current vehicle state information, driving condition information and predicted motion information to obtain the motor torque parameters, and can process the non-new relationship between the current vehicle state information, driving condition information, predicted motion information and motor torque parameters, so that the motor torque parameters are more accurate, so that the vehicle can maintain efficient and energy-saving operation under different vehicle states and driving conditions.

[0017] In a possible implementation, fuzzy reasoning is performed on the current vehicle state information, driving condition information and predicted motion information to obtain the motor torque parameter, including: using preset fuzzy rules and preset membership functions to perform fuzzy reasoning on the current vehicle state information, driving condition information and predicted motion information to determine the fuzzy set of the vehicle's motor torque. The fuzzy set is defuzzified to determine the motor torque parameter.

[0018] In this possible implementation, the present application utilizes preset fuzzy rules and preset membership functions to perform fuzzy reasoning on the current vehicle state information, driving condition information and predicted motion information, and can obtain a fuzzy set of the vehicle's motor torque, and then defuzzify the fuzzy set to obtain the motor torque parameters. It can handle the non-new relationship between the current vehicle state information, driving condition information, predicted motion information and motor torque parameters, making the motor torque parameters more accurate, so that the vehicle can maintain efficient and energy-saving operation under different vehicle states and driving conditions.

[0019] In a possible implementation, defuzzifying the fuzzy set to determine the motor torque parameter includes: defuzzifying the fuzzy set using a center of gravity method and / or a maximum membership method to determine the motor torque parameter.

[0020] In this possible implementation, the present application can obtain more accurate motor torque parameters by defuzzifying the fuzzy set using the center of gravity method and / or the maximum membership method.

[0021] In one possible implementation, controlling the vehicle to travel according to the driving information at the next driving moment includes: sending the motor torque parameter to the vehicle control system of the vehicle, so that the vehicle control system controls the vehicle's motor according to the motor torque parameter at the next driving moment, so as to control the vehicle to travel according to the driving information at the next driving moment.

[0022] In a possible implementation, the vehicle control method provided by the present application further includes: obtaining actual motor torque feedback information of the vehicle and adjusting the motor torque parameters using the actual motor torque feedback information.

[0023] In this possible implementation, after obtaining the actual motor torque feedback information of the vehicle, the motor torque parameters are adjusted by utilizing the actual motor torque feedback information to ensure that the motor torque output accurately matches the driving requirements, adapts to changes in the external environment, and maintains system stability and response speed.

[0024] In one possible implementation, the vehicle control method provided in the present application further includes: sending the predicted motion information and driving information to a display device of the vehicle so that the display device displays the predicted motion information and driving information to the user.

[0025] In this possible implementation, by sending the predicted motion information and driving information to the display device of the vehicle, the predicted motion information and driving information can be displayed to the user in real time, and the user can adjust the motion information and driving information in real time according to the user's needs to meet the user's needs.

[0026] In a second aspect, the present application provides a vehicle control device, which includes: an acquisition module, a processing module and a control module.

[0027] The acquisition module is used to acquire the current vehicle state information of the vehicle, the driving condition information of the current driving condition of the vehicle, and the driving habit information of the user driving the vehicle;

[0028] A processing module, used to predict the predicted motion information of the vehicle at the next driving moment under the current driving condition based on the current vehicle state information and driving habit information; and to determine the driving information of the vehicle based on the current vehicle state information, driving condition information and predicted motion information;

[0029] The control module is used to control the vehicle to travel according to the driving information at the next driving moment.

[0030] The vehicle control device provided in the embodiment of the present application obtains the current vehicle state information of the vehicle, the driving condition information of the current driving condition of the vehicle, and the driving habit information of the user driving the vehicle, and predicts the predicted motion information of the vehicle at the next driving moment under the current driving condition by utilizing the current vehicle state information and driving habit information. The driving information of the vehicle is determined by the current vehicle state information, the driving condition information, and the predicted motion information, and finally the vehicle is controlled to travel according to the driving information at the next driving moment. The device can adapt to the constantly changing current vehicle state information, driving condition information, and driving habit information to adjust the vehicle driving information, realize refined management of vehicle energy, effectively reduce unnecessary energy consumption, and improve vehicle range.

[0031] In a third aspect, the present application provides a vehicle control system, which includes: a cloud and the vehicle control device shown in the second aspect.

