Obstacle prediction method and device for vehicle, vehicle-mounted terminal and medium

Abstract

The invention is suitable for the technical field of automobiles, and provides a vehicle obstacle prediction method and device, a vehicle-mounted terminal and a medium, and the method comprises the steps: detecting a candidate obstacle having a collision risk with a target vehicle on a road when the target vehicle runs on the road; detecting first motion information of the candidate obstacle and a relative speed between the candidate obstacle and the target vehicle; according to the first motion information, second motion information of the target vehicle and the relative speed, predicting first position information of the target vehicle and second position information of the candidate obstacle when the target vehicle collides with the candidate obstacle; performing collision detection processing according to the first position information and the second position information by using a bounding box algorithm to obtain a collision detection result; and if the collision detection result is that collision exists, determining the candidate obstacle as a predicted obstacle of the target vehicle. Compared with the prior art, the method provided by the invention has the advantage that the obstacle prediction accuracy is improved.

Description

Technical Field

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

[0002] Autonomous driving has become a hot topic in the automotive field, and safety is one of the most critical factors restricting autonomous driving technology. Obviously, predicting the collision of vehicles to determine the target obstacles of the vehicles plays an important role in ensuring the safety of autonomous vehicles.

[0003] The existing technology usually only predicts collisions based on the distance between the target vehicle and other vehicles, and then determines the target obstacle corresponding to the target vehicle based on the collision prediction result, so as to control the target vehicle to avoid the obstacle. Since the existing technology simply predicts collisions based on distance, it is not comprehensive enough and cannot accurately determine the target obstacle corresponding to the target vehicle, which reduces the accuracy of obstacle prediction. Summary of the invention

[0004] The embodiments of the present application provide a vehicle obstacle prediction method, device, vehicle-mounted terminal and medium, which improve the prediction accuracy of vehicle obstacles.

[0005] In a first aspect, an embodiment of the present application provides a method for predicting an obstacle of a vehicle, comprising:

[0006] When the target vehicle is traveling on a road, detecting candidate obstacles on the road that have a risk of collision with the target vehicle;

[0007] Detecting first motion information of the candidate obstacle and a relative speed between the candidate obstacle and the target vehicle;

[0008] Predicting, based on the first motion information, the second motion information of the target vehicle, and the relative speed, first position information of the target vehicle and second position information of the candidate obstacle when the target vehicle collides with the candidate obstacle;

[0009] Using a bounding box algorithm, performing collision detection processing according to the first position information and the second position information to obtain a collision detection result;

[0010] If the collision detection result is a collision, the candidate obstacle is determined as the predicted obstacle of the target vehicle.

[0011] Optionally, when the target vehicle is traveling on a road, detecting candidate obstacles on the road that have a risk of collision with the target vehicle includes:

[0012] Obtaining vehicle obstacle probability information output by the auxiliary driving system of the target vehicle;

[0013] Detecting vehicle information of other vehicles on the road that are within a preset range from the target vehicle, and detecting distance information between the target vehicle and the other vehicles;

[0014] Whether the other vehicle becomes the candidate obstacle is determined according to the vehicle obstacle probability information, the vehicle information, and the distance information.

[0015] Optionally, the vehicle obstacle probability information includes a first probability value of the existence of the other vehicle and a second probability value of the other vehicle becoming the candidate obstacle, the vehicle information includes a type, a state, and a moving direction of the other vehicle, and determining the candidate obstacle from the other vehicles according to the vehicle obstacle probability information, the vehicle information, and the distance information includes:

[0016] If the first probability value is greater than or equal to a first threshold value, and the second probability value is greater than or equal to a second threshold value, determining a first proportional factor for the other vehicle to become the candidate obstacle according to the type, state, and movement direction of the other vehicle;

[0017] Determining, based on the distance information between the target vehicle and the other vehicle, a second proportional factor for the other vehicle to become the candidate obstacle;

[0018] Whether the other vehicle becomes the candidate obstacle is determined according to the first scale factor and the second scale factor.

