A static obstacle object recognition method and related device

Abstract

The present application relates to the field of automatic driving, and particularly relates to a static obstacle identification method and related equipment. The method comprises: acquiring m frames of point cloud data collected by a collection device; determining whether a target object that is continuously getting larger exists in the m frames of point cloud data; if the target object that is continuously getting larger exists, controlling the target vehicle to decelerate to a preset speed according to a preset deceleration strategy; acquiring a plurality of frames of point cloud data collected by a current collection device; determining whether the target object is a static obstacle according to the plurality of frames of point cloud data; and if the target object is a static obstacle, executing a corresponding avoidance strategy. In the embodiment of the present application, when a target object that is continuously getting larger is found in the collected point cloud data, the target vehicle is controlled to decelerate to a preset speed, and then whether the target object is a static obstacle is further determined according to the plurality of frames of point cloud data collected at present, so that the accuracy of static obstacle identification is improved.

Description

[Technical Field]

[0001] This invention relates to the field of autonomous driving, and in particular to a method and related equipment for identifying static obstacles. [Background Technology]

[0002] Current autonomous driving technology uses LiDAR to determine the presence of static obstacles in the vehicle's direction of travel. However, limited by the number of lines and detection range of LiDAR, it cannot accurately identify stationary or slowly moving obstacles at high speeds. For example, a 144-line LiDAR has a low accuracy rate in identifying static obstacles at speeds above 80 km / h, which can easily lead to misjudgments in autonomous driving mode, increasing the probability of accidents. [Summary of the Invention]

[0003] To address the aforementioned problems, embodiments of the present invention provide a method and related equipment for identifying static obstacles, which can improve the accuracy of identifying static obstacles.

[0004] In a first aspect, embodiments of the present invention provide a method for identifying static obstacles, comprising:

[0005] Acquire m frames of point cloud data collected by the acquisition device;

[0006] Determine whether there is a continuously increasing target object in the m-frame point cloud data;

[0007] If there is a target object that continues to grow larger, the target vehicle is controlled to decelerate to a preset speed according to a preset deceleration strategy.

[0008] Acquire multiple frames of point cloud data collected by the current acquisition device;

[0009] Determine whether the target object is a static obstacle based on the multi-frame point cloud data;

[0010] If the target object is a static obstacle, the corresponding avoidance strategy is executed.

[0011] In one possible implementation, controlling the target vehicle to decelerate to a preset speed according to a preset deceleration strategy includes:

[0012] Control the target vehicle to decelerate with an acceleration N;

[0013] When the speed change value of the target vehicle reaches the first threshold, it is determined whether the current speed of the target vehicle is less than or equal to the preset speed.

[0014] If not, the acceleration N is increased to continue deceleration and the speed change of the target vehicle is reassessed to see if it reaches the first threshold until the speed of the target vehicle is less than or equal to the preset speed.

[0015] In one possible implementation, before increasing the acceleration N to continue deceleration, the method further includes:

[0016] Acquire n frames of point cloud data during the deceleration process with acceleration N;

[0017] Determine whether the n frames of point cloud data meet the preset conditions;

[0018] If the preset conditions are met, the target object is determined not to be a static obstacle and deceleration stops;

[0019] If the preset conditions are not met, the acceleration N is increased to continue deceleration.

[0020] In one possible implementation, determining whether the n frames of point cloud data meet preset conditions includes:

[0021] Determine whether the target object in the n frames of point cloud data continues to grow larger;

[0022] If the target object in the n frames of point cloud data does not continue to grow larger, then the n frames of point cloud data are determined to meet the preset condition.

[0023] In one possible implementation, before determining whether a continuously increasing target object exists in the m-frame point cloud data, the method further includes:

[0024] Determine whether the current speed of the target vehicle is greater than the preset speed;

[0025] If so, then determine whether there is a continuously increasing target object in the m-frame point cloud data;

[0026] If not, determine whether a static obstacle exists based on the m-frame point cloud data.

[0027] In one possible implementation, executing the corresponding avoidance strategy includes:

[0028] Control the target vehicle to decelerate to a stop with acceleration M.

[0029] In one possible implementation, the value of the acceleration M is determined based on the distance between the target vehicle and the static obstacle.

