Vehicle control method and device, computer device and storage medium

Abstract

The application relates to a vehicle control method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring first driving data, image data, radar data in the process of automatic driving of a vehicle according to a preset planning path, and second driving data in the process of manual driving of the vehicle according to the preset planning path; fusing the image data and the radar data to obtain real-time map data; establishing a driver model according to the real-time map data, the first driving data and the second driving data; and controlling the vehicle to automatically drive according to the driver model. The method can improve the stability of vehicle driving.

Description

Technical Field

[0001] This application relates to the field of automotive electronics technology, and in particular to a vehicle control method, device, computer equipment, storage medium, and computer program product. Background Technology

[0002] Currently, most of the autonomous vehicles in the park's logistics system start and stop at fixed points and are scheduled according to a fixed control program. This results in insufficient adaptability of control and adjustment, rigid throttle and brake control during operation, jerky operation, and low adaptability to emergency and complex situations. Consequently, the experience of passengers is poor, and there is a greater risk to fragile goods and other cargo. Summary of the Invention

[0003] Therefore, it is necessary to provide a vehicle control method, device, computer equipment, computer-readable storage medium, and computer program product that can improve vehicle stability in response to the above-mentioned technical problems.

[0004] Firstly, this application provides a vehicle control method. The method includes:

[0005] Acquire first driving data, image data, and radar data during the automatic driving process of the vehicle according to the preset planned path, and second driving data during the manual driving process of the vehicle according to the preset planned path;

[0006] By fusing image data and radar data, real-time map data is obtained;

[0007] A driver model is established based on real-time map data, first driving data, and second driving data.

[0008] Control the vehicle to drive automatically according to the driver model.

[0009] In one embodiment, the second driving data includes multiple driving event data and key event annotations corresponding to each of the multiple driving event data;

[0010] Based on real-time map data, first driving data, and second driving data, a driver model is established, including:

[0011] Determine the type of obstacle environment based on real-time map data;

[0012] Match obstacle environment types with the labels of each key event;

[0013] The target driving data under the obstacle environment type in the first driving data is updated with the driving event data corresponding to the successfully matched key event labels to obtain the updated first driving data.

[0014] A driver model is built based on the updated initial driving data and obstacle environment type.

[0015] In one embodiment, a driver model is established based on the updated first driving data and the obstacle environment type, including:

[0016] Obtain the first mapping relationship, which is used to indicate the correspondence between preset driving states and preset driving data;

[0017] A second mapping relationship is established based on the obstacle environment type and its corresponding updated first driving data.

[0018] A driver model is established based on the first and second mapping relationships.

[0019] In one embodiment, the radar data includes lidar data and millimeter-wave radar data; the image data and radar data are fused to obtain real-time map data, including:

[0020] Image data, lidar data, and millimeter-wave radar data are fused to obtain real-time map data.

[0021] In one embodiment, controlling the vehicle to drive automatically according to a driver model includes:

[0022] The vehicle is controlled to drive automatically under different loads according to the driver model, and the vehicle operation data corresponding to different loads is obtained respectively.

[0023] For any given load, the driver model is adjusted based on the vehicle's operating data under the current load to obtain an adjusted driver model; the vehicle is then controlled to drive automatically under the current load according to the adjusted driver model.

[0024] In one embodiment, controlling the vehicle to drive automatically according to a driver model includes:

[0025] The vehicle is controlled to drive automatically under a preset obstacle course according to the driver model, and the vehicle operation data is acquired; the driver model is adjusted based on the vehicle operation data to obtain the adjusted driver model;

[0026] The vehicle is controlled to drive automatically through a preset obstacle course, following an adjusted driver model.

[0027] Secondly, this application also provides a vehicle control device. The device includes:

[0028] The acquisition module is used to acquire first driving data, image data, and radar data during the automatic driving process of the vehicle according to the preset planned path, and second driving data during the manual driving process of the vehicle according to the preset planned path.

[0029] The fusion module is used to fuse image data and radar data to obtain real-time map data;

[0030] A module is built to create a driver model based on real-time map data, first driving data, and second driving data.

[0031] The control module is used to control the vehicle to drive automatically according to the driver model.

