Intelligent vehicle control methods, devices and control systems

Abstract

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

Description

Technical Field

[0001] This application relates to the field of intelligent vehicles, and more particularly to a control method, device, and system for intelligent vehicles. Background Technology

[0002] With the development of artificial intelligence (AI) technology and its application in the automotive field, intelligent cars with automated driving capabilities have received widespread attention. Intelligent cars utilize control modules to control their movement. These modules need to determine the driving trajectory and speed. The trajectory depends on the destination set by the driver, while speed is often determined using traditional error feedback methods. To achieve the desired speed, the control module uses a proportional-integral-derivative (PID) method to adjust for errors, determining the current throttle and brake control values ​​based on the control algorithm and the previous throttle and brake values. However, due to the complex and diverse road conditions, intelligent cars need to consider the driving conditions of other vehicles and the condition of road infrastructure for obstacle avoidance, resulting in constantly changing speeds. For the control module, the larger the error between the current speed and the target speed, the larger the adjustment. In automated driving, this manifests as frequent switching between throttle and brake. Furthermore, the aforementioned error feedback method does not consider the comfort of the occupants, leading to a poor user experience. Therefore, how to provide a control method for intelligent vehicles that offers high comfort and a good user experience has become an urgent technical problem to be solved. Summary of the Invention

[0003] This application provides a control method for intelligent vehicles, which can improve the comfort and driving experience of intelligent vehicles.

[0004] Firstly, a control method for intelligent vehicles is provided. The vehicle control system first acquires the current driving mode, driving style model, and target speed of the intelligent vehicle; then, it determines a speed control command based on the driving style model and driving mode; and finally, it sends the speed control command to the vehicle execution system of the intelligent vehicle. Through this method, the intelligent vehicle can be controlled in conjunction with the driving style model selected by the driver, thereby improving the driver's driving experience and comfort.

[0005] In one possible implementation, the speed control command includes throttle opening and braking value. Throttle opening and braking value are key factors in controlling the driving of intelligent vehicles. Different drivers have different driving habits when manually driving intelligent vehicles; for example, in a gasoline-powered vehicle, a driver controls the accelerator and brake pedals, or in an electric vehicle, a driver controls the vehicle's acceleration and braking system. Here, throttle opening refers to the parameter used to control the vehicle's acceleration in the intelligent vehicle; and braking value refers to the parameter used to control the vehicle's braking. The above method determines the speed control command with throttle opening and braking value by utilizing the driver's selected driving style model, thereby controlling the intelligent vehicle to drive according to the driver's selected driving style model, thus improving the driver's comfort when driving the intelligent vehicle.

[0006] In another possible implementation, the vehicle control system includes a decision controller and an autonomous driving controller. The decision controller can determine the driving trajectory and target speed based on current road condition information, which includes one or more of the information provided by the intelligent vehicle's map system, positioning equipment, and fusion system. The autonomous driving controller acquires the driving mode and driving style model selected by the driver, and further determines speed control commands based on the driving style model, driving mode, and road condition information.

[0007] In another possible implementation, the intelligent vehicle's driving modes include manual driving and autonomous driving. In autonomous driving mode, the driver can select a driving style model through the intelligent vehicle. The intelligent vehicle includes a driving style model library containing a set of multiple preset driving style models, each with different throttle opening and braking values. By using the throttle opening and braking values ​​to indicate different driving habits, the intelligent vehicle is controlled according to the throttle opening and braking values ​​of different driving style models during operation. This simulates the driver's preferred driving style, thereby achieving a driving operation more in line with the driver's driving habits.

[0008] In another possible implementation, when the intelligent vehicle is in manual driving mode, the vehicle control system can collect the driver's driving data within a preset time period. Using machine learning algorithms, a customized driving style model that conforms to the driver's driving habits is obtained based on the driving data. This customized driving style model includes throttle opening and braking values ​​that match the driver's driving habits. The customized driving style model is then added to the intelligent vehicle's stored driving style model library. In addition to utilizing the intelligent vehicle's pre-installed driving style model library, this application can also collect the driver's driving data in manual driving mode and use this data as a basis to train a driving style model that conforms to the current driver's driving habits. If the intelligent vehicle switches to autonomous driving mode, the driver can select a customized driving style model, and the intelligent vehicle will control its driving according to the throttle opening and braking values ​​in the model, simulating the current driver's driving habits, thereby improving the driver's driving experience.

[0009] In another possible implementation, the autonomous driving controller calculates the error between the current vehicle speed and the target vehicle speed; then, it determines acceleration based on the error, where acceleration indicates the speed change of the vehicle from the current actual speed to the target speed per unit time; next, it determines a first throttle opening and a first braking value using a proportional-integral-differential algorithm; it determines a second throttle opening and a second braking value based on the driving style model selected by the driver; it calculates a third throttle opening based on the first throttle opening, a first weight value, the second throttle opening, and the second weight value; and it calculates a third braking value based on the first braking value, the third weight value, the second braking value, and a fourth weight value; wherein the first and second weight values ​​are throttle opening weight values, and their sum is 1; the third and fourth weight values ​​are braking value weight values, and their sum is 1. The third throttle opening and the third braking value are then sent to the vehicle execution system.

[0010] In another possible implementation, a human-machine interface (HMI) controller provides the driver with a library of driving style models for the intelligent vehicle. The driver can select a driving style model from this library through voice, text, buttons, and other human-machine interaction methods. The driver then receives the selected driving style model from the HMI controller. The driver can interact with the intelligent vehicle via voice or text through the HMI controller, understand the vehicle's driving status, and thus control the vehicle's operation, rather than experiencing autonomous driving without complete knowledge of its operation, thus improving the driving experience. Furthermore, in emergency situations, the driver can also control the intelligent vehicle through the interface or voice provided by the HMI controller, rather than relying entirely on the vehicle's controller, further enhancing the safety of the intelligent vehicle's operation.

