Vehicle braking control method, device, equipment and medium

Abstract

The invention discloses a vehicle braking control method, device and equipment and a medium. The method comprises the following steps: acquiring perception target information returned by a plurality of perception sensors, and identifying a collision target according to the perception target information; acquiring multiple features of the collision target, and performing misrecognition judgment on the collision target according to the features of the collision target and the multi-dimensional filtering condition; when it is determined that the collision target belongs to the correct recognition target, an emergency braking scheme is determined according to the characteristics of the collision target and the vehicle movement information, so that a vehicle braking actuator controls a vehicle braking system to conduct braking according to the emergency braking scheme. By the adoption of the technical scheme, the target which may be collided can be accurately recognized, secondary filtering is carried out on the target, the problem that in the prior art, mistaken recognition is often carried out on the collided target is solved, and therefore the reliability of vehicle emergency braking is improved, and driving safety is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a vehicle braking control method, device, equipment and medium. Background Technology

[0002] Forward collision warning and automatic emergency braking can assist drivers in emergency braking when faced with dangerous situations, thereby actively avoiding collisions and improving driving safety. However, automatic emergency braking relies on the accurate identification of various targets on the road. If the target identification results are inaccurate, it may lead to the vehicle braking unnecessarily, affecting the driving experience and even causing rear-end collisions.

[0003] In existing technologies, automatic emergency braking relies on data returned by perception sensors installed on the vehicle. If the perception sensors return a target that may be involved in a collision, the automatic emergency braking process is initiated directly.

[0004] However, sensing sensors inevitably experience false detections and missed detections. Relying solely on the detection results of sensing sensors may lead to false triggering of automatic emergency braking. Summary of the Invention

[0005] This invention provides a vehicle braking control method, device, equipment, and medium that can accurately identify targets that may collide with the vehicle and perform secondary filtering on the targets. This solves the problem of frequent misidentification of collision targets in the prior art, thereby improving the reliability of vehicle emergency braking and ensuring driving safety.

[0006] According to one aspect of the present invention, a vehicle braking control method is provided, comprising:

[0007] Acquire target information returned by multiple sensing sensors and identify collision targets based on the target information;

[0008] The system acquires multiple features of the collision target and determines the collision target as a false positive based on these features and multi-dimensional filtering conditions.

[0009] When the collision target is determined to be a correctly identified target, an emergency braking plan is determined based on the characteristics of the collision target and the vehicle's motion information, so that the vehicle's brake actuator can control the vehicle's braking system to brake according to the emergency braking plan.

[0010] According to another aspect of the present invention, a vehicle braking control device is provided, comprising:

[0011] The collision target recognition module is used to acquire the perception target information returned by multiple perception sensors and identify the collision target based on the perception target information.

[0012] The false identification judgment module is used to acquire multiple features of the collision target and, based on the features of the collision target and multi-dimensional filtering conditions, to judge the collision target as a false target.

[0013] The emergency braking control module is used to determine an emergency braking plan based on the characteristics of the collision target and the vehicle's motion information when the collision target is determined to be a correctly identified target. This plan is then used by the vehicle's brake actuator to control the vehicle's braking system to apply the brakes.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle braking control method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle braking control method according to any embodiment of the present invention.

[0019] The technical solution of this invention acquires target information returned by multiple sensing sensors, identifies collision targets based on this information, obtains multiple features of the collision targets, and determines whether a collision target is a false target based on these features and multi-dimensional filtering conditions. When a collision target is determined to be a correctly identified target, an emergency braking scheme is determined based on the characteristics of the collision target and vehicle motion information. This scheme allows the vehicle brake actuator to control the vehicle braking system to brake according to the emergency braking scheme. This method can accurately identify targets that may collide and perform secondary filtering on the targets, solving the problem of frequent false identification of collision targets in the prior art. It effectively reduces the false braking rate of the automatic emergency braking system during normal road driving, thereby improving driving safety and comfort, optimizing the driver's driving experience, and ensuring driving safety.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a vehicle braking control method provided in Embodiment 1 of the present invention;

