Control method, device, and control system for intelligent vehicles

Abstract

This application discloses a control method for an intelligent vehicle, in which a control system of the intelligent vehicle obtains the current driving mode, driving style model, and target speed of the intelligent vehicle, then determines a speed control command based on the driving mode and driving style model, and sends the speed control command to an execution system of the intelligent vehicle, thereby providing a control method for an intelligent vehicle with excellent comfort and a good experience.

Description

[Technical Field]

[0001] The present application relates to the field of intelligent vehicles, and in particular to methods, devices and systems for controlling intelligent vehicles. [Background technology]

[0002] With the advancement of artificial intelligence (AI) technology and its application to the automotive field, intelligent vehicles with automated driving capabilities have attracted widespread interest. A control module within an intelligent vehicle is used to control the vehicle's operation. The control module must determine the vehicle's trajectory and speed. The trajectory depends on the destination set by the driver, and the speed is typically determined using a conventional error feedback method. To ensure the vehicle reaches the desired speed, the control module adjusts the error using a proportional-integral-derivative (PID) method and determines the current accelerator and brake control amounts according to the control algorithm and the accelerator and brake values ​​at the previous point in time. However, due to the complex and diverse road conditions on the road section where the intelligent vehicle is traveling, the intelligent vehicle must avoid obstacles by taking into account the driving conditions of other vehicles and the road infrastructure conditions. As a result, the intelligent vehicle constantly travels at a variable speed. For the control module, a larger error between the current speed and the target speed indicates a larger adjustment range. During the autonomous driving of an intelligent vehicle, the control module frequently switches between the accelerator and the brake. The aforementioned error feedback method does not consider the comfort of the people inside the vehicle, and the experience is relatively poor. Therefore, how to provide a control method for an intelligent vehicle with excellent comfort and a good experience has become an urgent technical problem to be solved. Summary of the Invention

[0003] The present application provides a method for controlling an intelligent vehicle to improve the comfort and driving experience of the intelligent vehicle.

[0004] According to a first aspect, a method for controlling an intelligent vehicle is provided. A vehicle control system first obtains a current driving mode, a driving style model, and a target speed of the intelligent vehicle, then determines a speed control command based on the driving style model and the driving mode, and sends the speed control command to a vehicle execution system of the intelligent vehicle. According to the method, the driving of the intelligent vehicle may be controlled with reference to a driving style model selected by a driver, thereby improving the driver's driving experience and the driver's comfort in driving the intelligent vehicle.

[0005] In a possible implementation, the speed control command includes an accelerator position and a brake value. The accelerator position and the brake value are important factors for controlling the driving of an intelligent vehicle. When an intelligent vehicle is manually driven, different drivers have different driving habits. For example, in a fossil fuel-powered vehicle, the driver controls the accelerator pedal and the brake pedal differently, or in an electric vehicle, the driver controls the vehicle acceleration and braking systems differently. The accelerator position is a parameter used to control the vehicle acceleration of the intelligent vehicle, and the brake value is a parameter used to control the vehicle braking of the intelligent vehicle. According to the above method, the speed control command including the accelerator position and the brake value is determined by using a driving style model selected by the driver, thereby controlling the driving of the intelligent vehicle based on the driving style model selected by the driver. This improves the comfort of the driver when driving the intelligent vehicle.

[0006] In another possible implementation, the vehicle control system includes a decision-making controller and an autonomous driving controller. The decision-making controller may determine a driving trajectory and a target speed based on current road condition information. The road condition information may include one or more pieces of information provided by the intelligent vehicle's map system, positioning device, and fusion system. The autonomous driving controller obtains a driving mode and a driving style model selected by the driver, and further determines a speed control command based on the driving style model, the driving mode, and the road condition information.

[0007] In another possible implementation, the driving modes of the intelligent vehicle include a manual driving mode and an automatic driving mode. In the automatic driving mode, the driver can select a driving style model through the intelligent vehicle. The intelligent vehicle includes a driving style model library, which includes a set of multiple pre-configured driving style models, each including a different accelerator opening and a different brake value. The accelerator opening and brake value are used to represent the driving habits of multiple different drivers. In the driving process of the intelligent vehicle, the driving of the intelligent vehicle is controlled based on the accelerator opening and brake value in the different driving style models, simulating controlling the driving of the intelligent vehicle using a driving style selected by the driver based on the driver's preferences. This implements driving behavior that better matches the driver's driving habits.

[0008] In another possible implementation, when the driving mode of the intelligent vehicle is in a manual driving mode, the vehicle control system may collect driving data of a driver of the intelligent vehicle within a preset period of time, and obtain a customized driving style model that matches the driving habits of the driver based on the driving data by using a machine learning algorithm, where the customized driving style model includes an accelerator opening and a braking value that match the driving habits of the driver, and then add the customized driving style model to a driving style model library stored in the intelligent vehicle. In this application, in addition to using the driving style model library pre-configured in the intelligent vehicle, driving data of the driver in a manual driving mode can be collected and a driving style model that matches the driver's current driving habits can be obtained through training based on the driving data. When the intelligent vehicle switches to an autonomous driving mode, the driver may select the customized driving style model, and the intelligent vehicle will simulate the driver's current driving habits based on the accelerator opening and braking values ​​in the model to control the driving of the intelligent vehicle, thereby improving the driver's driving experience.

[0009] In another possible implementation, the autonomous driving controller calculates an error between an actual speed of the intelligent vehicle at a current time and a target speed, and determines an acceleration based on the error, where the acceleration is used to indicate a speed change amount of the intelligent vehicle from the actual speed at the current time to the target speed per unit time; determines a first accelerator opening and a first brake value according to a proportional-integral-derivative algorithm; determines a second accelerator opening and a second brake value based on a driving style model selected by the driver; obtains a third accelerator opening through a calculation based on the first accelerator opening, the first weight, the second accelerator opening, and the second weight, and obtains the third brake value through a calculation based on the first brake value, the third weight, the second brake value, and a fourth weight. The first weight and the second weight are weights for the accelerator opening, and the sum of the first weight and the second weight is 1. The third weight and the fourth weight are weights for the brake value, and the sum of the third weight and the fourth weight is 1. A speed control command including the third accelerator position and the third brake value is sent to the vehicle executive system.

[0010] In another possible implementation, the driving style model library of the intelligent vehicle is provided to the driver through a human-computer interaction controller. The driver can select a driving style model from the driving style model library in the form of human-computer interaction, such as voice, text, or a button. The driving style model selected by the driver and sent by the human-computer interaction controller is received. Instead of experiencing the automatic driving process when the driver has no knowledge of the driving process of the intelligent vehicle, the driver may exchange messages with the intelligent vehicle in the form of voice, text, or the like through the human-computer interaction controller to learn the driving status of the intelligent vehicle and further control the driving process of the intelligent vehicle. This improves the driver's driving experience. Furthermore, in an emergency, the driver may control the driving of the intelligent vehicle through an interaction interface provided by the human-computer interaction controller or in the form of voice, rather than completely relying on the controller of the intelligent vehicle. This further improves the safety of the driving process of the intelligent vehicle.

[0011] According to a second aspect, the present application provides a control device for an intelligent vehicle, the control device including a module configured to execute the control method for an intelligent vehicle according to the first aspect and any one of the possible implementations of the first aspect.