[0032] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0033] Acquire first driving data, image data, and radar data during the automatic driving process of the vehicle according to the preset planned path, and second driving data during the manual driving process of the vehicle according to the preset planned path;

[0034] By fusing image data and radar data, real-time map data is obtained;

[0035] A driver model is established based on real-time map data, first driving data, and second driving data.

[0036] Control the vehicle to drive automatically according to the driver model.

[0037] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0038] Acquire first driving data, image data, and radar data during the automatic driving process of the vehicle according to the preset planned path, and second driving data during the manual driving process of the vehicle according to the preset planned path;

[0039] By fusing image data and radar data, real-time map data is obtained;

[0040] A driver model is established based on real-time map data, first driving data, and second driving data.

[0041] Control the vehicle to drive automatically according to the driver model.

[0042] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0043] Acquire first driving data, image data, and radar data during the automatic driving process of the vehicle according to the preset planned path, and second driving data during the manual driving process of the vehicle according to the preset planned path;

[0044] By fusing image data and radar data, real-time map data is obtained;

[0045] A driver model is established based on real-time map data, first driving data, and second driving data.

[0046] Control the vehicle to drive automatically according to the driver model.

[0047] The aforementioned vehicle control method, device, computer equipment, storage medium, and computer program product acquire first driving data, image data, and radar data during the vehicle's automatic driving along a preset planned path, and second driving data during the vehicle's manual driving along the preset planned path. The image data and radar data are fused to obtain real-time map data. Based on the real-time map data, the first driving data, and the second driving data, a driver model is established, and the vehicle is controlled to drive automatically according to the driver model. This scheme, by integrating driving data from the automatic driving process, collected image data, radar data, and driving data from the manual driving process to establish a driver model, helps to improve the instability problem during automatic driving and enhances the stability of the vehicle during automatic driving. Attached Figure Description

[0048] Figure 1 This is a diagram illustrating the application environment of a vehicle control method in one embodiment.

[0049] Figure 2 This is a flowchart illustrating a vehicle control method in one embodiment;

[0050] Figure 3 This is a schematic diagram of the composition structure of a vehicle control system in one embodiment;

[0051] Figure 4 This is a schematic diagram of the overall flow of a vehicle control method in one embodiment;

[0052] Figure 5 This is a structural block diagram of a vehicle control device in one embodiment;

[0053] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] The vehicle control method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with vehicle 104 via a network. Terminal 102 acquires first driving data, image data, and radar data during the vehicle's automatic driving along a preset planned path, and second driving data during the vehicle's manual driving along the preset planned path; it fuses the image data and radar data to obtain real-time map data; based on the real-time map data, the first driving data, and the second driving data, it establishes a driver model; and it controls the vehicle to drive automatically according to the driver model. In some embodiments, terminal 102 can be the vehicle's Electronic Control Unit (ECU). In other embodiments, terminal 102 can also be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc.

[0056] In one embodiment, such as Figure 2 As shown, a vehicle control method is provided, which is applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps:

[0057] Step 202: Obtain first driving data, image data, and radar data during the automatic driving process of the vehicle according to the preset planned path, and second driving data during the manual driving process of the vehicle according to the preset planned path.

[0058] The preset planned route refers to the planned route for the vehicle to travel within a given park. In some embodiments, a network map of the given park is obtained. A preliminary driving route is planned using integrated navigation technology, and key locations such as stop points are set to obtain the preset planned route.

[0059] The first driving data refers to the driving data during the process of the vehicle automatically driving along a preset planned path. For example, the types of first driving data include vehicle speed, engine speed, etc.

[0060] Image data refers to the image data collected by image acquisition devices deployed on the vehicle during the vehicle's automatic driving according to a preset planned path. Radar data refers to the image data collected by radar devices deployed on the vehicle during the vehicle's automatic driving according to a preset planned path.

[0061] The second driving data is the driving data during the process of the vehicle being manually driven according to the preset planned path.

[0062] The vehicle supports both automatic and manual driving.

[0063] Step 204: The image data and radar data are fused to obtain real-time map data.

