A vehicle obstacle avoidance method and device, an unmanned vehicle and a storage medium

Abstract

The application provides a vehicle obstacle avoidance method and device, an unmanned vehicle and a storage medium. The method comprises: when an obstacle vehicle located in the driving direction of a target vehicle is identified, obtaining vehicle distances corresponding to at least two time points of the obstacle vehicle and the target vehicle; determining whether the obstacle vehicle is performing a reverse operation according to the at least two vehicle distances; if yes, controlling the target vehicle to perform an avoidance operation based on an avoidance space of the target vehicle under the condition that the avoidance space meets a preset condition. The method can control the target vehicle to automatically perform an avoidance operation when the obstacle vehicle is reversing, reduce the risk of collision of the target vehicle, and provide convenience for the reverse operation of the obstacle vehicle. Therefore, the method can improve the safety and smoothness of vehicle driving.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a vehicle obstacle avoidance method, device, terminal equipment, unmanned vehicle, and computer-readable storage medium. Background Technology

[0002] In recent years, autonomous driving technology has advanced rapidly. Detecting obstacles in the vehicle's direction of travel and controlling the vehicle to avoid those obstacles is currently one of the main methods to ensure driving safety. For example, when an obstacle is detected in the vehicle's direction of travel, the vehicle can be controlled to go around the obstacle and continue traveling in the direction of travel, or the vehicle can be controlled to stop and continue traveling after the obstacle is removed. However, with the increasing complexity of traffic conditions, using the above-mentioned traditional technologies for obstacle avoidance still poses safety hazards or causes traffic congestion.

[0003] Therefore, improving the safety and smoothness of vehicle driving is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this application is to provide a vehicle obstacle avoidance method, device, terminal equipment, unmanned vehicle, and computer-readable storage medium, which aim to improve the safety and smoothness of vehicle driving.

[0005] Firstly, this application provides a vehicle obstacle avoidance method. The method includes:

[0006] When an obstacle vehicle located in the driving direction of the target vehicle is identified, the vehicle distance between the obstacle vehicle and the target vehicle at least at two different times is obtained;

[0007] Determine whether the obstacle vehicle is reversing based on at least two vehicle distances;

[0008] If so, then if the avoidance space of the target vehicle meets the preset conditions, the target vehicle is controlled to perform an avoidance operation based on the avoidance space.

[0009] In one embodiment, when an obstacle vehicle located in the driving direction of the target vehicle is identified, obtaining the vehicle distance between the obstacle vehicle and the target vehicle at at least two time points includes:

[0010] When an obstacle is detected in the driving direction of the target vehicle, an obstacle image is acquired;

[0011] The obstacle image is input into a pre-trained recognition model, and the recognition result output by the recognition model is obtained;

[0012] When the identification result is a vehicle, the obstacle is identified as an obstructing vehicle;

[0013] Obtain the vehicle distances between the obstacle vehicle and the target vehicle at at least two time points.

[0014] In one embodiment, when an obstacle vehicle located in the driving direction of the target vehicle is identified, obtaining the vehicle distance between the obstacle vehicle and the target vehicle at at least two time points includes:

[0015] When an obstacle vehicle is detected in the driving direction of the target vehicle, it is determined whether the target vehicle is in the blind spot of the obstacle vehicle.

[0016] If so, then obtain the vehicle distances between the obstacle vehicle and the target vehicle at at least two time points.

[0017] In one embodiment, determining whether the target vehicle is in the blind spot of the obstacle vehicle includes:

[0018] Obtain the deviation values ​​corresponding to the center line of the target vehicle and the two side lines of the obstacle vehicle, respectively;

[0019] If all the deviation values ​​are greater than or equal to the preset deviation value, then the target vehicle is determined to be in the blind spot of the obstacle vehicle.

[0020] In one embodiment, obtaining the vehicle distances between the obstacle vehicle and the target vehicle at at least two time points includes:

[0021] Acquire at least two first measured distances between the obstacle vehicle and the target vehicle determined by radar ranging, and determine a first moment corresponding to each of the first measured distances;

[0022] Acquire at least two second measured distances between the obstacle vehicle and the target vehicle determined by visual ranging, and determine a second time point corresponding to each of the second measured distances;

[0023] When at least two of the at least two first moments and at least two of the at least two second moments are the same, for each of the at least two same moments, the vehicle distance at the same moment is determined based on the first measured distance and the second measured distance corresponding to the same moment.