[0019] Optionally, the first motion information includes a first motion direction of the candidate obstacle, the second motion information includes a first speed and a second motion direction of the target vehicle, and predicting, based on the first motion information, the second motion information of the target vehicle, and the relative speed, the first position information of the target vehicle and the second position information of the candidate obstacle when the target vehicle collides with the candidate obstacle, includes:

[0020] Calculating a second speed of the candidate obstacle according to the first speed and the relative speed;

[0021] Calculate the first position information according to the first speed, the second movement direction and the set collision duration;

[0022] The second position information is calculated according to the second speed, the first moving direction and the collision duration.

[0023] Optionally, the using a bounding box algorithm to perform collision detection processing according to the first position information and the second position information to obtain a collision detection result includes:

[0024] Acquire a first length, a first width, and a first heading angle of the target vehicle, and acquire a second length, a second width, and a second heading angle of the candidate obstacle;

[0025] Constructing a first bounding box corresponding to the target vehicle according to the first length, the first width, the first heading angle, and the first position information;

[0026] constructing a second bounding box corresponding to the candidate obstacle according to the second length, the second width, the second heading angle, and the second position information;

[0027] A collision detection process is performed according to the first bounding box and the second bounding box to obtain the collision detection result.

[0028] Optionally, performing collision detection processing according to the first bounding box and the second bounding box to obtain the collision detection result includes:

[0029] Performing intersection detection on the first bounding box and the second bounding box according to a polygon intersection judgment algorithm to obtain a bounding box intersection detection result;

[0030] If the bounding box intersection detection result is that there is intersection, then determining the collision detection result is that there is collision;

[0031] If the bounding box intersection detection result is no intersection, then the collision detection result is determined to be no collision.

[0032] Optionally, the first position information is composed of the first position coordinates of the target vehicle at various moments within a set collision duration; the second position information is composed of the second position coordinates of the candidate obstacle at various moments within the collision duration; and the collision detection result is obtained by performing collision detection processing based on the first position information and the second position information using a bounding box algorithm, including:

[0033] According to the bounding box algorithm, a third bounding box of the target vehicle at each of the first position coordinates is obtained, and a fourth bounding box of the candidate obstacle at each of the second position coordinates is obtained;

[0034] Performing collision detection processing on the third bounding box and the fourth bounding box at the same time to obtain the collision detection results at each time;

[0035] Accordingly, after determining the candidate obstacle as the predicted obstacle of the target vehicle, the method further includes:

[0036] If the collision detection result at the target time is a collision, the collision distance between the target vehicle and the predicted obstacle is calculated according to the current driving time of the target vehicle and the target time; wherein the target time is any time within the collision duration;

[0037] The target vehicle is controlled to decelerate according to the current driving time, the target time and the collision distance.

[0038] In a second aspect, an embodiment of the present application provides a vehicle obstacle prediction device, comprising:

[0039] A first detection unit is used to detect candidate obstacles on the road that have a collision risk with the target vehicle when the target vehicle is traveling on the road;

[0040] A second detection unit, configured to detect first motion information of the candidate obstacle and a relative speed between the candidate obstacle and the target vehicle;

[0041] a prediction unit, configured to predict, based on the first motion information, the second motion information of the target vehicle, and the relative speed, first position information of the target vehicle and second position information of the candidate obstacle when the target vehicle collides with the candidate obstacle;

[0042] A first processing unit, configured to use a bounding box algorithm to perform collision detection processing according to the first position information and the second position information to obtain a collision detection result;

[0043] The first determining unit is configured to determine the candidate obstacle as a predicted obstacle of the target vehicle if the collision detection result is a collision.

[0044] In a third aspect, an embodiment of the present application provides a vehicle-mounted terminal, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the vehicle obstacle prediction method as described in any one of the first aspects above is implemented.

[0045] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle obstacle prediction method as described in any one of the above-mentioned first aspects is implemented.

[0046] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a vehicle-mounted terminal, the vehicle-mounted terminal can execute the vehicle obstacle prediction method described in any one of the first aspects above.