[0064] As the vehicle moves, the image acquisition equipment collects environmental image data of the lane and its surroundings. However, it is difficult to identify the location information of objects in the environment based solely on image data. When radar equipment emits electromagnetic wave signals, if a target object encounters the radar signal, it will reflect the echo. The radar receiver will receive the echo signal, which contains information about the target's distance, direction, and speed. The radar antenna receives the reflected wave and sends it to the receiving equipment for processing, extracting certain information about the object. The angle of the target can also be measured based on the radar's emitted beam. Therefore, understanding the principle of radar equipment emitting and receiving electromagnetic waves is beneficial for obtaining the location information of objects in the environment.

[0065] Fusing image data and radar data is beneficial for obtaining accurate real-time map data. Real-time map data is used to characterize the real-time environment map as the vehicle automatically drives along a pre-planned path.

[0066] Step 206: Establish a driver model based on real-time map data, first driving data, and second driving data.

[0067] The driver model is used to represent the correspondence between environmental information and driving data. Normally, the driver model is directly built based on driving data during autonomous driving. This application proposes to build a driver model based on real-time map data, first driving data during autonomous driving, and second driving data during manual driving, which is beneficial to improving the stability of autonomous driving.

[0068] Step 208: Control the vehicle to drive automatically according to the driver model.

[0069] Among these, the terminal control vehicle performs autonomous driving according to the established driver model, which helps to improve the smoothness of the vehicle's autonomous driving.

[0070] In the aforementioned vehicle control method, first driving data, image data, and radar data are acquired during the vehicle's automatic driving along a preset planned path, and second driving data is acquired during the vehicle's manual driving along the same path. The image data and radar data are then fused to obtain real-time map data. Based on the real-time map data, the first driving data, and the second driving data, a driver model is established, and the vehicle is controlled to drive automatically according to the driver model. This scheme, by integrating driving data from automatic driving, acquired image data, radar data, and manual driving data to establish a driver model, helps to improve the instability problem during automatic driving and enhances the stability of the vehicle during automatic driving.

[0071] In one embodiment, the second driving data includes multiple driving event data and key event annotations corresponding to each of the multiple driving event data; establishing a driver model based on real-time map data, the first driving data, and the second driving data includes: determining the obstacle environment type based on the real-time map data; matching the obstacle environment type with each key event annotation; updating the target driving data under the obstacle environment type in the first driving data with the driving event data corresponding to the successfully matched key event annotations to obtain the updated first driving data; and establishing a driver model based on the updated first driving data and the obstacle environment type.

[0072] Specifically, the obstacle environment type is determined based on real-time map data. For example, if the real-time map data indicates that an object in the lane is moving at a speed of 5 kilometers per hour, the obstacle environment type is determined to be a moving pedestrian. If the real-time map data indicates that an object on the left side of the lane is moving at a speed of 50 kilometers per hour, the obstacle environment type is determined to be a moving vehicle.

[0073] Key event annotations are annotations manually added by the vehicle operation object for each driving event during manual driving. The second driving data includes multiple driving event data and their corresponding key event annotations. For example, a driving event could be a moving pedestrian in the lane, with the corresponding key event annotation being A1; or a driving vehicle in the lane, with the corresponding key event annotation being B1.

[0074] The terminal matches obstacle environment types with various key event labels according to preset matching relationships. The target driving data under each obstacle environment type in the first driving data is then updated with the driving event data corresponding to the successfully matched key event labels, resulting in the updated first driving data.

[0075] A driver model is established based on the updated first driving data and obstacle environment type. The driver model is used to represent the correspondence between driving data and obstacle environment type.

[0076] In this embodiment, by matching the obstacle environment type during the automatic driving process with the key event labels during the manual driving process, the first driving data during the automatic driving process is updated to the driving event data corresponding to the successfully matched key event labels. The driver model is established using the updated first driving data and obstacle environment type, which helps to improve the accuracy of the driver model during the autonomous driving process, thereby improving the smoothness of autonomous driving.

[0077] In one embodiment, establishing a driver model based on updated first driving data and obstacle environment type includes: obtaining a first mapping relationship, which indicates the correspondence between preset driving states and preset driving data; establishing a second mapping relationship based on obstacle environment type and corresponding updated first driving data; and establishing a driver model based on the first mapping relationship and the second mapping relationship.