[0030] Secondly, embodiments of the present invention provide a static obstacle recognition device, wherein the static obstacle recognition device is disposed on a target vehicle, comprising:

[0031] The acquisition module is used to acquire m frames of point cloud data collected by the acquisition device;

[0032] The processing module is used to determine whether there is a continuously increasing target object in the m-frame point cloud data;

[0033] The deceleration module is used to control the target vehicle to decelerate to a preset speed according to a preset deceleration strategy if there is a target object that is continuously growing larger.

[0034] The acquisition module is also used to acquire multi-frame point cloud data collected by the current acquisition device;

[0035] The processing module is further configured to determine whether the target object is a static obstacle object based on the multi-frame point cloud data;

[0036] The processing module is further configured to execute a corresponding avoidance strategy if the target object is a static obstacle object.

[0037] Thirdly, embodiments of the present invention provide an electronic device, comprising:

[0038] At least one processor; and

[0039] At least one memory communicatively connected to the processor, wherein:

[0040] The memory stores program instructions that can be executed by the processor, and the processor can execute the method described in the first aspect by calling the program instructions.

[0041] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions that cause the computer to perform the method described in the first aspect.

[0042] It should be understood that the second to fourth aspects of the embodiments of the present invention are consistent with the technical solutions of the first aspect of the embodiments of the present invention, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be described again.

[0043] In this embodiment of the invention, when a target object that continuously grows larger is detected in the collected point cloud data, the target vehicle is controlled to decelerate to a preset speed. Then, based on the currently collected multi-frame point cloud data, it is further determined whether the target object is a static obstacle. This improves the accuracy of static obstacle object recognition, enhances the safety of autonomous driving, and reduces the probability of accidents. [Attached Image Description]

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the 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.

[0045] Figure 1 A flowchart of a static obstacle object recognition method provided in an embodiment of the present invention;

[0046] Figure 2 A flowchart of another static obstacle object recognition method provided in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of the structure of a static obstacle object recognition device provided in an embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

Detailed Implementation Methods

[0049] To better understand the technical solutions in this specification, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0050] It should be understood that the described embodiments are merely some, not all, of the embodiments in this specification. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without inventive effort are within the scope of protection of this invention.

[0051] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0052] In this embodiment of the invention, when a target object that is continuously growing larger is found in the point cloud data, the vehicle speed is reduced to a preset speed that can accurately identify static obstacles before determining whether the target object is a static obstacle, thereby improving the accuracy of static obstacle identification.

[0053] Figure 1 This is a flowchart illustrating a static obstacle recognition method provided in an embodiment of the present invention. The executing entity of the static obstacle recognition method provided by the present invention can be an in-vehicle device with computing capabilities, such as a vehicle controller. Figure 1 As shown, the method includes:

[0054] Step 101: Acquire m frames of point cloud data collected by the acquisition device. The acquisition device can be a sensor such as a lidar. The lidar continuously scans at a preset frequency to generate point cloud data. Therefore, the m frames of point cloud data are the continuous multi-frame point cloud data obtained by the lidar scanning at the preset frequency.

[0055] Step 102: Determine whether there is a continuously increasing target object in the m-frame point cloud data. Optionally, since the LiDAR has continuously acquired m frames of data, the presence of a continuously increasing target object can be determined by whether there are continuously increasing points in several consecutive frames of point cloud data. For example, if the LiDAR has accumulated 120 frames of data at a frequency of 10Hz, and points with a progressive pattern are found in the most recent 5 consecutive frames of point cloud data, it can be determined that there is a target object that is suspected to be a static obstacle.

[0056] Step 103: If a target object continues to grow larger, the target vehicle is controlled to decelerate to a preset speed according to a preset deceleration strategy. The preset speed is determined based on the highest speed at which static obstacles are accurately identified. Therefore, when a target object suspected of being a static obstacle is present, the vehicle speed can be reduced to the preset speed to facilitate determination of whether the target object is indeed a static obstacle. For example, when the vehicle speed is below 80 km / h, the presence of static obstacles within the detection range can be accurately identified based on point cloud data. Therefore, the preset speed can be set accordingly to 80 km / h.