[0024] In one embodiment, determining the vehicle distance at the same time based on the first measured distance and the second measured distance corresponding to the same time includes any one of the following methods:

[0025] The vehicle distance at the same time is determined based on the average of the first measured distance and the second measured distance at the same time.

[0026] The vehicle distance at the same time is determined based on the weights corresponding to the first measurement distance and the second measurement distance, respectively, and the first measurement distance and the second measurement distance corresponding to the same time.

[0027] The delay time of the second measured distance determined by the visual ranging is obtained, and the vehicle distance at the same time is determined according to the delay time, the first measured distance and the second measured distance corresponding to the same time.

[0028] In one embodiment, determining whether the obstacle vehicle is performing a reversing operation based on at least two vehicle distances includes:

[0029] When the target vehicle is stationary and there are at least three vehicle distances, determine the difference between the vehicle distances at two adjacent moments;

[0030] If at least two of the differences in chronological order show a decreasing trend, then it is determined that the obstructing vehicle is performing a reversing operation.

[0031] Secondly, this application also provides a vehicle obstacle avoidance device. The device includes:

[0032] The acquisition module is used to acquire the vehicle distance between the obstacle vehicle and the target vehicle at at least two time points when an obstacle vehicle located in the driving direction of the target vehicle is identified.

[0033] The judgment module is used to determine whether the obstacle vehicle is performing a reversing operation based on the distance between at least two of the vehicles; if so, the control module is invoked.

[0034] The control module is used to control the target vehicle to perform an avoidance operation based on the avoidance space when the avoidance space of the target vehicle meets the preset conditions.

[0035] Thirdly, this application also provides a terminal device. The terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0036] Fourthly, this application also provides an unmanned vehicle, including an unmanned vehicle body, the unmanned vehicle further including a controller, the controller performing the steps of the method as described above.

[0037] Fifthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described above.

[0038] This application provides a vehicle obstacle avoidance method, comprising: when an obstacle vehicle located in the driving direction of a target vehicle is detected, obtaining the vehicle distances between the obstacle vehicle and the target vehicle at at least two time points; determining whether the obstacle vehicle is performing a reversing operation based on the at least two vehicle distances; if so, controlling the target vehicle to perform an obstacle avoidance operation based on the obstacle avoidance space, provided that the obstacle vehicle's avoidance space meets preset conditions. It is evident that this method can automatically control the target vehicle to perform an obstacle avoidance operation when the obstacle vehicle is reversing, reducing the target vehicle's risk of being collided with, while also facilitating the obstacle vehicle's reversing operation. Therefore, this method can improve the safety and smoothness of vehicle driving.

[0039] It is understood that the vehicle obstacle avoidance device, terminal equipment, unmanned vehicle and computer-readable storage medium provided in the embodiments of this application have the same beneficial effects as the vehicle obstacle avoidance method described above, and will not be repeated here. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0041] Figure 1 A flowchart of a vehicle obstacle avoidance method provided in an embodiment of this application;

[0042] Figure 2 A flowchart of another vehicle obstacle avoidance method provided in the embodiments of this application;

[0043] Figure 3 This is a schematic diagram of the structure of a vehicle obstacle avoidance device provided in an embodiment of this application;

[0044] Figure 4 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Detailed Implementation

[0045] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.

[0046] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0047] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0048] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0049] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0050] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized. "A plurality" means "two or more."

[0051] The vehicle obstacle avoidance method provided in this application embodiment can be executed by the processor of the terminal device installed on the target vehicle when running the corresponding computer program, or it can be executed by the server when running the corresponding computer program.

[0052] Figure 1 The flowchart illustrates a vehicle obstacle avoidance method according to an embodiment of this application. For ease of explanation, only the parts relevant to this embodiment are shown. The method provided in this embodiment includes the following steps:

[0053] S100: When an obstacle vehicle located in the driving direction of the target vehicle is detected, obtain the vehicle distance between the obstacle vehicle and the target vehicle at at least two time points.

[0054] Among them, an obstacle vehicle refers to a vehicle that affects the target vehicle's travel in the driving direction; the driving direction is generally consistent with the road's traffic direction.

[0055] In this embodiment, the vehicle distance between the target vehicle and the obstacle vehicle is the distance between the designated position of the target vehicle and the calibrated position of the obstacle vehicle. For example, the vehicle distance can be the distance between the distance detection device on the target vehicle and the rear of the obstacle vehicle, or it can be the distance between the front of the target vehicle and the rear of the obstacle vehicle. This embodiment does not limit the specific definition of vehicle distance. In actual operation, the distance detection device may include ultrasonic ranging devices, radar, and depth cameras, etc., that is, the vehicle distance can be obtained through ultrasonic ranging, radar ranging, and visual ranging. This embodiment does not limit the specific type of distance detection device or the method of obtaining vehicle distance. Furthermore, the vehicle distance can be obtained using a single distance detection device, or the corresponding vehicle distance can be determined by combining the measurement distances corresponding to two or more distance detection devices. This embodiment does not limit this as well.