[0011] Secondly, this application provides a control device for an intelligent vehicle, the control device comprising various modules for performing the control method for an intelligent vehicle in the first aspect or any possible implementation thereof.

[0012] Thirdly, this application provides a control system for an intelligent vehicle, the intelligent control system including a decision controller and an autonomous driving controller, the decision controller and the autonomous driving controller being used to execute the operation steps of the method executed by each execution entity in the first aspect or any possible implementation of the first aspect.

[0013] Fourthly, this 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, memory, and communication interface are connected via the bus and communicate with each other. The memory stores computer execution instructions. When the control system is running, the processor executes the computer execution instructions in the memory to utilize the hardware resources in the control system to perform the operation steps of the method described in the first aspect or any possible implementation of the first aspect.

[0014] Fifthly, this application provides an intelligent vehicle with a control system for performing functions including those implemented by the control system in the fourth aspect or any possible implementation of the fourth aspect.

[0015] Sixthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described in the above aspects.

[0016] In a seventh aspect, this application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the methods described in the above aspects.

[0017] Based on the implementation methods provided in the above aspects, this application can be further combined to provide more implementation methods. Attached Figure Description

[0018] Figure 1 A schematic diagram of the logical architecture of an intelligent vehicle provided in this application;

[0019] Figure 2 A flowchart illustrating a control method for an intelligent vehicle provided in this application;

[0020] Figure 3 A flowchart illustrating an autonomous driving mode control method for an intelligent vehicle provided in this application;

[0021] Figure 4 A schematic diagram of a human-computer interaction system for an intelligent vehicle provided in this application;

[0022] Figure 5 This application provides a schematic diagram of the structure of a control device for an intelligent vehicle.

[0023] Figure 6 This is a schematic diagram of the structure of a control system for an intelligent vehicle provided in this application. Detailed Implementation

[0024] The technical solutions in this application will be clearly described below with reference to the accompanying drawings in the embodiments of this application.

[0025] First, combined Figure 1 This application provides a schematic diagram of the logical architecture of an intelligent vehicle 100. As shown in the figure, the intelligent vehicle 100 includes a human-machine interaction controller 10, a driving mode selector 20, a vehicle control system 30, a vehicle execution system 40, a positioning device 50, a perception system 60, and a map system 70.

[0026] The human-machine interface controller 10 is used to enable message interaction between the intelligent vehicle and the driver. The driver can select the driving mode and driving style model of the intelligent vehicle through the human-machine interface controller 10. The human-machine interface controller 10 can provide message interaction with the driver in the form of voice, text, etc., and can also interact with the driver in other forms such as seat vibration and flashing in-vehicle indicator lights.

[0027] The driving mode selector 20 transmits the information input by the driver through the human-machine interface controller 10 to the vehicle control system 30. The vehicle control system 30 then controls the intelligent vehicle's movement according to the driving style model selected by the driver. The vehicle control system 30 controls the intelligent vehicle through the vehicle execution system 40. The vehicle execution system 40 includes, but is not limited to, devices or subsystems that control the vehicle's movement, such as the braking system, steering system, drive system, and lighting system.

[0028] The vehicle control system 30 further includes a manual driving controller 301, a decision controller 302, and an automatic driving controller 303. The manual driving controller 301 acquires and stores user driving data, and uses a neural network model to train the acquired data to obtain a driving style model based on the trained data. The manual driving controller 301 can store the acquired user driving data in its own memory or in other storage devices of the intelligent vehicle. The decision controller 302 is a subsystem for providing decision-making and path planning for the intelligent vehicle, including but not limited to global path planning, behavior planning, and operation planning. The automatic driving controller 303 controls the intelligent vehicle's driving based on the intelligent vehicle's driving trajectory and speed planned by the decision controller 302 and the driving style model selected by the driver.

[0029] As one possible implementation, the vehicle control system 30 can consist of one or a group of processors. The manual driving controller 301, decision controller 302, and automatic driving controller 303 each have their functions implemented by one or more processors, or a group of processors can each implement the functions of the manual driving controller 301, decision controller 302, and automatic driving controller 303. Optionally, the manual driving controller 301, decision controller 302, and automatic driving controller 303 can be implemented in software in addition to hardware implementation, or a combination of software and hardware implementation.

[0030] Positioning device 50 includes devices or subsystems used to determine the vehicle's location, such as a global positioning system (GPS) and an inertial navigation system (INS).

[0031] The fusion system 60 provides fusion, correlation, and prediction functions for the sensing devices 601 of the intelligent vehicle to obtain target objects, thereby providing accurate static and / or dynamic obstacle information for each subsystem of the intelligent vehicle, including but not limited to the position, size, attitude, and speed of physical objects such as people, vehicles, and roadblocks. The sensing devices 601 provide target detection and classification for the intelligent vehicle, including one or more sensing devices such as radar, sensors, and cameras.

[0032] Optionally, the intelligent vehicle 100 may also include a memory 70 for storing map files. The vehicle controller 30 can retrieve the map files from the memory 70 and control the intelligent vehicle's driving trajectory in conjunction with real-time traffic information.

[0033] It is worth noting that the intelligent vehicle in this application includes vehicles that support intelligent driving functions, which can be fuel vehicles, electric vehicles, or other new energy vehicles. Figure 1 The logical architecture of the intelligent vehicle shown is merely an example of an intelligent vehicle provided in this application, and its structure does not constitute a limitation on the technical solution to be protected in this application. On the other hand, the above... Figure 1 The various devices or systems shown can be implemented by software or hardware, and this application does not limit them.

[0034] Next, combined Figure 2 This application further describes the control method for an intelligent vehicle. As shown in the figure, the method includes:

[0035] S201. Obtain the driving mode selected by the driver.

[0036] Intelligent cars can be made by Figure 1 The human-machine interface controller 10 shown receives commands from the driver. For example, Figure 3 This is a schematic diagram of a human-computer interaction interface. As shown in the figure, the driver can select manual driving mode 101 or automatic driving mode 102 through the driving mode selection interface 10. This interface can use different colors and / or patterns to indicate different modes.