[0078] The first mapping relationship is established based on historical driving data and is used to indicate the correspondence between preset driving states and preset driving data. For example, the preset driving state is that there are no obstacles 500 meters ahead of the lane, and the preset driving data is that the vehicle speed is a preset speed and the accelerator pedal opening is increased by a preset angle.

[0079] A second mapping relationship is established based on the obstacle environment type and its corresponding updated first driving data. This second mapping relationship characterizes the mapping between obstacle environment types and driving data. The first and second mapping relationships are then integrated to build a driver model.

[0080] In this embodiment, by integrating the pre-established first mapping relationship and the second mapping relationship, a driver model is established, which is beneficial to enrich the driver model in various scenarios, improve the accuracy of the driver model, and improve the stability of the vehicle during automatic driving.

[0081] In one embodiment, the radar data includes lidar data and millimeter-wave radar data; fusing image data and radar data to obtain real-time map data includes: fusing image data, lidar data and millimeter-wave radar data to obtain real-time map data.

[0082] The fusion method employed can be the BEV (Bird's Eye View) algorithm. The BEV algorithm is a perspective view of an object or scene from above, capable of simplifying complex 3D environmental data into 2D images and performing real-time, efficient computation. Using the BEV algorithm facilitates the fusion of image data, LiDAR data, and millimeter-wave radar data to obtain real-time map data. Real-time map data includes both static and dynamic map data.

[0083] In some embodiments, the location information collected by the lidar device and the image collected by the camera are fused to obtain environmental information. This environmental information is then verified against the obstacle information collected by the lidar device to obtain updated environmental data. Based on the updated environmental data, static map data is obtained. For example, the environmental information indicates an obstacle 6 meters ahead of the lane, while the lidar indicates an obstacle 10 meters ahead, resulting in a 4-meter discrepancy. The environmental information data needs to be supplemented with this discrepancy to obtain the updated environmental information.

[0084] In other embodiments, dynamic environmental elements are determined based on image data, and the dynamic environmental elements in the image data, millimeter-wave radar data, and lidar data are fused using the BEV algorithm to obtain dynamic map data.

[0085] In this embodiment, image data, lidar data, and millimeter-wave radar data are fused to obtain real-time map data, which helps to obtain accurate real-time map data and thus improves the stability of the vehicle during autonomous driving.

[0086] In one embodiment, controlling a vehicle to drive automatically according to a driver model includes: controlling the vehicle to drive automatically according to the driver model under different loads, and obtaining vehicle operation data corresponding to different loads; for any load, adjusting the driver model based on the vehicle operation data under the current load to obtain an adjusted driver model; and controlling the vehicle to drive automatically according to the adjusted driver model under the current load.

[0087] In this process, the vehicle operates automatically according to the driver model, with different loads applied. For example, the vehicle is controlled to operate automatically under empty, half-load, and full-load conditions, respectively, obtaining vehicle operation data corresponding to different loads.

[0088] For any given load, the driver model is adjusted based on the vehicle's operating data under that load, resulting in an adjusted driver model. The vehicle is then controlled to drive automatically under the current load according to this adjusted model. Different loads have a significant impact on the vehicle's driving data. For example, under no-load conditions, the vehicle speed is increased for the corresponding obstacle environment type, while under full load conditions, the vehicle speed is decreased for the corresponding obstacle environment type.

[0089] In this embodiment, by controlling the vehicle to drive automatically according to the driver model under different loads, and adjusting the driver model based on the vehicle driving data under different loads, it is beneficial to obtain a more suitable driver model according to different loads, which is beneficial to improve the stability of the vehicle during automatic driving.

[0090] In one embodiment, controlling a vehicle to drive automatically according to a driver model includes: controlling the vehicle to drive automatically according to the driver model in a preset obstacle course, and acquiring vehicle operation data; adjusting the driver model based on the vehicle operation data to obtain an adjusted driver model; and controlling the vehicle to drive automatically according to the adjusted driver model in a preset obstacle course.