[0056] The vehicle distances at at least two times refer to the vehicle distances of the target vehicle and the obstacle vehicle acquired at at least two different times; this embodiment does not limit the number of vehicle distances acquired.

[0057] S200: Determine whether the obstacle vehicle is performing a reversing operation based on the distance between at least two vehicles; if so, proceed to S300; otherwise, return to S100.

[0058] In this context, reversing refers to the action of an obstacle vehicle moving backward, that is, moving in the opposite direction to the driving direction. In this embodiment, the vehicle distances at at least two points in time obtained in S100 are calculated and analyzed to determine whether the obstacle vehicle is performing a reversing operation.

[0059] It is understandable that one can determine whether an obstacle vehicle is reversing by judging whether the distance between each vehicle gradually decreases over time, or by determining the difference between the distances of two adjacent moments and judging whether the differences in time show a decreasing trend; this embodiment does not limit the judgment method.

[0060] In this embodiment, if it is determined that the obstacle vehicle is performing a reversing operation, then S300 is executed to perform a corresponding avoidance operation for the obstacle vehicle's reversing operation; otherwise, that is, the obstacle vehicle is not performing a reversing operation, then S100 is returned to continue to obtain the vehicle distances of the obstacle vehicle and the target vehicle at least at two different times.

[0061] S300: When the obstacle space of the target vehicle meets the preset conditions, control the target vehicle to perform an obstacle avoidance operation based on the obstacle space.

[0062] The avoidance maneuver refers to creating space for an obstacle vehicle, including straight-line reversing and side / rear reversing. Meeting the preset avoidance space condition means that there is sufficient space around the target vehicle to allow it to perform the avoidance maneuver. The target vehicle reverses to create more space for the obstacle vehicle, enabling it to easily reverse, while simultaneously allowing the target vehicle to avoid the obstacle vehicle's reversing maneuver, preventing a collision.

[0063] Specifically, when it is determined that an obstacle vehicle is performing a reversing operation, the corresponding avoidance space around the target vehicle is first obtained, and it is determined whether the avoidance space meets the preset conditions. If it does, the target vehicle is controlled to perform an avoidance operation based on the avoidance space. Otherwise, that is, if the avoidance space does not meet the preset conditions, a prompt message is generated and pushed to the prompting device of the target vehicle. The prompting device issues the corresponding prompt message, such as sounding a horn warning, to remind the obstacle vehicle to pay attention to the target vehicle behind it when reversing.

[0064] In practice, the process of controlling a target vehicle to perform an avoidance maneuver can be either by generating a control command and controlling the target vehicle to perform the avoidance maneuver based on the control command, or by generating an avoidance prompt message, and after the driver performs the corresponding driving operation based on the avoidance prompt message, controlling the target vehicle to perform the avoidance maneuver by responding to the driving operation.

[0065] This application provides a vehicle obstacle avoidance method, comprising: when an obstacle vehicle located in the driving direction of a target vehicle is detected, obtaining the vehicle distances between the obstacle vehicle and the target vehicle at at least two time points; determining whether the obstacle vehicle is performing a reversing operation based on the at least two vehicle distances; if so, controlling the target vehicle to perform an obstacle avoidance operation based on the obstacle avoidance space, provided that the obstacle vehicle's avoidance space meets preset conditions. It is evident that this method can automatically control the target vehicle to perform an obstacle avoidance operation when the obstacle vehicle is reversing, reducing the target vehicle's risk of being collided with, while also providing convenience for the obstacle vehicle's reversing operation. Therefore, this method can improve the safety and smoothness of vehicle driving.

[0066] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, when an obstacle vehicle located in the driving direction of the target vehicle is identified, the vehicle distances between the obstacle vehicle and the target vehicle at least at two different times are obtained, including:

[0067] When an obstacle is detected in the driving direction of the target vehicle, an obstacle image is acquired;

[0068] The obstacle image is input into a pre-trained recognition model, and the recognition result output by the recognition model is obtained;

[0069] When the identification result is a vehicle, the obstacle is identified as an obstructing vehicle;

[0070] Obtain the vehicle distances at at least two time points for the obstacle vehicle and the target vehicle.