[0037] Optionally, in addition to the prompts on the interface buttons mentioned above, the human-machine interface controller can also provide voice prompts and allow the driver to input commands via voice to facilitate the selection of driving modes. During the voice selection process, the driver can first select the driving mode by voice according to actual needs.

[0038] When the driver selects the autonomous driving mode, the human-machine interface system can also prompt the driver with the desired driving style through voice or interface. Furthermore, the system can provide a brief explanation of each driving style, specifically informing the driver of the characteristics of each driving style model through the interface or voice, so that the driver can better select the driving style they prefer. For example, Figure 3The diagram provides a driving style model selection interface 30. As shown, the intelligent vehicle includes three driving style models: driving style model 301, driving style model 302, and customized driving style model 303. On the other hand, the human-machine interface controller can present the interaction information between the intelligent vehicle and the driver in a visual interface within the intelligent vehicle. For example, the human-machine interface can be displayed on the windshield, the rearview mirror, or other in-vehicle devices or interfaces, facilitating interaction between the driver and the intelligent vehicle system. When the intelligent vehicle receives a command from the driver, the driving mode selector 20 obtains the driving mode selected by the driver and further plans the intelligent vehicle's driving trajectory and speed.

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

[0040] The vehicle control system needs to determine whether the driving mode selected by the driver is the automatic driving mode. If the driving mode is the automatic driving mode, then step S203 is executed; if the driving mode is the manual driving mode, then step S213 is executed.

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

[0042] When the driving mode is set to autonomous driving, the driver can also select a driving style through the human-machine interface. Each driving style corresponds to a driving style model. For example, such as... Figure 3 The driving style selection prompt 30 shown includes driving style model 301, driving style model 302, and customized driving style model 303. After the driver confirms the driving style model, the selected result (e.g., the driving style model identifier) ​​is transmitted to the vehicle controller through the human-machine interaction controller and driving mode selector. The autonomous driving controller then controls the intelligent vehicle to drive to the destination according to the driving style selected by the driver.

[0043] At least one driving style model in an intelligent vehicle, which can be obtained through any one or more of the following methods:

[0044] Method 1: Pre-install driving style models in smart cars.

[0045] Intelligent vehicles have a pre-installed driving style model library, which includes at least one driving style model. Each driving style model can be pre-installed when the intelligent vehicle leaves the factory. Specifically, it can be trained using driving data from multiple types of drivers as raw data (or driving data), and machine learning algorithms can be used to obtain a driving style model that conforms to the driving habits of each type of driver.

[0046] A driving style model can be obtained by training a neural network model on raw data. In practice, the training process can choose any neural network model to train the raw data based on business needs. For example, a three-layer neural network model can be used to train the driving data. This model mainly includes three layers: an input layer, a hidden layer, and an output layer. The input layer extracts some features from the driving data, the hidden layer extracts features other than those extracted by the input layer, and the output layer processes the features extracted by the input and hidden layers to output the final result. Optionally, the hidden layer can further extract the required content based on the features extracted by the input layer, and extract features other than those extracted by the input layer. Optionally, to ensure that the driving style model obtained by the neural network model is closer to the driver's real driving data, the back propagation (BP) principle can be used to correct the training results. This involves comparing the output results obtained by the neural network model with the real data and further adjusting the weights of neurons in each layer to make the results obtained by the neural network model training closer to the real data. The number of neurons in each layer of the neural network model can be set according to specific business needs.

[0047] During the training of the driving style model, the target vehicle speed, current vehicle speed, and acceleration are used as input values ​​to the backpropagation neural network model, while throttle opening and braking values ​​are the output values. Throttle opening refers to the parameter used in intelligent vehicles to control vehicle acceleration; a larger throttle opening results in greater acceleration. For example, in a gasoline-powered vehicle, the engine controls the fuel injection quantity based on the throttle opening, thereby controlling the vehicle's acceleration. Throttle opening refers to the throttle opening, specifically the driver's control of the throttle opening via the accelerator pedal. It can also be understood as the degree to which the accelerator pedal is pressed, similar to the angle formed between the accelerator pedal and the horizontal plane when the driver's foot is on it. Alternatively, it can be simply understood as the depth to which the driver presses the accelerator pedal. In electric vehicles, throttle opening refers to the parameter used to control vehicle acceleration via a throttle control device (e.g., an electric accelerator button). Braking value refers to the parameter used in intelligent vehicles to control braking; a larger braking value results in greater braking torque. For example, in a gasoline-powered vehicle, the braking force refers to the pressure applied by the driver's foot to the brake pedal. This pressure is amplified and transmitted through a vacuum booster; the amplified force pushes the master cylinder, pressurizing the brake fluid; the brake fluid is then distributed to the front and rear brakes through the brake combination valve, simultaneously illuminating the brake warning light and controlling the braking of the front and rear brakes, thus bringing the vehicle to a stop. In an electric vehicle, the braking force refers to the parameters controlled by the brake control device to regulate the vehicle's braking.

[0048] Next, the process of obtaining the driving style model in this application is further explained with examples. First, the vehicle speed v(t), accelerator pedal position (PP) PP(t), brake pedal position (BP) BP(t) at time t, and the vehicle speed v(t+k) at time t+k are extracted from the driving data of real drivers. Since there may be a delay in the process of obtaining the vehicle speed during the intelligent vehicle's operation, the actual output of the intelligent vehicle has a delay of k seconds, for example, the value of k is generally 1 to 2 seconds. Using v(t), PP(t), and BP(t) as inputs to the neural network model, the vehicle speed obtained at time t+k after training the neurons of each layer in the neural network model is v′(t+k). At this time, the difference between the vehicle speed obtained by the neural network model training and the actual vehicle speed is v(t+k) - v′(t+k); then, this difference is further corrected through the backpropagation principle to ensure that the data obtained by the neural network training model is closer to the real value, and finally the driving style model based on the neural network model training is obtained. By continuously training the driving data of drivers, the accuracy of the driving style model is improved, ultimately making the data obtained by the neural network model closer to the driving data of real drivers.