[0057] Step 104: Acquire multi-frame point cloud data collected by the current acquisition device. The multi-frame point cloud data refers to the point cloud data collected by the acquisition device after the vehicle speed decreases to a preset speed.

[0058] Step 105: Determine whether the target object is a static obstacle based on multi-frame point cloud data. Since the target vehicle's speed has decreased to a level where a static obstacle can be accurately identified, the collected multi-frame point cloud data can be used to accurately identify whether the target object is a static obstacle.

[0059] Step 106: If the target object is a static obstacle, execute the corresponding avoidance strategy. Specifically, the avoidance strategy may be: control the target vehicle to decelerate to a stop with acceleration M. The value of acceleration M is determined based on the distance between the target vehicle and the static obstacle.

[0060] For example, after determining that the target object is a static obstacle based on multi-frame point cloud data, the distance between the current target vehicle and the static obstacle is determined. Based on this distance, a matching acceleration M value is determined, and then this acceleration M is used to decelerate the vehicle to a stop. For instance, if the distance between the target vehicle and the static obstacle is large after determining that the target object is a static obstacle, the value of acceleration M can be relatively small. Conversely, if the distance between the target vehicle and the static obstacle is small, the value of acceleration M can be relatively large to ensure that the target vehicle stops before colliding with the static obstacle. This method can minimize the value of acceleration M while ensuring that a collision with a static obstacle is avoided, thereby improving the passenger experience.

[0061] Optionally, it can be determined first whether the static obstacle can be bypassed. If bypassing is not possible, the vehicle can be braked to a stop. If bypassing is possible, the vehicle can be slowed to a safe speed and a detour route determined. Then, the vehicle can proceed along the detour route at a safe speed to bypass the static obstacle. Specifically, after identifying the target object as a static obstacle, it can be determined whether the static obstacle is on the current driving route. If it is, further determination on whether bypassing is possible is made based on the road width, the size of the static obstacle, and its position. Alternatively, the data acquisition device can identify lane lines and, in the acquired m-frame point cloud data, determine only whether a continuously increasing target object exists within the currently driving lane.

[0062] In some embodiments, if it is determined from multi-frame point cloud data that the target object is not a static obstacle, the target vehicle can be accelerated according to a preset acceleration strategy to restore its original speed.

[0063] In some embodiments, the specific implementation process of step 103 above is as follows: Figure 2 As shown. Figure 2 A flowchart illustrating another static obstacle object recognition method provided in an embodiment of the present invention. Figure 2 As shown, the processing steps of this method include:

[0064] Step 201: Control the target vehicle to decelerate with acceleration N.

[0065] Step 202: When the speed change value of the target vehicle reaches the first threshold, determine whether the current speed of the target vehicle is less than or equal to the preset speed.

[0066] Step 203: If not, increase the acceleration N to continue deceleration and re-evaluate whether the speed change of the target vehicle has reached the first threshold, until the speed of the target vehicle is less than or equal to the preset speed.

[0067] The process involves reassessing the target vehicle's speed change after it reaches a first threshold. If the vehicle's speed is still greater than a preset speed, the acceleration N is gradually increased to avoid a poor passenger experience caused by directly using a large acceleration N. For example, the vehicle's initial speed is 100 km / h, the preset speed is 80 km / h, the first threshold is 10 km / h, and the initial acceleration N is 3. When a continuously increasing target object is detected in m frames of point cloud data, a gradual deceleration is performed. First, the first stage of deceleration is performed with an acceleration of 3 m / s². When the vehicle speed decreases to 90 km / h, the second stage of deceleration is initiated, increasing N to 4 and decelerating with an acceleration of 4 m / s². When the vehicle speed decreases to 80 km / h, the target vehicle's speed is determined to be less than or equal to the preset speed.

[0068] In some embodiments, the accuracy of identifying static obstacles gradually increases as the vehicle speed decreases. Therefore, before performing the next level of deceleration, a determination can be made based on the point cloud data from the previous level of deceleration. Specifically, before increasing the acceleration N to continue deceleration, n frames of point cloud data can be acquired during the deceleration process at acceleration N. Then, it is determined whether the n frames of point cloud data meet preset conditions. If the preset conditions are met, the target object is determined not to be a static obstacle, and deceleration stops. If the preset conditions are not met, the acceleration N is increased to continue deceleration.