[0071] Understandably, in practice, obstacles around the target vehicle are first detected by radar. When an obstacle in the driving direction of the target vehicle is detected, an image acquisition device is used to further acquire an image of the obstacle. Then, the obstacle image acquired by the image acquisition device is input into a pre-trained recognition model. The recognition model is used to analyze and identify the obstacle image, determine the recognition result corresponding to the obstacle image, and output the recognition result.

[0072] The image acquisition device can be a depth camera or a binocular camera, etc. The recognition model is a model trained in a deep neural network by pre-inputting a large number of vehicle image samples with labeled information. Deep neural networks include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory Networks (LSTMs), Feed-forward Neural Networks (FNNs), etc. This embodiment does not limit the specific type of deep neural network. In actual operation, the vehicle image sample can be a whole vehicle image, i.e., determining whether an obstacle in the obstacle image is a vehicle by judging whether the obstacle image is a whole vehicle image; the vehicle image sample can also be a license plate image, i.e., determining whether an obstacle in the obstacle image is a vehicle by judging whether the obstacle image is a license plate image.

[0073] When the identification result is obtained and determined to be a vehicle, the obstacle is identified as an obstacle vehicle, and the vehicle distances between the obstacle vehicle and the target vehicle at least at two time points are obtained. If the identification result characterizes the obstacle image as an object other than a vehicle, such as a roadblock, sand pile, or pile of stones, the obstacle is determined to be a non-vehicle, and the detection of obstacles located in the driving direction of the target vehicle continues.

[0074] According to the method of this embodiment, obstacle vehicles located in the driving direction of the target vehicle can be easily and accurately identified.

[0075] Figure 2 This is a flowchart of another vehicle obstacle avoidance method provided in this application embodiment. Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, when an obstacle vehicle located in the driving direction of the target vehicle is identified, the vehicle distances between the obstacle vehicle and the target vehicle at least at two different times are obtained, including:

[0076] S101: When an obstacle vehicle is detected in the driving direction of the target vehicle, determine whether the target vehicle is in the obstacle vehicle's blind spot; if so, execute S102; otherwise, execute S103.

[0077] S102: Obtain the vehicle distances between the obstacle vehicle and the target vehicle at at least two time points;

[0078] S103: Terminate process.

[0079] In this context, the blind spot refers to the area outside the vehicle that the driver of the obstacle vehicle cannot directly see when sitting in the driver's seat due to obstructed vision. Since the obstacle vehicle is located in the driving direction of the target vehicle, the blind spot in this embodiment mainly includes the rear blind spot, that is, the obstacle vehicle cannot see the target vehicle located behind it.

[0080] Specifically, in actual operation, first determine whether the width of the target vehicle is greater than the width of the obstacle vehicle; if it is greater, it means that the obstacle vehicle can see the target vehicle behind it, so the target vehicle is not in the obstacle vehicle's blind spot; otherwise, it means that the obstacle vehicle may not be able to see the target vehicle behind it, so it is necessary to further determine whether the target vehicle is in the obstacle vehicle's blind spot based on factors such as the driver's field of vision angle of the obstacle vehicle and the relative position of the target vehicle and the obstacle vehicle.

[0081] Generally, if the target vehicle is in the blind spot of the obstacle vehicle, it means that the obstacle vehicle may pose a safety hazard to the target vehicle when it is reversing. Therefore, it is necessary to obtain the distance between the obstacle vehicle and the target vehicle at least at two different times in order to control the target vehicle to avoid the obstacle vehicle when it is reversing. If the target vehicle is not in the blind spot of the obstacle vehicle, the obstacle vehicle can ensure the safety of the target vehicle by observing the target vehicle behind it when it is reversing, and therefore the process can be terminated.

[0082] This embodiment determines whether to perform the operation of obtaining the vehicle distance between the obstacle vehicle and the target vehicle at least at two different times by determining whether the target vehicle is in the blind spot of the obstacle vehicle. The vehicle obstacle avoidance method is only executed when the target vehicle is in the blind spot of the obstacle vehicle, which can save operational resources.

[0083] In one embodiment, determining whether the target vehicle is in the blind spot of the obstacle vehicle includes:

[0084] Obtain the deviation values ​​between the centerline of the target vehicle and the two side lines of the obstacle vehicle;

[0085] If all deviation values ​​are greater than or equal to the preset deviation value, the target vehicle is determined to be in the blind spot of the obstacle vehicle.

[0086] The vehicle centerline refers to the straight line corresponding to the middle position of the windshield of the target vehicle from left to right; the side lines of the obstacle vehicle refer to the straight lines corresponding to the two sides of the obstacle vehicle.

