Vehicle, method and device for controlling vehicle driving

Abstract

The present invention discloses a vehicle, a method and a device for controlling vehicle driving, which obtain a vehicle contour model of a current vehicle and a target feature of a target vehicle, determine a target contour model of the target vehicle in a preset vehicle model library according to the target feature, use the target feature to perform data comparison to identify the target vehicle, quickly determine the vehicle target contour model, and update the current measured distance between the target vehicle and the current vehicle according to the vehicle contour model and the target contour model. The relative distance between the current vehicle and the target vehicle can be calculated more accurately, the calculation accuracy of assisted driving can be greatly improved, the collision risk between the current vehicle and the target vehicle can be predicted more accurately, and the safety of vehicle driving control can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle driving control, and in particular to a vehicle, a method and a device for controlling vehicle driving. Background Art

[0002] The current mainstream vehicles are equipped with assisted driving. The configuration related to collision safety in assisted driving is mainly active braking. The main functional principle of active braking is that when the vehicle is driving normally in non-adaptive cruise control, if the vehicle encounters an unexpected dangerous situation, it can actively produce a braking effect to slow down the vehicle (but vehicles with this function may not be able to completely stop the vehicle), thereby improving driving safety. According to different names given by various car manufacturers, there are also names such as Pre-crash System, Forward Collision Warning System, Collision Mitigating System, Pre-Collision Safety System, and Collision Mitigation Brake System.

[0003] The current active braking system uses vision to collect road conditions, determine whether there are obstacles ahead, and use radar to detect the distance to the obstacle. This processing system cannot accurately identify the vehicle in front, and may result in misjudgment or failure to identify the vehicle in front, resulting in untimely braking and the risk of collision with the vehicle under assisted driving control.

[0004] Therefore, how to improve the safety of vehicle driving control is a technical problem that needs to be solved urgently. Summary of the invention

[0005] A vehicle, a method and a device for controlling vehicle driving of the present invention improve the safety of vehicle driving control.

[0006] The embodiment of the present invention provides the following solution:

[0007] In a first aspect, an embodiment of the present invention provides a method for controlling vehicle driving, the method comprising:

[0008] Acquire a vehicle contour model of a current vehicle and target features of a target vehicle, wherein the target vehicle is a vehicle located around the current vehicle;

[0009] Determining a target contour model of the target vehicle in a preset vehicle model library according to the target feature;

[0010] According to the vehicle contour model and the target contour model, updating the current measured distance between the target vehicle and the current vehicle, wherein the current measured distance is the minimum distance between the target vehicle and the current vehicle measured by a distance sensor;

[0011] When it is predicted that there is a risk of collision between the current vehicle and the target vehicle according to the updated current measured distance, the current vehicle is controlled to avoid the collision.

[0012] In an optional embodiment, before determining the target contour model of the target vehicle in a preset vehicle model library according to the target feature, the method further includes:

[0013] Obtain vehicle announcement data, manufacturer data and industry shared data;

[0014] The vehicle model library is updated according to the vehicle announcement data, the manufacturer data and the industry shared data.

[0015] In an optional embodiment, the target feature is an outer contour feature and / or a component feature, and determining the target contour model of the target vehicle in a preset vehicle model library according to the target feature includes:

[0016] Identify the vehicle model of the target vehicle according to the outer contour feature and / or the component feature;

[0017] The target contour model is correspondingly determined in the vehicle model library according to the vehicle model.

[0018] In an optional embodiment, when the target vehicle is located behind the current vehicle, when it is predicted that there is a risk of collision between the current vehicle and the target vehicle according to the updated current measured distance, controlling the current vehicle to avoid the collision includes:

[0019] When the updated current measured distance is less than the preset safety distance, the current vehicle is controlled to accelerate.

[0020] In an optional embodiment, before controlling the current vehicle to avoid collision, the method further includes:

[0021] Obtaining a speed deviation and an acceleration deviation between the current vehicle and the target vehicle;

[0022] Determining a collision risk level between the current vehicle and the target vehicle and predicting a collision result according to the speed deviation, the acceleration deviation and the updated current measured distance;

[0023] According to the collision risk level and the predicted collision result, a preset control strategy is executed accordingly.

