Vehicle braking method and device, vehicle-mounted equipment and medium

Abstract

The embodiment of the invention is suitable for the technical field of vehicles, and provides a vehicle braking method and device, vehicle-mounted equipment and a medium, the method comprises the steps that the lane line state of a current driving road of a vehicle is determined, and the lane line state comprises a clear state or a non-clear state; if the lane line state is a non-clear state, predicting a driving track of the vehicle; determining a target obstacle having a collision risk with the vehicle according to the driving track; and braking the vehicle based on the target obstacle. Through the method, the vehicle can be accurately and emergently braked under the condition that the lane line is not clear.

Description

Technical Field

[0001] The present application belongs to the field of vehicle technology, and in particular relates to a vehicle braking method, device, vehicle-mounted equipment and medium. Background Art

[0002] The AEB (Autonomous Emergency Braking) system is a driver assistance system that helps the driver to brake the vehicle in an emergency. The AEB system can provide the driver with a vehicle collision warning in advance and perform automatic emergency braking to the maximum extent possible to reduce the probability of collision with obstacles such as pedestrians, electric vehicles and vehicles ahead, thus ensuring driving safety.

[0003] When the AEB system is working, it needs to identify the target with a collision risk and make braking decisions based on the target. However, the emergency braking methods of the current AEB system are mostly suitable for structured roads. When the vehicle is driving on an unstructured road, it is difficult for the AEB system to collect the data required for braking decisions or the error rate of the collected data is relatively high, making it difficult to identify or misidentify the target with a collision risk.

[0004] For example, when a vehicle is traveling on urban or rural roads, the road lane lines and other signs may have long been worn out and lost, or the road is flooded, making it impossible to clearly distinguish the road lane lines. The AEB system may find it difficult to collect accurate lane line data and may be unable to normally screen out targets that pose a risk of collision with the vehicle, which may cause false triggering or missed triggering of the entire AEB system. Summary of the invention

[0005] In view of this, embodiments of the present application provide a vehicle braking method, apparatus, vehicle-mounted equipment and medium to improve the accuracy of vehicle emergency braking decisions.

[0006] A first aspect of an embodiment of the present application provides a vehicle braking method, comprising:

[0007] Determine a lane line state of a road on which the vehicle is currently traveling, wherein the lane line state includes a clear state or an unclear state;

[0008] If the lane line state is an unclear state, predicting the driving trajectory of the vehicle;

[0009] Determining, based on the driving trajectory, a target obstacle that has a collision risk with the vehicle;

[0010] The vehicle is braked based on the target obstacle.

[0011] A second aspect of an embodiment of the present application provides a vehicle braking device, comprising:

[0012] A state determination module, used to determine the lane line state of the road the vehicle is currently traveling on, wherein the lane line state includes a clear state or an unclear state;

[0013] A trajectory prediction module, used for predicting the driving trajectory of the vehicle if the lane line state is not clear;

[0014] A target screening module, used to determine a target obstacle that has a collision risk with the vehicle according to the driving trajectory;

[0015] A braking decision module is used to brake the vehicle based on the target obstacle.

[0016] A third aspect of an embodiment of the present application provides a vehicle-mounted device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0017] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect above is implemented.

[0018] A fifth aspect of the embodiments of the present application provides a computer program product. When the computer program product is run on a vehicle-mounted device, the vehicle-mounted device executes the method described in the first aspect above.

[0019] Compared with the prior art, the embodiments of the present application have at least the following advantages:

[0020] By applying the vehicle braking method in the embodiment of the present application, the accuracy of the vehicle emergency braking decision can be improved when the lane lines are unclear. When the vehicle is traveling on the road, the clarity of the lane lines of the current road can be determined; if the lane lines are unclear, the vehicle's driving trajectory can be predicted; thus, the target obstacle body that poses a risk of collision with the vehicle can be determined based on the driving trajectory; based on the determined target obstacle body, an emergency braking decision for the vehicle can be executed. The method in the embodiment of the present application can determine the target obstacle body that poses a risk of collision with the vehicle based on the predicted driving trajectory when the lane lines are unclear, thereby improving the accuracy of the target obstacle body, thereby making the vehicle's emergency braking more accurate and avoiding false triggering and missed triggering of the vehicle's emergency braking. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art.