[0087] Specifically, in this embodiment, the deviation values ​​corresponding to the centerline of the target vehicle and the two side lines of the obstacle vehicle are obtained, and the two determined deviation values ​​are compared with preset deviation values. If both deviation values ​​are greater than or equal to the preset deviation values, the target vehicle is determined to be in the blind spot of the obstacle vehicle. If any one deviation value is less than the preset deviation value, or both deviation values ​​are less than the preset deviation value, the target vehicle is determined to be outside the blind spot of the obstacle vehicle. The preset deviation value is generally between 30cm and 50cm, and this embodiment does not limit the specific value of the preset deviation value.

[0088] As can be seen, the method of this embodiment can conveniently and accurately determine whether the target vehicle is in the blind spot of the obstacle vehicle.

[0089] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, obtaining the vehicle distances between the obstacle vehicle and the target vehicle at at least two time points includes:

[0090] Acquire at least two first measured distances to the obstacle vehicle and the target vehicle determined by radar ranging, and determine the first time point corresponding to each first measured distance;

[0091] Acquire at least two second measured distances of the obstacle vehicle and the target vehicle determined by visual ranging, and determine the second time point corresponding to each second measured distance;

[0092] When at least two of the at least two first moments and at least two of the at least two second moments are the same, for each of the at least two same moments, the vehicle distance at the same moment is determined based on the first measurement distance and the second measurement distance corresponding to the same moment.

[0093] Specifically, in this embodiment, the first measured distance refers to the vehicle distance between the obstacle vehicle and the target vehicle determined by radar ranging; the second measured distance refers to the vehicle distance between the obstacle vehicle and the target vehicle determined by visual ranging. It should be noted that when acquiring the first measured distance determined by radar ranging, a first time corresponding to acquiring the first measured distance is simultaneously determined; when acquiring the second measured distance determined by visual ranging, a second time corresponding to acquiring the second measured distance is simultaneously determined. In this embodiment, at least two first measured distances and at least two second measured distances are acquired, along with at least two first times and at least two second times.

[0094] Then, it is determined whether there is a common time among at least two first time moments and at least two second time moments, that is, whether there are at least two first measurement distances and second measurement distances acquired simultaneously; in this embodiment, a certain error range is allowed when determining whether the first time moment and the second time moment are the same time moment.

[0095] When at least two of the at least two first moments and at least two of the at least two second moments are the same, for each of the at least two same moments, the vehicle distance at the same moment is determined based on the first measurement distance and the second measurement distance corresponding to the same moment.

[0096] In this embodiment, the first measurement distance and the second measurement distance are determined by radar ranging and visual ranging, respectively. Then, the vehicle distance at the same time is determined based on the first measurement distance and the second measurement distance acquired simultaneously. This not only improves the accuracy of vehicle distance determination by using multiple methods, but also avoids the influence of ambient temperature and humidity on the determination of vehicle distance. That is, the method of this embodiment can accurately determine the vehicle distance between obstacle vehicles and target vehicles under humid, extreme temperature and harsh conditions, and thus can accurately perform vehicle obstacle avoidance under humid, extreme temperature and harsh conditions.

[0097] In one embodiment, the vehicle distance at the same time is determined based on a first measured distance and a second measured distance corresponding to the same time, including any of the following methods:

[0098] Method 1: Determine the vehicle distance at the same time based on the average of the first and second measured distances at the same time.

[0099] Specifically, the average of the first and second measured distances at the same time can be directly calculated, and this average value can be determined as the vehicle distance between the obstacle vehicle and the target vehicle at the same time.

[0100] In practice, if two or more first measurement distances or two or more second measurement distances are obtained at the same time, the first average of the two or more first measurement distances or the second average of the two or more second measurement distances at the same time can be calculated first; then the average of the first average and the second average at the same time can be calculated to obtain the vehicle distance between the obstacle vehicle and the target vehicle at the same time.

[0101] Method 2: Determine the vehicle distance at the same time based on the weights corresponding to the first and second measured distances, as well as the first and second measured distances at the same time.

[0102] Specifically, the weights corresponding to radar ranging and visual ranging are pre-set, that is, the weights corresponding to the first and second measured distances are determined respectively; after obtaining the first and second measured distances at the same time, the vehicle distance at the same time is obtained by weighted calculation using the weights corresponding to the first and second measured distances respectively and the first and second measured distances at the same time.