[0012] According to a third aspect, the present application provides a control system for an intelligent vehicle, the control system for the intelligent vehicle including a decision-making controller and an autonomous driving controller, the decision-making controller and the autonomous driving controller configured to execute operation steps of the method executed by each executing entity according to the first aspect and any one of the possible implementations of the first aspect.

[0013] According to a fourth aspect, the present application provides a control system for an intelligent vehicle. The control system includes a processor, a memory, a communication interface, and a bus. The processor, the memory, and the communication interface are connected to and communicate with each other via the bus. The memory is configured to store computer-executable instructions. When the control system is running, the processor executes the computer-executable instructions in the memory to perform the operational steps of the method according to the first aspect and any one of the possible implementations of the first aspect by using hardware resources in the control system.

[0014] According to a fifth aspect, the present application provides an intelligent vehicle, the intelligent vehicle including a control system, the control system configured to perform functions implemented by the control system according to the fourth aspect and any one of the possible implementations of the fourth aspect.

[0015] According to a sixth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium storing instructions that, when executed on a computer, can cause the computer to perform the method in the previous aspect.

[0016] According to a seventh aspect, the present application provides a computer program product comprising instructions, which when executed on a computer, can cause the computer to perform a method according to the previous aspect.

[0017] The present application may provide more implementations through further combinations based on the implementations provided in the above aspects. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a schematic diagram of the logical architecture of an intelligent vehicle according to the present application;

[0019] [Figure 2A] 1 is a schematic flowchart of a control method for an intelligent vehicle according to the present application; [Figure 2B] 1 is a schematic flowchart of a control method for an intelligent vehicle according to the present application;

[0020] [Figure 3] 1 is a schematic flow chart of a method for controlling an intelligent vehicle in an autonomous driving mode according to the present application;

[0021] [Figure 4] 1 is a schematic diagram of a human-computer interaction system for an intelligent vehicle according to the present application;

[0022] [Figure 5] 1 is a schematic diagram of the structure of a control device for an intelligent vehicle according to the present application;

[0023] [Figure 6] 1 is a schematic diagram of the structure of a control system for an intelligent vehicle according to the present application; DETAILED DESCRIPTION OF THE INVENTION

[0024] The following clearly describes the technical solutions in this application with reference to the accompanying drawings in the embodiments of this application.

[0025] 1 is a schematic diagram of the logical architecture of an intelligent vehicle 100 according to the present invention. As shown in the figure, the intelligent vehicle 100 includes a human-computer interaction controller 10, a driving mode selector 20, a vehicle control system 30, a vehicle execution system 40, a positioning device 50, a fusion system 60, and a map system 70.

[0026] The human-computer interaction controller 10 is configured to implement message exchange between the intelligent vehicle and the driver. The driver may select a driving mode and a driving style model for the intelligent vehicle through the human-computer interaction controller 10. The human-computer interaction controller 10 may exchange messages with the driver in the form of voice or text, or in another form, such as through seat vibration or flashing of an in-vehicle indicator.

[0027] The driving mode selector 20 is configured to transfer information input by the driver by using the human-computer interaction controller 10 to the vehicle control system 30, which then controls the driving of the intelligent vehicle based on the driving style model selected by the driver. In this case, the vehicle control system 30 controls the intelligent vehicle through the vehicle execution system 40. The vehicle execution system 40 includes devices or subsystems that control the driving of the vehicle body, such as, but not limited to, a braking system, a steering system, a driving system, or a lighting system.

[0028] The vehicle control system 30 further includes a manual driving controller 301, a decision-making controller 302, and an automatic driving controller 303. The manual driving controller 301 is configured to acquire and store user driving data and to train the collected data by using a neural network model to acquire a driving style model of the training data. The manual driving controller 301 may store the acquired user driving data in a memory of the manual driving controller or may store the user data in another storage device of the intelligent vehicle. The decision-making controller 302 is a subsystem configured to provide decision-making and route planning, including, but not limited to, a global route plan, an action plan, and a motion plan, to the intelligent vehicle. The automatic driving controller 303 is configured to control the driving of the intelligent vehicle based on the driving trajectory and speed of the intelligent vehicle planned by the decision-making controller 302 and the driving style model selected by the driver.

[0029] In a possible implementation, the vehicle control system 30 may include one processor or a group of processors. The functions of the manual driving controller 301, the decision-making controller 302, and the autonomous driving controller 303 are implemented by one or more processors, or the functions of the manual driving controller 301, the decision-making controller 302, and the autonomous driving controller 303 are implemented by a group of processors. Optionally, the functions of the manual driving controller 301, the decision-making controller 302, and the autonomous driving controller 303 may be implemented using software in addition to hardware, or by using a combination of software and hardware.

[0030] Positioning device 50 includes a device or subsystem configured to determine the vehicle position, such as a global positioning system (GPS) or an inertial navigation system (INS).

[0031] The fusion system 60 is configured to provide fusion, association, and prediction capabilities to the sensing device 601 of the intelligent vehicle to acquire target objects, thereby providing accurate static and / or dynamic obstacle information to each subsystem of the intelligent vehicle, including, but not limited to, the position, size, attitude, and velocity of physical objects such as people, vehicles, or barricades. The sensing device 601 is configured to provide target detection and classification to the intelligent vehicle and includes one or more of sensing devices such as radar, sensors, and cameras.

[0032] Optionally, the intelligent vehicle 100 may further include a memory 80 configured to store a map file. The vehicle controller 30 may retrieve the map file from the memory 80 and refer to real-time road condition information to control the driving trajectory of the intelligent vehicle.

[0033] It should be noted that the intelligent vehicle of the present application includes a vehicle that supports intelligent driving functions, and may be a fossil fuel-powered vehicle, an electric vehicle, or another new energy vehicle. The logical architecture of the intelligent vehicle shown in FIG. 1 is merely an example of an intelligent vehicle provided in the present application, and the structure of the intelligent vehicle does not limit the technical solution to be protected in the present application. Furthermore, the device or system shown in FIG. 1 may be implemented by using software or hardware, and the present application does not limit this.

[0034] The control method for an intelligent vehicle provided in the present application will be further described below with reference to Figures 2A and 2B. As shown in the figures, the method includes the following steps:

[0035] S201: The driving mode selected by the driver is acquired.

[0036] An intelligent vehicle may receive driver commands through a human-computer interaction controller 10 shown in Figure 1. For example, Figure 3 is a schematic diagram of a human-computer interaction interface. As shown, a driver may select a manual driving mode 101 or an automated driving mode 102 through a driving mode selection interface 10. The interface may indicate different modes by using identifiers such as colors and / or patterns that can distinguish between different modes.

[0037] Optionally, the human-computer interaction controller may provide voice prompts in addition to the aforementioned interface button prompts, allowing the driver to input instructions by using voice, so that the user can conveniently select a driving mode. During voice selection, the driver can first select a driving mode in voice form according to actual requirements.

[0038] If the driver selects the autonomous driving mode, the human-computer interaction system may further prompt the driver to select a driving style through voice or an interface. Furthermore, the human-computer interaction system may provide a brief description of each driving style. Specifically, the human-computer interaction system may inform the driver of the characteristics of each driving style model through an interface or voice, so that the driver can better select the driving style they require. For example, FIG. 3 provides a schematic diagram of a driving style model selection interface 30. As shown in the figure, the intelligent vehicle includes three driving style models: driving style model 301, driving style model 302, and customized driving style model 303. The human-computer interaction controller may also present information about the interaction between the intelligent vehicle and the driver of the intelligent vehicle through a visualized interface. For example, the human-computer interaction interface may be displayed on the windshield, the rearview mirror, or another in-vehicle device or interface. This facilitates interaction between the driver and the intelligent vehicle system. After the intelligent vehicle receives the driver's command, the driving mode selector 20 obtains the driving mode selected by the driver and further plans the driving trajectory and speed of the intelligent vehicle.