[0023] Figure 2 This is a flowchart of another vehicle braking control method provided according to Embodiment 2 of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of a vehicle braking control device according to Embodiment 3 of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the vehicle braking control method of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] Figure 1This is a flowchart of a vehicle braking control method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where a collision target that may occur between the vehicle and the vehicle is accurately identified and emergency braking is triggered. This method can be executed by a vehicle braking control device, which can be implemented in hardware and / or software, and is generally configured in a vehicle infotainment system or central controller with data processing capabilities. Figure 1 As shown, the method includes:

[0030] S110. Obtain the target information returned by multiple sensing sensors and identify the collision target based on the target information.

[0031] This process of acquiring target information returned by multiple sensing sensors and identifying collision targets based on that information may include:

[0032] The system acquires target information returned by multiple sensing sensors and performs data fusion on the target information using a spatiotemporal calibration algorithm to generate a structured dataset for each target.

[0033] Based on the structured datasets of each sensing target, the multi-dimensional risk factors of each sensing target are determined, and the risk entropy value of each sensing target is calculated based on the multi-dimensional risk factors.

[0034] Based on the risk entropy value of each sensing target, the collision target with the highest collision risk is determined among all sensing targets.

[0035] Optionally, perception sensors can refer to a set of sensors at the front / around the vehicle used to detect external targets, including but not limited to cameras, millimeter-wave radar, lidar, etc. Perception sensors can collect information about the vehicle's surrounding environment in real time.

[0036] Optionally, the perceived target information may refer to the preliminary processed data output by the sensing sensor, including but not limited to basic target information, spatiotemporal information, motion information, feature information, and classification information.

[0037] Optionally, the target basic information may include whether the target was detected; the spatiotemporal information may include the target's relative position, timestamp, etc.; the motion information may include the target's relative velocity, direction of motion, and acceleration, etc.; the feature information may include the target's size, point cloud information, etc.; and the classification information may include the target type label and confidence level.

[0038] Optionally, the spatiotemporal calibration algorithm may include time calibration and spatial calibration. Time calibration may refer to unifying the timestamps of data from various sensors through the vehicle clock, and controlling the error within a specified time threshold, such as controlling the error within 1ms. Spatial calibration may refer to transforming the target coordinates of different sensors to the vehicle coordinate system based on external parameters such as the installation position and angle of the sensors.

[0039] Optionally, a structured dataset can refer to a standardized set of target data generated after spatiotemporal calibration of multi-sensor data. The core fields of a structured dataset for sensing targets may include: unique target identifier, timestamp, position, velocity, acceleration, target type, size, point cloud density, occlusion rate, historical trajectory, etc.

[0040] Optionally, the multi-dimensional risk factors can refer to a set of core indicators that quantify the collision threat posed by the perceived target to the vehicle. These can include dynamic collision time, behavioral uncertainty, vehicle response capability (such as the vehicle's current braking performance deviation rate), environmental attenuation coefficient, and field of vision obstruction factor. The multi-dimensional risk factors are then normalized, and a weighted calculation is performed based on the weight of each risk factor after normalization. The weighted calculation result is used as the risk entropy value. The risk entropy value can be used to quantify the collision risk between the vehicle and each perceived target. The higher the risk entropy value, the greater the probability of collision risk.

[0041] Optionally, the target with the highest risk threshold can be identified as the collision target.

[0042] S120. Obtain multiple features of the collision target, and determine the collision target as a false positive based on the features of the collision target and multi-dimensional filtering conditions.

[0043] Optionally, the multi-dimensional filtering conditions can refer to four core conditions used to determine whether a collision target is misidentified. If any one of these conditions is met, it is determined to be a misidentification.

