Brake Control Method and Device, Intelligent Driving Vehicle, and Storage Medium

Abstract

The present disclosure provides a braking control method and apparatus, an intelligent driving vehicle, and a storage medium, relating to the field of computer technologies. The braking control method includes: processing the point cloud data at the current moment and the point cloud data at the previous moment collected by a lidar using a motion perception model to obtain the position information, motion information, and category information of each target point in a target point set; clustering the target point set according to the position information, motion information, and category information of each target point to identify a target object; and performing braking control on the intelligent driving vehicle according to the current motion information of the intelligent driving vehicle, the position information and motion information of the target object, the braking distance at which the intelligent driving vehicle currently performs a braking operation, and the orientation of the target object relative to the intelligent driving vehicle.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and particularly to a braking control method and apparatus, an intelligent driving vehicle, and a storage medium. Background Art

[0002] The active safety system is an important safety guarantee module in the intelligent driving system. It determines the real-time driving situation of the vehicle and performs emergency braking when there is a collision risk between the vehicle and the target, thus ensuring the safety of the vehicle.

[0003] The existing active safety technologies are usually developed based on millimeter-wave radars. Millimeter-wave radars can directly measure the speed of a target based on the Doppler effect, thereby realizing the perception of the target's motion state. Summary of the Invention

[0004] The inventors noticed that the existing millimeter-wave radars have three disadvantages: 1) The point clouds collected by millimeter-wave radars are sparse, and the response to small targets is relatively weak, such as children, cats, and dogs. 2) The vertical resolution of millimeter-wave radars is very low, and the reflection points are located on the BEV (Bird's Eye View) 2D plane. Therefore, it is difficult to distinguish static obstacles (such as parked cars on the roadside) from non-obstacle background objects (such as the road surface). So, millimeter-wave radars are difficult to handle stationary obstacles and can only effectively perceive dynamic obstacles. 3) The speed perception principle of millimeter-wave radars is based on the Doppler effect, and effective speed perception can only be achieved in the radial direction (the direction of the line connecting the radar and the target object), lacking effective perception in the transverse direction. Therefore, millimeter-wave radars cannot measure the real motion state of an object, and thus cannot achieve precise braking control of intelligent driving vehicles.

[0005] Accordingly, the present disclosure provides a braking control method. By using the point cloud data collected by a lidar at the current moment and the previous moment, the position information, motion information, and category information of each target point are obtained. By clustering the target points to identify the target object, and then, based on the current motion information of the intelligent driving vehicle, the braking distance for the current braking operation, the position information and motion information of the target object, and the orientation of the target object relative to the intelligent driving vehicle, the braking control of the intelligent driving vehicle is performed, so as to ensure the driving safety of the intelligent driving vehicle through precise braking control.

[0006] According to a first aspect of the embodiments of the present disclosure, there is provided a braking control method, which is executed by a braking control device in an intelligent driving vehicle, and includes: processing the point cloud data at the current moment and the point cloud data at the previous moment collected by a lidar using a motion perception model to obtain the position information, motion information, and category information of each target point in the target point set; clustering the target point set according to the position information, motion information, and category information of each target point to identify a target object; and performing braking control on the intelligent driving vehicle according to the current motion information of the intelligent driving vehicle, the position information and motion information of the target object, the braking distance at which the intelligent driving vehicle currently performs a braking operation, and the orientation of the target object relative to the intelligent driving vehicle.

[0007] In some embodiments, the performing braking control on the intelligent driving vehicle includes: determining whether there is a collision risk between the intelligent driving vehicle and the target object within the braking distance according to the current motion information of the intelligent driving vehicle, the position information and motion information of the target object; in the case that there is a collision risk between the intelligent driving vehicle and the target object within the braking distance, determining whether the target object is in front of the intelligent driving vehicle according to the position information of the target object; and in the case that the target object is in front of the intelligent driving vehicle, controlling the intelligent driving vehicle to perform a braking operation.

[0008] In some embodiments, the performing braking control on the intelligent driving vehicle includes: in the case that the target object is behind or on the side of the intelligent driving vehicle, not performing braking on the intelligent driving vehicle.

[0009] In some embodiments, the controlling the intelligent driving vehicle to perform a braking operation in the case that the target object is in front of the intelligent driving vehicle includes: in the case that the target object is in front of the intelligent driving vehicle, determining whether the motion direction of the target object is the same as the motion direction of the intelligent driving vehicle according to the current motion information of the intelligent driving vehicle and the motion information of the target object; and in the case that the motion direction of the target object is the same as the motion direction of the intelligent driving vehicle, controlling the intelligent driving vehicle to perform a braking operation.