[0024] In an optional embodiment, executing a preset control strategy correspondingly according to the collision risk level and the predicted collision result includes:

[0025] When the collision risk level is high risk and the predicted collision result is a collision, the seat belt is controlled to be tightened to control the current vehicle to avoid the collision and an alarm message is issued;

[0026] When the collision risk level is high risk and the predicted collision result is no collision, controlling the seat belt to be tightened to control the current vehicle to avoid collision;

[0027] When the collision risk level is medium risk, controlling the issuance of an approach warning of the target vehicle and a speed lane keeping warning of the current vehicle;

[0028] When the collision risk level is low risk, control is performed to issue an approach warning of the target vehicle and display the position information of the target vehicle.

[0029] In a second aspect, an embodiment of the present invention further provides a vehicle, wherein the vehicle is controlled to travel by any method described in the first aspect.

[0030] In a third aspect, an embodiment of the present invention further provides a device for controlling vehicle travel, the device comprising:

[0031] A first acquisition module is used to acquire a vehicle contour model of a current vehicle and a target feature of a target vehicle, wherein the target vehicle is a vehicle located around the current vehicle;

[0032] A first determination module, used to determine a target contour model of the target vehicle in a preset vehicle model library according to the target feature;

[0033] A first updating module, configured to update a current measured distance between the target vehicle and the current vehicle according to the vehicle contour model and the target contour model, wherein the current measured distance is a minimum distance between the target vehicle and the current vehicle measured by a distance sensor;

[0034] The first control module is used to control the current vehicle to avoid collision when predicting that there is a risk of collision between the current vehicle and the target vehicle according to the updated current measured distance.

[0035] In a fourth aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory is coupled to the processor, and the memory stores instructions, which, when executed by the processor, enable the electronic device to perform the steps of any one of the methods described in the first aspect.

[0036] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0037] Compared with the prior art, the vehicle, method and device for controlling vehicle driving provided by the present invention have the following advantages:

[0038] The present invention obtains a vehicle contour model of the current vehicle and a target feature of a target vehicle, determines a target contour model of the target vehicle in a preset vehicle model library according to the target feature, uses the target feature to perform data comparison to identify the target vehicle, quickly determines the vehicle target contour model, and updates the current measured distance between the target vehicle and the current vehicle according to the vehicle contour model and the target contour model. The relative distance between the current vehicle and the target vehicle can be calculated more accurately, the calculation accuracy of assisted driving can be greatly improved, the collision risk between the current vehicle and the target vehicle can be predicted more accurately, and the safety of vehicle driving control can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A flow chart of a method for controlling vehicle driving provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of obtaining target features of a current vehicle provided by an embodiment of the present invention;

[0042] Figure 3 A schematic diagram of the distribution of cameras and radars on a current vehicle provided by an embodiment of the present invention;

[0043] Figure 4 A schematic diagram of the current vehicle recognition target features provided by an embodiment of the present invention;

[0044] Figure 5 A schematic diagram of determining a collision risk level of a current vehicle provided by an embodiment of the present invention;

[0045] Figure 6 A schematic diagram of control strategies for different collision risk levels provided by an embodiment of the present invention;

[0046] Figure 7 A schematic diagram of the structure of a device for controlling vehicle travel provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention belong to the scope of protection of the embodiments of the present invention.

[0048] See also Figure 1 , Figure 1 A flow chart of a method for controlling vehicle driving provided by an embodiment of the present invention, the method comprising:

[0049] S11. Acquire a vehicle contour model of a current vehicle and target features of a target vehicle, wherein the target vehicle is a vehicle located around the current vehicle.

[0050] Specifically, the vehicle contour model is a three-dimensional digital model (or 3D model) that represents the current vehicle's external contour. The model is established through the relevant geometric parameters of the current vehicle. There are many specific implementations, such as generating an external contour geometric model through matlab, or setting parameter information such as length, width, height, wheelbase and track through Catia, and parameterizing the vehicle contour model. Of course, the vehicle contour model can also be generated through the point cloud data of the current vehicle or the corresponding model. The target feature is the key feature for identifying the target vehicle model, such as the design shape of the rear or front of the vehicle.

[0051] It is understood that the acquisition of target features can be achieved based on the camera on the current vehicle, see Figure 2-3 Surround view cameras can be arranged on the front, rear and left and right rearview mirrors of the current vehicle to obtain target features of surrounding target vehicles at different angles, and the target features can be extracted from the pictures taken by the cameras. The specific extraction method can be implemented by an algorithm based on a convolutional neural network. The convolutional neural network is one of the representative algorithms of deep learning and can accurately extract target features. It will not be described in detail here. In addition, radar sensors are installed on both sides, four corners and the front and rear ends of the current vehicle to obtain the current measured distance between the current vehicle and the target vehicle; of course, it can also be obtained through a laser sensor. After obtaining the vehicle contour model of the current vehicle and the target features of the target vehicle, enter step S12.