[0044] This process, which involves acquiring multiple features of the collision target and determining whether a collision target is falsely identified based on these features and multi-dimensional filtering conditions, may include:

[0045] The system acquires multiple features of the collision target and determines whether the target meets any of the multi-dimensional filtering conditions based on these features. These multi-dimensional filtering conditions include abnormal changes in motion features, abnormal drift in position features, abnormal splitting of the target, and target classification errors.

[0046] If so, the collision target is determined to be a misidentified target, and the emergency braking procedure is not triggered;

[0047] If not, then the collision target is determined to be a correctly identified target.

[0048] Optionally, abnormal changes in motion features can refer to changes in motion parameters exceeding physical limits in consecutive frames, such as a pedestrian's speed suddenly changing from 1 m / s to 8 m / s; abnormal drift in position features can refer to cumulative position offsets exceeding sensor noise limits across multiple frames, such as a stationary target shifting more than 0.5 meters within 5 frames; abnormal splitting of targets can refer to a single real target being mistakenly split into multiple targets, such as targets with a spacing of less than 1 meter and consistent motion after splitting; and incorrect target classification can refer to a contradiction between classification labels and physical attributes, such as a pedestrian label corresponding to a size that exceeds or is smaller than the range of human body dimensions.

[0049] S130. When it is determined that the collision target is a correctly identified target, an emergency braking plan is determined based on the characteristics of the collision target and the vehicle motion information, so that the vehicle brake actuator can control the vehicle braking system to brake according to the emergency braking plan.

[0050] Optionally, vehicle motion information is the dynamic state data of the vehicle itself, which can be obtained by the vehicle's onboard sensors. These sensors may include, but are not limited to, wheel speed sensors and inertial measurement units. Vehicle motion information may include, but is not limited to, current vehicle speed, longitudinal acceleration, steering angle, yaw rate, current brake pedal displacement, and brake fluid pressure.

[0051] Optionally, the emergency braking scheme is a control strategy based on the characteristics of the collision target and the vehicle's motion information. The emergency braking scheme may include information such as the required deceleration, braking distance, and braking trigger timing. By executing the emergency braking scheme, the vehicle can avoid a collision with the collision target and ensure the safety of both the vehicle and the collision target.

[0052] The technical solution of this invention acquires target information returned by multiple sensing sensors, identifies collision targets based on this information, obtains multiple features of the collision targets, and determines whether a collision target is a false target based on these features and multi-dimensional filtering conditions. When a collision target is determined to be a correctly identified target, an emergency braking scheme is determined based on the characteristics of the collision target and vehicle motion information. This scheme allows the vehicle brake actuator to control the vehicle braking system to brake according to the emergency braking scheme. This method can accurately identify targets that may collide and perform secondary filtering on the targets, solving the problem of frequent false identification of collision targets in the prior art. It effectively reduces the false braking rate of the automatic emergency braking system during normal road driving, thereby improving driving safety and comfort, optimizing the driver's driving experience, and ensuring driving safety.

[0053] Example 2

[0054] Figure 2This is a flowchart of a vehicle braking control method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment specifically illustrates the process of misidentifying and determining a collision target. For example... Figure 2 As shown, the method includes:

[0055] S210. Acquire the target information returned by multiple sensing sensors, and perform data fusion on the target information through a spatiotemporal calibration algorithm to generate a structured dataset for each target.

[0056] S220. Based on the structured dataset of each sensing target, determine the multi-dimensional risk factors for each sensing target, and calculate the risk entropy value of each sensing target based on the multi-dimensional risk factors.

[0057] S230. Based on the risk entropy value of each perceived target, determine the collision target with the highest collision risk among all perceived targets.

[0058] S240. Obtain multiple features of the collision target, and determine whether the collision target meets any of the multi-dimensional filtering conditions based on the features of the collision target; if yes, proceed to step S250; if no, proceed to step S260.

[0059] The multi-dimensional filtering conditions include abnormal jumps in motion features, abnormal drifts in position features, abnormal splitting of the target, and target classification errors.