[0069] Specifically, when determining whether n frames of point cloud data meet preset conditions, it can be determined whether the target object in the n frames of point cloud data continuously increases in size. If the target object in the n frames of point cloud data does not continuously increase in size, it is determined that the n frames of point cloud data meet the preset conditions, that is, the target object is not a static obstacle. If the target object in the n frames of point cloud data continues to increase in size, the acceleration N is increased and the next level of deceleration is executed. In this embodiment, during the gradual deceleration process, it is determined whether the target object is a static obstacle. If the target object continuously increases in size throughout the process, the target object has a high probability of being a static obstacle. Further determination is performed after the vehicle speed decreases to the preset speed.

[0070] Since the static obstacle recognition method provided in the embodiments of the invention is based on the premise that the target vehicle's speed is greater than a preset speed, and the target vehicle continuously receives point cloud data collected by the acquisition device, it is necessary to first determine whether the target vehicle's current speed is greater than the preset speed before determining whether there is a continuously increasing target object in the m-frame point cloud data. If so, then it is necessary to determine whether there is a continuously increasing target object in the m-frame point cloud data. If not, the existence of a static obstacle object can be determined directly based on the m-frame point cloud data.

[0071] In a specific example, the process of identifying static obstacles is as follows: the target vehicle is traveling at a speed of 120 km / h, the LiDAR acquisition frequency is 10 Hz, and the point cloud density is 150 m @ 10%.

[0072] Process 1: The first frame of point cloud data is acquired when the target vehicle is 150m away from the static obstacle. In the following five consecutive frames, the target object gradually increases in size. During these five frames, the target vehicle travels a distance of 16.67m and is 133.33m away from the target. The first stage of deceleration is initiated, with an acceleration of 3m / s². When the speed drops to 110km / h, the vehicle has traveled another 29.58 meters, at which point it is 103.75 meters away from the static obstacle.

[0073] Step Two: Analyze the last 5 frames of point cloud data from Step One. If a gradually increasing target object is still detected, initiate the second stage of deceleration, accelerating at 4 m / s². When the speed drops to 100 km / h, the vehicle has traveled another 20.25 meters, at which point it is 83.5 meters away from the static obstacle.

[0074] Step 3: Analyze the last 5 frames of point cloud data from Step 2. If a gradually increasing target object is still detected, initiate the third stage of deceleration, accelerating at 5 m / s². When the speed drops to 90 km / h, the vehicle has traveled another 14.66 meters, at which point it is 68.84 meters away from the static obstacle.

[0075] Step 4: Analyze the last 5 frames of data from Step 3. If a gradually increasing target object is still detected, initiate the fourth stage of deceleration, accelerating at 6 m / s². When the speed drops to 80 km / h, the vehicle has traveled another 10.93 meters, at which point it is 57.91 meters away from the static obstacle.

[0076] Step 5: At this point, the vehicle speed has decreased to below 80 km / h, within the normal obstacle detection range. There is still a distance of 57.91 meters between the vehicle and the static obstacle, sufficient for safe braking. If deceleration is applied at 6 m / s², the distance to the static obstacle will be 16.75 meters upon stopping. If deceleration is applied at 7 m / s², the distance to the static obstacle will be 22.64 meters upon stopping, ensuring the target vehicle does not collide with the obstacle.

[0077] The static obstacle recognition method provided in this invention improves passenger comfort by gradually reducing speed, thereby avoiding collisions, reducing accidents, ensuring passenger safety, and enhancing passenger comfort.

[0078] In accordance with the above-mentioned static obstacle recognition method, the present invention provides a static obstacle recognition device, which is installed on the target vehicle. Figure 3This is a schematic diagram of a static obstacle recognition device provided in an embodiment of the present invention. Figure 3 As shown, the static obstacle object recognition device includes: an acquisition module 301, a processing module 302, and a deceleration module 303.

[0079] The acquisition module 301 is used to acquire m frames of point cloud data collected by the acquisition device.