[0103] Method 3: Obtain the delay time of the second measurement distance determined by visual ranging, and determine the vehicle distance at the same time based on the delay time, the first measurement distance, and the second measurement distance corresponding to the time.

[0104] Specifically, a delay time threshold is preset. After obtaining the second measured distance at the second moment determined by visual ranging, the delay time corresponding to the second measured distance at the second moment is obtained, and then it is determined whether the delay time is greater than the delay time threshold. If the delay time is greater than the delay time threshold, the first moment corresponding to the second moment is determined, and the first measured distance corresponding to the first moment is determined as the vehicle distance between the obstacle vehicle and the target vehicle at the same moment. Otherwise, the second measured distance corresponding to the second moment is determined as the vehicle distance between the obstacle vehicle and the target vehicle at the same moment.

[0105] As can be seen, this embodiment provides multiple methods for determining vehicle distance, allowing for flexible selection of the appropriate method based on actual circumstances.

[0106] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, determining whether an obstacle vehicle is performing a reversing operation based on the distance between at least two vehicles includes:

[0107] When the target vehicle is stationary and there are at least three vehicle distances, determine the difference between the vehicle distances at two adjacent time points;

[0108] If at least two differences in chronological order show a decreasing trend, then the obstructed vehicle is determined to be performing a reversing operation.

[0109] In this context, "the target vehicle is stationary" means that the target vehicle has not moved. In this embodiment, when the target vehicle is stationary and there are at least three vehicle distances, the difference between the vehicle distances at two adjacent moments is determined, resulting in at least two differences. These at least two differences are then arranged in chronological order, and it is determined whether they show a decreasing trend. If the differences decrease over time, the obstacle vehicle is determined to be reversing; if the differences remain constant over time, the obstacle vehicle is also stationary; if the differences increase over time, the obstacle vehicle is determined to be traveling in the driving direction.

[0110] The method described in this embodiment can conveniently and accurately determine whether a vehicle with an obstacle is performing a reversing operation.

[0111] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0112] Figure 3 The diagram shown is a structural schematic of a vehicle obstacle avoidance device provided in an embodiment of this application. Figure 3 As shown, the vehicle obstacle avoidance device in this embodiment includes an acquisition module 301, a judgment module 302, and a control module 303; wherein,

[0113] The acquisition module 301 is used to acquire the vehicle distance between the obstacle vehicle and the target vehicle at at least two time points when an obstacle vehicle located in the driving direction of the target vehicle is identified.

[0114] The judgment module 302 is used to determine whether the obstacle vehicle is performing a reversing operation based on the distance between at least two vehicles; if so, the control module 303 is invoked.

[0115] The control module 303 is used to control the target vehicle to perform an avoidance operation based on the avoidance space when the avoidance space of the target vehicle meets the preset conditions.

[0116] The vehicle obstacle avoidance device provided in this application embodiment has the same beneficial effects as the vehicle obstacle avoidance method described above.

[0117] In one embodiment, the acquisition module 301 includes:

[0118] The first acquisition submodule is used to acquire an obstacle image when an obstacle located in the driving direction of the target vehicle is detected.

[0119] The input submodule is used to input obstacle images into a pre-trained recognition model and obtain the recognition results output by the recognition model;

[0120] The determination submodule is used to identify obstacles as vehicles when the recognition result is a vehicle;

[0121] The second acquisition submodule is used to acquire the vehicle distances of the obstacle vehicle and the target vehicle at at least two time points.

[0122] In one embodiment, the acquisition module 301 includes:

[0123] The judgment submodule is used to determine whether the target vehicle is in the blind spot of the obstacle vehicle when an obstacle vehicle is detected in the driving direction of the target vehicle; if so, the third acquisition submodule is called.

[0124] The third acquisition submodule is used to acquire the vehicle distances of the obstacle vehicle and the target vehicle at at least two time points.

[0125] In one embodiment, the determination submodule includes:

[0126] The acquisition unit is used to acquire the deviation values ​​between the center line of the target vehicle and the two side lines of the obstacle vehicle, respectively.

[0127] The determination unit is used to determine that the target vehicle is in the blind spot of the obstacle vehicle if all deviation values ​​are greater than or equal to the preset deviation value.

[0128] In one embodiment, the acquisition module 301 includes:

[0129] The first distance acquisition submodule is used to acquire at least two first measured distances of the obstacle vehicle and the target vehicle determined by radar ranging, and to determine the first time corresponding to each first measured distance;

[0130] The second distance acquisition submodule is used to acquire at least two second measured distances of the obstacle vehicle and the target vehicle determined by visual ranging, and to determine the second time corresponding to each second measured distance;

[0131] The distance determination submodule is used to determine the vehicle distance at each of the at least two identical times when there are at least two identical times among at least two first times and at least two second times. This determination is based on the first and second measured distances corresponding to the identical times.