[0091] Among them, the preset obstacle passage refers to a passage with various obstacle scenarios. For example, temporary vehicles can be placed at intersections, or objects left behind can be placed in front of vehicles.

[0092] The system controls the vehicle to automatically navigate a pre-defined obstacle course according to a driver model. Vehicle operation data is acquired, and the driver model is adjusted based on this data to obtain a revised driver model. The vehicle then navigates the obstacle course according to this revised model. For example, in a scenario where a dropped object is placed in front of the vehicle, the vehicle might run over the object if it follows the original driver model. Accordingly, in scenarios with a dropped object in front of the vehicle, the vehicle speed is reduced and the brake pedal angle is increased, resulting in the revised driver model.

[0093] In this embodiment, by setting up multiple obstacle channels, the driver model is adjusted, which helps to improve the robustness of the driver model and thus improve the smoothness of the vehicle during automatic operation.

[0094] To illustrate the vehicle control method and its effects in this solution in detail, a specific embodiment is described below:

[0095] For vehicle control in industrial park logistics scenarios, vehicle control methods are applied to the vehicle control system. The system includes a perception fusion unit, a memory storage unit, a decision-making and planning unit, and a vehicle control unit. For example... Figure 3 The diagram illustrates the structural composition of the vehicle control system. It utilizes technologies such as cameras, LiDAR, millimeter-wave radar, and integrated navigation to fuse vehicle driving perception data. This collected data is sent to the decision-making and planning unit, which performs real-time global calculations based on the driver's behavioral habits. The algorithm results are then transmitted to the vehicle control unit, which executes the engine, braking, and steering mechanisms to achieve precise, stable, flexible, and reliable operation of the park's logistics vehicles. The perception fusion unit, serving as the data source for autonomous driving, uses integrated navigation technology and high-precision sensors such as onboard cameras, LiDAR, and millimeter-wave radar to collect environmental information in real time. It sets map points such as start / end points and stopping points, creating a park map and forming the overall autonomous driving solution for the park's logistics vehicles. The memory storage unit records data from the driver's manual operation of the park's logistics vehicles, including engine speed, accelerator pedal opening, braking distance, and light status for different road sections and unexpected events, forming a complete manual driving plan for each road segment. The decision-making and planning unit integrates the autonomous driving solution with the manual driving solution, establishing a driver model. Based on autonomous driving and combined with manual driving data, it makes the autonomous driving of park vehicles more intelligent, flexible, and comfortable. Vehicle control unit: Similar to the transmission vehicle control unit, it can accept algorithm instructions from the decision planning unit to control the vehicle's EMS (Engine Management System), braking, steering, and lighting systems to perform corresponding operations.

[0096] like Figure 4 The diagram shows the overall flow of the vehicle control method. The terminal acquires first driving data, image data, and radar data during the automatic driving process of the vehicle according to the preset planned path, and second driving data during the manual driving process of the vehicle according to the preset planned path. The radar data includes lidar data and millimeter-wave radar data. The second driving data includes multiple driving event data and key event annotations corresponding to each of the multiple driving event data.

[0097] In some embodiments, a network map of the park is obtained. A preliminary driving route is planned using integrated navigation technology, key locations such as stop points are set, and a preset planned path is obtained.

[0098] Image data, LiDAR data, and millimeter-wave radar data are fused to obtain real-time map data. Based on the real-time map data, obstacle environment types are determined, and these types are matched with various key event annotations. The target driving data under each obstacle environment type in the first driving data is updated with the driving event data corresponding to the successfully matched key event annotations, resulting in the updated first driving data.

[0099] Obtain a first mapping relationship, which indicates the correspondence between preset driving states and preset driving data. Establish a second mapping relationship based on the obstacle environment type and the corresponding updated first driving data. Establish a driver model based on the first and second mapping relationships.