[0060] Among these, determining whether any one of the multi-dimensional filtering conditions is satisfied based on the characteristics of the collision target can include:

[0061] Based on the motion characteristics and classification labels of the collision target in consecutive frames, determine whether the motion characteristics of the collision target conform to the physical constraints corresponding to the classification labels.

[0062] If so, then a temporal consistency check is performed based on the motion characteristics. If the temporal consistency check fails, then it is determined that the motion characteristics have an abnormal jump.

[0063] If not, then the abnormal jump in motion characteristics is confirmed.

[0064] Optionally, the motion features and classification labels of the collision target in consecutive frames can be extracted from the structured dataset of the collision target, and then physical constraint judgment can be performed. If a motion parameter in any frame in the consecutive frames exceeds the constraint threshold of the corresponding classification label, it is determined that it does not meet the physical constraint. For example, the speed constraint threshold for pedestrians is 7 m / s. When the classification label is pedestrian and the speed is 8.5 m / s, it exceeds the upper limit of the speed constraint threshold and does not meet the physical constraint.

[0065] Optionally, the constraint threshold can be adapted to the current vehicle scenario. For example, if the current scenario is rainy or snowy, the physical constraint threshold can be adjusted appropriately. For instance, the upper limit of the acceleration constraint can be appropriately reduced to avoid misjudgment due to environmental interference.

[0066] The timing consistency check based on the motion characteristics may include:

[0067] Based on the motion parameter sequence of each motion parameter in consecutive frames, calculate the mean and standard deviation of each motion parameter, and calculate the standard interval of each motion parameter corresponding to the target confidence based on the mean and standard deviation.

[0068] If the target motion parameters exceed their corresponding standard range in two consecutive image frames, then the timing consistency check is deemed to have failed.

[0069] Optionally, timing consistency verification is used to detect situations where motion parameters are within the physical range but there are irregular abrupt changes in timing.

[0070] Optionally, the motion parameter sequence can refer to an ordered set of data formed in consecutive frames for a single motion parameter of the colliding target.

[0071] Optionally, the target confidence level can be determined based on the statistical laws of the normal distribution; for example, the target confidence level can be set to 99.7%.

[0072] Optionally, the standard interval is a statistical confidence interval calculated based on the mean and standard deviation of the motion parameter sequence.

[0073] Among these, determining whether a condition in the multi-dimensional filtering criteria is satisfied based on the characteristics of the collision target can include:

[0074] Based on the positional characteristics of the collision target within consecutive frames, obtain the fitted trajectory of the collision target within consecutive frames;

[0075] Calculate the mean positional residual based on the positional features of each image frame and the fitted trajectory;

[0076] If the mean value of the position residual is greater than the preset residual threshold, then the position feature of the collision target is determined to be abnormally drifted.

[0077] Optionally, the position features may include information such as the coordinates of the colliding target in each frame, the cumulative position offset in consecutive frames, and position stability.

[0078] Optionally, the fitted trajectory can be used to quantify the deviation between the actual position and the ideal motion law. Based on the position characteristics and the fitting algorithm, the fitted trajectory of the colliding target in consecutive frames can be calculated.

[0079] Optionally, the mean position residual is the average deviation between the actual position features and the fitted trajectory in each frame of a continuous series of frames. It can reflect the overall level of deviation of the actual position from the ideal trajectory. The position residual of a single frame can be calculated first, which is the Euclidean distance between the actual coordinates of each frame and the corresponding coordinates of the fitted trajectory. Then, the arithmetic mean of the single frame residuals of the continuous series of frames can be taken to obtain the mean position residual. The larger the mean residual, the more serious the position drift.

[0080] Among these, determining whether any one of the multi-dimensional filtering conditions is satisfied based on the characteristics of the collision target can include:

[0081] Based on the shape and motion characteristics of the collision target, determine whether the collision target conforms to the physical attributes of the target classification.

[0082] If so, perform a classification time stability test; if the classification time stability test fails, the target classification is determined to be incorrect.

[0083] If not, then the target classification is directly determined to be incorrect.