[0032] In a fourth aspect, the present application provides a vehicle controller having the function of implementing the vehicle control method of the first aspect or any possible implementation method. The function can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0033] In a fifth aspect, a computer-readable storage medium is provided, in which instructions are stored, and when the computer-readable storage medium is run on a computer, the computer can execute the vehicle control method of the first aspect or any possible implementation method.

[0034] In a sixth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the vehicle control method of the first aspect or any possible implementation method.

[0035] Among them, the technical effects brought about by any design method in the second to sixth aspects can refer to the technical effects brought about by different possible implementation methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A schematic diagram of the structure of a vehicle controller provided in an embodiment of the present application;

[0038] Figure 2 A schematic diagram of the structure of a vehicle control system provided in an embodiment of the present application;

[0039] Figure 3 A specific flow chart of a vehicle control method provided in an embodiment of the present application;

[0040] Figure 4 A specific example diagram of a vehicle control method provided in an embodiment of the present application;

[0041] Figure 5 Another specific flow chart of a vehicle control method provided by an embodiment of the present application;

[0042] Figure 6 A specific schematic diagram of the acceleration distribution of a vehicle under a WLTC condition in a vehicle control method provided in an embodiment of the present application;

[0043] Figure 7 A specific schematic diagram of the impact degree distribution of a vehicle under WLTC conditions in a vehicle control method provided in an embodiment of the present application;

[0044] Figure 8 A specific schematic diagram of the performance of the battery SOC of a vehicle under WLTC conditions in a vehicle control method provided in an embodiment of the present application;

[0045] Fig. 9 A specific schematic diagram of the performance of the battery capacity decay rate of a vehicle under WLTC conditions in a vehicle control method provided in an embodiment of the present application;

[0046] Fig.10 A schematic diagram of the structure of a vehicle control device provided in an embodiment of the present application;

[0047] Fig.11 A structural schematic diagram of a vehicle control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0049] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0050] First, some concepts involved in a vehicle control method and device, system, electronic device, and storage medium provided in an embodiment of the present application are explained.

[0051] The state space integrates the vehicle's current state information, the vehicle's current driving condition information, and the driving habit information of the user driving the vehicle into the state space input of the reinforcement learning model. The state space can reflect the vehicle's current and expected operating state.

[0052] Action space is used to represent the movement trend of the vehicle. It can include acceleration, deceleration, and maintaining the current movement speed.

[0053] At present, existing pure electric buses usually rely on the driver to send an opening signal to the vehicle's control system by controlling the vehicle's electric pedal. After receiving the opening signal, the control system generates a motor torque command based on the opening signal to adjust the vehicle's motor output torque, thereby controlling the vehicle's acceleration or deceleration. In this method, there is a preset mapping relationship between the electric pedal and the motor output torque, that is, the greater the opening of the electric pedal, the greater the motor output torque, and the greater the vehicle's acceleration. This strategy is simple and intuitive, and the driver is easy to operate.

[0054] However, in this vehicle control method, due to the driver's driving habits and the degree of control the driver has over the vehicle's electric pedal, the vehicle's acceleration may not be ideal, resulting in frequent sudden stops and starts, which increases the vehicle's energy consumption. At the same time, in this method, the vehicle cannot perceive future changes in road conditions in advance, cannot drive to adapt to future road conditions, and it is difficult to achieve refined management of the vehicle's energy.

[0055] Based on this, the present application provides a vehicle control method and device, system, electronic device, and storage medium, the basic principle of which is: obtaining the current vehicle state information of the vehicle, the driving condition information of the vehicle's current driving condition, and the driving habit information of the user driving the vehicle, and predicting the predicted motion information of the vehicle at the next driving moment under the current driving condition through the current vehicle state information and driving habit information. Determine the vehicle's driving information through the current vehicle state information, driving condition information, and predicted motion information. Controlling the vehicle to drive according to the driving information at the next driving moment can enable the vehicle control strategy to learn and adapt to the vehicle state information, the driving condition information of the vehicle's current driving condition, and the driving habit information of the user driving the vehicle, thereby improving the intelligence and predictability of driving decisions, reducing unnecessary sudden stops and starts of the vehicle, and reducing the vehicle's energy consumption.