[0132] In one embodiment, the distance determination submodule includes:

[0133] The first distance determination unit is used to determine the vehicle distance at the same time based on the average of the first measured distance and the second measured distance at the same time.

[0134] In one embodiment, the distance determination submodule includes:

[0135] The second distance determination unit is used to determine the vehicle distance at the same time based on the weights corresponding to the first and second measured distances, respectively, and the first and second measured distances at the same time.

[0136] In one embodiment, the distance determination submodule includes:

[0137] The third distance determination unit is used to obtain the delay time of the second measured distance determined by visual ranging, and to determine the vehicle distance at the same time based on the delay time, the first measured distance and the second measured distance at the same time.

[0138] In one embodiment, the determination module 302 includes:

[0139] The difference determination submodule is used to determine the difference between the vehicle distances at two adjacent moments when the target vehicle is stationary and there are at least three vehicle distances.

[0140] The status determination submodule is used to determine that the obstructed vehicle is performing a reversing operation if at least two differences in chronological order show a decreasing trend.

[0141] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0142] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments 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 as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0143] Figure 4 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Figure 4 As shown, the terminal device 400 of this embodiment includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and executable on the processor 402; when the processor 402 executes the computer program 403, it implements the steps in the various vehicle obstacle avoidance method embodiments described above, for example... Figure 1 S100 to S300 are shown; or when the processor 402 executes the computer program 403, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 3 The diagram shows the acquisition module, judgment module, and control module.

[0144] For example, computer program 403 can be divided into one or more modules / units, one or more of which are stored in memory 401 and executed by processor 402 to implement the method of the embodiments of this application. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of computer program 403 in terminal device 400. For example, computer program 403 can be divided into an acquisition module, a judgment module, and a control module, with the specific functions of each module as follows:

[0145] The acquisition module is used to acquire the vehicle distances between the obstacle vehicle and the target vehicle at at least two time points when an obstacle vehicle located in the driving direction of the target vehicle is identified.

[0146] The judgment module is used to determine whether the obstacle vehicle is performing a reversing operation based on the distance between at least two vehicles; if so, the control module is invoked.

[0147] The control module is used to control the target vehicle to perform an avoidance operation based on the avoidance space when the avoidance space of the target vehicle meets the preset conditions.

[0148] In applications, terminal device 400 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. Terminal device 400 may include, but is not limited to, memory 401 and processor 402. Those skilled in the art will understand that... Figure 4 This is merely an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown, or combine certain components, or different components. For example, a terminal device may also include input / output devices, network access devices, buses, etc.; among which, input / output devices may include cameras, audio acquisition / playback devices, displays, etc.; network access devices may include communication modules for wireless communication with external devices.

[0149] In applications, the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0150] In applications, memory can be an internal storage unit of a terminal device, such as its hard drive or RAM; it can also be an external storage device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card; or it can include both internal and external storage units. Memory is used to store operating systems, applications, boot loaders, data, and other programs, such as computer program code. Memory can also be used to temporarily store data that has been output or will be output.

[0151] This application also provides an unmanned vehicle, including an unmanned vehicle body and a controller, which executes the steps in the above-described method embodiments.

[0152] The unmanned vehicle provided in this application embodiment has the same beneficial effects as the vehicle obstacle avoidance method described above.

[0153] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps in the above-described method embodiments.

[0154] The computer-readable storage medium provided in this application embodiment has the same beneficial effects as the vehicle obstacle avoidance method described above.

[0155] This application implements all or part of the processes in the methods of the above embodiments, which can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0156] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0157] Those skilled in the art will recognize that the device and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0158] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interface, or the device may be indirectly coupled or communicated, and may be electrical, mechanical, or other forms.