[0010] In some embodiments, the controlling the intelligent driving vehicle to perform a braking operation in the case that the target object is in front of the intelligent driving vehicle includes: in the case that the motion direction of the target object is opposite to the motion direction of the intelligent driving vehicle, not performing braking on the intelligent driving vehicle.

[0011] In some embodiments, when the moving direction of the target object is the same as that of the intelligent driving vehicle, controlling the intelligent driving vehicle to perform a braking operation includes: when the moving direction of the target object is the same as that of the intelligent driving vehicle, obtaining the position information and motion information of the target object at the previous N moments of the current moment, where N is a natural number greater than 0; if the change amount of the relative position between the intelligent driving vehicle and the target object is not within a predetermined range at the current moment and the previous N moments, then controlling the intelligent driving vehicle to perform a braking operation.

[0012] In some embodiments, when the moving direction of the target object is the same as that of the intelligent driving vehicle, controlling the intelligent driving vehicle to perform a braking operation includes: if the change amount of the relative position between the intelligent driving vehicle and the target object is within a predetermined range at the current moment and the previous N moments, then not performing braking on the intelligent driving vehicle.

[0013] In some embodiments, after identifying the target object, determining whether the target object is included in the target point set obtained at the previous M moments of the current moment, where M is a natural number greater than 0; when the target object is included in the target point set obtained at the previous M moments, performing braking control on the intelligent driving vehicle.

[0014] In some embodiments, when the target object is not included in the target point set obtained at the previous M moments, not performing emergency braking on the intelligent driving vehicle.

[0015] In some embodiments, the motion information of each target point includes the speed information, acceleration information, and angular velocity information of each target point.

[0016] In some embodiments, deleting the background points in the original point cloud data collected by the lidar at the current moment to obtain the point cloud to be processed; performing voxelization processing on the point cloud to be processed to obtain the point cloud data at the current moment.

[0017] In some embodiments, clustering the target point set includes: cleaning the target point set to delete the abnormal target points in the target point set; in the cleaned target point set, clustering the target points with the same position information, the same motion information, and the same category information to identify the target object.

[0018] According to a second aspect of the embodiments of the present disclosure, there is provided a braking control device, including: a memory; a processor coupled to the memory, the processor being configured to execute based on the instructions stored in the memory to implement the braking control method as described in any one of the above embodiments.

[0019] According to a third aspect of the embodiments of the present disclosure, there is provided an intelligent driving vehicle, including: a braking control device as described in any of the above embodiments; a lidar, configured to collect original point cloud data around the intelligent driving vehicle and send the original point cloud data to the braking control device.

[0020] According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the methods related to any of the above embodiments are implemented.

[0021] According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product, including computer instructions, wherein when the computer instructions are executed by a processor, the methods related to any of the above embodiments are implemented.

[0022] Through the following detailed description of the exemplary embodiments of the present disclosure with reference to the accompanying drawings, other features and advantages of the present disclosure will become clear. Description of the Drawings

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0024] Figure 1 It is a schematic flow chart of a braking control method according to an embodiment of the present disclosure.

[0025] Figure 2 It is a schematic diagram of braking control according to an embodiment of the present disclosure.

[0026] Figure 3 It is a schematic structural diagram of a braking control device according to an embodiment of the present disclosure.

[0027] Figure 4 It is a schematic structural diagram of an intelligent driving vehicle according to an embodiment of the present disclosure. Detailed Embodiments

[0028] Next, the technical solutions in the embodiments of the present disclosure will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and in no way limits the present disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present disclosure.

[0029] Unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure.

[0030] At the same time, it should be understood that, for the sake of description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationship.

[0031] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods, and devices should be regarded as part of the authorization specification.

[0032] In all the examples shown and discussed here, any specific value should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values.

[0033] It should be noted that: like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0034] Figure 1 It is a schematic flowchart of a braking control method according to an embodiment of the present disclosure. In some embodiments, the following braking control method is executed by a braking control device in an intelligent driving vehicle, including steps 11-13.

[0035] In step 11, a motion perception model is used to process the point cloud data at the current moment and the point cloud data at the previous moment collected by the lidar to obtain the position information, motion information, and category information of each target point in the target point set.