[0052] S12: determining a target contour model of the target vehicle in a preset vehicle model library according to the target feature.

[0053] Specifically, the outer contours of vehicles have their own design characteristics. The target features are used as identification features. The vehicle model library is a database established based on the contour models of various vehicle models. By comparing the target features, the target contour model of the target vehicle can be determined in the vehicle model library. It can be understood that the vehicle model library can be established by collecting public data, such as vehicle announcement data, manufacturer data, and industry shared data on the Internet. Usually, such public data can characterize the outer contour features of the vehicle. Among them, vehicle announcement data can be obtained through the announcement information network, manufacturer data can be obtained through the manufacturer's self-built database, and industry shared data can be obtained through the shared database of the automotive industry.

[0054] Since vehicles are constantly updated or modified over time, target features may change, resulting in differences in the target profile model or target feature determination.

[0055] To solve the above problem, in a specific implementation, before determining the target contour model of the target vehicle in a preset vehicle model library according to the target feature, the method further includes:

[0056] Obtain vehicle announcement data, manufacturer data and industry shared data; update the vehicle model library based on the vehicle announcement data, manufacturer data and industry shared data.

[0057] Specifically, after obtaining vehicle announcement data, manufacturer data and industry shared data, the historical data is compared. If there are differences, a new contour model is re-established through the vehicle announcement data, manufacturer data and industry shared data, so that the vehicle model library can include contour models of more modified models.

[0058] In a specific implementation, the target feature is an outer contour feature and / or a component feature, and determining a target contour model of the target vehicle in a preset vehicle model library according to the target feature includes:

[0059] The vehicle model of the target vehicle is identified according to the outer contour features and / or component features; and the target contour model is correspondingly determined in the vehicle model library according to the vehicle model.

[0060] Specifically, the outer contour features may be the shape features of the doors, hoods, windows, or the waistline features of the vehicle; the component features may be special identifying features such as lights and logos. The vehicle model of the target vehicle is identified by the outer contour features or component features, and the target contour model can be determined by searching in the vehicle model library. Of course, corresponding weight coefficients can also be set according to the outer contour features and component features to more accurately identify the corresponding target contour model. After determining the target contour model of the target vehicle, step S13 is entered.

[0061] S13. Update a current measured distance between the target vehicle and the current vehicle according to the vehicle contour model and the target contour model, wherein the current measured distance is a minimum distance between the target vehicle and the current vehicle measured by a distance sensor.

[0062] Specifically, the distance sensor may be a radar or laser sensor installed on the current vehicle. Affected by the installation position of the distance sensor or the measurement position on the target vehicle, the actual distance may deviate from the current measured distance. The vehicle profile model represents the outer contour of the current vehicle, and the target profile model represents the outer contour of the target vehicle. Further comparison is performed through the model so that the updated current measured distance can represent the actual distance. After the current measured distance is updated, step S14 is entered.

[0063] S14: When it is predicted that there is a risk of collision between the current vehicle and the target vehicle according to the updated current measured distance, the current vehicle is controlled to avoid the collision.

[0064] Specifically, when the current vehicle and the target vehicle are in a driving state, the collision risk is predicted based on the updated current measured distance. A distance threshold can be set. If the distance between the two vehicles is exceeded, it means that there is a collision risk, and the current vehicle is controlled to avoid the collision. For example, when the target vehicle is in front of the current vehicle, the current vehicle is controlled to brake to ensure that it is at a safe distance from the target vehicle.

[0065] In the existing control strategy for vehicle collision avoidance, only the rear vehicle takes braking action, while the front vehicle does not take the initiative to avoid the collision, resulting in the following defects in the control strategy:

[0066] 1. When the vehicle is going too fast, although the active braking system of the assisted driving intervenes to brake, it cannot stop the vehicle and a rear-end collision will still occur. For example, when driving at high speed, the speed is generally 70-90km / h, and it is basically impossible to stop the vehicle.

[0067] 2. When there is a risk of collision, only the rear vehicle takes measures. Similar to real life, if a person senses danger while driving, he or she will instinctively take measures to avoid or reduce the danger. Therefore, avoiding collision requires not only the rear vehicle to actively brake, but also the front vehicle to make corresponding avoidance strategies.

[0068] 3. If there is a vehicle coming from the side or a vehicle suddenly driving out at an intersection, it is better to take the initiative to avoid it rather than being hit passively.