[0049] Optionally, driving style model training is an iterative process. Through continuous training, the final driving style model is made closer to the driving data of real drivers. In specific implementations, the number of iterations can be determined according to preset conditions. For example, the training process can be stopped when the difference between the vehicle speed obtained by the neural network model training and the actual vehicle speed is less than a preset value. Alternatively, the training process can be completed when the difference between the training result and the actual result is within a preset error range.

[0050] It is worth noting that the training process of a neural network model can be understood as a black-box process. Multiple sets of driving data are used as input to the model, and the computational processing of neurons in each layer during each iteration makes the final model more closely resemble the actual driving process. In specific implementations, the number of neurons in the input layer, hidden layer, and output layer can be set according to specific needs. This application does not limit the neural network model; the specific implementation can select a neural network model based on business requirements. Furthermore, the processing procedures of neurons at each layer in the neural network model, as well as the result correction process, are not limited by this application.

[0051] For example, using driving data from driver A and driver B as sample data in the experience base, driving data from both drivers while driving the intelligent car is collected and used as input to a machine learning algorithm. The algorithm trains the algorithm to obtain different driving style models as preset driving style models. In this case, the experience base includes two different driver style models. If driver A likes to drive fast, the driving style model trained using driver A's driving data will consider the driver's preferences, with more frequent switching between accelerator and acceleration. If driver B drives more smoothly, the driving style model trained using driver B's driving data will show fewer instances of emergency braking and frequent acceleration.

[0052] Method 2: Intelligent vehicles train a driving style model based on the current driver's driving data.

[0053] Drivers may also choose to train a customized driving style model based on driving data collected from their driving habits. For the specific training process, please refer to the training process of the preset driving style model in Method 1. This application does not limit this process.

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

[0055] When the intelligent vehicle is in autonomous driving mode, the decision controller can obtain obstacle information (including but not limited to obstacle type, height, speed, etc.) from the fusion system and its own location information from the map system and positioning device. Then, the decision controller in the vehicle control system performs global and / or local path planning and outputs all or part of the intelligent vehicle's driving trajectory to the destination. Then, the decision controller sends all or part of the intelligent vehicle's driving trajectory to the autonomous driving controller to execute the operation in step S205.

[0056] Optionally, the decision controller may also obtain information from at least one of the fusion system, map system, and positioning device, and perform global and / or local path planning based on the above information to output the entire or partial driving trajectory of the intelligent vehicle to its destination.

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

[0058] The vehicle control system's automated driving controller combines a driving style model with traditional target speed adjustment methods to control the input target vehicle speed and output longitudinal commands, including throttle and brake control. It then sends these lateral and longitudinal commands to the vehicle's execution system to control the intelligent vehicle's operation. The traditional target speed adjustment method can be a proportional-integral-derivative method or other methods; this application does not limit its application to these methods.

[0059] Figure 4 The figure illustrates a control process for an autonomous driving mode provided in this application. The autonomous driving controller in the vehicle control system obtains the target vehicle speed and the actual vehicle speed from the decision controller. It calculates the error based on the target and actual speeds and uses this error as input to a proportional-integral-derivative (PI-DI) algorithm. Following error feedback, it calculates the throttle opening and braking value required for the intelligent vehicle to reach the target speed, thus defining the common requirements for the intelligent vehicle to achieve the target speed. The PI-DI 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; the larger the error, the greater the adjustment. Specific implementation details can be found in conventional technologies, which will not be elaborated upon here.

[0060] On the other hand, the autonomous driving controller calculates the acceleration required for the intelligent vehicle to reach the target speed based on the target speed and error. This acceleration is used to determine the speed change of the intelligent vehicle to the target speed per unit time. The expected acceleration and target speed are used as inputs to the driving style model algorithm. A machine learning algorithm is used to calculate the throttle opening and braking values, which are then used as the personalized components. This application does not limit the type of machine learning algorithm; a neural network algorithm containing neurons in an input layer, hidden layer, and output layer can be used. The number of neurons in each layer can be set according to specific business needs. For example, in specific implementations, the number of neurons in each layer can be set according to accuracy requirements; more neurons result in higher accuracy. This leads to the throttle opening and braking values ​​obtained by the driving style model algorithm.

[0061] Finally, the throttle opening and braking values ​​obtained from the driving style model algorithm and the proportional-integral-derivative (PI-DI) algorithm are superimposed. A weighted method can be used for this superposition, setting weights for the driving style model algorithm and the throttle opening and braking values ​​obtained from the PI-DI algorithm based on the specific business requirements of the implementation. These weights indicate the proportion of the throttle opening or braking value obtained by the two algorithms. For example, weights can be assigned to the throttle opening obtained by the PI-DI algorithm and the driving style model algorithm based on the hardware capabilities of the intelligent vehicle, with the sum of these weights being 1. Similarly, weights can be assigned to the braking values ​​obtained by the PI-DI algorithm and the driving style model algorithm, with the sum of these weights also being 1. Finally, the throttle opening and braking values ​​obtained from the driving style model algorithm and the traditional algorithm, combined with the weighted superposition, are sent as speed control commands to the vehicle's execution system. For example, suppose the throttle opening obtained by the driving style model algorithm is S1, and the braking value is B1; the throttle opening obtained by the proportional-integral-derivative (PID) algorithm is S2, and the braking value is B2; the intelligent driving vehicle is a vehicle with superior drive and engine performance. Assume the weight of the throttle opening obtained by the driving style model algorithm is a1, the weight of the throttle opening obtained by the PID algorithm is a2, the weight of the braking value obtained by the PID algorithm is b1, and the weight of the braking value obtained by the driving style model algorithm is b2, and a1 + a2 = 1, b1 + b2 = 1. Then the final determined throttle opening S is (S1*a1 + S2*a2), and the braking value B is (B1*b1 + B2*b2). At this point, the autonomous driving controller can send the throttle opening S and the braking value B as speed control commands to the vehicle's execution system, thereby controlling the operation of the intelligent vehicle.