[0056] The implementation of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0057] The solution shown in the embodiment of the present application can be executed by an electronic device, which can be a vehicle controller of a vehicle. Figure 1 As shown, the vehicle controller 100 may include a sensor 101, a communication module 102, an electronic control unit 103, and a motor controller 104. The sensor 101 is connected to the electronic control unit 103 for communication, the communication module 102 is connected to the electronic control unit 103 for communication, and the electronic control unit 103 is connected to the motor controller 104 for communication.

[0058] Among them, the sensor 101 can be deployed at different positions of the vehicle to obtain the current status information of the vehicle, such as the current speed, acceleration, battery power, motor speed, dynamic load change and external ambient temperature of the vehicle, etc. The current status information of the vehicle can also include the charging and discharging current value of the battery of the vehicle, the battery voltage, the remaining battery power (state of charge, SOC), the health status of the battery (state of health, SOH), the number of people getting on and off the vehicle at the station, the time interval of getting on and off, and the distribution of passengers in the car. After obtaining the status information of the vehicle, the sensor 101 converts the status information into an analog signal or a digital signal and sends it to the electronic control unit 103.

[0059] Exemplarily, the sensor 101 may be a vehicle speed sensor, an accelerometer, a battery management system (BMS) interface, an on-board weighing system, an ambient temperature sensor, etc., for collecting the current status information of the vehicle in real time.

[0060] The communication module 102 is used to obtain the driving condition information of the vehicle's current driving condition, such as the vehicle's temperature, humidity, wind speed, road conditions (dry, slippery, icy, etc.) and light intensity. After obtaining the driving condition information, the communication module 102 sends the driving condition information to the electronic control unit 103.

[0061] Exemplarily, the communication module 102 may be a 4G / 5G module, a Wi-Fi module, etc.

[0062] The electronic control unit 103 is used to execute the vehicle control method provided in the embodiment of the present application after receiving the analog signal or digital signal sent by the sensor 101, and predict the predicted motion information of the vehicle at the next driving moment under the current driving condition by using the vehicle state information of the vehicle, the driving condition information of the vehicle's current driving condition, and the driving habit information of the user stored in the electronic control unit. The electronic control unit 103 is also used to determine the driving information of the vehicle through the current vehicle state information, the driving condition information, and the predicted motion information, and send the driving information to the motor controller 104.

[0063] The motor controller 104 is used to control the motor of the vehicle using the driving information after receiving the driving information sent by the electronic control unit 103, so that the vehicle drives according to the driving information at the next driving moment.

[0064] The solution provided in the embodiment of the present application can be executed by the vehicle control system. Figure 2 As shown, the vehicle control system 200 may include a vehicle controller 100 and a cloud 201 .

[0065] The cloud 201 is used to remotely obtain the driving condition information of the current driving condition of the vehicle and send the driving condition information to the communication module 102 of the vehicle controller 100 .

[0066] For example, the developed control software can be burned into an embedded computer and the relevant communication parameters can be configured, so that the communication module can communicate normally with the cloud and the electronic control unit. The control software can be developed based on C# or other suitable programming languages ​​to implement functions such as reinforcement learning algorithms, fuzzy control logic, data acquisition and communication, and driver interaction interfaces.

[0067] It should be noted that the above Figure 1 Schematic electronic equipment and Figure 2 The illustrated vehicle control system is only an example of the application scenario of the present application solution, and is not a limitation of the application scenario of the present application solution.

[0068] On the one hand, the present application discloses a vehicle control method, which can be deployed by Figure 2The vehicle control system shown in Figure 1 The vehicle controller shown in the figure is executed. Figure 3 As shown, the method may include the following steps.

[0069] S301, obtaining current vehicle state information of the vehicle, driving condition information of the current driving condition of the vehicle, and driving habit information of the user driving the vehicle.

[0070] In a possible implementation, the electronic control unit sends a current vehicle status information request message to a sensor of the vehicle, and after receiving the current vehicle status information request message, the sensor sends the current vehicle status information of the vehicle to the electronic control unit.

[0071] It should be noted that the current vehicle status information can also be the current vehicle status information of the vehicle collected by the vehicle's sensor at a preset time, and the current vehicle status information is uploaded to the electronic control unit after collection. This application does not limit the process of obtaining the vehicle status information.

[0072] Exemplarily, the current vehicle state information of the vehicle may include one or more of the following: current speed, acceleration, battery power, motor speed, dynamic load change, and external ambient temperature, etc. The dynamic load change may be a weight change of the vehicle caused by passengers getting on and off the vehicle.