[0047] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0048] The embodiment of the present application provides a method for predicting obstacles of a vehicle, which detects candidate obstacles on the road that have a risk of collision with the target vehicle when the target vehicle is traveling on the road; detects the first motion information of the candidate obstacle, and the relative speed between the candidate obstacle and the target vehicle; predicts the first position information of the target vehicle and the second position information of the candidate obstacle when the target vehicle collides with the candidate obstacle based on the first motion information, the second motion information of the target vehicle, and the relative speed; uses a bounding box algorithm to perform collision detection processing based on the first position information and the second position information to obtain a collision detection result; if the collision detection result is a collision, the candidate obstacle is determined as the predicted obstacle of the target vehicle. The embodiment of the present application can first predict the position where the vehicle and the candidate obstacle collide, and then perform collision detection on the vehicle and the candidate obstacle at the position to determine the final obstacle corresponding to the vehicle, which improves the accuracy of obstacle prediction compared with the prior art that performs collision detection based only on distance. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 is a flow chart of an implementation method of a vehicle obstacle prediction method provided in an embodiment of the present application;

[0051] Figure 2 is a schematic diagram of a candidate obstacle that crosses and has a risk of collision with a target vehicle provided by an embodiment of the present application;

[0052] Figure 3 is a flow chart of an implementation method of an obstacle prediction method for a vehicle provided in another embodiment of the present application;

[0053] Figure 4 is a flow chart of an implementation method of an obstacle prediction method for a vehicle provided in yet another embodiment of the present application;

[0054] Figure 5is a flow chart of an implementation method of an obstacle prediction method for a vehicle provided in another embodiment of the present application;

[0055] Figure 6 is a flow chart of an implementation method of an obstacle prediction method for a vehicle provided in another embodiment of the present application;

[0056] Figure 7 is a schematic structural diagram of a vehicle obstacle prediction device provided in one embodiment of the present application;

[0057] Figure 8 It is a structural diagram of a vehicle-mounted terminal provided in one embodiment of the present application. DETAILED DESCRIPTION

[0058] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0059] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0060] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0061] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0062] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0063] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0064] See also Figure 1 , Figure 1 The following is a flowchart of an implementation of a vehicle obstacle prediction method provided by an embodiment of the present application. In the embodiment of the present application, the execution subject of the vehicle obstacle prediction method is a vehicle-mounted terminal.

[0065] like Figure 1 As shown, the vehicle obstacle prediction method provided by an embodiment of the present application may include S101 to S105, which are described in detail as follows:

[0066] In S101 , when a target vehicle is traveling on a road, candidate obstacles on the road that have a risk of collision with the target vehicle are detected.

[0067] In the embodiment of the present application, in order to improve the user experience, obstacles with a risk of collision with the target vehicle are determined in advance to decelerate the target vehicle, thereby avoiding the collision. When the target vehicle is detected to be traveling on the road, the vehicle-mounted terminal can detect candidate obstacles on the road with a risk of collision with the target vehicle. The candidate obstacles can be obstacles that are transverse to the driving direction of the target vehicle.

[0068] For example, see Figure 2 , Figure 2 is a schematic diagram of a candidate obstacle that crosses and has a collision risk with the target vehicle, wherein A represents the target vehicle and B represents the candidate obstacle.

[0069] It should be noted that the candidate obstacle may be one or more.

[0070] In one embodiment of the present application, the vehicle-mounted terminal can be specifically configured as follows: Figure 3 Steps S201 to S203 shown in the figure determine candidate obstacles that have a risk of collision with the target vehicle, as detailed below:

[0071] In S201, vehicle obstacle probability information output by the auxiliary driving system of the target vehicle is obtained.

[0072] In this embodiment, the assisted driving system of the target vehicle may be an advanced driving assistance system.

[0073] In actual applications, the Advanced Driving Assistance System (ADAS) uses a variety of sensors installed on the vehicle (such as millimeter-wave radar, lidar, monocular / binocular cameras, and satellite navigation, etc.) to sense the surrounding environment at any time during the vehicle's driving, collect data, and identify, detect, and track static and dynamic objects. It also combines navigation map data to perform systematic calculations and analysis, thereby allowing the driver to be aware of possible dangers in advance and effectively increasing the comfort and safety of car driving.

[0074] Based on this, in this embodiment, the vehicle terminal can obtain the vehicle obstacle probability information through the above-mentioned auxiliary driving system in the vehicle.