[0069] In a specific implementation, when the target vehicle is located behind the current vehicle, when it is predicted that there is a risk of collision between the current vehicle and the target vehicle according to the updated current measured distance, the current vehicle is controlled to avoid the collision, including:

[0070] When the updated current measured distance is less than the preset safety distance, the current vehicle is controlled to accelerate.

[0071] Specifically, the safety distance can be set to a fixed value; it can also be determined based on the speed and acceleration of the two vehicles to ensure that the two vehicles do not collide. Controlling the current vehicle to accelerate can ensure that a safe distance is maintained from the following vehicle, reducing the occurrence of rear-end collisions and rear-side collisions.

[0072] In a specific implementation manner, before controlling the current vehicle to avoid a collision, the method further includes:

[0073] Obtain the speed deviation and acceleration deviation between the current vehicle and the target vehicle; determine the collision risk level between the current vehicle and the target vehicle based on the speed deviation, acceleration deviation and the updated current measured distance, and predict the collision result; execute the preset control strategy accordingly based on the collision risk level and the predicted collision result.

[0074] For details, please refer to Figure 4-5 When the current vehicle and the target vehicle are in motion, the distance between the two vehicles will change due to the different speeds and accelerations. If the speed deviation and acceleration deviation are larger, and the updated current measured distance is smaller, it means that there may be a risk of collision between the two vehicles. The current vehicle will correspondingly accelerate or brake to keep the two vehicles at a safe distance; conversely, if the speed deviation and acceleration deviation are smaller, and the updated current measured distance is larger, it means that the risk of collision between the two vehicles is lower, and the driver is reminded to drive safely.

[0075] In a specific implementation, according to the collision risk level and the predicted collision result, a preset control strategy is executed accordingly, including:

[0076] When the collision risk level is high risk and the predicted collision result is a collision, the control tightens the seat belt to control the current vehicle to avoid collision, and issues an alarm message; when the collision risk level is high risk and the predicted collision result is no collision, the control tightens the seat belt to control the current vehicle to avoid collision; when the collision risk level is medium risk, the control issues an approach warning of the target vehicle and a speed lane keeping warning of the current vehicle; when the collision risk level is low risk, the control issues an approach warning of the target vehicle and displays the position information of the target vehicle.

[0077] For details, please refer to Figure 6, when the current vehicle detects that the target vehicle is close, identify the vehicle model and size specifications; obtain the distance, speed, acceleration and road information of the two vehicles to determine the risk level of collision. When the collision risk level is high risk and the predicted collision result is a collision, tighten the seat belt to control the current vehicle to avoid the collision, and issue an alarm message. In order to reduce the damage caused by the collision, the driver is prompted to take active avoidance measures, and the collision direction is displayed on the central control screen. The driving assistance system is started, and the braking system, steering system and drive module are started through control instructions, and video recording, snapshot and one-button alarm are started. When the collision risk level is high risk and the predicted collision result is no collision, the above strategy is also implemented to avoid the collision, but the one-button alarm is not started, and the alarm is eliminated after the collision risk is eliminated. When the collision risk level is medium risk, the approach warning of the target vehicle and the speed lane keeping warning of the current vehicle are issued, and the seat belt can also be tightened simultaneously. The central control screen displays the surround view image from the perspective of the target vehicle to prompt the driver to drive safely, and the alarm is eliminated after the collision risk is eliminated.

[0078] It should be noted that the method for controlling vehicle driving in an embodiment of the present invention is applied to a vehicle equipped with a detection device and a controller. The detection device includes a surround-view camera arranged in the surrounding area of ​​the vehicle (front, left and right sides of the front, left and right sides, rear, left and right sides of the rear), and a ranging radar arranged around the vehicle; static parameters of the vehicle such as vehicle model and size are obtained, and dynamic parameters of the vehicle such as distance, speed, acceleration, etc. are measured; the controller establishes a collision analysis model based on the collected parameters, and determines whether there is a collision risk, whether there is evasive space in the front and sides, current traffic signs and Whether the road conditions support emergency avoidance operations; the establishment of a collision analysis model requires multiple parameter adjustments and calibration verifications to form a rigorous and reliable control strategy; the execution module links the various relevant modules of the vehicle based on the analysis of the collision model, such as: the display module, which mainly includes instrument screen prompts, which can be warning symbols, indicator lights, etc.; such as passive safety modules, seat belt pre-tensioners, doors and windows / sunroofs, etc.; such as driving-related modules, based on risk calculations and judgments, whether the braking system brakes, whether the steering module steers, whether the drive module accelerates or decelerates, etc.; the auxiliary imaging module displays / records and captures videos and images close to the vehicle.