[0073] In a possible implementation, the electronic control unit sends a driving condition information request message to the communication module, and the driving condition information request message is used to request to obtain the driving condition information of the current driving condition of the vehicle. After receiving the driving condition request message, the communication module uploads the driving condition request message to the cloud, and after receiving the driving condition request message, the cloud sends the driving condition information to the communication module, and finally the communication module sends the driving condition information to the electronic control unit.

[0074] Exemplarily, the driving condition information of the current driving condition of the vehicle may include one or more of the following: the slope of the vehicle driving section, the curve, the position of the traffic light, the expected waiting time at the red light, and the expected arrival time at the next stop, etc.

[0075] In a possible implementation, the driving habit information of the user driving the vehicle may be the driving habit information recorded by the electronic control unit of the vehicle when the user drove the vehicle in the past, and the driving habit information is stored in the memory of the vehicle controller. The electronic control unit may directly obtain the driving habit information of the user driving the vehicle from the memory of the vehicle controller.

[0076] Exemplarily, the driving habit information of the user driving the vehicle may include one or more of the following: the user's average parking time at a specific bus stop, a starting speed curve, a stopping speed curve, and the like.

[0077] S302, predicting the predicted motion information of the vehicle at the next driving moment under the current driving condition based on the current vehicle state information and driving habit information.

[0078] In one possible implementation, the electronic control unit inputs the current vehicle state information, driving condition information, and driving habit information into a trained reinforcement learning model to obtain predicted motion information.

[0079] Specifically, Figure 4 As shown, the electronic control unit takes the vehicle's external temperature, vehicle dynamic load, ground adhesion, real-time traffic information, vehicle station location, future driving conditions, and real-time pedal opening as input values, and inputs them into the trained reinforcement learning model to calculate the energy efficiency, driving time, and smoothness of the vehicle switching from the first state to the second state. Among them, smoothness is used to represent the rate of change of acceleration from the first state to the second state. Then, the energy efficiency, driving time, and smoothness are input into the reward function to calculate the vehicle operating parameters. The vehicle operating parameters may include the pedal opening information of the vehicle at the next moment.

[0080] The vehicle control method provided in the embodiment of the present application obtains predicted motion information by inputting current vehicle state information, driving condition information and driving habit information into a trained reinforcement learning model. The optimal predicted motion information can be found according to the reward value in the reinforcement learning model by continuously interacting with the driving condition information.

[0081] The training process of the reinforcement learning model may include: obtaining first state information and second state information of the vehicle.

[0082] The first state information is used to indicate historical state information of the first state of the vehicle. The second state information is used to indicate state information of the vehicle switching from the first state to the second state according to the first action information.

[0083] In a possible implementation, the first state information may include: the first external temperature T1, the first vehicle dynamic load m1, the first ground adhesion condition μ1, the first real-time traffic information τ1, the first vehicle station position p1, the first future driving condition ε1, and the first real-time pedal opening θ1. The second state information may include: the second external temperature T2, the second vehicle dynamic load m2, the second ground adhesion condition μ2, the second real-time traffic information τ2, the second vehicle station position p2, the second future driving condition ε2, and the second real-time pedal opening θ2. The action information may include: acceleration a, deceleration b, and maintaining the current speed c.

[0084] First, the vehicle operation parameters of the vehicle switching from the first state to the second state are calculated using the first state information, the second state information and the first action information. A loss function of the reinforcement learning model is generated according to the vehicle operation parameters. The model parameters of the reinforcement learning model are adjusted using a preset adjustment algorithm so that the loss function converges.

[0085] Exemplarily, the first state information is used to establish a first state vector, and the first state space S1={T1, m1, μ1, τ1, p1, ε1, θ1} of the vehicle's environment is obtained. The second state information is used to establish a second state vector, and the second state space S2={T2, m2, μ2, τ2, p2, ε2, θ2} of the vehicle's environment is obtained. The vehicle's action information is used to accelerate a, decelerate b, and maintain the current speed c to establish a motion vector, and the vehicle's action space α={a, b, c} is obtained.

[0086] Then, the preset reward function is used to calculate the contribution value of the vehicle switching from the first state space S1 to the second state space S2 after the vehicle executes the action space α.