[0022] Figure 1It is a schematic flow chart of the steps of a vehicle braking method provided in an embodiment of the present application;

[0023] Figure 2 This is a schematic diagram of a scenario for determining a target obstacle provided by an embodiment of the present application;

[0024] Figure 3 is a schematic diagram of a vehicle braking system provided in an embodiment of the present application;

[0025] Figure 4 is a schematic diagram of a vehicle braking device provided in an embodiment of the present application;

[0026] Figure 5 It is a schematic diagram of a vehicle-mounted device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In the following description, specific details such as specific system structures, technologies, etc. are proposed for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from hindering the description of the present application.

[0028] Lane lines are part of the road markings and are used to guide, restrict and warn traffic participants. When driving, vehicles generally need to drive within the specified area as defined by the lane lines. When making emergency braking decisions, the future driving route of the vehicle can be directly determined based on the lane lines, so that obstacles that affect the vehicle's driving can be directly determined within the lane lines. On structured roads, it can generally include clear and complete lane lines and various signs for indicating vehicles. At present, the emergency braking methods of AEB systems are mostly suitable for structured roads.

[0029] However, vehicles cannot collect clear lane lines in all driving scenarios. When a vehicle is driving on an unstructured road, such as a road that has been in disrepair for a long time or a rural road, it is usually difficult to collect lane lines. When lane lines are unclear or missing, it is difficult to determine the vehicle's next driving path, and thus it is difficult to determine obstacles that affect the vehicle's driving.

[0030] For example, on rural roads, when there are no lane lines, obstacles may be screened from living or non-living objects in the entire road area, and non-obstacles may be judged as obstacles; judging non-obstacles as obstacles may easily cause false triggering of vehicle emergency braking, which will reduce the user's driving experience. When the lane lines are not clear, obstacles that affect vehicle driving may be missed, which may affect driving safety.

[0031] Based on this, an embodiment of the present application provides a vehicle braking method, which can improve the accuracy of obstacle judgment when the lane lines are unclear or missing, thereby ensuring driving safety and improving user experience.

[0032] The technical solution of the present application is described below through specific embodiments.

[0033] Reference Figure 1 , shows a schematic flow chart of a vehicle braking method provided by an embodiment of the present application, which may specifically include the following steps:

[0034] S101, determining a lane line state of a road on which a vehicle is currently traveling, wherein the lane line state includes a clear state or an unclear state.

[0035] The braking method in the present application is vehicle emergency braking, that is, when the vehicle is driving and a possible collision is detected, the vehicle can brake to avoid the occurrence of a collision accident. The executor of the present application may be a vehicle-mounted device, and the vehicle-mounted device may be a vehicle computer, an emergency braking controller, a vehicle-mounted terminal, and other devices that can make vehicle emergency braking decisions. Different vehicles may have different designated vehicle emergency braking devices according to their different device integration methods. In some possible implementations, the vehicle-mounted device may also include other types of electronic devices such as mobile terminals. That is, a mobile terminal can be used as a vehicle-mounted device on the vehicle to implement the relevant functions of the method provided in the embodiment of the present application. The embodiment of the present application does not limit the type of vehicle-mounted device.

[0036] The vehicle may include a visual sensor to collect image data; based on the collected image data, obstacles with which the vehicle may have a collision risk may be determined, the lane line status of the road the vehicle is currently traveling on may be determined, etc. For example, cameras may be provided on the front, back, left, and right sides of the vehicle to collect images or videos of the road the vehicle is currently traveling on.

[0037] The lane line status may include a clear state and an unclear state. The unclear state may include a fuzzy state and a missing state. The fuzzy state may be caused by lane line wear and discontinuity; the missing state may be caused by the absence of a lane line. On unstructured roads, such as township roads, there are usually no standard lane line markings. In this case, the lane line status may be determined to be an unclear state. On roads that have been in disrepair for a long time, when the lane line is difficult to detect, the lane line status may also be determined to be an unclear state.