[0036] Compared with millimeter-wave radar, the point cloud of lidar is dense and includes richer semantic and geometric information.

[0037] In some embodiments, the motion information of each target point includes the speed information, acceleration information, and angular velocity information of each target point.

[0038] It should be noted here that the motion perception model can utilize the point cloud data at the current moment and the point cloud data at the previous moment to extract spatio-temporal semantic information, thereby outputting rich information about the target points. For example, the output of the motion perception model includes the position information (x, y), velocity information (vx, vy), acceleration information (ax, ay), angular velocity information (w), and category information (objType) of the target points, so as to be able to completely describe the targets in the scene.

[0039] In some embodiments, background points in the original point cloud data collected by the lidar at the current moment are deleted to obtain the point cloud to be processed. Next, the point cloud to be processed is voxelized to obtain the point cloud data at the current moment.

[0040] It should be noted here that background points in the original point cloud data (for example, point cloud data related to the ground) will interfere with braking control and even cause a large number of emergency braking false triggers. Therefore, by deleting the background points in the original point cloud data, the occurrence of emergency braking false triggers can be effectively avoided.

[0041] In some embodiments, the background points in the original point cloud data are deleted through a clustering algorithm. For example, the clustering algorithm includes the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm.

[0042] In step 12, according to the position information, motion information, and category information of each target point, the target point set is clustered to identify the target object.

[0043] It should be noted here that multiple target points on the same object have consistent information. For example, target points located on the same car should have the same speed, acceleration, and category information, and at the same time, the position deviation between the target points located on the same car should also be within a predetermined range.

[0044] In some embodiments, the target point set is cleaned to delete abnormal target points in the target point set. Next, in the cleaned target point set, target points with the same position information, the same motion information, and the same category information are clustered to identify the target object.

[0045] For example, the clustering algorithm includes the DBSCAN algorithm.

[0046] It should be noted here that by cleaning the target set, outliers can be deleted, thereby effectively reducing the occurrence of false triggering of emergency braking.

[0047] For example, using the above processing, the following information can be obtained: a car is located in front of the intelligent driving vehicle , the speed is , the acceleration is , the angular velocity is 15 degrees counterclockwise per second.

[0048] In some embodiments, after the target object is identified, it is determined whether the target object is included in the target point set obtained at the previous M moments before the current moment, where M is a natural number greater than 0. If the target object is included in the target point set obtained at the previous M moments, the following step 13 is performed. If the target object is not included in the target point set obtained at the previous M moments, emergency braking is not performed on the intelligent driving vehicle.

[0049] It should be noted here that if the target object is recognized at the current moment, but not recognized at the M moments before the current moment, it means that the target object is recognized for the first time, which may be an erroneous result caused by interference from background points. Therefore, in this case, there is no need to perform emergency braking on the intelligent driving vehicle.

[0050] If the target object is identified at the current moment and the target object is also identified at the M moments before the current moment, it indicates that the target object does exist. In this case, the following step 13 is performed to perform the operation of braking control on the intelligent driving vehicle.

[0051] It should also be noted that if the value of parameter M is too large, the processing time of the brake control device may be too long. Since the vehicle is usually traveling at a high speed, a vehicle collision may occur before the brake control device completes the judgment process. To avoid this, the value of M is not greater than 3. For example, M is 1.

[0052] In step 13, the intelligent driving vehicle is braked according to the current motion information of the intelligent driving vehicle, the position information and motion information of the target object, the braking distance of the intelligent driving vehicle currently performing the braking operation, and the orientation of the target object relative to the intelligent driving vehicle.

[0053] For example, the current motion information of the intelligent driving vehicle includes information such as the speed and acceleration of the intelligent driving vehicle, and also includes the driving trajectory of the intelligent driving vehicle in the future.

[0054] In some embodiments, the steps of performing braking control on an intelligent driving vehicle include the following.

[0055] 1) Based on the current motion information of the intelligent driving vehicle and the position and motion information of the target object, determine whether there is a risk of collision between the intelligent driving vehicle and the target object within the braking distance.

[0056] 2) When there is a risk of collision between the intelligent driving vehicle and the target within the braking distance, determine whether the target is in front of the intelligent driving vehicle according to the position information of the target.

[0057] 3) When the target is in front of the intelligent driving vehicle, control the intelligent driving vehicle to perform a braking operation.

[0058] In some embodiments, when the target is behind or on the side of the intelligent driving vehicle, no braking is performed on the intelligent driving vehicle.