[0087] The reward function can be R(s,α)=w1*R_energy(s,α)+w2*R_time(s,α)+w3*R_comfort(s,α).

[0088] Among them, R_energy(s, α) represents the reward of vehicle energy efficiency and state space and action space, R_time(s, α) represents the reward of vehicle driving time and state space and action space, and R_comfort(s, α) represents the reward of vehicle smoothness and state space and action space. w1, w2, w3 are weight coefficients, which can be adjusted according to the user's needs for energy efficiency, driving time and smoothness. The reward function is a composite reward function based on the highest energy efficiency, the shortest driving time, the maximum passenger comfort (such as reducing acceleration mutations) and driving safety.

[0089] Secondly, the contribution value is combined with the Q function and the Bellman equation to determine the expected cumulative reward that the vehicle will obtain in the future after switching from state S1 to state S2 after executing action α under strategy π. Among them, strategy π represents the probability distribution of the vehicle choosing action α in state S1.

[0090] Among them, the Bellman equation can be Qπ(s1,α1)=E[R(s1,α1)+γ*max_{α2}Qπ(s2,α2)|s1,α1]. Qπ(s1,α1) represents the action value function of state S1. E represents the expected value in state S. R(s1,α1) represents the reward value function, which means that in state S1, selecting action α results in S2. γ represents the discount factor (0<γ<1).

[0091] Finally, by combining the current driving conditions in actual operation, multiple α in the action space are selected according to the current state S1, and the new state S2 after executing multiple α and multiple expected accumulated rewards R are calculated. By repeatedly iteratively updating the Q function or π strategy, the optimal strategy π*(s) is finally converged.

[0092] In a possible implementation, after calculating the vehicle operating parameters, the electronic control unit also receives feedback information from the vehicle user, which may include the driver and / or passenger of the vehicle, and uses the feedback information to adjust the model parameters of the reinforcement learning model.

[0093] The feedback information is the vehicle user's evaluation information on the vehicle's comfort, such as the driver's or passengers' subjective evaluation of the vehicle's driving comfort, riding experience, etc.

[0094] The vehicle control method provided in the embodiment of the present application receives user feedback information and uses the feedback information to adjust model parameters. It can learn and adapt to user feedback in real time to make the vehicle operating parameters more accurate.

[0095] S303, determining the vehicle's driving information through the current vehicle state information, driving condition information and predicted motion information.

[0096] The driving information includes the motor torque parameters of the vehicle.

[0097] In one possible implementation, the electronic control unit uses preset fuzzy rules and preset membership functions to perform fuzzy reasoning on the current vehicle state information, driving condition information, and predicted motion information to determine the fuzzy set of the vehicle's motor torque. The electronic control unit defuzzifies the fuzzy set to determine the motor torque parameter.

[0098] It should be noted that the defuzzification process may be a centroid method and / or a maximum membership method, or other methods, and the present application does not limit the defuzzification process.

[0099] Among them, the determination process of fuzzy rules and membership functions can be that the electronic control unit takes historical vehicle status information, historical driving condition information and historical predicted motion information as input, and takes the historical motor torque parameters of the vehicle as output, defines the interval of the fuzzy set, establishes fuzzy control rules, converts the input into real-time membership through the fuzzy control rules, and constructs the operation rules of the membership function motor torque parameters according to the real-time membership.

[0100] For example, the fuzzy rules can be control rules developed based on expert knowledge or previous test data, such as "if the pedal opening is large and the load is light, increase the torque".

[0101] The vehicle control method provided in the application embodiment performs fuzzy reasoning through the current vehicle state information, driving condition information and predicted motion information to obtain the motor torque parameters. It can handle the non-new relationship between the current vehicle state information, driving condition information, predicted motion information and the motor torque parameters, making the motor torque parameters more accurate, so that the vehicle can maintain efficient and energy-saving operation under different vehicle states and driving conditions.

[0102] S304, controlling the vehicle to travel according to the driving information at the next driving moment.

[0103] The driving information may be a motor torque parameter of the vehicle.

[0104] Specifically, the electronic control unit sends the motor torque parameter to the vehicle control system of the vehicle, so that the vehicle control system controls the motor of the vehicle according to the motor torque parameter at the next driving moment, so as to control the vehicle to drive according to the driving information at the next driving moment.