[0039] S202: Determine whether the driving mode is the automatic driving mode.

[0040] The vehicle control system needs to determine whether the driving mode selected by the driver is an automatic driving mode, and if the driving mode is an automatic driving mode, executes step S203, or if the driving mode is a manual driving mode, executes step S213.

[0041] S203: If the driving mode is the automatic driving mode, obtain the driving style model selected by the driver.

[0042] If the driving mode is autonomous driving, the driver may further select a driving style through the human-computer interaction interface. Each driving style corresponds to one driving style model. For example, in the case of the driving style selection prompt 30 shown in FIG. 3, the interface includes driving style model 301, driving style model 302, and customized driving style model 303. After the driver determines the driving style model, the selection result (e.g., the identifier of the driving style model) is transferred to the vehicle controller through the human-computer interaction controller and the driving mode selector, and the autonomous driving controller controls the intelligent vehicle to travel to the destination based on the driving style selected by the driver.

[0043] An intelligent vehicle has at least one driving style model, which may be obtained in any one or more of the following ways:

[0044] Method 1: A driving style model is pre-configured in the intelligent vehicle.

[0045] A driving style model library is preset in the intelligent vehicle, and the driving style model library includes at least one driving style model. Each driving style model may be preset during manufacturing of the intelligent vehicle. Specifically, multiple preset types of driving data of the driver may be used as raw data (also called driving data), and the raw data is trained by using a machine learning algorithm to obtain a driving style model that is compatible with each type of driving habit of the driver.

[0046] Specifically, the driving style model may be obtained by training the original data by using a neural network model. During implementation, the driving style model may be obtained by training the original data by selecting any neural network model according to service requirements. For example, the driving data is trained by using a neural network model with three layers of neurons. The neural network model mainly includes three layers: an input layer, a hidden layer, and an output layer. The input layer is used to extract some features of the driving data, the hidden layer is used to extract features of the driving data other than the features extracted by the input layer, and the output layer is used to process the features extracted by the input layer and the hidden layer and output the final result. Optionally, the hidden layer may further extract what is needed based on the features extracted by the input layer and extract features other than the features extracted by the input layer. Optionally, to ensure that the driving style model obtained by the neural network model is close to the driver's actual driving data, the training result may be corrected by using the principle of back propagation (BP). Specifically, the output results obtained by the neural network model are compared with the actual data, and the weights of the neurons in each layer are further adjusted, so that the results obtained through training the neural network model are closer to the actual data. The number of neurons in each layer in the neural network model can be set according to specific service requirements.

[0047] During training of the driving style model, the target speed, current speed, and acceleration are used as input values ​​for the backpropagation neural network model, and the accelerator position and brake value are output values ​​for the neural network model. The accelerator position is a parameter used to control vehicle acceleration in an intelligent vehicle, with a larger accelerator position indicating a larger acceleration. For example, in a fossil fuel-powered vehicle, the engine controls the fuel injection amount based on the air throttle position, thereby controlling vehicle acceleration. The accelerator position is the air throttle position. In implementation, the accelerator position refers to the driver controlling the air throttle position through the accelerator pedal. Alternatively, the accelerator position may be understood as the accelerator pedal position, which is similar to the angle formed between the accelerator pedal and a horizontal plane when the driver presses the accelerator pedal to apply pressure to it. Alternatively, the accelerator position may simply be understood as the depth to which the driver presses the accelerator pedal. In an electric vehicle, the accelerator position is a parameter used to control vehicle acceleration through an accelerator control device (e.g., an electric acceleration button). The brake value is a parameter used to control vehicle brakes in an intelligent vehicle, and a higher brake value indicates a higher braking torque. For example, in a fossil fuel-powered vehicle, the brake value refers to the driver applying pressure to the brake pedal, the pressure being amplified and transmitted through a vacuum booster, the amplified force pushing against a brake master cylinder to pressurize brake fluid, the brake fluid being distributed to the front and rear brakes through a brake combination valve, the brake warning light being illuminated simultaneously, controlling the front and rear brakes, and thereby braking the vehicle. In an electric vehicle, the brake value is a parameter used to control vehicle brakes through a brake control device.

[0048] The process of obtaining a driving style model in this application will be further described below with reference to an example. First, the speed v(t), accelerator pedal position (PP) PP(t), brake pedal position (BP) BP(t), and speed v(t+k) at time t+k are extracted from the driver's actual driving data. Because there may be a delay in the process of obtaining the speed while the intelligent vehicle is running, the actual output of the intelligent vehicle has a delay of k seconds. For example, the value of k is usually 1 to 2 seconds. Here, v(t), PP(t), and BP(t) are used as inputs to a neural network model, and the speed v'(t+k) at time t+k obtained after training neurons in each layer within the neural network model is used. In this case, the difference between the speed obtained through training the neural network model and the actual speed is v(t+k) - v'(t+k). Next, this difference is further corrected using the principle of backpropagation to ensure that the data obtained by the neural network training model is close to the actual value. Finally, a driving style model trained based on the neural network model is obtained. By continuously training with the driver's driving data, the accuracy of the driving style model is improved, and finally, the data acquired by the neural network model is closer to the driver's actual driving data.

[0049] Optionally, the training of the driving style model is continuous and iterative. Through continuous training, the finally obtained driving style model approaches the driver's actual driving data. During implementation, the number of iterations may be determined based on a preset situation. For example, if the difference between the speed obtained through training of the neural network model and the actual speed is smaller than a preset value, the training of the neural network model stops. Alternatively, if the difference between the training result and the actual result is within a preset error range, the training of the model is completed.

[0050] It should be noted that training of a neural network model can be understood as a black-box process, specifically, a process that uses multiple driving data sets as model inputs and performs calculation processing on neurons in each layer in each iteration process, so that the finally obtained model can be closer to the actual operation of the driver. During implementation, the number of neurons in the input layer, hidden layer, and output layer can be set according to specific requirements. This application does not limit the neural network model. During implementation, the neural network model can be selected according to service requirements. Furthermore, the process of processing neurons in each layer in the neural network model and the result correction process do not limit this application.

[0051] For example, driving data of driver A and driving data of driver B are used as sample data in the experience library. Driving data generated when these two drivers drive an intelligent vehicle is collected, and the driving data is used as input for a machine learning algorithm. Multiple different driving style models are obtained through machine learning algorithm training and used as pre-set driving style models. In this case, the experience library includes two different driver style models. If driver A prefers high-speed driving, the driving style model obtained by training driver A's driving data takes the driver's preferences into account and frequently switches between the accelerator and brake. If driver B drives smoothly, the driving style model obtained by training driver B's driving data rarely uses emergency braking and frequent acceleration.

[0052] Method 2: The intelligent vehicle acquires a driving style model through training based on the driver's current driving data.

[0053] Alternatively, the driver may select a customized driving style model obtained by training driving data collected based on the driver's driving habits. For a specific training process, please refer to the process of training a pre-set driving style model in Scheme 1. This application is not limited thereto.