[0059] It should be noted here that when there is a risk of collision between the target and the intelligent driving vehicle, and the target is behind or on the side of the intelligent driving vehicle, the possible collision is a passive collision for the intelligent driving vehicle. In this case, if the intelligent driving vehicle performs braking or other operations, it may not be conducive to the avoidance operation of the target, and at the same time, a rear-end collision is more likely to occur. Therefore, in this case, the braking control device does not perform braking on the intelligent driving vehicle.

[0060] In some embodiments, when the target is in front of the intelligent driving vehicle, determine whether the moving direction of the target is the same as that of the intelligent driving vehicle according to the current motion information of the intelligent driving vehicle and the motion information of the target. When the moving direction of the target is the same as that of the intelligent driving vehicle, control the intelligent driving vehicle to perform a braking operation.

[0061] That is to say, when there is a risk of collision between the target and the intelligent driving vehicle, the target is in front of the intelligent driving vehicle, and the moving direction of the target is the same as that of the intelligent driving vehicle. In this case, the intelligent driving vehicle may have a rear-end collision with the target in front. Therefore, in this case, the braking control device controls the intelligent driving vehicle to perform a braking operation to avoid a rear-end collision with the target in front.

[0062] In some embodiments, when the moving direction of the target is opposite to that of the intelligent driving vehicle, no braking is performed on the intelligent driving vehicle.

[0063] That is to say, when there is a risk of collision between the target and the intelligent driving vehicle, the target is in front of the intelligent driving vehicle, and the moving direction of the target is opposite to that of the intelligent driving vehicle. In this case, the target is moving in the opposite direction relative to the intelligent driving vehicle. Usually in this case, the target in the reverse driving state will take corresponding avoidance measures. If the intelligent driving vehicle performs emergency braking at this time, it may cause the vehicle behind the intelligent driving vehicle to have a rear-end collision with the intelligent driving vehicle. Therefore, in this case, the braking control device does not perform braking on the intelligent driving vehicle.

[0064] In some embodiments, when the moving direction of the target object is the same as that of the intelligent driving vehicle, the position information and movement information of the target object at the previous N moments before the current moment are obtained, where N is a natural number greater than 0. If the change amount of the relative position between the intelligent driving vehicle and the target object at the current moment and the previous N moments is not within a predetermined range, the intelligent driving vehicle is controlled to perform a braking operation.

[0065] That is to say, if the change amount of the relative position between the intelligent driving vehicle and the target object at the current moment and the previous N moments is not within a predetermined range, it indicates that the intelligent driving vehicle and the target object are not in a state of accompanying driving. In this case, the braking control device controls the intelligent driving vehicle to perform a braking operation.

[0066] In some embodiments, if the change amount of the relative position between the intelligent driving vehicle and the target object at the current moment and the previous N moments is within a predetermined range, no braking is performed on the intelligent driving vehicle.

[0067] That is to say, if the change amount of the relative position between the intelligent driving vehicle and the target object at the current moment and the previous N moments is within a predetermined range, it indicates that the intelligent driving vehicle and the target object are in a state of accompanying driving. In this case, the braking control device does not perform braking on the intelligent driving vehicle.

[0068] It should be noted here that if the intelligent driving vehicle and the target object are in a state of accompanying driving, it means that although the distance between the intelligent driving vehicle and the target object is relatively close, the probability of collision is very small. Therefore, in this case, the braking control device does not perform braking on the intelligent driving vehicle.

[0069] For example, at the current moment and the previous N moments, if the driving directions of the intelligent driving vehicle and the target object are the same, the azimuth of the target object relative to the intelligent driving vehicle does not change, and the change amount of the distance between the target object and the intelligent driving vehicle is within a predetermined range, it is determined that the intelligent driving vehicle and the target object are in a state of accompanying driving.

[0070] It should also be noted here that if the value of the parameter N is too large, it may cause the processing time of the braking control device to be too long. Since the driving speed of the vehicle is usually relatively fast, it may happen that the vehicle collides before the braking control device finishes the judgment process. To avoid this situation, the value of N is not greater than 3. For example, N is set to 1.

[0071] Figure 2 This is a schematic diagram of braking control according to an embodiment of the present disclosure.

[0072] As Figure 2 shown, the original point cloud data collected by the lidar at the current moment T is preprocessed to obtain the point cloud data at moment T.

[0073] For example, by deleting the background points in the original point cloud data, the point cloud to be processed is obtained. The point cloud to be processed is voxelized to obtain the point cloud data at time T.