[0105] In one possible implementation, when the vehicle control system controls the vehicle's motor to drive using the motor torque according to driving information, the electronic control unit continuously receives actual motor torque feedback information, and adjusts the motor torque parameters based on the deviation between the actual motor torque feedback information and the driving information, so that the actual motor torque is more biased towards the driving information.

[0106] After obtaining the actual motor torque feedback information of the vehicle, the vehicle control method provided in the embodiment of the present application adjusts the motor torque parameters by utilizing the actual motor torque feedback information, thereby ensuring that the motor torque output accurately matches the driving requirements, adapts to changes in the external environment, and maintains system stability and response speed.

[0107] In a possible implementation, the vehicle control method provided in the embodiment of the present application may further include: S305. Figure 5 As shown, S305 may be executed after S304.

[0108] S305: Send the predicted motion information and driving information to a display device of the vehicle, so that the display device displays the predicted motion information and driving information to the user.

[0109] Specifically, the electronic control unit sends the predicted motion information and driving information to the display device of the vehicle through the CAN bus of the vehicle, so that the display device displays the motion information and driving information to the user, and the user can adjust the motion information and driving information in real time according to the user's needs. If the user adjusts the motion information and driving information, the display device sends the adjusted motion information and driving information to the electronic control unit, and the electronic control unit sends the adjusted motion information and driving information to the vehicle control system of the vehicle, so that the vehicle control system controls the motor of the vehicle according to the adjusted motion information and driving information at the next driving moment, so as to control the vehicle to drive according to the driving information at the next driving moment.

[0110] The vehicle control method provided in the embodiment of the present application can display the predicted motion information and driving information to the user in real time by sending the predicted motion information and driving information to the display device of the vehicle, and the user can adjust the motion information and driving information in real time according to the user's needs to meet the user's needs.

[0111] One possible implementation method is to continuously detect the actual driving conditions of the vehicle after determining the predicted motion information and driving information, and feed back information such as actual torque output and environmental changes to the reinforcement learning model and fuzzy controller for online learning and parameter adjustment to adapt to new working conditions and driving requirements.

[0112] The vehicle control method provided in the embodiment of the present application obtains the current vehicle state information of the vehicle, the driving condition information of the current driving condition of the vehicle, and the driving habit information of the user driving the vehicle, and predicts the predicted motion information of the vehicle at the next driving moment under the current driving condition by utilizing the current vehicle state information and driving habit information. The driving information of the vehicle is determined by the current vehicle state information, the driving condition information, and the predicted motion information, and finally the vehicle is controlled to travel according to the driving information at the next driving moment. The method can adapt to the constantly changing current vehicle state information, driving condition information, and driving habit information to adjust the vehicle driving information, realize the refined management of vehicle energy, effectively reduce unnecessary energy consumption, and improve the vehicle's cruising range.

[0113] For example, Figure 6 and Figure 7 As shown, Figure 6 It shows the acceleration distribution of the vehicle under WLTC conditions. Figure 7The diagram illustrates the impact degree distribution of the vehicle under the WLTC condition. For a vehicle to which the vehicle control method provided in the embodiment of the present application is applied, the vehicle acceleration distribution can be ensured to be between [-2, 2] and the impact degree distribution can be between [-2.5, 3] during driving, thereby ensuring the comfort of passengers during driving. A larger impact degree is generated when the vehicle brakes, thereby providing safer driving for passengers.

[0114] At the same time, if Figure 8 As shown, Figure 8 The performance of the battery SOC of the vehicle under the WLTC condition is shown. Compared with the energy-saving performance of other controllers, the vehicle control method provided by the embodiment of the present application has a lower decrease in the vehicle SOC as the usage time increases, and has a higher energy-saving efficiency. Fig. 9 As shown, Fig. 9 The performance of the battery capacity decay rate of the vehicle under the WLTC condition is illustrated. Compared with the battery capacity decay rate of other controllers, the vehicle control method provided in the embodiment of the present application has a smaller battery capacity decay rate as time increases, and has better energy-saving efficiency.

[0115] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the working principle of the device. It can be understood that in order to realize the above functions, the vehicle controller includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0116] The embodiment of the present application can divide the functional modules of the vehicle controller according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or software functional module.

[0117] It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. Fig.10 FIG. 2 shows a possible schematic diagram of the vehicle control device involved in the above-mentioned embodiment. Fig.10As shown, the vehicle control device 1000 may include: an acquisition module 1001 , a processing module 1002 , and a control module 1003 .