[0054] S204: The decision controller determines the target speed and trajectory control command based on the current road condition information.

[0055] When the intelligent vehicle is in autonomous driving mode, the decision-making controller may obtain obstacle information (including but not limited to obstacle type, height, and speed, etc.) from the fusion system and obtain location information of the intelligent vehicle from the map system and the positioning device. Then, the decision-making controller in the vehicle control system performs global path planning and / or local path planning, and outputs all or some of the driving trajectories that the intelligent vehicle will take to reach the destination. Then, the decision-making controller sends all or some of the driving trajectories that the intelligent vehicle will take to reach the destination to the autonomous driving controller, and performs the operation of step S205.

[0056] Optionally, the decision-making controller may only obtain information provided by at least one of the fusion system, the map system, and the positioning device, perform global path planning and / or local path planning based on the aforementioned information, and output all or some of the driving trajectories for the intelligent vehicle to reach the destination.

[0057] S205: Determine a speed control command based on a driving style model selected by the driver and a target speed.

[0058] Referring to the driving style model and the conventional target speed adjustment method, the autonomous driving controller in the vehicle control system controls the input target speed, outputs longitudinal commands including accelerator and brake controls, and sends lateral commands and longitudinal commands to the vehicle execution system, thereby controlling the driving of the intelligent vehicle. The conventional target speed adjustment method may be a proportional-integral-differential method or another method, and this application is not limited thereto.

[0059] FIG. 4 is a schematic diagram of the control process in the autonomous driving mode of the present application. As shown in the figure, the autonomous driving controller in the vehicle control system obtains the target speed and actual speed of the intelligent vehicle from the decision-making controller, calculates an error based on the target speed and actual speed, and uses the error as input for a proportional-integral-derivative algorithm. Using an error feedback method, the accelerator opening and braking value required for the intelligent vehicle to reach the target speed are calculated, and the accelerator opening and braking value are used as some common requirements for the intelligent vehicle to reach the target speed. The proportional-integral-derivative algorithm includes a proportional unit, an integral unit, and a derivative unit. The error can be adjusted by adjusting the gains of these three units, with a larger error indicating a larger adjustment range. For specific implementation processes, please refer to the processing processes in the prior art. Details are not provided in this application.

[0060] The autonomous driving controller also calculates an acceleration for the intelligent vehicle to reach a target speed based on the target speed and an error, where the acceleration is used to implement a speed change amount by which the speed of the intelligent vehicle is adjusted to the target speed within a unit time; uses the predicted acceleration and the target speed as inputs to a driving style model algorithm; obtains an accelerator opening and a brake value through calculation using a machine learning algorithm; and uses the accelerator opening and the brake value as personality parts. The present application does not limit the type of machine learning algorithm. A neural network algorithm including neurons in the input layer, hidden layer, and output layer may be used. The number of neurons in each layer may be set according to specific service requirements. For example, during implementation, the number of neurons in each layer may be set according to accuracy requirements, with a larger number of neurons indicating higher accuracy. Next, the accelerator opening and brake value obtained using the driving style model algorithm are obtained.

[0061] Finally, the accelerator opening obtained by using the driving style model algorithm and the accelerator opening obtained by using the proportional-integral-derivative algorithm are added together, and the brake value obtained by using the driving style model algorithm and the brake value obtained by using the proportional-integral-derivative algorithm are added together. A specific addition method may be to use a weighting method to set the weights of the accelerator opening and brake value obtained by using the driving style model algorithm and the weights of the accelerator opening and brake value obtained by using the proportional-integral-derivative algorithm according to the service requirements being implemented. The weights are used to indicate the proportions of the accelerator opening or brake value obtained by using each of these two algorithms. For example, based on the hardware capabilities of the intelligent vehicle, weights are respectively configured for the accelerator opening obtained by using the proportional-integral-derivative algorithm and the accelerator opening obtained by using the driving style model algorithm, where the sum of the weights for the accelerator opening is 1; weights are respectively configured for the brake value obtained by using the proportional-integral-derivative algorithm and the brake value obtained by using the driving style model algorithm, where the sum of the weights for the brake values ​​is 1. Finally, the accelerator opening and brake value obtained after weight addition based on the accelerator opening and brake value obtained by using the driving style model algorithm and the accelerator opening and brake value obtained by using the conventional algorithm are transmitted to the vehicle execution system as speed control commands. For example, assume that the accelerator opening obtained by using the driving style model algorithm is S1, the brake value obtained by using the driving style model algorithm is B1, the accelerator opening obtained by using the proportional-integral-derivative algorithm is S2, and the brake value obtained by using the proportional-integral-derivative algorithm is B2. An intelligent driving vehicle is a vehicle that has relatively good driving and engine performance.Assume that the weight of the accelerator opening obtained by using the driving style model algorithm is a1, the weight of the accelerator opening obtained by using the proportional-integral-derivative algorithm is a2, the weight of the brake value obtained by using the proportional-integral-derivative algorithm is b1, the weight of the brake value obtained by using the driving style model algorithm is b2, and a1+a2=1 and b1+b2=1. In this case, the finally determined accelerator opening S is (S1×a1+S2×a2), and the finally determined brake value B is (B1×b1+B2×b2). Therefore, the autonomous driving controller may transmit the accelerator opening S and the brake value B to the vehicle execution system in the intelligent vehicle as the content of a speed control command, thereby controlling the driving of the intelligent vehicle.

[0062] In a possible embodiment, in the weight setting process described above, a weight may be set for each algorithm. In this case, the finally determined accelerator opening and brake value are obtained through calculation using the weight assigned to each algorithm. For example, the weight setting in the above example is a1=b1 and a2=b2. In this case, the finally determined accelerator opening S is (S1+S2)xa1, and the finally determined brake value B is (B1+B2)xb1.

[0063] In a possible embodiment, during the driving process of an intelligent vehicle, the driving trajectory and speed of other vehicles are uncertain, and as a result, the driving trajectory and speed of one vehicle affect the driving trajectory and speed of the intelligent vehicle. Therefore, the above-mentioned process of determining the speed and driving trajectory needs to be adjusted multiple times based on multiple different road conditions. In addition, the accelerator opening and brake value of the vehicle driving need to be adjusted in real time or periodically based on multiple different road conditions during the vehicle driving process. That is, when the intelligent vehicle is driving in an autonomous driving mode, the processes of steps S204 and S205 may need to be repeated. In addition, the intelligent vehicle needs to be designed taking into account the driving mode switching process. For example, the driving mode of the intelligent vehicle is switched from autonomous driving to manual driving. In this case, the operation process of S206 needs to be performed.

[0064] It should be noted that in an intelligent vehicle, in addition to the proportional-integral-derivative algorithm, another algorithm may be used to determine the intersection to reach the target speed, but this application is not limited thereto.

[0065] S206: Determine whether the driver adjusts the driving style model.

[0066] S207: If the driver adjusts the driving style model, update the speed control command based on the driving style model adjusted by the driver and the target speed.

[0067] If the intelligent vehicle includes multiple driving style models, the driver can freely change the driving style model during the driving process of the intelligent vehicle, thereby obtaining different driving experiences. When the driver adjusts the driving style, new trajectory control commands and speed control commands are determined by referring to step S204 and step S205.

[0068] S208: Send the updated trajectory control command and the updated speed control command to the vehicle execution system.