[0084] Optionally, the shape features of the collision target may include features such as three-dimensional size, point cloud morphology, visual contour features, and shape integrity.

[0085] Optionally, if the shape or motion features exceed the range of physical attributes for the corresponding classification, then the collision target is determined to be a physical attribute that does not conform to the target classification.

[0086] Optionally, classification temporal stability detection refers to the detection process that verifies whether the classification labels of colliding targets remain smooth and consistent in consecutive frames. Classification temporal stability detection can eliminate instantaneous classification misjudgments and ensure the temporal continuity of classification results.

[0087] Optionally, the classification temporal stability detection includes the following detection items: classification consistency ratio, classification jump magnitude, and jump recoverability. The classification consistency ratio can refer to the percentage of frames with the same classification label as the current frame within the sliding window. If the percentage is less than a certain ratio, the classification consistency detection is determined to have failed. The classification jump magnitude can refer to the jump magnitude of the classification labels of consecutive frames based on a semantic distance dictionary. If the semantic distance is greater than a specified distance threshold, it is considered an abnormal jump. The jump recoverability detection refers to determining whether the subsequent frame recovers to the original classification if a single frame classification jump occurs. If it does, it is considered a temporary misjudgment; otherwise, it is considered a continuous instability.

[0088] S250: If the collision target is determined to be a misidentified target, the emergency braking procedure is not triggered.

[0089] S260. Determine that the collision target is a correctly identified target and proceed to step S270.

[0090] S270. Based on the characteristics of the collision target and the vehicle motion information, determine an emergency braking plan so that the vehicle brake actuator can control the vehicle braking system to brake according to the emergency braking plan.

[0091] The technical solution of this invention acquires target information returned by multiple sensing sensors, identifies collision targets based on this information, obtains multiple features of the collision targets, and determines whether a collision target is a false target based on these features and multi-dimensional filtering conditions. When a collision target is determined to be a correctly identified target, an emergency braking scheme is determined based on the characteristics of the collision target and vehicle motion information. This scheme allows the vehicle brake actuator to control the vehicle braking system to brake according to the emergency braking scheme. This method can accurately identify targets that may collide and perform secondary filtering on the targets, solving the problem of frequent false identification of collision targets in the prior art. It effectively reduces the false braking rate of the automatic emergency braking system during normal road driving, thereby improving driving safety and comfort, optimizing the driver's driving experience, and ensuring driving safety.

[0092] Example 3

[0093] Figure 3 This is a schematic diagram of a vehicle braking control device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a collision target recognition module 310, a false recognition determination module 320, and an emergency braking control module 330.

[0094] The collision target recognition module 310 is used to acquire the perception target information returned by multiple perception sensors and to identify the collision target based on the perception target information.

[0095] The false identification judgment module 320 is used to acquire multiple features of the collision target and, based on the features of the collision target and multi-dimensional filtering conditions, to make a false identification judgment of the collision target.

[0096] The emergency braking control module 330 is used to determine an emergency braking plan based on the characteristics of the collision target and the vehicle motion information when it is determined that the collision target is a correctly identified target, so that the vehicle brake actuator can control the vehicle braking system to brake according to the emergency braking plan.

[0097] The technical solution of this invention acquires target information returned by multiple sensing sensors, identifies collision targets based on this information, obtains multiple features of the collision targets, and determines whether a collision target is a false target based on these features and multi-dimensional filtering conditions. When a collision target is determined to be a correctly identified target, an emergency braking scheme is determined based on the characteristics of the collision target and vehicle motion information. This scheme allows the vehicle brake actuator to control the vehicle braking system to brake according to the emergency braking scheme. This method can accurately identify targets that may collide and perform secondary filtering on the targets, solving the problem of frequent false identification of collision targets in the prior art. It effectively reduces the false braking rate of the automatic emergency braking system during normal road driving, thereby improving driving safety and comfort, optimizing the driver's driving experience, and ensuring driving safety.