[0074] The point cloud data at the current time T and the point cloud data at time T-1 are input into the motion perception network, so that the motion perception network outputs the position information, velocity information, acceleration information, angle information, and category information of each target point in the target point set.

[0075] Next, according to the position information, motion information, and category information of each target point, the target point set is clustered to identify the target object.

[0076] Then, the braking control device performs braking control on the intelligent driving vehicle according to the current motion information of the intelligent driving vehicle, the position information and motion information of the target object, the braking distance at which the intelligent driving vehicle currently performs the braking operation, and the orientation of the target object relative to the intelligent driving vehicle.

[0077] Figure 3 It is a schematic structural diagram of a braking control device according to an embodiment of the present disclosure.

[0078] As Figure 3 shown, the braking control device 30 is presented in the form of a general computing device. The braking control device 30 includes a memory 31, a processor 32, and a bus 33 connecting different system components.

[0079] The memory 31 may include, for example, a system memory, a non-volatile storage medium, etc. The system memory stores, for example, an operating system, application programs, a boot loader, and other programs. The system memory may include a volatile storage medium, such as a random access memory (RAM) and / or a cache memory. The non-volatile storage medium stores, for example, instructions corresponding to at least one embodiment of the braking control method in execution. The non-volatile storage medium includes, but is not limited to, a disk memory, an optical memory, a flash memory, etc.

[0080] The processor 32 may be implemented in the form of a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor and other discrete hardware components. Correspondingly, each module, such as an acquisition module, a calculation module, and an adjustment module, may be implemented by a central processing unit (CPU) running instructions for executing corresponding steps in the memory, or may be implemented by a dedicated circuit for executing the corresponding steps.

[0081] For example, the processor 32 is configured to execute based on the instructions stored in the memory to implement as Figure 1The method involved in any of the embodiments

[0082] The bus 33 can use any of a variety of bus structures. For example, the bus structure includes, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, and a Peripheral Component Interconnect (PCI) bus.

[0083] These interfaces 34, 35, 36 of the brake control device 30, as well as the memory 31 and the processor 32, can be connected through the bus 33. The input / output interface 34 can provide a connection interface for input / output devices such as a display, a mouse, and a keyboard. The network interface 35 provides a connection interface for various networking devices. The storage interface 36 provides a connection interface for external storage devices such as a floppy disk, a USB flash drive, and an SD card.

[0084] Here, various aspects of the present disclosure have been described with reference to the flowcharts and / or block diagrams of methods, apparatuses, and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of the blocks, can be implemented by computer-readable program instructions.

[0085] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable devices to generate a machine, such that the device implemented by executing the instructions by the processor performs the functions specified in one or more blocks in the flowchart and / or block diagram.

[0086] These computer-readable program instructions can also be stored in a computer-readable memory, and these instructions cause the computer to work in a specific manner, thereby generating a manufactured article including instructions for implementing the functions specified in one or more blocks in the flowchart and / or block diagram.

[0087] The present disclosure can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

[0088] The present disclosure also provides a computer-readable storage medium, in which computer instructions are stored, and when the instructions are executed by a processor, the method involved in any of the embodiments as Figure 1 is implemented.

[0089] The present disclosure also provides a computer program product, including computer instructions, and when the computer instructions are executed by a processor, the method involved in any of the embodiments as Figure 1 is implemented.

[0090] Figure 4 is a schematic structural diagram of an intelligent driving vehicle according to an embodiment of the present disclosure. As Figure 4 shown, the intelligent driving vehicle includes a brake control device 41 and a lidar 42. The brake control device 41 includes Figure 2The braking control device according to any one of the embodiments.

[0091] The lidar 42 is configured to collect the original point cloud data around the intelligent driving vehicle and send the original point cloud data to the braking control device 41.

[0092] The present disclosure obtains the position information, motion information, and category information of each target point by using the point cloud data collected by the lidar at the current moment and the previous moment, identifies the target object by clustering the target points, and then performs braking control on the intelligent driving vehicle according to the current motion information of the intelligent driving vehicle, the braking distance when performing the braking operation currently, the position information and motion information of the target object, and the orientation of the target object relative to the intelligent driving vehicle, so as to ensure the driving safety of the intelligent driving vehicle through precise braking control.

[0093] In some embodiments, the above-described functional modules can be implemented as a general-purpose processor, a programmable logic controller (PLC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or any suitable combination thereof for performing the functions described in the present disclosure.