[0069] In an intelligent vehicle, a vehicle executive system is responsible for managing vehicle control. The vehicle executive system includes a braking system (e.g., brakes), a steering system (e.g., steering wheel), a driving system (e.g., engine), and a lighting system (e.g., vehicle lamps). The vehicle executive system needs to execute trajectory control commands and speed control commands to control the running of the intelligent vehicle.

[0070] S209: Obtain the speed feedback result returned by the vehicle execution system.

[0071] In an optional step, the vehicle execution system may return an execution result to the vehicle control system after executing the trajectory control command and the velocity control command, The execution result includes success or failure of the command execution.

[0072] S210: If the driver does not adjust the driving style model, send a trajectory control command and a speed control command to the vehicle execution system.

[0073] S211: Obtain the speed feedback result returned by the vehicle execution system.

[0074] In a possible embodiment, if the driver does not adjust the driving mode, the vehicle control system directly sends the trajectory control command and speed control command determined in step S205 to the vehicle execution system, and the vehicle execution system controls the driving of the intelligent vehicle based on the content of the command.

[0075] S212: Next, it is determined whether the driver adjusts the driving mode.

[0076] During the driving process of the intelligent vehicle, the current driver may adjust the driving mode at any time through the steering wheel, braking, or human-computer interaction interface. If the driver does not adjust the driving mode, step S203 is repeated. If the driver adjusts the driving mode to the manual driving mode, step S213 is executed.

[0077] In a possible embodiment, the intelligent vehicle is pre-configured with a driving style model before delivery. However, in order to adapt to the driving habits of multiple different drivers, when the intelligent vehicle enters a manual driving mode, driving data of the current driver may be collected, and the driving data may be used as input to train a customized driving style model by reusing a machine learning algorithm, and the driving style model of the intelligent vehicle is updated. For specific operation steps, see steps S213 to S215. The vehicle control system may obtain the customized driving style model based on the current driving data.

[0078] S213: If the driving mode is the manual driving mode, the driving data of the driver is acquired.

[0079] When the intelligent vehicle is in a manual driving mode, the driver may be prompted through an interface whether to customize the driving style model. As shown in Figure 3, when the intelligent vehicle is in a manual driving mode, the driver may be prompted through the manual driving mode selection interface 20 of Figure 3 whether to customize the driving style model. If the driver taps on the customized driving style model 201, the current driving data of the driver is collected, and then the driving data is used as input for the machine learning algorithm.

[0080] Optionally, if the intelligent vehicle is in manual driving mode, the vehicle control system may further exchange messages, voice or otherwise, with the driver to determine whether to customize the driving style model.

[0081] It should be noted that Figure 3 is only an example provided herein, and after studying this application, one skilled in the art may use another form or interface structure to prompt the driver to select a driving mode, a driving style model, or a customized driving style model.

[0082] S214: Training the driving data by using a machine learning algorithm to obtain a trained driving style model.

[0083] S215: Add customized driving style models to the intelligent vehicle driving style model library.

[0084] When the intelligent vehicle is in manual driving mode, the manual driving controller of the vehicle control system first collects the driver's driving data, then trains the said driving data based on the driving data by using the method of method 1, obtains a driving style model through training based on the current driver's driving data, and adds the driving style model to the driving style model library of the intelligent vehicle as a customized driving style model, so that the driver can select the driving style model in automatic driving mode and control the driving of the intelligent vehicle by using the operation process from step S203 to step S209.

[0085] In a possible embodiment, after collecting the driving data of the current driver, the vehicle control system may complete training on the driving data of the intelligent vehicle and further transmit the driving data to a cloud data center, which then generates a customized driving style model based on the driving data and a machine learning algorithm. According to the process description above, the driving data is transmitted to the cloud data center, and the cloud data center may schedule a virtual machine to train the driving data, thereby obtaining a customized driving style model. This avoids the problem that the computing power of the vehicle control system in the intelligent vehicle limits the processing speed and reduces the computing load of the intelligent vehicle. The cloud data center may also store the model, add the model to a driving style model library stored in the cloud data center, and add the driving style model to another vehicle in addition to the intelligent vehicle in which the driver is located, so that the other vehicle updates the driving style model library and increases the number of driving style models available for driver selection. Furthermore, the intelligent vehicle may send updated driving data of the driver to the cloud data center, and the cloud data center updates the driving style model corresponding to the driver, so that the result output by the driving style model is closer to the driver's actual driving process. Optionally, the driver's driving data may be stored in the cloud data center, and when the driver selects a customized model through a human-computer interaction interface, the driving process of the intelligent vehicle may be remotely controlled by the cloud data center. That is, an identifier of the driving style model selected by the driver is sent to the cloud data center, and the cloud data center controls the driving process of the intelligent vehicle according to the accelerator opening and brake values ​​specified in the driving style model.

[0086] According to the control method for an intelligent vehicle provided herein, the intelligent vehicle can be set to two modes: a manual driving mode and an automatic driving mode. In the manual driving mode, the vehicle control system collects current driver driving data in real time, trains a customized driving style model for the driver by using a machine learning algorithm, updates the driving style model library of the intelligent vehicle, and allows the driver to select the customized driving style model to control the driving of the intelligent vehicle in the automatic driving mode. This improves the driver's driving experience. In the automatic driving mode, the driving style model selected by the driver is combined with the traditional proportional-integral-derivative method. When adjusting the current speed, the driver's driving habits are further taken into account in the driving process based on the driving style model selected by the driver, thereby implementing anthropomorphic control of the intelligent vehicle. The automatic driving process of the intelligent vehicle approaches the driver's driving habits. This improves the driving experience. Furthermore, in addition to pre-setting a typical driving style model library when manufacturing the intelligent vehicle, a customized driving style model may be retrained based on driving data of the current driver of the intelligent vehicle, and the customized driving style model is added to the driving style model library of the intelligent vehicle. In the autonomous driving mode, the driver can select the customized driving style model, so that the intelligent vehicle drives based on the parameters in the driving style model selected by the driver, which further improves the driver's driving experience.

[0087] It should be noted that for ease of explanation, the method embodiments are described as a combination of a series of operations, however, one skilled in the art will appreciate that the present application is not limited to the order of operations described.

[0088] The above has described in detail the control method for an intelligent vehicle provided in the present application with reference to Figures 1 to 4. Below, the intelligent vehicle control device, control system, and intelligent vehicle provided in the present application will be further described with reference to Figures 5 and 6.

[0089] 5 is a schematic diagram of the structure of a control device 500 according to the present application. As shown in the figure, the control device 500 includes: an acquisition unit 501, an autonomous driving control unit 502, and a sending unit 503.

[0090] The obtaining unit 501 is configured to obtain the driving mode, driving style model, and target speed of the intelligent vehicle at the current time.

[0091] The automatic driving control unit 502 is configured to determine a speed control command based on a driving mode and a driving style model.

[0092] The sending unit 503 is configured to send a speed control command to a vehicle executive system of the intelligent vehicle.

[0093] It should be understood that the apparatus 500 in this embodiment of the present application can be implemented by using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. Alternatively, if the control method for an intelligent vehicle shown in Figures 2A and 2B can be implemented by using software, the apparatus 500 and the modules of the apparatus may be software modules.

[0094] Optionally, the speed control command includes an accelerator opening and a brake value, where the accelerator opening is a parameter used to control vehicle acceleration of the intelligent vehicle and the brake value is a parameter used to control vehicle braking of the intelligent vehicle.