[0098] Based on the above embodiments, the collision target recognition module 310 can be specifically used for:

[0099] The system acquires target information returned by multiple sensing sensors and performs data fusion on the target information using a spatiotemporal calibration algorithm to generate a structured dataset for each target.

[0100] Based on the structured datasets of each sensing target, the multi-dimensional risk factors of each sensing target are determined, and the risk entropy value of each sensing target is calculated based on the multi-dimensional risk factors.

[0101] Based on the risk entropy value of each sensing target, the collision target with the highest collision risk is determined among all sensing targets.

[0102] Based on the above embodiments, the misidentification determination module 320 can be specifically used for:

[0103] The system acquires multiple features of the collision target and determines whether the target meets any of the multi-dimensional filtering conditions based on these features. These multi-dimensional filtering conditions include abnormal changes in motion features, abnormal drift in position features, abnormal splitting of the target, and target classification errors.

[0104] If so, the collision target is determined to be a misidentified target, and the emergency braking procedure is not triggered;

[0105] If not, then the collision target is determined to be a correctly identified target.

[0106] Based on the above embodiments, the misidentification determination module 320 may include a motion feature jump detection unit, used for:

[0107] Based on the motion characteristics and classification labels of the collision target in consecutive frames, determine whether the motion characteristics of the collision target conform to the physical constraints corresponding to the classification labels.

[0108] If so, then a temporal consistency check is performed based on the motion characteristics. If the temporal consistency check fails, then it is determined that the motion characteristics have an abnormal jump.

[0109] If not, then the abnormal jump in motion characteristics is confirmed.

[0110] Based on the above embodiments, the motion feature jump detection unit can be further specifically used for:

[0111] Based on the motion parameter sequence of each motion parameter in consecutive frames, calculate the mean and standard deviation of each motion parameter, and calculate the standard interval of each motion parameter corresponding to the target confidence based on the mean and standard deviation.

[0112] If the target motion parameters exceed their corresponding standard range in two consecutive image frames, then the timing consistency check is deemed to have failed.

[0113] Based on the above embodiments, the misidentification determination module 320 may include a position feature drift detection unit, used for:

[0114] Based on the positional characteristics of the collision target within consecutive frames, obtain the fitted trajectory of the collision target within consecutive frames;

[0115] Calculate the mean positional residual based on the positional features of each image frame and the fitted trajectory;

[0116] If the mean value of the position residual is greater than the preset residual threshold, then the position feature of the collision target is determined to be abnormally drifted.

[0117] Based on the above embodiments, the misidentification determination module 320 may include a classification detection unit for:

[0118] Based on the shape and motion characteristics of the collision target, determine whether the collision target conforms to the physical attributes of the target classification.

[0119] If so, perform a classification time stability test; if the classification time stability test fails, the target classification is determined to be incorrect.

[0120] If not, then the target classification is directly determined to be incorrect.

[0121] The vehicle braking control device provided in the embodiments of the present invention can execute the vehicle braking control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0122] Example 4

[0123] Figure 4A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0124] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0125] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0126] Processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the vehicle braking control method described in the embodiments of the present invention. That is:

[0127] Acquire target information returned by multiple sensing sensors and identify collision targets based on the target information;

[0128] The system acquires multiple features of the collision target and determines the collision target as a false positive based on these features and multi-dimensional filtering conditions.

[0129] When the collision target is determined to be a correctly identified target, an emergency braking plan is determined based on the characteristics of the collision target and the vehicle's motion information, so that the vehicle's brake actuator can control the vehicle's braking system to brake according to the emergency braking plan.

[0130] In some embodiments, the vehicle braking control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle braking control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle braking control method by any other suitable means (e.g., by means of firmware).

[0131] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0132] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0133] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0134] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0135] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0136] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0137] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0138] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle brake control method characterized by, The method comprises the following steps: obtaining perception target information returned by a plurality of perception sensors, and identifying a collision target according to the perception target information; obtaining a plurality of features of the collision target, and performing misrecognition determination on the collision target according to the features of the collision target and a multi-dimensional filtering condition; when it is determined that the collision target belongs to a correct recognition target, determining an emergency braking scheme according to the features of the collision target and vehicle motion information, so that a vehicle braking actuator controls a vehicle braking system to brake according to the emergency braking scheme.