[0079] Based on the same inventive concept as the control method, an embodiment of the present invention further provides a vehicle, wherein the vehicle is controlled to travel by any of the methods described in the first aspect.

[0080] Based on the same inventive concept as the control method, the embodiment of the present invention also provides a device for controlling vehicle travel, see Figure 7 , the device comprises:

[0081] A first acquisition module 701 is used to acquire a vehicle contour model of a current vehicle and a target feature of a target vehicle, wherein the target vehicle is a vehicle located around the current vehicle;

[0082] A first determination module 702 is used to determine a target contour model of the target vehicle in a preset vehicle model library according to the target feature;

[0083] A first updating module 703 is used to update the current measured distance between the target vehicle and the current vehicle according to the vehicle contour model and the target contour model, wherein the current measured distance is the minimum distance between the target vehicle and the current vehicle measured by the distance sensor;

[0084] The first control module 704 is used to control the current vehicle to avoid collision when predicting that there is a collision risk between the current vehicle and the target vehicle according to the updated current measured distance.

[0085] In an optional embodiment, the device further includes:

[0086] The second acquisition module is used to acquire vehicle announcement data, manufacturer data and industry shared data;

[0087] The second updating module is used to update the vehicle model library according to the vehicle announcement data, the manufacturer data and the industry shared data.

[0088] In an optional embodiment, the target feature is an outer contour feature and / or a component feature, and the first determination module includes:

[0089] A first identification submodule, used for identifying the vehicle model of the target vehicle according to the outer contour feature and / or the component feature;

[0090] The first determination submodule is used to determine the target contour model in the vehicle model library according to the vehicle model.

[0091] In an optional embodiment, when the target vehicle is located behind the current vehicle, the first control module includes:

[0092] The first control submodule is used to control the current vehicle to accelerate when the updated current measured distance is less than a preset safety distance.

[0093] In an optional embodiment, the device further includes:

[0094] A third acquisition module is used to obtain a speed deviation and an acceleration deviation between the current vehicle and the target vehicle;

[0095] A first determination module, configured to determine a collision risk level between the current vehicle and the target vehicle and predict a collision result according to the speed deviation, the acceleration deviation and the updated current measured distance;

[0096] The first execution module is used to execute a preset control strategy according to the collision risk level and the predicted collision result.

[0097] In an optional embodiment, the first execution module includes:

[0098] A second control submodule is used for controlling the tightening of the seat belt to control the current vehicle to avoid collision and issuing an alarm message when the collision risk level is high risk and the predicted collision result is collision;

[0099] A third control submodule is used for controlling the tightening of the seat belt to control the current vehicle to avoid collision when the collision risk level is high risk and the predicted collision result is no collision;

[0100] a fourth control submodule, configured to control issuing of an approach warning of the target vehicle and a speed lane keeping warning of the current vehicle when the collision risk level is medium risk;

[0101] The fifth control submodule is used to control the issuance of an approach warning of the target vehicle and display the position information of the target vehicle when the collision risk level is low risk.

[0102] Based on the same inventive concept as the control method, an embodiment of the present invention also provides an electronic device, including a processor and a memory, wherein the memory is coupled to the processor, and the memory stores instructions, which, when executed by the processor, enable the electronic device to perform the steps of any one of the methods described in the first aspect.

[0103] Based on the same inventive concept as the control method, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0104] The technical solution provided in the embodiments of the present invention has at least the following technical effects or advantages:

[0105] 1. By obtaining the vehicle contour model of the current vehicle and the target features of the target vehicle, the target contour model of the target vehicle is determined in the preset vehicle model library according to the target features, and the target vehicle is identified by data comparison using the target features, and the vehicle target contour model is quickly determined. According to the vehicle contour model and the target contour model, the current measured distance between the target vehicle and the current vehicle is updated, and the relative distance between the current vehicle and the target vehicle can be calculated more accurately, which greatly improves the calculation accuracy of assisted driving, and predicts the collision risk between the current vehicle and the target vehicle more accurately, thereby improving the safety of vehicle driving control.

[0106] 2. Through image recognition of the target vehicle and linkage with databases (such as product announcements, traffic control information databases), the vehicle model and size parameters can be quickly identified, and the dynamic key parameter information of the target vehicle can be analyzed and calculated to make the identification more accurate.