[0075] The vehicle obstacle probability information includes, but is not limited to: a first probability value of the existence of other vehicles and a second probability value of other vehicles becoming candidate obstacles for the target vehicle.

[0076] In S202, vehicle information of other vehicles on the road that are within a preset range from the target vehicle is detected, and distance information between the target vehicle and the other vehicles is detected.

[0077] In this embodiment, the target vehicle is equipped with sensors such as laser radar, monocular / binocular cameras, etc. Therefore, the vehicle terminal can obtain the vehicle information of other vehicles within the preset range of the target vehicle in real time through the above sensors, and detect the distance information between the target vehicle and each other vehicle. Among them, the preset range can be determined according to actual needs and is not limited here.

[0078] In some possible embodiments, the preset range may be determined according to the detection range of the above-mentioned sensor.

[0079] The vehicle information of other vehicles includes, but is not limited to: the type, status and movement direction of other vehicles.

[0080] The distance information includes but is not limited to the horizontal distance and the vertical distance.

[0081] In S203, it is determined whether the other vehicle becomes the candidate obstacle according to the vehicle obstacle probability information, the vehicle information and the distance information.

[0082] In this embodiment, for any other vehicle, the vehicle-mounted terminal can determine the first weight corresponding to the vehicle obstacle probability information of the other vehicle, the second weight corresponding to the vehicle information of the other vehicle, and the third weight corresponding to the distance information between the other vehicle and the target vehicle.

[0083] In some possible embodiments, since the importance of vehicle obstacle probability information is greater than vehicle information and distance information, and the importance of distance information is greater than vehicle information, the first weight is greater than the second weight and the third weight, and the third weight is greater than the second weight.

[0084] It should be noted that, for any other vehicle, the vehicle terminal can compare the vehicle obstacle probability information of the other vehicle with the standard obstacle probability information to obtain the first score of the vehicle obstacle probability information of the other vehicle; compare the vehicle information of the other vehicle with the standard vehicle information to obtain the second score of the vehicle information of the other vehicle; compare the distance information of the other vehicle with the standard distance information to obtain the third score of the distance information of the other vehicle. Among them, the standard obstacle probability information, standard vehicle information and standard distance information can all be set according to actual needs and are not limited here.

[0085] Based on this, the vehicle terminal can sum the first score, the second score, the third score, the first weight, the second weight and the third weight to obtain the total score corresponding to each other vehicle, and compare the total score with the set score. The set score can be determined according to actual needs and is not limited here.

[0086] In this embodiment, when the vehicle terminal detects that the total score of any other vehicle is greater than or equal to the set score, it can determine that the other vehicle is a candidate obstacle; when the vehicle terminal detects that the total score of any other vehicle is less than the set score, it can determine that the other vehicle is not a candidate obstacle.

[0087] In one embodiment of the present application, in combination with S201 to S202, since the vehicle obstacle probability information includes the first probability value of the existence of other vehicles and the second probability value of other vehicles becoming candidate obstacles, and the vehicle information includes the type, state, and movement direction of other vehicles, for any other vehicle, the vehicle-mounted terminal can compare the first probability value of the other vehicle with the first threshold value, and compare the second probability value of the other vehicle with the second threshold value. The first threshold value and the second threshold value can be set according to actual needs and are not limited here.

[0088] In this embodiment, when the vehicle terminal detects that the first probability value of the other vehicle is greater than or equal to the first threshold value, and the second probability value is greater than or equal to the second threshold value, it indicates that the other vehicle has a probability of becoming a candidate obstacle. Therefore, in order to further improve the accuracy of determining the candidate obstacle, for any other vehicle, the vehicle terminal can also Figure 4 Steps S301 to S303 shown implement step S203, which are described in detail as follows:

[0089] In S301, if the first probability value is greater than or equal to a first threshold value, and the second probability value is greater than or equal to a second threshold value, a first proportional factor of the other vehicle becoming the candidate obstacle is determined according to the type, state and movement direction of the other vehicle.