[0062] As a possible implementation, during the weight setting process described above, a weight value can also be assigned to each algorithm. In this case, the final determined throttle opening and braking value are calculated using the weight values ​​assigned to each algorithm. For example, let's set the weight values ​​in the above example to a1 = b1 and a2 = b2. Then, the final determined throttle opening S is (S1 + S2) * a1, and the braking value B is (B1 + B2) * b1.

[0063] As one possible implementation, during the operation of an intelligent vehicle, the uncertainties surrounding the trajectories and speeds of other vehicles affect the vehicle's own trajectory and speed. Therefore, the process of determining the vehicle's speed and trajectory requires multiple adjustments based on different road conditions. Furthermore, as road conditions change, the throttle opening and braking values ​​need to be adjusted in real-time or periodically. In other words, during the autonomous driving mode of an intelligent vehicle, steps S204 to S205 may need to be executed repeatedly. On the other hand, the design of an intelligent vehicle also needs to consider the switching process between driving modes. For example, when switching from autonomous driving to manual driving, step S206 needs to be executed.

[0064] It is worth noting that, in addition to using the proportional-integral-differential algorithm to calculate the common part of reaching the target speed in intelligent vehicles, other algorithms can also be used to determine the common part of reaching the target speed, and this application does not limit this.

[0065] S206. Determine whether the driver has adjusted the driving style model.

[0066] S207. When the driver adjusts the driving style model, update the speed control command according to the adjusted driving style model and the target vehicle speed.

[0067] When an intelligent vehicle includes multiple driving style models, the driver is allowed to freely switch between these models during operation to obtain different driving experiences. When the driver adjusts the driving style, new trajectory control commands and speed control commands are determined by referring to steps S204 to S205.

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

[0069] In intelligent vehicles, vehicle control is managed by the vehicle execution system, which includes the braking system (such as brakes), steering system (such as steering wheel), drive system (such as engine), and lighting system (such as headlights). Trajectory control commands and speed control commands need to be executed by the vehicle execution system to control the driving of the intelligent vehicle.

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

[0071] As an optional step, after completing the execution of trajectory control commands and speed control commands, the vehicle execution system can return the execution result to the vehicle control system, which includes whether the command was executed successfully or not.

[0072] S210. When the driver does not adjust the driving style model, the trajectory control command and speed control command are sent to the vehicle execution system.

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

[0074] As a possible implementation, when 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, which then controls the intelligent vehicle to drive according to the contents of the above commands.

[0075] S212. Then, determine whether the driver has adjusted the driving mode.

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

[0077] As one possible implementation, intelligent vehicles have a pre-installed driving style model at the factory. However, to accommodate different drivers' driving habits, when the intelligent vehicle enters manual driving mode, it can collect the current driver's driving data and use this data as input to retrain a customized driving style model using machine learning algorithms, thus updating the intelligent vehicle's driving style model. Specific operation steps are detailed in steps S213 to S215. The vehicle control system can obtain a customized driving style model based on the driver's data at the current moment.

[0078] S213. When the driving mode is manual driving mode, obtain the driver's driving data.

[0079] When the intelligent vehicle is in manual driving mode, the interface can prompt the driver whether to customize the driving style model, such as... Figure 3 As shown, if the intelligent vehicle is in manual driving mode, it can be... Figure 3 The manual driving mode 20 interface prompts the driver whether to customize the driving style model. If the driver clicks "Customize Driving Style Model 201", the driver's driving data at the current moment will be collected as input for subsequent machine learning algorithms.

[0080] Optionally, when the intelligent vehicle is in manual driving mode, the vehicle control system can also interact with the driver via voice or other means to confirm whether to customize the driving style model.

[0081] It is worth noting that, Figure 3This is merely one example provided in this application. Those skilled in the art, upon learning of this application, may also prompt the driver to select a driving mode, driving style model, or custom driving style model through other forms or interface structures.

[0082] S214. Use machine learning algorithms to train the driving data and obtain a trained driving style model.

[0083] S215. Add customized driving style models to the driving style model library of intelligent vehicles.

[0084] When the intelligent vehicle is in manual driving mode, firstly, the manual driving controller of the vehicle control system collects the driver's driving data. Then, based on this driving data, it trains the driving data using the method described in Method 1 above, thereby obtaining a driving style model trained based on the current driver's driving data. This driving style model is then added as a customized driving style model to the intelligent vehicle's driving style model library, allowing the driver to select this driving style model in autonomous driving mode and control the intelligent vehicle's driving using the operation process from steps S203 to S209.

[0085] As one possible implementation, after the vehicle control system collects the current driver's driving data, in addition to training the driving data within the intelligent vehicle, it can also send the driving data to a cloud data center. The cloud data center then generates a customized driving style model based on the driving data and machine learning algorithms. As described above, sending the driving data to the cloud data center allows the cloud data center to schedule virtual machines to train the driving data, thereby obtaining a customized driving style model. On one hand, this avoids the problem of the computing power limiting the processing speed of the vehicle control system in the intelligent vehicle, reducing the computational load on the intelligent vehicle. On the other hand, the cloud data center can also save the model to its stored driving style model library and add the driving style model to other vehicles besides the intelligent vehicle where the driver is located, so that other vehicles can update their driving style model libraries, increasing the number of driving style models available for the driver to choose from. Furthermore, the intelligent vehicle can also send the driver's updated driving data to the cloud data center, which then updates the driving style model corresponding to that driver, making the output of the driving style model closer to the driver's actual driving process. Optionally, the driver's driving data can be saved to a cloud data center. When the driver selects the customized model through the human-machine interface, the cloud data center can also remotely control the intelligent vehicle's driving process. In other words, the identifier of the driving style model selected by the driver will be sent to the cloud data center, which will then control the intelligent vehicle's driving process based on the throttle opening and braking values ​​defined in the driving style model.