[0100] The vehicle is controlled to drive automatically according to a driver model. Specifically, in some embodiments, the vehicle is controlled to drive automatically under different loads according to the driver model, obtaining vehicle operation data corresponding to different loads. For any load, the driver model is adjusted based on the vehicle operation data under the current load to obtain an adjusted driver model; the vehicle is then controlled to drive automatically under the current load according to the adjusted driver model. In other embodiments, the vehicle is controlled to drive automatically under a preset obstacle course according to the driver model, acquiring vehicle operation data; the driver model is adjusted based on the vehicle operation data to obtain an adjusted driver model; the vehicle is then controlled to drive automatically under a preset obstacle course according to the adjusted driver model.

[0101] By acquiring first driving data, image data, and radar data during the vehicle's automatic driving along a preset planned path, and second driving data during the vehicle's manual driving along the same preset planned path, the image data and radar data are fused to obtain real-time map data. Based on the real-time map data, the first driving data, and the second driving data, a driver model is established, and the vehicle is controlled to drive automatically according to the driver model. This scheme, by integrating driving data from the automatic driving process, collected image data, radar data, and driving data from the manual driving process to establish a driver model, helps to improve the instability problem during automatic driving and enhances the stability of the vehicle during automatic driving.

[0102] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0103] Based on the same inventive concept, this application also provides a vehicle control device for implementing the vehicle control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle control device embodiments provided below can be found in the limitations of the vehicle control method described above, and will not be repeated here.

[0104] In one embodiment, such as Figure 5 As shown, a vehicle control device 100 is provided, including: an acquisition module 120, a fusion module 140, an establishment module 160, and a control module 180, wherein:

[0105] The acquisition module 120 is used to acquire first driving data, image data, and radar data during the automatic driving process of the vehicle according to the preset planned path, and second driving data during the manual driving process of the vehicle according to the preset planned path.

[0106] The fusion module 140 is used to fuse image data and radar data to obtain real-time map data;

[0107] Module 160 is used to build a driver model based on real-time map data, first driving data, and second driving data.

[0108] The control module 180 is used to control the vehicle to drive automatically according to the driver model.

[0109] The aforementioned vehicle control device acquires first driving data, image data, and radar data during the vehicle's automatic driving along a preset planned path, and second driving data during the vehicle's manual driving along the same path. It then fuses the image data and radar data to obtain real-time map data. Based on the real-time map data, the first driving data, and the second driving data, a driver model is established, and the vehicle is controlled to drive automatically according to this model. This solution integrates driving data from automatic driving, collected image data, radar data, and manual driving data to establish a driver model, which helps to improve the instability during automatic driving and enhances the vehicle's stability during automatic driving.

[0110] In one embodiment, the second driving data includes multiple driving event data and key event labels corresponding to each of the multiple driving event data; a driver model is established based on real-time map data, the first driving data, and the second driving data. The modeling module 160 is further configured to: determine the obstacle environment type based on the real-time map data; match the obstacle environment type with each key event label; update the target driving data under the obstacle environment type in the first driving data with the driving event data corresponding to the successfully matched key event labels to obtain the updated first driving data; and establish the driver model based on the updated first driving data and the obstacle environment type.

[0111] In one embodiment, a driver model is established based on the updated first driving data and the obstacle environment type. The establishment module 160 is further configured to: obtain a first mapping relationship, which indicates the correspondence between a preset driving state and preset driving data; establish a second mapping relationship based on the obstacle environment type and the corresponding updated first driving data; and establish a driver model based on the first mapping relationship and the second mapping relationship.

[0112] In one embodiment, the radar data includes lidar data and millimeter-wave radar data; the image data and radar data are fused to obtain real-time map data, and the fusion module 140 is further configured to: fuse image data, lidar data and millimeter-wave radar data to obtain real-time map data.

[0113] In one embodiment, the control module 180 controls the vehicle to drive automatically according to the driver model. The control module 180 is further configured to: control the vehicle to drive automatically according to the driver model under different loads, and obtain vehicle operation data corresponding to different loads; adjust the driver model according to the vehicle operation data under the current load for any load, and obtain the adjusted driver model; and control the vehicle to drive automatically according to the adjusted driver model under the current load.

[0114] In one embodiment, the control module 180 is further configured to: control the vehicle to drive automatically according to the driver model in a preset obstacle course, and obtain vehicle operation data; adjust the driver model according to the vehicle operation data to obtain an adjusted driver model; and control the vehicle to drive automatically according to the adjusted driver model in a preset obstacle course.