[0107] 3. Through control measurement, collision analysis, and linkage execution (brake, steering, drive, passive safety, doors and windows, imaging, rescue and other modules), the solution of active collision avoidance of the vehicle in front is realized. If the vehicle speed is too fast or the distance is too close, the vehicle in front can also actively avoid the collision (move forward, pull over to the side, etc.), which can avoid the collision or greatly reduce the damage caused by the collision.

[0108] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (modules, systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0110] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0112] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0113] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for controlling vehicle travel, characterized in that: The method comprises: Acquire a vehicle contour model of a current vehicle and target features of a target vehicle, wherein the target vehicle is a vehicle located around the current vehicle; Determining a target contour model of the target vehicle in a preset vehicle model library according to the target feature; According to the vehicle contour model and the target contour model, updating the current measured distance between the target vehicle and the current vehicle, wherein the current measured distance is the minimum distance between the target vehicle and the current vehicle measured by a distance sensor; When it is predicted that there is a risk of collision between the current vehicle and the target vehicle according to the updated current measured distance, the current vehicle is controlled to avoid the collision; wherein, When the target vehicle is located behind the current vehicle, when it is predicted that there is a risk of collision between the current vehicle and the target vehicle according to the updated current measured distance, the current vehicle is controlled to avoid the collision, including: When the updated current measured distance is less than the preset safety distance, the current vehicle is controlled to accelerate.

2. The method for controlling vehicle travel according to claim 1, characterized in that: Before determining the target contour model of the target vehicle in a preset vehicle model library according to the target feature, the method further includes: Obtain vehicle announcement data, manufacturer data and industry shared data; The vehicle model library is updated according to the vehicle announcement data, the manufacturer data and the industry shared data.

3. The method for controlling vehicle travel according to claim 1, characterized in that: The target feature is an outer contour feature and / or a component feature, and determining the target contour model of the target vehicle in a preset vehicle model library according to the target feature includes: Identify the vehicle model of the target vehicle according to the outer contour feature and / or the component feature; The target contour model is correspondingly determined in the vehicle model library according to the vehicle model.

4. The method for controlling vehicle travel according to claim 1, characterized in that: Before controlling the current vehicle to avoid collision, the method further includes: Obtaining a speed deviation and an acceleration deviation between the current vehicle and the target vehicle; Determining a collision risk level between the current vehicle and the target vehicle and predicting a collision result according to the speed deviation, the acceleration deviation and the updated current measured distance; According to the collision risk level and the predicted collision result, a preset control strategy is executed accordingly.

5. The method for controlling vehicle travel according to claim 4, characterized in that: The executing a preset control strategy according to the collision risk level and the predicted collision result includes: When the collision risk level is high risk and the predicted collision result is a collision, the seat belt is controlled to be tightened to control the current vehicle to avoid the collision and an alarm message is issued; When the collision risk level is high risk and the predicted collision result is no collision, controlling the seat belt to be tightened to control the current vehicle to avoid collision; When the collision risk level is medium risk, controlling the issuance of an approach warning of the target vehicle and a speed lane keeping warning of the current vehicle; When the collision risk level is low risk, control is performed to issue an approach warning of the target vehicle and display the position information of the target vehicle.

6. A vehicle, characterized in that: The vehicle is controlled to travel by the method described in any one of claims 1-5.

7. A device for controlling vehicle travel, characterized in that: The device comprises: A first acquisition module is used to acquire a vehicle contour model of a current vehicle and a target feature of a target vehicle, wherein the target vehicle is a vehicle located around the current vehicle; A first determination module, used to determine a target contour model of the target vehicle in a preset vehicle model library according to the target feature; A first updating module, configured to update a current measured distance between the target vehicle and the current vehicle according to the vehicle contour model and the target contour model, wherein the current measured distance is a minimum distance between the target vehicle and the current vehicle measured by a distance sensor; A first control module, configured to control the current vehicle to avoid collision when predicting a collision risk between the current vehicle and the target vehicle according to the updated current measured distance; When the target vehicle is located behind the current vehicle, when it is predicted that there is a risk of collision between the current vehicle and the target vehicle according to the updated current measured distance, the current vehicle is controlled to avoid the collision, including: When the updated current measured distance is less than the preset safety distance, the current vehicle is controlled to accelerate.

8. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory is coupled to the processor and stores instructions, and when the instructions are executed by the processor, the electronic device executes the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 5 are implemented.

Images