[0094] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware or by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a magnetic disk, or an optical disc, etc.

[0095] The description of the present disclosure is given for purposes of illustration and description, and is not intended to be exhaustive or to limit the present disclosure to the disclosed form. Many modifications and variations are obvious to those of ordinary skill in the art. The embodiments are chosen and described in order to better illustrate the principles and practical applications of the present disclosure, and to enable those of ordinary skill in the art to understand the present disclosure and design various embodiments suitable for specific purposes with various modifications.

Claims

1. A braking control method, performed by a braking control device in an intelligent driving vehicle, comprising: The point cloud data at the current moment and the point cloud data at the previous moment collected by the laser radar are processed by using the motion perception model to obtain the position information, motion information and category information of each target point in the target point set, wherein the motion information of each target point includes the speed information, acceleration information and angular velocity information of each target point; Clustering the target point set according to the position information, motion information and category information of each target point to identify the target object; Performing braking control on the intelligent driving vehicle according to the current motion information of the intelligent driving vehicle, the position information and motion information of the target object, the braking distance of the intelligent driving vehicle currently performing the braking operation, and the orientation of the target object relative to the intelligent driving vehicle; The step of performing braking control on the intelligent driving vehicle includes: Determining whether there is a risk of collision between the intelligent driving vehicle and the target object within the braking distance according to the current motion information of the intelligent driving vehicle and the position information and motion information of the target object; When there is a risk of collision between the intelligent driving vehicle and the target object within the braking distance, judging whether the target object is located in front of the intelligent driving vehicle according to the position information of the target object; When the target object is located in front of the intelligent driving vehicle, judging whether the movement direction of the target object is the same as the movement direction of the intelligent driving vehicle according to the current movement information of the intelligent driving vehicle and the movement information of the target object; When the moving direction of the target object is the same as the moving direction of the intelligent driving vehicle, obtaining the position information and movement information of the target object at N moments before the current moment, where N is a natural number greater than 0; If the change in the relative position of the intelligent driving vehicle and the target object between the current moment and the previous N moments is not within a predetermined range, the intelligent driving vehicle is controlled to perform a braking operation.

2. The braking control method according to claim 1, wherein: The braking control of the intelligent driving vehicle includes: In the case where the target object is located behind or on the side of the intelligent driving vehicle, the intelligent driving vehicle is not braked.

3. The braking control method according to claim 1, wherein: When the target object is located in front of the intelligent driving vehicle, controlling the intelligent driving vehicle to perform a braking operation includes: When the moving direction of the target object is opposite to the moving direction of the intelligent driving vehicle, the intelligent driving vehicle is not braked.

4. The brake control method according to claim 1, wherein: The braking control of the intelligent driving vehicle includes: If the change in the relative position between the intelligent driving vehicle and the target object between the current moment and the previous N moments is within a predetermined range, the intelligent driving vehicle is not braked.

5. The brake control method according to claim 1, further comprising: After the target object is identified, it is determined whether the target object is included in the target point set obtained at M moments before the current moment, where M is a natural number greater than 0; In a case where the target point set obtained at the first M moments includes the target object, braking control is performed on the intelligent driving vehicle.

6. The braking control method according to claim 5, further comprising: When the target object is not included in the target point set obtained at the first M moments, emergency braking is not performed on the intelligent driving vehicle.

7. The braking control method according to any one of claims 1 to 6, further comprising: Deleting background points in the original point cloud data collected by the laser radar at the current moment to obtain a point cloud to be processed; The point cloud to be processed is voxelized to obtain the point cloud data at the current moment.

8. The braking control method according to any one of claims 1 to 6, wherein: The clustering of the target point set comprises: Cleaning the target point set to delete abnormal target points in the target point set; In the cleaned target point set, target points with the same position information, the same motion information and the same category information are clustered to identify the target object.

9. A brake control device, comprising: Memory; A processor is coupled to the memory, and the processor is configured to execute the brake control method according to any one of claims 1 to 8 based on instructions stored in the memory.

10. An intelligent driving vehicle, comprising: The brake control device according to claim 9; The laser radar is configured to collect raw point cloud data around the intelligent driving vehicle and send the raw point cloud data to the braking control device.

11. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the braking control method according to any one of claims 1 to 8 is implemented.

12. A computer program product, comprising computer instructions, wherein when the computer instructions are executed by a processor, the brake control method according to any one of claims 1 to 8 is implemented.

Images