[0095] Optionally, the autonomous driving control unit 502 is further configured to determine a driving trajectory and a target speed based on current road condition information, where the road condition information includes information provided by the map system, the positioning device, and the fusion system of the intelligent vehicle, and the acquisition unit 501 is further configured to acquire a driving mode and a driving style model selected by the driver.

[0096] Optionally, the driving mode is an autonomous driving mode, and the intelligent vehicle includes a driving style model library, the driving style model library including a set of multiple driving style models, each driving style model including a different accelerator opening and braking value.

[0097] Optionally, the acquisition unit 501 is further configured to collect driving data of a driver of the intelligent vehicle within a preset period when the driving mode is a manual driving mode, and the automatic driving control unit 502 is further configured to acquire a customized driving style model based on the driving data by using a machine learning method, where the customized driving style model includes an accelerator opening and a brake value that match the driving habits of the driver, and add the customized driving style model to a driving style model library.

[0098] Optionally, the autonomous driving control unit 502 is further configured to: calculate an error between an actual speed of the intelligent vehicle at a current time and a target speed; and determine an acceleration based on the error, where the acceleration is used to indicate a speed change amount of the intelligent vehicle from the actual speed at the current time to the target speed within a unit time; determine a first accelerator opening and a first brake value according to a proportional-integral-derivative algorithm; determine a second accelerator opening and a second brake value based on a driving style model selected by a driver; obtain a third accelerator opening through calculation based on the first accelerator opening, the first weight, the second accelerator opening, and the second weight, where the sum of the first weight and the second weight is 1; and obtain the third brake value through calculation based on the first brake value, the third weight, the second brake value, and a fourth weight, where the sum of the third weight and the fourth weight is 1.

[0099] The sending unit 503 is further configured to send a speed control command including the third accelerator opening and the third brake value to the vehicle execution system.

[0100] Optionally, the apparatus further includes a prompt unit 504 configured to provide a driving style model library of the intelligent vehicle to the driver through the human-computer interaction controller, and the driver can select a driving style model from the driving style model library in the form of voice, text, or button.

[0101] The obtaining unit 501 is further configured to receive a driving style model selected by the driver and sent by the human-computer interaction controller.

[0102] Correspondingly, the control device 500 in this embodiment of the present application may perform the method described in the embodiment of the present application. Also, the above-mentioned operations and / or functions and other operations and / or functions of the units in the control device 500 are used to implement the corresponding steps of the method in Figures 2A and 2B. For the sake of brevity, the details will not be described again here.

[0103] 6 is a schematic diagram of a control system 600 according to the present disclosure. As shown in the figure, the control system 600 includes a processor 601, a memory 602, a communication interface 603, a memory 604, and a bus 605. The processor 601, the memory 602, the communication interface 603, and the memory 604 may communicate with each other via the bus 605 or in another manner, for example, via wireless transmission. The memory 602 is configured to store instructions. The processor 601 is configured to execute the instructions stored in the memory 602. The memory 602 may store program code, and the processor 601 may invoke the program code stored in the memory 602 to perform the following operations: obtain a current driving mode, a driving style model, and a target speed of the intelligent vehicle; determine a speed control command based on the driving mode and the driving style model; and send the speed control command to a vehicle execution system of the intelligent vehicle.

[0104] It is to be understood that in this embodiment of the present application, processor 601 may be a CPU, or processor 601 may be another general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0105] The memory 602 may include read-only memory and random access memory to provide instructions and data to the processor 601. The memory 602 may further include non-volatile random access memory. For example, the memory 602 may further store information about the device type.

[0106] The memory 602 may be volatile, nonvolatile, or include both volatile and nonvolatile memory. Nonvolatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM), used as an external cache. By way of example and not limitation, many forms of RAM may be used, such as static random access memory (static RAM, SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchlink dynamic random access memory (synchlink DRAM, SLDRAM), and direct rambus random access memory (direct rambus RAM, DR RAM).

[0107] The communication interface 603 includes a network interface / module configured to communicate with another device or system.

[0108] Memory 604 may be physically integrated with processor 601, located in processor 601, or may exist in the form of an independent unit. Computer programs may be stored in memory 604 or memory 602. Optionally, computer program code stored in memory 602 (e.g., a kernel or a program to be debugged) is copied to memory 604 for further execution by processor 601.

[0109] In addition to a data bus, bus 605 may further include a power bus, a control bus, a status signal bus, etc. However, for clarity of explanation, various types of buses are depicted in the figure as bus 605. Optionally, bus 605 may be a Peripheral Component Interconnect Express (PCIe), a controller area network (CAN), an automotive Ethernet (Ethernet), or another internal bus for implementing connections between components / devices shown in FIG.

[0110] It should be understood that the control system 600 of the intelligent vehicle in this embodiment of the present application may correspond to the control device 500 in this embodiment of the present application, and may correspondingly correspond to the entity that performs the method shown in Figures 2A and 2B in this embodiment of the present application. Also, the above-mentioned operations and / or functions and other operations and / or functions of the modules in the control system 600 are used to implement corresponding procedures of the method in Figures 2A and 2B. For the sake of brevity, the details will not be described again here.

[0111] The present application further provides a control system for an intelligent vehicle, which includes a manual driving controller 301, a decision-making controller 302, and an automatic driving controller 303 shown in Figure 1. The components in the control system are configured to execute the operational steps performed by corresponding execution entities in the methods shown in Figures 2A and 2B. For the sake of brevity, the details will not be repeated here.

[0112] The present application further provides an intelligent vehicle, which includes a human-computer interaction controller, a driving mode selector, a vehicle control system, and a vehicle execution system as shown in Figure 1. The components within the intelligent vehicle are configured to perform the operational steps performed by the corresponding execution entities in the methods shown in Figures 2A and 2B. For the sake of brevity, the details will not be repeated here.

[0113] The present application also provides a control system. The system includes a cloud data center in addition to the intelligent vehicle shown in FIG. 1. The intelligent vehicle includes the human-computer interaction controller, driving mode selector, vehicle control system, and vehicle execution system shown in FIG. 1. The components in the intelligent vehicle are configured to execute the operation steps performed by the corresponding execution entities in the methods shown in FIG. 2A and FIG. 2B. For brevity, the details will not be repeated here. The cloud data center is also configured to receive driving data sent by the vehicle control system and schedule a virtual machine in the cloud data center to train the driving data, thereby obtaining a customized driving style model. This avoids the problem that the computing power of the vehicle control system in the intelligent vehicle limits the processing speed and reduces the computing load of the intelligent vehicle. The cloud data center is also configured to store the model, add the model to a driving style model library stored in the cloud data center, and add the driving style model to another vehicle in addition to the intelligent vehicle in which the driver is located, so that the other vehicle updates the driving style model library and increases the number of driving style models for the driver's selection. Furthermore, the intelligent vehicle may send updated driving data of the driver to the cloud data center, and the cloud data center updates the driving style model corresponding to the driver, so that the result output by the driving style model is closer to the actual driving process of the driver. Furthermore, the intelligent vehicle may send an identifier of the driving style model selected by the driver to the cloud data center, and the cloud data center controls the driving process of the intelligent vehicle according to the accelerator opening and braking value specified in the driving style model.