[0038] In a possible implementation, the vehicle-mounted device can determine the lane line state through the video information collected in real time during the vehicle's travel. The vehicle-mounted device can obtain the real-time video collected by the visual sensor, and obtain multiple continuous video frames from the real-time video. For each video frame, the lane line can be identified from the video frame through an image recognition algorithm; if the vehicle-mounted device can identify the lane line from multiple continuous video frames, the lane line state can be considered to be in a clear state. During the vehicle's travel, the real-time video will be continuously updated, and the vehicle-mounted device can extract video frames from the real-time video for lane line recognition. When the vehicle-mounted device fails to recognize the lane line from the first real-time video frame, it can collect multiple continuous second video frames after the first real-time video, and perform lane line recognition on each second video frame. If the lane line cannot be recognized in multiple second video frames, it can be determined that the lane line state is not clear.

[0039] In another possible implementation, after determining the lane line status based on the real-time video, the vehicle-mounted device can associate the location information with the lane line status and send it to the cloud platform, so that the cloud platform can obtain the association between the location information and the lane line status. When determining the lane line status, the vehicle-mounted device can first obtain the corresponding lane line status from the cloud platform based on the location information; if the vehicle-mounted device can obtain the corresponding lane line status from the cloud platform based on the location information, the obtained lane line status can be directly used to perform subsequent steps. If the vehicle-mounted device fails to obtain the corresponding lane line status from the cloud platform based on the location information, it can determine the lane line status through the collected real-time video, and associate the location information with the lane line status and send it to the cloud platform to update the data of the cloud platform.

[0040] S102: If the lane line state is unclear, predict the driving trajectory of the vehicle.

[0041] The vehicle braking in this embodiment refers to emergency braking of the vehicle when it is determined that the vehicle will collide with an obstacle during driving, so as to ensure driving safety.

[0042] In order to determine whether a collision occurs, it is necessary to first determine the obstacles that may collide with the vehicle. The obstacles that may collide with the vehicle may be living or non-living objects that appear on the next running track of the vehicle. Therefore, to determine the obstacles that may collide with the vehicle, it is necessary to first determine the next running track of the vehicle.

[0043] When the lane lines are clear, the vehicle will travel within the lane lines. At this time, the on-board equipment can determine the vehicle's driving trajectory based on the identified lane lines.

[0044] When the lane line state is unclear, no clear lane line can be identified. At this time, the on-board equipment can predict the driving trajectory of the vehicle.

[0045] The vehicle-mounted device can predict the vehicle's driving trajectory based on the vehicle's acceleration and angular velocity. The vehicle-mounted device can predict the vehicle's driving direction and driving speed based on the vehicle's current speed, acceleration and angular velocity, and then based on the predicted driving direction and driving speed, the vehicle's displacement within a preset time can be predicted; based on the vehicle's displacement within a preset time and the vehicle's current position, the vehicle-mounted device can determine and predict multiple positions of the vehicle within a preset time, and the multiple positions of the vehicle within a preset time can constitute the predicted vehicle's driving trajectory.

[0046] The vehicle may be equipped with a sensor device, so that the vehicle-mounted equipment can determine the acceleration and angular velocity of the vehicle based on the sensor data collected by the sensor device. Exemplarily, an inertial measurement unit may be installed on the vehicle, and based on the data collected by the inertial measurement unit, the vehicle-mounted equipment can determine the posture information of the vehicle during driving; based on the posture information, the vehicle-mounted equipment can calculate the acceleration and angular velocity of the vehicle. Among them, the method of determining the posture information based on the data collected by the inertial measurement unit is a prior art and will not be described in detail here.

[0047] In one possible implementation, the vehicle may predict the vehicle's driving trajectory based on vehicle speed information and vehicle steering wheel information.