[0159] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A vehicle obstacle avoidance method characterized by, The method comprises: When an obstacle vehicle in the driving direction of a target vehicle is identified, vehicle distances corresponding to at least two time points of the obstacle vehicle and the target vehicle are obtained; when the obstacle vehicle in the driving direction of the target vehicle is identified, the vehicle distances corresponding to at least two time points of the obstacle vehicle and the target vehicle are obtained, comprising: when the obstacle vehicle in the driving direction of the target vehicle is identified, it is determined whether the target vehicle is in the blind area of the field of view of the obstacle vehicle; if yes, the vehicle distances corresponding to at least two time points of the obstacle vehicle and the target vehicle are obtained; The determination of whether the target vehicle is in the blind area of the field of view of the obstacle vehicle comprises: obtaining the deviation values corresponding to the center line of the vehicle body of the target vehicle and the two sides of the obstacle vehicle; if the deviation values are both greater than or equal to a preset deviation value, it is determined that the target vehicle is in the blind area of the field of view of the obstacle vehicle; It is determined whether the obstacle vehicle is performing a reversing operation according to at least two vehicle distances; If yes, the target vehicle performs an avoidance operation based on an avoidance space of the target vehicle under the condition that the avoidance space meets a preset condition; the avoidance space meeting the preset condition comprises that there is a space around the target vehicle to enable the target vehicle to perform an avoidance operation.

2. The method of claim 1, wherein, When an obstacle vehicle in the driving direction of a target vehicle is identified, vehicle distances corresponding to at least two time points of the obstacle vehicle and the target vehicle are obtained, comprising: When an obstacle in the driving direction of a target vehicle is detected, an obstacle image of the obstacle is obtained; The obstacle image is input into a pre-trained identification model, and an identification result output by the identification model is obtained; When the identification result is a vehicle, the obstacle is determined as an obstacle vehicle; Vehicle distances corresponding to at least two time points of the obstacle vehicle and the target vehicle are obtained.

3. The method of claim 1, wherein, The vehicle distances corresponding to at least two time points of the obstacle vehicle and the target vehicle are obtained, comprising: At least two first measurement distances of the obstacle vehicle and the target vehicle determined by radar ranging are obtained, and first time points corresponding to the first measurement distances are determined; At least two second measurement distances of the obstacle vehicle and the target vehicle determined by visual ranging are obtained, and second time points corresponding to the second measurement distances are determined; When there are at least two same time points in at least two first time points and at least two second time points, for each same time point in the at least two same time points, a vehicle distance of the same time point is determined according to the first measurement distance and the second measurement distance corresponding to the same time point.

4. The method of claim 3, wherein, The vehicle distance of the same time point is determined according to the first measurement distance and the second measurement distance corresponding to the same time point, comprising any one of the following methods: The vehicle distance of the same time point is determined according to the average value of the first measurement distance and the second measurement distance corresponding to the same time point; The vehicle distance of the same time point is determined according to the average value of the first measurement distance and the second measurement distance corresponding to the same time point; determine the vehicle distance at the same time according to the first measured distance and the second measured distance corresponding to the weight and the first measured distance and the second measured distance corresponding to the same time; obtain the delay time of the second measured distance determined by the visual ranging, and determine the vehicle distance at the same time according to the delay time, the first measured distance and the second measured distance corresponding to the same time.

5. The method according to any one of claims 1 to 4, characterized in that, the method further comprises: when the target vehicle is in a stationary state and there are at least three vehicle distances, determine the difference between the vehicle distances at adjacent two times; if at least two of the differences in time sequence show a decreasing trend, it is determined that the obstacle vehicle is performing a reversing operation.

6. A vehicle obstacle avoidance apparatus characterized by comprising: The device comprises: an obtaining module, configured to, when an obstacle vehicle located in the driving direction of a target vehicle is identified, obtain vehicle distances corresponding to at least two times of the obstacle vehicle and the target vehicle; the obtaining module comprises: a judging sub-module, configured to, when an obstacle vehicle located in the driving direction of a target vehicle is identified, judge whether the target vehicle is in the blind area of the field of view of the obstacle vehicle; if yes, a third obtaining sub-module is invoked; the third obtaining sub-module is configured to obtain vehicle distances corresponding to at least two times of the obstacle vehicle and the target vehicle; the judging sub-module comprises: an obtaining unit, configured to obtain offset values corresponding to the center line of the vehicle body of the target vehicle and the two side lines of the obstacle vehicle respectively; a determining unit, configured to, if the offset values are both greater than or equal to a preset offset value, determine that the target vehicle is in the blind area of the field of view of the obstacle vehicle; a judging module, configured to judge whether the obstacle vehicle is performing a reversing operation according to at least two vehicle distances; if yes, a control module is invoked; the control module is configured to, in the case that the avoidance space of the target vehicle meets a preset condition, control the target vehicle to perform an avoidance operation based on the avoidance space; the avoidance space meeting the preset condition includes that there is space around the target vehicle to enable the target vehicle to perform an avoidance operation.

7. An unmanned vehicle comprising an unmanned vehicle body, characterized by The unmanned vehicle further comprises a controller, which performs the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: The computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 5.

Images