[0090] In this embodiment, when the vehicle-mounted terminal detects that the first probability value of the above-mentioned other vehicles is greater than or equal to the first threshold, and the second probability value is greater than or equal to the second threshold, it indicates that the other vehicle has a probability of becoming a candidate obstacle. Therefore, in order to further improve the accuracy of determining the candidate obstacles, the vehicle-mounted terminal can determine the first proportional factor of the other vehicle becoming a candidate obstacle based on the type, state and movement direction of the other vehicle.

[0091] The states of other vehicles include but are not limited to stationary state and moving state.

[0092] In S302, a second proportional factor for the other vehicle to become the candidate obstacle is determined according to the distance information between the target vehicle and the other vehicle.

[0093] In this embodiment, combined with S202, since the larger the lateral distance and / or longitudinal distance between the target vehicle and the other vehicles, the higher the risk of collision between the target vehicle and the other vehicles, the on-board terminal can determine the second proportional factor for the other vehicles to become candidate obstacles based on the distance information between the target vehicle and the other vehicles.

[0094] In S303, it is determined whether the other vehicle becomes the candidate obstacle according to the first scale factor and the second scale factor.

[0095] In this embodiment, after obtaining the first proportional factor and the second proportional factor, the vehicle-mounted terminal may import the first proportional factor and the second proportional factor into a preset conversion formula to calculate the target probability value of the other vehicles becoming candidate obstacles.

[0096] In one embodiment of the present application, the preset conversion formula is specifically:

[0097] P = α*(l1*S1)+β*(l2*S2);

[0098] Among them, P represents the target probability value, l1 represents the first proportional factor, S1 represents the reference vehicle information, l2 represents the second proportional factor, S2 represents the reference distance information, α represents the first preset coefficient corresponding to the first proportional factor, and β represents the second preset coefficient corresponding to the second proportional factor.

[0099] The first preset coefficient and the second preset coefficient can be set according to actual needs and are not limited here.

[0100] It should be noted that the reference vehicle information and reference distance information can be determined according to actual needs and are not limited here.

[0101] In this embodiment, after determining the target probability value of the other vehicles being candidate obstacles, the vehicle-mounted terminal may compare the target probability value with a set probability value, wherein the set probability value may be set and determined according to actual needs and is not limited here.

[0102] When the vehicle-mounted terminal detects that the target probability value of the other vehicle becoming a candidate obstacle is greater than or equal to the set probability value, it can determine that the other vehicle is a candidate obstacle; when the vehicle-mounted terminal detects that the target probability value of the other vehicle becoming a candidate obstacle is less than the set probability value, it can determine that the other vehicle is not a candidate obstacle.

[0103] In S102, first motion information of the candidate obstacle and a relative speed between the candidate obstacle and the target vehicle are detected.

[0104] In the embodiment of the present application, the first motion information includes but is not limited to the first motion direction of the candidate obstacle.

[0105] In one implementation of an embodiment of the present application, the vehicle-mounted terminal can detect the first motion information of the candidate obstacle and the relative speed between the candidate obstacle and the target vehicle in real time through various sensors set in the vehicle (such as lidar, camera, distance sensor, etc.).

[0106] In S103, based on the first motion information, the second motion information of the target vehicle, and the relative speed, the first position information of the target vehicle and the second position information of the candidate obstacle are predicted when the target vehicle collides with the candidate obstacle.

[0107] It should be noted that the second motion information includes but is not limited to the first speed and the second motion direction of the target vehicle.

[0108] The first position information is used to describe the coordinate information of the center of the target vehicle, and the second position information is used to describe the coordinate information of the center of the candidate obstacle.

[0109] In one embodiment of the present application, the vehicle-mounted terminal may specifically predict the first position information of the target vehicle and the second position information of the candidate obstacle through the following steps, which are described in detail as follows:

[0110] Calculating a second speed of the candidate obstacle according to the first speed and the relative speed;

[0111] Calculate the first position information according to the first speed, the second movement direction and the set collision duration;

[0112] The second position information is calculated according to the second speed, the first moving direction and the collision duration.

[0113] In this embodiment, the collision time is used to describe the time period from the moment the target vehicle discovers the candidate obstacle to the moment the target vehicle collides with the candidate obstacle. The collision time can be set according to actual needs and is not limited here.