2. The method of claim 1, wherein, The method comprises the following steps: obtaining perception target information returned by a plurality of perception sensors, and identifying a collision target according to the perception target information, comprising: obtaining perception target information returned by a plurality of perception sensors, and performing data fusion on the perception target information through a space-time calibration algorithm to generate a structured data set of each perception target; determining a plurality of dimensional risk factors of each perception target according to the structured data set of each perception target, and calculating a risk entropy value of each perception target according to the plurality of dimensional risk factors; 3. The method of claim 1, wherein, determining a collision target with the largest collision risk among the perception targets according to the risk entropy values of the perception targets. The method comprises the following steps: obtaining a plurality of features of the collision target, and performing misrecognition determination on the collision target according to the features of the collision target and a multi-dimensional filtering condition, comprising: obtaining a plurality of features of the collision target, and determining whether any of the multi-dimensional filtering conditions is met according to the features of the collision target; wherein the multi-dimensional filtering conditions include motion feature abnormal jump, position feature abnormal drift, target abnormal splitting and target classification error; 4. The method of claim 3, wherein, if yes, it is determined that the collision target belongs to a misrecognition target, and the emergency braking process is not triggered; if no, it is determined that the collision target belongs to a correct recognition target. The method comprises the following steps: determining whether any of the multi-dimensional filtering conditions is met according to the features of the collision target, comprising:

5. The method of claim 4, wherein, determining whether the motion feature of the collision target conforms to the physical constraint corresponding to the classification label according to the motion feature and the classification label of the collision target in the continuous frames; if yes, performing time sequence consistency verification according to the motion feature, and if the time sequence consistency verification fails, it is determined that the motion feature abnormal jump is met; if no, it is determined that the motion feature abnormal jump is met.

6. The method of claim 3, wherein, The method comprises the following steps: performing time sequence consistency verification according to the motion feature, comprising: calculating the mean and standard deviation of each motion parameter according to the motion parameter sequence of each motion parameter in the continuous frames, and calculating the standard interval of each motion parameter corresponding to the target confidence according to the mean and standard deviation; if the target motion parameters in two continuous image frames all exceed the corresponding standard interval, it is determined that the time sequence consistency verification fails.

7. The method of claim 3, wherein, The method comprises the following steps: determining whether any of the multi-dimensional filtering conditions is met according to the features of the collision target, comprising: obtaining a fitting trajectory of the collision target in the continuous frames according to the position feature of the collision target in the continuous frames; calculating the position residual mean according to the position feature of each image frame and the fitting trajectory; if the position residual mean is greater than a preset residual threshold, it is determined that the position feature of the collision target is abnormally drifted. The method comprises the following steps: According to the shape feature and the motion feature of the collision target, it is judged whether the collision target meets the physical attribute of target classification; If yes, the classification time sequence stability detection is performed, and if the classification time sequence stability detection fails, it is determined that the target classification is wrong; If no, it is directly determined that the target classification is wrong.

8. A vehicle brake control device characterized by comprising: It comprises: a collision target identification module, configured to obtain the sensing target information returned by a plurality of sensing sensors, and identify the collision target according to the sensing target information; a misrecognition judgment module, configured to obtain a plurality of features of the collision target, and perform misrecognition judgment on the collision target according to the features of the collision target and multi-dimensional filtering conditions; an emergency braking control module, configured to determine an emergency braking scheme according to the features of the collision target and vehicle motion information when it is determined that the collision target belongs to a correct identification target, so that the vehicle braking actuator controls the vehicle braking system to brake according to the emergency braking scheme.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the vehicle braking control method in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, and the computer instructions are used to enable the processor to execute the vehicle braking control method in any one of claims 1-7 when executed.

Images