[0115] Each module in the aforementioned vehicle control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0116] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a vehicle control method.

[0117] Those skilled in the art will understand that Figure 6The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0118] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0119] Acquire first driving data, image data, and radar data during the vehicle's automatic driving along a preset planned path, and second driving data during the vehicle's manual driving along the preset planned path; fuse the image data and radar data to obtain real-time map data; establish a driver model based on the real-time map data, the first driving data, and the second driving data; and control the vehicle to drive automatically according to the driver model.

[0120] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0121] The second driving data includes multiple driving event data and key event labels corresponding to each driving event data; based on real-time map data, the obstacle environment type is determined; the obstacle environment type is matched with each key event label; the target driving data under the obstacle environment type in the first driving data is updated with the driving event data corresponding to the successfully matched key event labels to obtain the updated first driving data; a driver model is established based on the updated first driving data and the obstacle environment type.

[0122] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0123] Obtain a first mapping relationship, which indicates the correspondence between preset driving states and preset driving data; establish a second mapping relationship based on obstacle environment types and their corresponding updated first driving data; and establish a driver model based on the first and second mapping relationships.

[0124] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0125] Radar data includes lidar data and millimeter-wave radar data; by fusing image data, lidar data, and millimeter-wave radar data, real-time map data is obtained.

[0126] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0127] The system controls the vehicle to drive automatically under different loads according to the driver model, and obtains vehicle operation data corresponding to different loads. For any load, the driver model is adjusted based on the vehicle operation data under the current load to obtain the adjusted driver model. The system then controls the vehicle to drive automatically under the current load according to the adjusted driver model.

[0128] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0129] The system controls the vehicle to drive automatically through a preset obstacle course according to the driver model, and acquires vehicle operation data; the driver model is adjusted based on the vehicle operation data to obtain an adjusted driver model; the system then controls the vehicle to drive automatically through the preset obstacle course according to the adjusted driver model.

[0130] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0131] Acquire first driving data, image data, and radar data during the vehicle's automatic driving along a preset planned path, and second driving data during the vehicle's manual driving along the preset planned path; fuse the image data and radar data to obtain real-time map data; establish a driver model based on the real-time map data, the first driving data, and the second driving data; and control the vehicle to drive automatically according to the driver model.

[0132] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0133] The second driving data includes multiple driving event data and key event labels corresponding to each driving event data; based on real-time map data, the obstacle environment type is determined; the obstacle environment type is matched with each key event label; the target driving data under the obstacle environment type in the first driving data is updated with the driving event data corresponding to the successfully matched key event labels to obtain the updated first driving data; a driver model is established based on the updated first driving data and the obstacle environment type.

[0134] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0135] Obtain a first mapping relationship, which indicates the correspondence between preset driving states and preset driving data; establish a second mapping relationship based on obstacle environment types and their corresponding updated first driving data; and establish a driver model based on the first and second mapping relationships.

[0136] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0137] Radar data includes lidar data and millimeter-wave radar data; by fusing image data, lidar data, and millimeter-wave radar data, real-time map data is obtained.

[0138] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0139] The system controls the vehicle to drive automatically under different loads according to the driver model, and obtains vehicle operation data corresponding to different loads. For any load, the driver model is adjusted based on the vehicle operation data under the current load to obtain the adjusted driver model. The system then controls the vehicle to drive automatically under the current load according to the adjusted driver model.

[0140] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0141] The system controls the vehicle to drive automatically through a preset obstacle course according to the driver model, and acquires vehicle operation data; the driver model is adjusted based on the vehicle operation data to obtain an adjusted driver model; the system then controls the vehicle to drive automatically through the preset obstacle course according to the adjusted driver model.

[0142] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0143] Acquire first driving data, image data, and radar data during the vehicle's automatic driving along a preset planned path, and second driving data during the vehicle's manual driving along the preset planned path; fuse the image data and radar data to obtain real-time map data; establish a driver model based on the real-time map data, the first driving data, and the second driving data; and control the vehicle to drive automatically according to the driver model.