[0080] Processing module 302 is used to determine whether there is a target object that is continuously increasing in size in the m-frame point cloud data.

[0081] The deceleration module 303 is used to control the target vehicle to decelerate to a preset speed according to a preset deceleration strategy if there is a target object that is continuously increasing in size.

[0082] The acquisition module 301 is also used to acquire multi-frame point cloud data collected by the current acquisition device.

[0083] The processing module 302 is also used to determine whether the target object is a static obstacle object based on multi-frame point cloud data.

[0084] The processing module 302 is also used to execute the corresponding avoidance strategy if the target object is a static obstacle object.

[0085] In some embodiments, the deceleration module 303 is specifically used for:

[0086] The target vehicle is controlled to decelerate with an acceleration of N. When the speed change of the target vehicle reaches a first threshold, it is determined whether the current speed of the target vehicle is less than or equal to a preset speed. If not, the acceleration N is increased to continue deceleration, and the speed change of the target vehicle is re-evaluated to see if it reaches the first threshold, until the speed of the target vehicle is less than or equal to the preset speed.

[0087] In some embodiments, the acquisition module 301 is further configured to: acquire n frames of point cloud data during the deceleration process with acceleration N.

[0088] The processing module 302 is also used to determine whether the n frames of point cloud data meet preset conditions. If the preset conditions are met, the target object is determined not to be a static obstacle and deceleration stops. If the preset conditions are not met, the acceleration N is increased and deceleration continues.

[0089] In some embodiments, the processing module 302 is specifically used for:

[0090] Determine whether the target object in the n frames of point cloud data continues to increase in size. If the target object in the n frames of point cloud data does not continue to increase in size, then the n frames of point cloud data are determined to meet the preset conditions.

[0091] In some embodiments, the processing module 302 is further configured to:

[0092] Determine if the target vehicle's current speed is greater than a preset speed. If yes, determine if a continuously increasing target object exists in the m-frame point cloud data. If not, determine if a static obstacle exists based on the m-frame point cloud data.

[0093] In some embodiments, the processing module 302 is specifically used for:

[0094] Control the target vehicle to decelerate to a stop with an acceleration M. The value of acceleration M is determined based on the distance between the target vehicle and the static obstacle.

[0095] Figure 3 The static obstacle recognition device provided in the illustrated embodiment can be used to perform the functions described in this specification. Figures 1-2 The implementation principle and technical effects of the method embodiment shown can be further referred to the relevant description in the method embodiment.

[0096] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 4 As shown, the aforementioned electronic device may include at least one processor and at least one memory communicatively connected to the processor, wherein the memory stores program instructions executable by the processor, and the processor can execute this specification by calling the program instructions. Figures 1-2 The illustrated embodiment provides a static obstacle object recognition method.

[0097] like Figure 4 As shown, the electronic device is represented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors 410, communication interface 420 and memory 430, and a communication bus 440 connecting different system components (including memory 430, communication interface 420 and processor 410).

[0098] Communication bus 440 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) buses, Micro Channel Architecture (MAC) buses, Enhanced ISA buses, Video Electronics Standards Association (VESA) local buses, and Peripheral Component Interconnect (PCI) buses.

[0099] Electronic devices typically include a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, and removable and non-removable media.

[0100] Memory 430 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 430 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments described herein.

[0101] A program / utility having a set (at least one) of program modules may be stored in memory 430. Such program modules include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules typically perform the functions and / or methods described in the embodiments of this specification.

[0102] Processor 410 executes various functional applications and data processing by running programs stored in memory 430, such as implementing the functions described in this specification. Figures 1-2 The illustrated embodiment provides a static obstacle object recognition method.

[0103] This specification provides a computer-readable storage medium storing computer instructions that cause a computer to execute this specification. Figures 1-2The illustrated embodiment provides a static obstacle object recognition method.

[0104] The aforementioned computer-readable storage medium may be any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0105] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0106] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0107] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this specification, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0108] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this specification includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which the embodiments of this specification pertain.

[0109] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0110] It should be noted that the devices involved in the embodiments of this specification may include, but are not limited to, personal computers (hereinafter referred to as PCs), personal digital assistants (hereinafter referred to as PDAs), wireless handheld devices, tablet computers, mobile phones, MP3 displays, MP4 displays, etc.