[0086] The intelligent vehicle control method provided in this application sets the intelligent vehicle into two modes: manual driving mode and autonomous driving mode. In manual driving mode, the vehicle control system can collect the current driver's driving data in real time and use machine learning algorithms to train a customized driving style model for the driver, updating the intelligent vehicle's driving style model library. This allows the driver to select a customized driving style model to control the intelligent vehicle in autonomous driving mode, improving the driver's driving experience. In autonomous driving mode, the driver's selected driving style model is combined with the traditional proportional-integral-derivative method. When adjusting the current vehicle speed, the method further considers the driver's driving habits during the driving process based on the selected driving style model, achieving human-like control of the intelligent vehicle. This makes the autonomous driving process of the intelligent vehicle more closely resemble the driver's driving habits, further enhancing the driving experience. On the other hand, in addition to pre-installing a classic driving style model library when a smart car leaves the factory, a customized driving style model can also be retrained based on the current driving data of the smart car's driver. This customized driving style model can then be added to the smart car's driving style model library. In autonomous driving mode, the driver can select this customized driving style model, thereby enabling the smart car to operate according to the parameters in the driving style model selected by the driver, further enhancing the driver's driving experience.

[0087] It is worth noting that, for the sake of simplicity, the above method embodiments are described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions.

[0088] The above text combines Figures 1 to 4 The control method for an intelligent vehicle provided according to this application is described in detail below, in conjunction with... Figures 5 to 6 This application further describes the control device, control system, and intelligent vehicle provided in this application.

[0089] Figure 5 A schematic diagram of a control device 500 provided in this application is shown in the figure. The control device 500 includes an acquisition unit 501, an automatic driving control unit 502, and a transmission unit 503, wherein...

[0090] The acquisition unit 501 is used to acquire the driving mode, driving style model and target speed of the intelligent vehicle at the current moment;

[0091] The automatic driving control unit 502 is used to determine speed control commands based on the driving mode and driving style model.

[0092] The sending unit 503 is used to send the speed control command to the vehicle execution system of the intelligent vehicle.

[0093] It should be understood that the device 500 in this application embodiment can be implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD can be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. It can also be implemented using software. Figure 2 In the control method of the intelligent vehicle shown, the device 500 and its various modules can also be software modules.

[0094] Optionally, the speed control command includes throttle opening and braking value; the throttle opening refers to a parameter used in intelligent vehicles to control vehicle acceleration; the braking value refers to a parameter used in intelligent vehicles to control vehicle braking.

[0095] Optionally, the autonomous driving control unit 502 is further configured to determine the driving trajectory instruction and the target vehicle speed based on the current road condition information, wherein the road condition information includes information provided by the intelligent vehicle's map system, positioning device, and fusion system; the acquisition unit 501 is further configured to acquire the driving mode and 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, which includes a set of multiple driving style models, each of which includes different throttle opening and braking values.

[0097] Optionally, the acquisition unit 501 is further configured to collect the driver's driving data of the intelligent vehicle within a preset time period when the driving mode is manual driving mode; the autonomous driving control unit 502 is further configured to obtain a customized driving style model based on the driving data using machine learning methods, the customized driving style model including throttle opening and braking value that meet the driver's driving habits; and add the customized driving style model to the driving style model library.

[0098] Optionally, the autonomous driving control unit 502 is further configured to calculate the error between the actual speed of the intelligent vehicle at the current moment and the target speed; determine acceleration based on the error, the acceleration being used to indicate the speed change of the intelligent vehicle from the actual speed at the current moment to the target speed per unit time; determine a first throttle opening and a first braking value based on a proportional-integral-derivative algorithm; determine a second throttle opening and a second braking value based on the driving style model selected by the driver; calculate a third throttle opening based on the first throttle opening, a first weight value, the second throttle opening, and the second weight value, wherein the sum of the first weight value and the second weight value is 1; and calculate a third braking value based on the first braking value, the third weight value, the second braking value, and a fourth weight value, wherein the sum of the third weight value and the fourth weight value is 1.

[0099] The sending unit 503 is also used to send the speed control command, including the third throttle opening and the third braking value, to the vehicle execution system.

[0100] Optionally, the device further includes a prompting unit 504, which provides the driver with the driving style model library of the intelligent vehicle using a human-machine interaction controller. The driver can select a driving style model from the driving style model library by voice, text, or buttons.

[0101] The acquisition unit 501 is also used to receive the driving style model selected by the driver sent by the human-machine interaction controller.

[0102] The control device 500 according to the embodiments of this application can correspond to executing the method described in the embodiments of this application, and the above and other operations and / or functions of each unit in the control device 500 are respectively for implementing Figure 2 For the sake of brevity, the corresponding processes of each method in the code will not be elaborated here.

[0103] Figure 6 A schematic diagram of a control system 600 provided in this application is shown in the figure. The control system 600 includes a processor 601, a memory 602, a communication interface 603, a RAM 604, and a bus 705. The processor 601, memory 602, communication interface 603, RAM 604, and storage device 605 communicate via the bus 605, or via other means such as wireless transmission. The memory 602 stores instructions, and the processor 601 executes the instructions stored in the memory 602. The memory 602 stores program code, and the processor 601 can call the program code stored in the memory 602 to perform the following operations:

[0104] Obtain the driving mode, driving style model, and target speed of the intelligent vehicle at the current moment;

[0105] Speed ​​control commands are determined based on the driving mode and driving style model;

[0106] The speed control command is sent to the vehicle execution system of the intelligent vehicle.