[0118] The acquisition module 1001 is used to support the vehicle control device 1000 to execute Figure 3 S301 in the illustrated vehicle control method.

[0119] Processing module 1002, used to support the vehicle control device 1000 to execute Figure 3 S302 and S303 in the illustrated vehicle control method.

[0120] Control module 1003, used to support vehicle control device 1000 to execute Figure 3 Illustrated vehicle control method S304.

[0121] In one possible implementation, Fig.10 As shown, the vehicle control device 1000 provided in the embodiment of the present application may further include: a sending module 1004.

[0122] The sending module 1004 is used to support the vehicle control device 1000 to execute Figure 5 Illustrated vehicle control method S305.

[0123] It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0124] The vehicle control device 1000 provided in the embodiment of the present application is used to execute the above Figure 3 or Figure 5 The vehicle control method shown can therefore achieve the same effect as the above-mentioned vehicle control method.

[0125] An embodiment of the present application also provides a vehicle control system, which may include: a cloud, and a vehicle control device 1000.

[0126] The present application also provides a vehicle controller, which can be the vehicle controller described in the above embodiment. Figure 1 The vehicle controller 100 shown can execute the vehicle control method and related steps in the above method embodiment.

[0127] An embodiment of the present application also provides a computer-readable storage medium having instructions stored thereon, which, when executed, execute the vehicle control method and related steps in the above method embodiment.

[0128] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer, the computer executes the vehicle control method and related steps in the above method embodiment.

[0129] In some embodiments, the methods described herein may be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or encoded on other non-transitory media or articles of manufacture.

[0130] The present application also provides a vehicle control system 1100, such as Fig.11 As shown, the vehicle control system 1100 includes at least one processor 1101 and at least one interface circuit 1102 .

[0131] As an example, when the vehicle control system 1100 includes a processor and an interface circuit, the processor may be Fig.11 The processor 1101 shown in the solid line frame (or the processor 1101 shown in the dotted line frame) may be Fig.11 The interface circuit 1102 shown in the solid line frame (or the interface circuit 1102 shown in the dotted line frame). When the chip system 1100 includes two processors and two interface circuits, the two processors include Fig.11 The processor 1101 shown in the solid line frame and the processor 1101 shown in the dotted line frame, the two interface circuits include Fig.11 The interface circuit 1102 shown in the solid line frame and the interface circuit 1102 shown in the dotted line frame are not limited to this.

[0132] The processor 1101 and the interface circuit 1102 may be interconnected via a line. For example, the interface circuit 1102 may be used to receive a signal. In another example, the interface circuit 1102 may be used to send a signal to another device (e.g., the processor 1101). For example, the interface circuit 1102 may read a computer instruction stored in a memory and send the computer instruction to the processor 1101. The processor 1101 executes the instruction and implements the various steps in the above embodiments in combination with the input and output devices, such as implementing Figure 3 Figure 5 Of course, the chip system may also include other discrete devices, which are not specifically limited in the embodiments of the present application.

[0133] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0137] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0138] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A vehicle control method, applied to a vehicle, characterized in that: The method comprises: Acquire the current vehicle state information of the vehicle, the driving condition information of the current driving condition of the vehicle, and the driving habit information of the user driving the vehicle; the vehicle state information includes the external temperature of the vehicle and the vehicle dynamic load change of the vehicle; the dynamic load change is the weight change of the vehicle caused by passengers getting on and off the vehicle; the driving condition information includes ground adhesion, real-time traffic information, vehicle station location, and future driving conditions; the driving habit information includes the average parking time of the user at a specific bus station, the starting speed curve, and the stopping speed curve; Inputting the current vehicle state information, the driving condition information and the driving habit information into the trained reinforcement learning model to obtain predicted motion information; The training process of the reinforcement learning model includes: obtaining first state information and second state information of the vehicle; the first state information is used to indicate historical state information of the first state of the vehicle; the second state information is used to indicate state information of the vehicle switching from the first state to the second state according to first action information; Calculating the energy efficiency, driving time and ride comfort of the vehicle when it switches from the first state to the second state by using the first state information, the second state information and the first action information; the ride comfort is used to indicate the acceleration change rate of the vehicle when it switches from the first state to the second state; Input the energy efficiency, the driving time and the smoothness into a reward function to calculate vehicle operating parameters; Generating a loss function of the reinforcement learning model according to the vehicle operation parameters; adjusting model parameters of the reinforcement learning model using a preset adjustment algorithm so that the loss function converges; Determining driving information of the vehicle through the current vehicle state information, the driving condition information and the predicted motion information; The vehicle is controlled to travel according to the travel information at the next travel moment.