[0048] Specifically, the vehicle can determine the current speed and trajectory curvature of the vehicle. Exemplarily, the trajectory curvature of the vehicle can be determined by the following formula:

[0049] tanδ=l / R

[0050]

[0051] Among them, Fj is the steering wheel angle of the vehicle, Fc is the steering wheel transmission ratio of the vehicle, Q is the trajectory curvature, and l is the wheelbase of the vehicle.

[0052] Based on the vehicle speed and trajectory curvature, the acceleration and angular velocity can be integrated to obtain the predicted speed and predicted driving direction of the vehicle; thus, the vehicle's driving trajectory can be predicted based on the predicted speed and predicted driving direction.

[0053] In this embodiment, the vehicle-mounted device can collect vehicle information while the vehicle is driving, so as to predict the vehicle's driving trajectory based on the vehicle information. The vehicle information may include the vehicle's posture information, speed information, and position information. The vehicle may be equipped with an inertial measurement unit, and based on the inertial measurement unit, the vehicle-mounted device can collect the vehicle's posture information during driving. The vehicle-mounted device can obtain the vehicle's speed information from the body domain control signal. The vehicle-mounted device can obtain the vehicle's position information based on the positioning device installed on the vehicle.

[0054] When predicting the driving trajectory of a vehicle, the vehicle speed can be predicted, and the vehicle's next driving position can be predicted based on the predicted speed and the vehicle's position information, and the vehicle's driving trajectory can be determined based on the predicted vehicle's driving position.

[0055] S103: Determine, according to the driving trajectory, a target obstacle that has a collision risk with the vehicle.

[0056] After determining the driving trajectory of the vehicle, the area where the vehicle is about to travel can be determined based on the driving trajectory, so that obstacles that pose a risk of collision with the vehicle can be determined from the area where the vehicle is about to travel based on the collected image data.

[0057] In one possible implementation, the vehicle's driving trajectory can be represented by the predicted center position of the vehicle. If the distance between other living or non-living objects and the center of the vehicle is less than or equal to the width of the vehicle when the vehicle travels to a certain position, it can be said that the living or non-living object is an obstacle that affects the vehicle's travel.

[0058] Therefore, when determining an obstacle, the width of the vehicle and the center position of the vehicle can be determined; then, according to the width, the lateral screening threshold of the vehicle can be determined; the lateral screening threshold can be equal to half the width of the vehicle, or equal to the sum of half the width of the vehicle and a preset width. The preset width can be a set fault tolerance value.

[0059] Based on the image data collected by the vehicle, the position information of living and non-living objects in front of the vehicle can be determined, and then living or non-living objects whose lateral distance from the center position is less than the lateral screening threshold are determined as obstacles.

[0060] In another possible implementation, when determining an obstacle, the driving area of ​​the vehicle may be determined from the image data, and then living or non-living objects in the driving area may be determined as obstacles.

[0061] The predicted vehicle's driving trajectory can be characterized based on the predicted multiple positions of the vehicle. The predicted multiple positions of the vehicle can determine a driving curve of the vehicle, and with the curve as the center, an area with a width of the vehicle can be determined, and the area is the driving area of ​​the vehicle. Based on the image or video frame collected at the current moment, the driving area of ​​the vehicle can be determined from the image or video frame according to the predicted vehicle's driving trajectory at the current moment, and then the driving area is subjected to target detection based on the target detection algorithm to determine the obstacle.

[0062] In another possible implementation, when determining an obstacle, a screening area can be determined from the image data, and then living or non-living objects in the driving area can be determined as obstacles. The screening area can be the driving area and the area adjacent to the driving area. For example, the vehicle's driving trajectory can be used as the center and twice the lateral screening distance can be used as the width to determine the screening area. Based on the image or video frame captured at the current moment, the vehicle's screening area can be determined from the image or video frame based on the vehicle's driving trajectory predicted at the current moment, and then the screening area can be subjected to target detection based on the target detection algorithm to determine the obstacle.

[0063] The vehicle driving area may include multiple obstacles. After determining the multiple obstacles, a target obstacle with a risk of collision with the vehicle can be screened from the obstacles. In a possible implementation, the target obstacle with the vehicle can be determined from the multiple obstacles based on the vehicle emergency braking algorithm provided by the vehicle emergency braking module, so as to make an emergency braking decision according to the target obstacle and the driving state of the vehicle.