[0107] It should be understood that in the embodiments of this application, the processor 601 may be a CPU, or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0108] The memory 602 may include read-only memory and random access memory, and provides instructions and data to the processor 601. The memory 602 may also include non-volatile random access memory. For example, the memory 602 may also store device type information.

[0109] The memory 602 can be volatile memory or non-volatile memory, or it can include both. The non-volatile memory can 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. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0110] Communication interface 603 includes a network interface / module for communicating with other devices or systems.

[0111] Memory 604 may be physically integrated with processor 601, or exist within processor 601 or as a separate unit. Computer programs may be stored in memory 604 or memory 602. Optionally, computer program code (e.g., kernel, program to be debugged, etc.) stored in memory 602 is copied to memory 604 and then executed by processor 601.

[0112] In addition to the data bus, bus 605 may also include a power bus, a control bus, and a status signal bus. However, for clarity, all buses are labeled as bus 604 in the figure. Optionally, bus 605 can be a Peripheral Component Interconnect Express (PCIe), a Controller Area Network (CAN), an automotive Ethernet, or other internal bus implementations. Figure 6 The connections of the various devices / equipment shown.

[0113] It should be understood that the intelligent vehicle control system 600 according to the embodiments of this application can correspond to the control device 500 in the embodiments of this application, and can correspond to the execution of the system according to the embodiments of this application. Figure 2 The corresponding entities in the method shown, and the above and other operations and / or functions of each module in the control system 600, are respectively implemented to achieve Figure 2 For the sake of brevity, the corresponding processes of each method in the code will not be elaborated here.

[0114] This application also provides a control system for an intelligent vehicle, the control system including as follows: Figure 1 The manual driving controller 301, decision controller 302, and automatic driving controller 303 shown are components of this control system used to perform the aforementioned tasks. Figure 2 For the sake of brevity, the operational steps performed by the corresponding execution entity in the method shown will not be described in detail here.

[0115] This application also provides a smart car, which includes, as follows: Figure 1 The human-machine interface controller, driving mode selector, vehicle control system, and vehicle execution system shown are components of the aforementioned intelligent vehicle used for execution. Figure 2 For the sake of brevity, the operational steps performed by the corresponding execution entity in the method shown will not be described in detail here.

[0116] This application also provides a control system, which, in addition to including, as shown in the example, Figure 1In addition to the smart car shown, it also includes a cloud data center, wherein the smart car includes, for example... Figure 1 The human-machine interface controller, driving mode selector, vehicle control system, and vehicle execution system shown are components of the aforementioned intelligent vehicle used for execution. Figure 2 The operational steps performed by the corresponding execution entities in the illustrated method will not be elaborated here for simplicity. Additionally, the cloud data center receives driving data sent by the vehicle control system and schedules virtual machines in the cloud data center to train the driving data, thereby obtaining a customized driving style model. On one hand, this avoids the problem of the computing power of the vehicle control system limiting processing speed in intelligent vehicles, reducing the computational load on the intelligent vehicle. On the other hand, the cloud data center can also save the above model to its stored driving style model library and add the driving style model to other vehicles besides the intelligent vehicle where the driver is located, so that other vehicles can update their driving style model libraries, increasing the number of driving style models available for the driver to choose from. Furthermore, the intelligent vehicle can also send the driver's updated driving data to the cloud data center, which will update the driving style model corresponding to that driver, making the output of the driving style model closer to the driver's actual driving process. Even further, the intelligent vehicle can also send the identifier of the driving style model selected by the driver to the cloud data center, which will then control the intelligent vehicle's driving process based on the throttle opening and braking values ​​defined in the driving style model.

[0117] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can 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, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive (SSD).

[0118] The above description is merely a specific embodiment of this application. Any variations or substitutions conceived by those skilled in the art based on the specific embodiments provided in this application should be covered within the protection scope of this application.

Claims

1. A method for controlling a vehicle, characterized in that, The method includes: Obtain the current driving style model and target speed of the vehicle; The speed control command is determined based on the target vehicle speed and the driving style model; The target vehicle speed is determined based on the current road condition information, which includes one or more of the information provided by the vehicle's map system, positioning device, and fusion system. The input to the driving style model includes at least the target vehicle speed; The vehicle is controlled to move according to the speed control command.

2. The control method according to claim 1, characterized in that, The speed control command includes throttle opening and braking value; wherein, the throttle opening includes parameters for controlling the vehicle's acceleration; and the braking value includes parameters for controlling the vehicle's braking.

3. The control method according to claim 1 or 2, characterized in that, The vehicle includes a driving style model library, which includes multiple driving style models, each of which includes different throttle opening and braking values.

4. The control method according to claim 3, characterized in that, The vehicle's driving style model library also includes driving style models obtained from cloud data centers.

5. The control method according to claim 3, characterized in that, The method further includes: The vehicle is controlled to display the driving style model library through a human-machine interface. The driving style model selected through the human-computer interaction interface is determined as the driving style model of the vehicle at the current moment.

6. The control method according to claim 5, characterized in that, The method further includes: Send the identifier of the driving model selected through the human-computer interaction interface to the cloud data center; The step of controlling the vehicle's movement according to the speed control command includes: The vehicle is controlled to drive according to the throttle opening and braking value defined by the cloud data center based on the driving model corresponding to the identifier; Alternatively, receive the identifier of the driving model selected through the human-machine interface sent by the vehicle; The speed control command is determined based on the driving model corresponding to the identifier; Send the speed control command to the vehicle.

7. The control method according to claim 1, characterized in that, The method includes: The driver selects the driving mode, which includes manual driving mode and automatic driving mode. The step of determining control commands based on the target vehicle speed and the driving style model further includes: The speed control command is determined based on the driving mode selected by the driver, the target vehicle speed, and the driving style model.