[0111] In the several embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0112] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0113] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, a connector, or a network device, etc.) or a processor to execute some steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0114] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

Claims

1. A static obstacle object recognition method characterized by, The method is applied to a target vehicle, and comprises: acquiring m frames of point cloud data collected by a collection device; determining whether a target object that continuously increases exists in the m frames of point cloud data; if the target object that continuously increases exists, controlling the target vehicle to decelerate to a preset speed according to a preset deceleration strategy; acquiring multiple frames of point cloud data collected by a current collection device; determining whether the target object is a static obstacle according to the multiple frames of point cloud data; if the target object is a static obstacle, executing a corresponding avoidance strategy; the controlling the target vehicle to decelerate to the preset speed according to the preset deceleration strategy comprises: controlling the target vehicle to decelerate at an acceleration N; when a speed change value of the target vehicle reaches a first threshold, determining whether a current speed of the target vehicle is less than or equal to the preset speed; if not, increasing the acceleration N to continue deceleration and re-determining whether the speed change value of the target vehicle reaches the first threshold, until the speed of the target vehicle is less than or equal to the preset speed; wherein the preset speed is determined according to a highest speed of accurately identifying a static obstacle.

2. The method of claim 1, wherein, Before the increasing the acceleration N to continue deceleration, the method further comprises: acquiring n frames of point cloud data in the process of decelerating at the acceleration N; determining whether the n frames of point cloud data satisfy a preset condition; if the n frames of point cloud data satisfy the preset condition, determining that the target object is not a static obstacle and stopping deceleration; if the n frames of point cloud data do not satisfy the preset condition, increasing the acceleration N to continue deceleration.

3. The method of claim 2, wherein, the determining whether the n frames of point cloud data satisfy the preset condition comprises: determining whether the target object in the n frames of point cloud data continuously increases; if the target object in the n frames of point cloud data does not continuously increase, determining that the n frames of point cloud data satisfy the preset condition.

4. The method of claim 1, wherein, Before the determining whether the target object that continuously increases exists in the m frames of point cloud data, the method further comprises: determining whether a current speed of the target vehicle is greater than the preset speed; if yes, determining whether the target object that continuously increases exists in the m frames of point cloud data; if no, determining whether a static obstacle exists according to the m frames of point cloud data.

5. The method of claim 1, wherein, the executing the corresponding avoidance strategy comprises: controlling the target vehicle to decelerate to a stop at an acceleration M.

6. The method of claim 5, wherein, a value of the acceleration M is determined according to a distance between the target vehicle and the static obstacle.

7. A stationary obstacle object recognition apparatus characterized by comprising: The static obstacle identification device is arranged in a target vehicle, and comprises: an acquisition module, configured to acquire m frames of point cloud data collected by a collection device; a processing module, configured to determine whether a target object that continuously increases exists in the m frames of point cloud data; a deceleration module, configured to, if the target object that continuously increases exists, control the target vehicle to decelerate to a preset speed according to a preset deceleration strategy; the acquisition module is further configured to acquire multiple frames of point cloud data collected by a current collection device; the processing module is further configured to determine whether the target object is a static obstacle according to the multiple frames of point cloud data; the processing module is further configured to, if the target object is a static obstacle, execute a corresponding avoidance strategy; the deceleration module is specifically configured to: controlling the target vehicle to decelerate at an acceleration N; when the speed change value of the target vehicle reaches a first threshold value, determining whether the current speed of the target vehicle is less than or equal to the preset speed; if not, increasing the acceleration N to continue deceleration and re-determining whether the speed change value of the target vehicle reaches the first threshold value until the speed of the target vehicle is less than or equal to the preset speed; wherein the preset speed is determined according to the highest speed of the vehicle for accurately identifying the static obstacle object.

8. An electronic device, comprising: comprising: at least one processor; and at least one memory connected to the processor in communication, wherein: the memory stores program instructions executable by the processor, and the processor invoking the program instructions can execute the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, the computer readable storage medium stores computer instructions, and the computer instructions make the computer execute the method of any one of claims 1 to 6.

Images