[0064] Figure 2 It is a schematic diagram of a scenario for determining a target obstacle provided in an embodiment of the present application. Figure 2 A in is a vehicle. Figure 2 As shown, the road that vehicle A is currently traveling on is a structured road with no lane lines. When the vehicle is traveling on a road without lane lines, vehicle A can determine the vehicle's driving trajectory based on the method in the embodiment of the present application. The vehicle's driving trajectory can be represented by a curve formed by connecting the predicted positions of the vehicle's center. Figure 2 As shown, the arc passing through the center of the vehicle can be the predicted vehicle driving trajectory.

[0065] After determining the driving trajectory, the width of the vehicle can be determined, and the driving area of ​​the vehicle can be determined based on the width of the vehicle. Using 1 / 2 of the width of the vehicle plus a preset error width, the half width corresponding to the vehicle driving area can be determined. Taking the arc corresponding to the vehicle driving trajectory as the midpoint, two boundary lines at half the width of the arc can be determined respectively, such as Figure 2The two dotted lines in the figure are the predicted driving area of ​​the vehicle. Based on the driving area, the obstacles that affect the vehicle can be determined. Figure 2 , pedestrian B is not in the area, then it can be determined that pedestrian B is not an obstacle. Vehicle C is partially in the driving area, then it can be determined that vehicle C is an obstacle to vehicle A.

[0066] S104: Braking the vehicle based on the target obstacle.

[0067] After determining the target obstacle, the on-board equipment can use the braking algorithm in the AEB system to make braking decisions, thereby avoiding collision between the target obstacle and the vehicle and ensuring the driving safety of the vehicle.

[0068] Of course, if the lane line state is clear, the vehicle's driving area can be directly determined based on the lane line; then the target obstacle that has a risk of collision with the vehicle can be determined from the driving area.

[0069] In this embodiment, when the lane line on the road where the vehicle is traveling is in an unclear state, the vehicle's driving trajectory can be predicted based on the sensor data and vehicle information collected by the vehicle, so that based on the vehicle's driving trajectory, the area that needs to be screened can be determined from the image data; then the obstacle body is determined from the area that needs to be screened, and then the target obstacle body is determined from the obstacle body. Based on the method of this embodiment, when the lane line is unclear, the target obstacle body that has a risk of collision with the vehicle is determined based on the predicted driving trajectory, which improves the accuracy of the target obstacle body, thereby making the vehicle's emergency braking more accurate and avoiding false triggering and missed triggering of the vehicle's emergency braking.

[0070] It should be noted that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0071] Figure 3 is a schematic diagram of a vehicle braking system provided in an embodiment of the present application, such as Figure 3As shown, an AEB module can be deployed in a vehicle. Multiple sensing devices, such as radar, camera, inertial measurement unit, etc., can be installed in the vehicle. For example, a millimeter-wave radar and a high-definition camera can be arranged in front of the vehicle to realize obstacle detection and road recognition; a blind spot camera is set on each side of the vehicle to effectively monitor pedestrians or obstacles in the blind spot of the vehicle to reduce driving blind spots; a camera is also configured at the rear of the vehicle to monitor the road conditions behind and avoid reversing collision accidents; multiple ultrasonic radars are arranged at the front and rear of the vehicle, which can perceive the surrounding environment in real time, improve the accuracy of distance and position information, and assist the interaction between the vehicle and surrounding objects; a high-precision inertial measurement unit can be installed inside the vehicle body, which can continuously detect the vehicle's posture, acceleration and other key data, so as to smoothly estimate the vehicle's own trajectory.