2. The method according to claim 1, characterized in that The method further comprises: receiving feedback information from a user of the vehicle; the feedback information is comfort evaluation information of the vehicle by the user of the vehicle; the user includes a driver and / or a passenger of the vehicle; The model parameters are adjusted using the feedback information.

3. The method according to claim 1, characterized in that The driving information includes a motor torque parameter of the vehicle; the driving information of the vehicle is determined by using the current vehicle state information, the driving condition information and the predicted motion information, including: The motor torque parameter is obtained by performing fuzzy reasoning through the current vehicle state information, the driving condition information and the predicted motion information.

4. The method according to claim 3, characterized in that The obtaining of the motor torque parameter by performing fuzzy reasoning on the current vehicle state information, the driving condition information and the predicted motion information includes: Performing fuzzy reasoning on the current vehicle state information, the driving condition information, and the predicted motion information using preset fuzzy rules and preset membership functions to determine a fuzzy set of the motor torque of the vehicle; The fuzzy set is defuzzified to determine the motor torque parameter.

5. The method according to claim 4, characterized in that The defuzzifying the fuzzy set to determine the motor torque parameter includes: The fuzzy set is defuzzified by using a center of gravity method and / or a maximum membership method to determine the motor torque parameter.

6. The method according to any one of claims 3 to 5, characterized in that: The controlling the vehicle to travel according to the travel information at the next travel moment includes: The motor torque parameter is sent to a vehicle control system of the vehicle, so that the vehicle control system controls the motor of the vehicle according to the motor torque parameter at the next driving moment, so as to control the vehicle to drive according to the driving information at the next driving moment.

7. The method according to claim 6, characterized in that The method further comprises: Obtaining actual motor torque feedback information of the vehicle; The motor torque parameter is adjusted using the actual motor torque feedback information.

8. The method according to claim 1, characterized in that The method further comprises: The predicted motion information and the driving information are sent to a display device of the vehicle so that the display device displays the predicted motion information and the driving information to a user.

9. A vehicle control device, characterized in that: The device comprises: An acquisition module is used to acquire the current vehicle state information of the vehicle, the driving condition information of the current driving condition of the vehicle, and the driving habit information of the user driving the vehicle; the vehicle state information includes the external temperature of the vehicle and the vehicle dynamic load change of the vehicle; the dynamic load change is the weight change of the vehicle caused by passengers getting on and off the vehicle; the driving condition information includes ground adhesion, real-time traffic information, vehicle station location, and future driving conditions; the driving habit information includes the average parking time of the user at a specific bus station, the starting speed curve, and the stopping speed curve; A processing module, used to input the current vehicle state information, the driving condition information and the driving habit information into the trained reinforcement learning model to obtain predicted motion information; wherein the training process of the reinforcement learning model includes: obtaining the first state information and the second state information of the vehicle; the first state information is used to indicate the historical state information of the first state of the vehicle; the second state information is used to indicate the state information of the vehicle switching from the first state to the second state according to the first action information; using the first state information, the second state information and the first action information, calculating the energy efficiency, driving time and smoothness of the vehicle switching from the first state to the second state; the smoothness is used to represent the acceleration change rate of the vehicle switching from the first state to the second state; inputting the energy efficiency, the driving time and the smoothness into the reward function to calculate the vehicle operation parameters; generating the loss function of the reinforcement learning model according to the vehicle operation parameters; adjusting the model parameters of the reinforcement learning model using a preset adjustment algorithm to make the loss function converge; determining the driving information of the vehicle through the current vehicle state information, the driving condition information and the predicted motion information; A control module is used to control the vehicle to travel according to the travel information at the next travel moment.

10. A vehicle control system, characterized in that: The system comprises: Cloud; The vehicle control device as claimed in claim 9.

11. A vehicle controller, characterized in that: The vehicle controller includes a processor and a memory, the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the vehicle control method according to any one of claims 1 to 8.

12. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to implement the vehicle control method according to any one of claims 1 to 8.

Images