[0114] All or some of the above-described embodiments may be implemented using software, hardware, firmware, or any other combination thereof. When software is used to implement an embodiment, all or some of the above-described embodiments may be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded onto or executed on a computer, the procedures or functions of the embodiments herein are generated, in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or another programmable device. The computer instructions may be stored on a computer-readable storage medium or transmitted from a computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, or digital subscriber line (DSL)) or wireless (e.g., infrared, radio waves, or microwave) transmission. The computer-readable storage medium may be any available medium accessible by a computer, or a data storage device such as a server or data center that consolidates one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, or a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state drive (SSD).

[0115] The above description is merely a specific implementation of the present application. Any modifications or replacements that can be easily thought up by those skilled in the art based on the specific implementations provided herein shall fall within the protection scope of the present application. [Other possible items] (Item 1) 1. A method for controlling an intelligent vehicle, comprising: The vehicle control system obtains a driving mode, a driving style model, and a target speed of the intelligent vehicle at a current time; the vehicle control system determining a speed control command based on the driving mode and the driving style model; the vehicle control system transmitting the speed control command to a vehicle execution system of the intelligent vehicle; A control method comprising: (Item 2) Item 1, wherein the speed control command includes an accelerator opening and a brake value, the accelerator opening is a parameter used to control vehicle acceleration of the intelligent vehicle, and the brake value is a parameter used to control vehicle braking of the intelligent vehicle. (Item 3) The vehicle control system includes a decision-making controller and an autonomous driving controller, and the method includes: the decision-making controller determining a driving trajectory command and the target speed based on the current road condition information, the road condition information including one or more information provided by a map system, a positioning device, and a fusion system of the intelligent vehicle; the automatic driving controller obtaining a driving mode and a driving style model selected by a driver; 3. The control method according to item 1 or 2, further comprising: (Item 4) 4. The control method according to any one of items 1 to 3, wherein the driving mode is an autonomous driving mode, the intelligent vehicle includes a driving style model library, the driving style model library includes a set of multiple pre-configured driving style models, and each driving style model includes a different accelerator opening and braking value. (Item 5) Before the step of the vehicle control system obtaining a driving mode, a driving style model, and a target speed of the current intelligent vehicle, the method includes: When the driving mode of the intelligent vehicle is a manual driving mode, the vehicle control system collects driving data of the driver of the intelligent vehicle within a preset period of time; The vehicle control system obtains a customized driving style model based on the driving data by using a machine learning algorithm, the customized driving style model including accelerator opening and braking values ​​that match the driving habits of the driver; adding the customized driving style model to the driving style model library of the intelligent vehicle by the vehicle control system; 4. The control method according to any one of items 1 to 3, further comprising: (Item 6) The step of the vehicle control system determining a speed control command based on the driving mode and the driving style model comprises: the autonomous driving controller calculating an error between the actual speed of the intelligent vehicle at the current time and the target speed; a step of determining an acceleration based on the error by the autonomous driving controller, the acceleration being used to indicate a speed change amount of the intelligent vehicle from the current actual speed to the target speed per unit time; The autonomous driving controller determines a first accelerator opening and a first brake value according to a proportional-integral-derivative algorithm; The automatic driving controller determines a second accelerator opening amount and a second brake value based on the driving style model selected by the driver; a step in which the autonomous driving controller obtains a third accelerator opening through calculation based on the first accelerator opening, the first weight, the second accelerator opening, and the second weight, and obtains a third brake value through calculation based on the first brake value, the third weight, the second brake value, and a fourth weight, wherein the first weight and the second weight are weights of accelerator opening, the sum of the first weight and the second weight is 1, and the third weight and the fourth weight are weights of brake values, the sum of the third weight and the fourth weight is 1; and The step of the vehicle control system transmitting the speed control command to a vehicle execution system of the intelligent vehicle comprises: the autonomous driving controller transmitting the speed control command to the vehicle execution system, the speed control command including the third accelerator opening and the third brake value; having 6. The control method according to any one of items 1 to 5. (Item 7) The method comprises: The vehicle control system provides the driving style model library of the intelligent vehicle to the driver through a human-computer interaction controller, wherein the driver can select a driving style model from the driving style model library in the form of voice, text, or buttons; receiving, by the vehicle control system, the driving style model selected by the driver and transmitted by the human-computer interaction controller; 7. The control method according to any one of items 1 to 6, further comprising: (Item 8) A control device for an intelligent vehicle, comprising: an acquisition unit configured to acquire a driving mode, a driving style model, and a target speed of the intelligent vehicle at a current time; an automatic driving control unit configured to determine a speed control command based on the driving mode and the driving style model; a transmitting unit configured to transmit the speed control command to a vehicle execution system of the intelligent vehicle; A control device comprising: (Item 9) The control device described in item 1, wherein the speed control command includes an accelerator opening and a brake value, the accelerator opening is a parameter used to control vehicle acceleration of the intelligent vehicle, and the brake value is a parameter used to control vehicle braking of the intelligent vehicle. (Item 10) the autonomous driving control unit is further configured to determine a driving trajectory command and the target speed based on the current road condition information, the road condition information including one or more pieces of information provided by a map system, a positioning device, and a fusion system of the intelligent vehicle; The acquisition unit is further configured to acquire a driving mode and a driving style model selected by a driver. 10. The control device according to item 8 or 9. (Item 11) 11. The control device of any one of items 8 to 10, wherein the driving mode is an autonomous driving mode, the intelligent vehicle includes a driving style model library, the driving style model library includes a set of multiple driving style models, each driving style model including a different accelerator opening and braking value. (Item 12) The acquisition unit is further configured to collect driving data of the driver of the intelligent vehicle within a preset period when the driving mode is a manual driving mode; The autonomous driving control unit is further configured to: obtain a customized driving style model based on the driving data by using a machine learning method, the customized driving style model including an accelerator opening and a brake value that match the driving habits of the driver; and add the customized driving style model to the driving style model library. 11. The control device according to any one of items 8 to 10. (Item 13) the autonomous driving control unit is further configured to: calculate an error between an actual speed of the intelligent vehicle at the current time and the target speed; determine an acceleration based on the error, the acceleration being used to indicate a speed change amount of the intelligent vehicle from the actual speed at the current time to the target speed within a unit time; determine a first accelerator opening and a first brake value according to a proportional-integral-derivative algorithm; determine a second accelerator opening and a second brake value based on the driving style model selected by the driver; obtain a third accelerator opening through calculation based on the first accelerator opening, a first weight, the second accelerator opening, and the second weight, wherein a sum of the first weight and the second weight is 1; and obtain a third brake value through calculation based on the first brake value, a third weight, the second brake value, and a fourth weight, wherein a sum of the third weight and the fourth weight is 1; the sending unit is further configured to send the speed control command including the third accelerator opening and the third brake value to the vehicle execution system. 13. The control device according to any one of items 8 to 12. (Item 14) The apparatus further comprises a prompt unit; the prompting unit is configured to provide the driving style model library of the intelligent vehicle to the driver through a human-computer interaction controller, and the driver can select a driving style model from the driving style model library in the form of voice, text, or button; the acquisition unit is further configured to receive the driving style model selected by the driver and sent by the human-computer interaction controller. 14. The control device according to any one of items 8 to 13. (Item 15) 8. A control system for an intelligent vehicle comprising a processor and a memory, the memory configured to store computer-executable instructions, and when the control system is run, the processor executes the computer-executable instructions in the memory to perform the operational steps of the method of any one of items 1 to 7 by using hardware resources in the control system.