[0072] The quality of lane lines can be judged by the front camera, rear camera, and left and right cameras. Figure 3 As shown, logic switching can be performed based on whether the lane line is clear. If the lane line quality information obtained by the vehicle through the visual sensor is high, the vehicle trajectory module obtained by the IMU posture solution can be executed without executing it, thereby reducing the waste of AEB algorithm resources. If the lane line quality information obtained by the vehicle through the visual sensor is not high, the IMU estimation vehicle trajectory module can be started, and the data obtained by the IMU can be used to estimate the vehicle's driving trajectory, to make up for the misscreening and missed obstacles caused by the lack of lane lines, and to avoid traffic accidents. In this embodiment, the vehicle can obtain the real-time speed, acceleration and other important parameters of the vehicle through the analysis of the entire CAN (Controller Area Network) protocol, and then estimate its own trajectory in combination with the IMU, so as to better serve the AEB system.

[0073] That is, when the lane lines on the road are clear, the targets that may affect the vehicle's driving can be determined based on the lane lines, so as to make judgments and decisions on emergency braking. If the lane lines on the road are unclear, the lane lines of the vehicle can be estimated based on the steering wheel and IMU. Based on the estimated lane lines of the vehicle, the AEB module can determine the targets that may affect the vehicle's driving, so as to make judgments and decisions on emergency braking.

[0074] Reference Figure 4 , shows a schematic diagram of a vehicle braking device provided in an embodiment of the present application, which may specifically include a state determination module 41, a trajectory prediction module 42, a target screening module 43 and a braking decision module 44, wherein:

[0075] A state determination module 41 is used to determine the lane line state of the road on which the vehicle is currently traveling, wherein the lane line state includes a clear state or an unclear state;

[0076] A trajectory prediction module 42, configured to predict the driving trajectory of the vehicle if the lane line state is not clear;

[0077] A target screening module 43 is used to determine a target obstacle that has a collision risk with the vehicle according to the driving trajectory;

[0078] The braking decision module 44 is used to brake the vehicle based on the target obstacle.

[0079] In a possible implementation, the trajectory prediction module 42 includes:

[0080] a determination submodule, configured to determine the acceleration and angular velocity of the vehicle by means of an inertial measurement unit installed on the vehicle;

[0081] A prediction submodule is used to predict the driving trajectory of the vehicle based on the acceleration and the angular velocity.

[0082] In a possible implementation, the prediction submodule includes:

[0083] A determination unit, used to determine the current speed and trajectory curvature of the vehicle;

[0084] a prediction unit, configured to integrate the acceleration and the angular velocity based on the vehicle speed and the trajectory curvature to obtain a predicted speed and a predicted driving direction of the vehicle;

[0085] A trajectory prediction unit is used to predict the driving trajectory of the vehicle based on the predicted speed and the predicted driving direction.

[0086] In a possible implementation, the trajectory curvature of the vehicle is determined by the following formula:

[0087] tanδ=l / R

[0088]

[0089] Wherein, Fj is the steering wheel angle of the vehicle, Fc is the steering wheel transmission ratio of the vehicle, Q is the trajectory curvature, and l is the wheelbase of the vehicle.

[0090] In a possible implementation, the target screening module 43 includes:

[0091] An obstacle determination submodule, used to determine an obstacle that affects the driving of the vehicle according to the driving trajectory;

[0092] The target obstacle screening submodule is used to screen target obstacles that have a collision risk with the vehicle from the obstacles.

[0093] In a possible implementation, the obstacle determination submodule includes:

[0094] a driving area determination unit, used to determine the width of the vehicle and the center position of the vehicle;

[0095] a transverse screening threshold determination unit, configured to determine a transverse screening threshold of the vehicle according to the width;

[0096] The obstacle determination unit is used to determine a living body or a non-living body whose lateral distance from the central position is less than the lateral screening threshold as the obstacle.

[0097] In a possible implementation, the above device further includes:

[0098] A driving area determination module, configured to determine a driving area of ​​the vehicle according to the lane line if the lane line state is a clear state;

[0099] The target screening module 43 is further used to determine target obstacles that may have a collision risk with the vehicle in the driving area.

[0100] The vehicle braking device provided in the embodiment of the present application can be the vehicle-mounted device in the above-mentioned various method embodiments, or can also be a related unit in the vehicle-mounted device. The above-mentioned vehicle braking device can be used to implement the steps in the above-mentioned various method embodiments.