[0144] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0145] The second driving data includes multiple driving event data and key event labels corresponding to each driving event data; based on real-time map data, the obstacle environment type is determined; the obstacle environment type is matched with each key event label; the target driving data under the obstacle environment type in the first driving data is updated with the driving event data corresponding to the successfully matched key event labels to obtain the updated first driving data; a driver model is established based on the updated first driving data and the obstacle environment type.

[0146] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0147] Obtain a first mapping relationship, which indicates the correspondence between preset driving states and preset driving data; establish a second mapping relationship based on obstacle environment types and their corresponding updated first driving data; and establish a driver model based on the first and second mapping relationships.

[0148] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0149] Radar data includes lidar data and millimeter-wave radar data; by fusing image data, lidar data, and millimeter-wave radar data, real-time map data is obtained.

[0150] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0151] The system controls the vehicle to drive automatically under different loads according to the driver model, and obtains vehicle operation data corresponding to different loads. For any load, the driver model is adjusted based on the vehicle operation data under the current load to obtain the adjusted driver model. The system then controls the vehicle to drive automatically under the current load according to the adjusted driver model.

[0152] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0153] The system controls the vehicle to drive automatically through a preset obstacle course according to the driver model, and acquires vehicle operation data; the driver model is adjusted based on the vehicle operation data to obtain an adjusted driver model; the system then controls the vehicle to drive automatically through the preset obstacle course according to the adjusted driver model.

[0154] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0156] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0157] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle control method, characterized in that, The method includes: Acquire first driving data, image data, and radar data during the automatic driving process of the vehicle according to the preset planned path, and second driving data during the manual driving process of the vehicle according to the preset planned path; The image data and the radar data are fused to obtain real-time map data; A driver model is established based on the real-time map data, the first driving data, and the second driving data. The vehicle is controlled to drive automatically according to the driver model described above; The second driving data includes multiple driving event data and key event annotations corresponding to each of the multiple driving event data; The step of establishing a driver model based on the real-time map data, the first driving data, and the second driving data includes: Based on the real-time map data, determine the type of obstacle environment; Match the obstacle environment types with the labels of each key event; The target driving data under the obstacle environment type in the first driving data is updated with the driving event data corresponding to the successfully matched key event annotations to obtain the updated first driving data. Obtain a first mapping relationship, which is established based on historical driving data, and the first mapping relationship is used to indicate the correspondence between preset driving states and preset driving data; A second mapping relationship is established based on the obstacle environment type and the corresponding updated first driving data; A driver model is established based on the first mapping relationship and the second mapping relationship.

2. The method according to claim 1, characterized in that, The radar data includes lidar data and millimeter-wave radar data; the process of fusing the image data and the radar data to obtain real-time map data includes: The image data, the lidar data, and the millimeter-wave radar data are fused to obtain real-time map data.

3. The method according to claim 1, characterized in that, The controlled vehicle drives automatically according to the driver model, including: The vehicle is controlled to drive automatically under different loads according to the driver model, and vehicle operation data corresponding to different loads is obtained respectively. For any given load, the driver model is adjusted based on the vehicle's operating data under the current load to obtain an adjusted driver model; the vehicle is then controlled to drive automatically under the current load according to the adjusted driver model.

4. The method according to claim 1, characterized in that, The controlled vehicle drives automatically according to the driver model, including: The vehicle is controlled to drive automatically under a preset obstacle course according to the driver model, and vehicle operation data is acquired; the driver model is adjusted according to the vehicle operation data to obtain an adjusted driver model; The vehicle is controlled to drive automatically under a preset obstacle course, according to the adjusted driver model.

5. A vehicle control device, characterized in that, The apparatus for implementing the vehicle control method according to any one of claims 1 to 4, the apparatus comprising: The acquisition module is used to acquire first driving data, image data, and radar data during the automatic driving process of the vehicle according to the preset planned path, and second driving data during the manual driving process of the vehicle according to the preset planned path. The fusion module is used to fuse the image data and the radar data to obtain real-time map data; A module is established to build a driver model based on the real-time map data, the first driving data, and the second driving data; The control module is used to control the vehicle to drive automatically according to the driver model.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images