Claims

1. 1. A method for controlling an intelligent vehicle, executed by a vehicle control system included in the intelligent vehicle, comprising: The vehicle control system obtains a driving mode, a driving style model, and a target speed of the current intelligent vehicle; the vehicle control system determining a speed control command based on the driving mode, the driving style model, and the target speed, the target speed being obtained based on the current road condition information, the road condition information including one or more information provided by a map system, a positioning device, or a sensing device fusion system of the intelligent vehicle; the vehicle control system transmitting the speed control command to a vehicle execution system of the intelligent vehicle; and determining the speed control command comprises: calculating an acceleration at which the intelligent vehicle reaches the target speed based on the target speed and the actual speed; obtaining an accelerator opening and a brake value by using the acceleration and the target speed as inputs of the driving style model; A control method comprising:

2. 2. The control method of claim 1, wherein the speed control command includes an accelerator opening and a brake value, the accelerator opening being a parameter used to control vehicle acceleration of the intelligent vehicle, and the brake value being a parameter used to control vehicle braking of the intelligent vehicle.

3. The vehicle control system includes a decision-making controller and an autonomous driving controller, and the control method includes: the decision-making controller determining a driving trajectory and the target speed based on the current road condition information, the road condition information including one or more information provided by a map system, a positioning device, and a fusion system of the intelligent vehicle; the automatic driving controller obtaining a driving mode and a driving style model selected by a driver; The control method according to claim 1 or 2, further comprising:

4. 4. The control method according to claim 1, wherein the driving mode is an autonomous driving mode, the intelligent vehicle includes a driving style model library, the driving style model library includes a set of multiple pre-configured driving style models, and each driving style model includes a different accelerator opening and braking value.

5. Before the step of the vehicle control system obtaining a driving mode, a driving style model, and a target speed of the intelligent vehicle at the current time, the control method includes: When the driving mode of the intelligent vehicle is a manual driving mode, the vehicle control system collects driving data of a driver of the intelligent vehicle within a preset period of time; The vehicle control system obtains a customized driving style model based on the driving data by using a machine learning algorithm, the customized driving style model including accelerator opening and braking values ​​that match the driving habits of the driver; adding the customized driving style model to a driving style model library of the intelligent vehicle by the vehicle control system; The control method according to claim 1 , further comprising:

6. The step of the vehicle control system determining a speed control command based on the driving mode, the driving style model, and the target speed comprises: an automatic driving controller of the vehicle control system calculating an error between the actual speed of the intelligent vehicle at the current time and the target speed; a step of determining an acceleration based on the error by the autonomous driving controller, the acceleration being used to indicate a speed change amount of the intelligent vehicle from the current actual speed to the target speed per unit time; The autonomous driving controller determines a first accelerator opening and a first brake value according to a proportional-integral-derivative algorithm; The automatic driving controller determines a second accelerator opening amount and a second brake value based on the driving style model selected by a driver; a step in which the autonomous driving controller obtains a third accelerator opening through calculation based on the first accelerator opening, the first weight, the second accelerator opening, and the second weight, and obtains a third brake value through calculation based on the first brake value, the third weight, the second brake value, and a fourth weight, wherein the first weight and the second weight are weights of the accelerator opening, the sum of the first weight and the second weight is 1, and the third weight and the fourth weight are weights of the brake value, the sum of the third weight and the fourth weight is 1; and The step of the vehicle control system transmitting the speed control command to a vehicle execution system of the intelligent vehicle comprises: the autonomous driving controller transmitting the speed control command to the vehicle execution system, the speed control command including the third accelerator opening and the third brake value; having A control method according to any one of claims 1 to 5.

7. The control method includes: The vehicle control system provides a driving style model library of the intelligent vehicle to a driver through a human-computer interaction controller, and the driver can select a driving style model from the driving style model library in the form of voice, text, or buttons; receiving, by the vehicle control system, the driving style model selected by the driver and transmitted by the human-computer interaction controller; The control method according to claim 1 , further comprising:

8. A control device for an intelligent vehicle, comprising: an acquisition unit configured to acquire a driving mode, a driving style model, and a target speed of the intelligent vehicle at a current time; an autonomous driving control unit configured to determine a speed control command based on the driving mode, the driving style model, and the target speed, wherein the target speed is obtained based on the current road condition information, and the road condition information includes one or more pieces of information provided by a map system, a positioning device, or a sensing device fusion system of the intelligent vehicle; a transmitting unit configured to transmit the speed control command to a vehicle execution system of the intelligent vehicle; The automatic driving control unit comprises: calculating an acceleration at which the intelligent vehicle reaches the target speed based on the target speed and the actual speed; obtaining an accelerator opening and a brake value by using the acceleration and the target speed as inputs of the driving style model; A control device that executes the above.

9. 9. The control device of claim 8, wherein the speed control command includes an accelerator opening and a brake value, the accelerator opening being a parameter used to control vehicle acceleration of the intelligent vehicle, and the brake value being a parameter used to control vehicle braking of the intelligent vehicle.

10. the autonomous driving control unit is further configured to determine a driving trajectory and the target speed based on the current road condition information, the road condition information including one or more pieces of information provided by a map system, a positioning device, and a fusion system of the intelligent vehicle; The acquisition unit is further configured to acquire a driving mode and a driving style model selected by a driver. The control device according to claim 8 or 9.

11. 11. The control device according to claim 8, wherein the driving mode is an autonomous driving mode, the intelligent vehicle includes a driving style model library, the driving style model library includes a set of multiple driving style models, and each driving style model includes a different accelerator opening and braking value.

12. The acquisition unit is further configured to collect driving data of a driver of the intelligent vehicle within a preset period when the driving mode is a manual driving mode; The autonomous driving control unit is further configured to: obtain a customized driving style model based on the driving data by using a machine learning method, the customized driving style model including an accelerator opening and a brake value that match the driving habits of the driver; and add the customized driving style model to a driving style model library of the intelligent vehicle. The control device according to any one of claims 8 to 10.

13. the autonomous driving control unit is further configured to: calculate an error between an actual speed of the intelligent vehicle at the current time and the target speed; determine an acceleration based on the error, the acceleration being used to indicate a speed change amount of the intelligent vehicle from the actual speed at the current time to the target speed within a unit time; determine a first accelerator opening and a first brake value according to a proportional-integral-differential algorithm; determine a second accelerator opening and a second brake value based on the driving style model selected by a driver; obtain a third accelerator opening through calculation based on the first accelerator opening, a first weight, the second accelerator opening, and the second weight, wherein a sum of the first weight and the second weight is 1; and obtain a third brake value through calculation based on the first brake value, a third weight, the second brake value, and a fourth weight, wherein a sum of the third weight and the fourth weight is 1; the sending unit is further configured to send the speed control command including the third accelerator opening and the third brake value to the vehicle execution system. A control device according to any one of claims 8 to 12.

14. The control device further comprises a prompt unit; the prompting unit is configured to provide a driving style model library of the intelligent vehicle to the driver through a human-computer interaction controller, and the driver can select a driving style model from the driving style model library in the form of voice, text, or button; the acquisition unit is further configured to receive the driving style model selected by the driver and sent by the human-computer interaction controller. A control device according to any one of claims 8 to 13.

15. 8. A control system for an intelligent vehicle comprising a processor and a memory, the memory configured to store computer-executable instructions, and when the control system is run, the processor executes the computer-executable instructions in the memory to perform the operational steps of the control method of any one of claims 1 to 7 by using hardware resources in the control system.

Images