[0101] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment part.

[0102] Figure 5 This is a schematic diagram of the structure of a vehicle-mounted device provided in an embodiment of the present application. Figure 5 As shown, the vehicle-mounted device 5 of this embodiment includes: at least one processor 50 ( Figure 5 Only one is shown in the figure), a memory 51, and a computer program 52 stored in the memory 51 and executable on the at least one processor 50, wherein the processor 50 implements the steps of any of the above-mentioned method embodiments when executing the computer program 52.

[0103] The vehicle-mounted device may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will appreciate that Figure 5 It is only an example of the vehicle-mounted device 5 and does not constitute a limitation on the vehicle-mounted device 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0104] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0105] In some embodiments, the memory 51 may be an internal storage unit of the vehicle-mounted device 5, such as a hard disk or memory of the vehicle-mounted device 5. In other embodiments, the memory 51 may also be an external storage device of the vehicle-mounted device 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the vehicle-mounted device 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the vehicle-mounted device 5. The memory 51 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 51 may also be used to temporarily store data that has been output or is to be output.

[0106] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0107] An embodiment of the present application provides a computer program product. When the computer program product is run on a vehicle-mounted device, the vehicle-mounted device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0108] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application is described in detail with reference to the above-mentioned embodiments, a person skilled in the art should understand that the technical solutions described in the above-mentioned embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A vehicle braking method, characterized in that: include: Determine a lane line state of a road on which the vehicle is currently traveling, wherein the lane line state includes a clear state or an unclear state; If the lane line state is an unclear state, predicting the driving trajectory of the vehicle; Determining, based on the driving trajectory, a target obstacle that has a collision risk with the vehicle; The vehicle is braked based on the target obstacle.

2. The method according to claim 1, characterized in that The predicting the driving trajectory of the vehicle includes: Determining the acceleration and angular velocity of the vehicle by an inertial measurement unit installed on the vehicle; Based on the acceleration and the angular velocity, a driving trajectory of the vehicle is predicted.

3. The method according to claim 2, characterized in that The predicting the driving trajectory of the vehicle based on the acceleration and the angular velocity includes: Determining a current speed and trajectory curvature of the vehicle; Based on the vehicle speed and the trajectory curvature, integrating the acceleration and the angular velocity to obtain a predicted speed and a predicted driving direction of the vehicle; Based on the predicted speed and the predicted driving direction, a driving trajectory of the vehicle is predicted.

4. The method according to claim 3, characterized in that The curvature of the trajectory of the vehicle is determined by the following formula: tanδ=l / R Wherein, Fj is the steering wheel angle of the vehicle, Fc is the steering wheel transmission ratio of the vehicle, Q is the trajectory curvature, and l is the wheelbase of the vehicle.

5. The method according to any one of claims 1 to 4, characterized in that: The step of determining a target obstacle body that has a collision risk with the vehicle based on the driving trajectory includes: Determining obstacles that affect the driving of the vehicle according to the driving trajectory; From the obstacles, target obstacles that have a risk of collision with the vehicle are screened.

6. The method according to claim 5, characterized in that The step of determining an obstacle that affects the driving of the vehicle according to the driving trajectory includes: determining a width of the vehicle and a center position of the vehicle; determining a lateral screening threshold of the vehicle according to the width; A living object or non-living object whose lateral distance from the central position is less than the lateral screening threshold is determined as the obstacle.

7. The method according to claim 1, characterized in that The method further comprises: If the lane line state is a clear state, determining the driving area of ​​the vehicle according to the lane line; A target obstacle that has a collision risk with the vehicle is determined from the driving area.

8. A vehicle braking device, characterized in that: include: A state determination module, used to determine the lane line state of the road the vehicle is currently traveling on, wherein the lane line state includes a clear state or an unclear state; A trajectory prediction module, used for predicting the driving trajectory of the vehicle if the lane line state is not clear; A target screening module, used to determine a target obstacle that has a collision risk with the vehicle according to the driving trajectory; A braking decision module is used to brake the vehicle based on the target obstacle.

9. A vehicle-mounted device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images