8. The control method according to claim 7, characterized in that, The method includes: When the driving mode is automatic driving mode, calculate the error between the actual vehicle speed and the target vehicle speed at the current moment; The acceleration of the vehicle is determined based on the error; wherein the acceleration is used to indicate the change in speed of the vehicle from the actual vehicle speed at the current moment to the target vehicle speed per unit time. The step of determining the speed control command based on the target vehicle speed and the driving style model includes: The speed control command is determined based on the vehicle's acceleration.

9. The control method according to claim 8, characterized in that, The method includes: The first throttle opening and the first braking value are determined using a proportional-integral-differential algorithm. The second throttle opening and the second braking value are determined based on the driving style model at the current moment; The third throttle opening is calculated based on the first throttle opening, the first weight value, the second throttle opening, and the second weight value. The third braking value is calculated based on the first braking value, the third weight value, the second braking value, and the fourth weight value. Wherein, the first weight value and the second weight value are throttle opening weight values, and the sum of the first weight value and the second weight value is 1; The third weight value and the fourth weight value are braking value weight values, and the sum of the third weight value and the fourth weight value is 1; The step of controlling the vehicle's movement according to the speed control command includes: The vehicle is controlled to move according to the third throttle opening and the third braking value.

10. The control method according to claim 1, characterized in that, The method includes: Collect driving data of the vehicle during the first time period; A customized driving style model is obtained using machine learning algorithms based on the driving data. The customized driving style model includes throttle opening and braking value that meet the driver's driving habits.

11. The control method according to claim 1, characterized in that, The method includes: The driver's driving data for the vehicle during the second time period was collected; The driver's driving data is sent to the cloud data center; A customized driving style model is obtained, which is trained by the cloud data center on the driving data.

12. The control method according to claim 3, characterized in that, The driving style model library includes at least one of the preset driving style models and the customized driving style models.

13. A vehicle control device, characterized in that, The control device includes: The acquisition unit is used to acquire the driving style model and target vehicle speed of the vehicle at the current moment; The control unit is used to determine speed control commands based on the target vehicle speed and the driving style model; The target vehicle speed is determined based on the current road condition information, which includes one or more of the information provided by the vehicle's map system, positioning device, and fusion system. The input to the driving style model includes at least the target vehicle speed; the control unit is used to control the vehicle's movement according to the speed control command.

14. The control device according to claim 13, characterized in that, The speed control command includes throttle opening and braking value; the throttle opening includes parameters for controlling vehicle acceleration; the braking value includes parameters for controlling vehicle braking.

15. The control device according to claim 13 or 14, wherein the vehicle includes a driving style model library, the driving style model library including multiple driving style models, each of the driving style models including different throttle opening and braking values.

16. The control device according to claim 15, characterized in that, The vehicle's driving style model library also includes driving style models obtained from cloud data centers.

17. The control device according to claim 15, characterized in that, The control unit is also used for: The vehicle is controlled to display the driving style model library through a human-machine interface. The driving style model selected through the human-computer interaction interface is determined as the driving style model of the vehicle at the current moment.

18. The control device according to claim 17, characterized in that, The control device further includes a transmitting unit; wherein... The sending unit is used to send the identifier of the driving model selected through the human-machine interface to the cloud data center; The control unit is used to control the vehicle's movement according to the throttle opening and braking value defined by the cloud data center based on the driving model corresponding to the identifier; or, The acquisition unit is used to acquire the identifier of the driving model selected through the human-machine interface sent by the vehicle; The control unit is used to determine the speed control command based on the driving model corresponding to the identifier; The sending unit is used to send the speed control command to the vehicle.

19. The control device according to claim 13, characterized in that, The acquisition unit is used to acquire the driving mode selected by the driver, the driving mode including manual driving mode and automatic driving mode; The control unit is used to determine the speed control command based on the driving mode selected by the driver, the target vehicle speed, and the driving style model.

20. The control device according to claim 19, characterized in that, The control unit is used for: When the driving mode is automatic driving mode, calculate the error between the actual vehicle speed and the target vehicle speed at the current moment; The acceleration of the vehicle is determined based on the error; wherein the acceleration is used to indicate the change in speed of the vehicle from the actual vehicle speed at the current moment to the target vehicle speed per unit time. The speed control command is determined based on the vehicle's acceleration.

21. The control device according to claim 20, characterized in that, The control unit is used for: The first throttle opening and the first braking value are determined using a proportional-integral-differential algorithm. The second throttle opening and the second braking value are determined based on the driving style model at the current moment; The third throttle opening is calculated based on the first throttle opening, the first weight value, the second throttle opening, and the second weight value. The third braking value is calculated based on the first braking value, the third weight value, the second braking value, and the fourth weight value. Wherein, the first weight value and the second weight value are throttle opening weight values, and the sum of the first weight value and the second weight value is 1; The third weight value and the fourth weight value are braking value weight values, and the sum of the third weight value and the fourth weight value is 1; The vehicle is controlled to move according to the third throttle opening and the third braking value.

22. The control device according to claim 13, characterized in that, The acquisition unit is used to collect driving data of the vehicle during a first time period; The control unit is used to obtain a customized driving style model based on the driving data using a machine learning algorithm. The customized driving style model includes throttle opening and braking value that meet the driver's driving habits.

23. The control device according to claim 13, characterized in that, It also includes a sending unit. The acquisition unit is used to collect the driver's driving data of the vehicle during the second time period; The sending unit is used to send the driver's driving data to the cloud data center; The acquisition unit is used to acquire a customized driving style model, which is obtained by training the driving data in the cloud data center.

24. The control device according to claim 17, characterized in that, The driving style model library includes at least one of the preset driving style models and the customized driving style models.

25. An electronic control device, characterized in that, It includes a processor and a memory, wherein the memory is used to store computer instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 12.

26. A computer-readable storage medium, characterized in that, It stores a computer program thereon, which, when executed, implements the method as described in any one of claims 1 to 12.

27. A vehicle, characterized in that, The vehicle includes the control device as described in any one of claims 13-24.

Images