[0114] The vehicle-mounted terminal can calculate the first driving distance of the target vehicle based on the first speed of the target vehicle and the above-mentioned collision duration. Afterwards, the vehicle-mounted terminal can determine the first position information of the target vehicle based on the first initial position of the target vehicle at the initial moment of the collision duration, the above-mentioned first driving distance and the second movement direction of the target vehicle.

[0115] The vehicle-mounted terminal can calculate the second driving distance of the candidate obstacle based on the second speed of the candidate obstacle and the above-mentioned collision time. Afterwards, the vehicle-mounted terminal can determine the second position information of the candidate obstacle based on the second initial position of the candidate obstacle at the initial moment of the collision time, the above-mentioned second driving distance and the first movement direction of the candidate obstacle.

[0116] In S104, a bounding box algorithm is used to perform collision detection processing according to the first position information and the second position information to obtain a collision detection result.

[0117] In practical applications, the bounding box algorithm is an algorithm for solving the optimal bounding space of a discrete point set. The basic idea is to use a slightly larger geometric body with simpler characteristics (called a bounding box) to approximately replace complex geometric objects. Among them, the bounding box algorithm includes but is not limited to axis-aligned bounding box (AABB), bounding sphere (Sphere), oriented bounding box (OBB) and fixed directions hulls (FDH or k-DOP).

[0118] In this embodiment, the vehicle terminal can use a bounding box algorithm to construct a first bounding box corresponding to the target vehicle with the coordinates described by the first position information as the center, and construct a second bounding box corresponding to the candidate obstacle with the coordinates described by the second position information as the center.

[0119] Based on this, the vehicle-mounted terminal can perform collision detection processing according to the first bounding box and the second bounding box to obtain a collision detection result between the target vehicle and the candidate obstacle.

[0120] It should be noted that the collision detection results include but are not limited to collision and no collision.

[0121] In some possible embodiments, the vehicle-mounted terminal may detect whether there is an overlapping portion between the first bounding box and the second bounding box, so as to detect whether a collision occurs between the target vehicle and the candidate obstacle.

[0122] In this embodiment, when the vehicle-mounted terminal detects that there is an overlapping part between the first bounding box and the second bounding box, it can determine that the collision detection result between the target vehicle and the candidate obstacle is a collision. When the vehicle-mounted terminal detects that there is no overlapping part between the first bounding box and the second bounding box, it can determine that the collision detection result between the target vehicle and the candidate obstacle is no collision.

[0123] In one embodiment of the present application, in order to restore the true shapes of the target vehicle and the candidate obstacles to improve the accuracy of collision detection of the target vehicle and the candidate obstacles, the vehicle-mounted terminal can specifically perform the following steps: Figure 5 The collision detection results obtained in steps S401 to S404 are described in detail as follows:

[0124] In S401, a first length, a first width, and a first heading angle of the target vehicle are obtained, and a second length, a second width, and a second heading angle of the candidate obstacle are obtained.

[0125] In S402, a first bounding box corresponding to the target vehicle is constructed according to the first length, the first width, the first heading angle, and the first position information.

[0126] In S403, a second bounding box corresponding to the candidate obstacle is constructed according to the second length, the second width, the second heading angle, and the second position information.

[0127] In S404, collision detection processing is performed according to the first bounding box and the second bounding box to obtain the collision detection result.

[0128] In practical applications, the vehicle heading angle refers to the angular difference between the vehicle's forward direction and the vehicle's longitudinal axis, that is, the angle between the vehicle's front wheel steering angle and the vehicle's driving direction.

[0129] In one implementation of this embodiment, the vehicle-mounted terminal can obtain the first length and the first width of the target vehicle in real time through a server to which it is wirelessly connected, and obtain the front wheel steering angle of the target vehicle in real time through an angle sensor in the vehicle.

[0130] Afterwards, the vehicle-mounted terminal can determine the first heading angle of the target vehicle according to the driving direction of the target vehicle and the above-mentioned front wheel steering angle.

[0131] In another implementation of this embodiment, the vehicle-mounted terminal can obtain the second length, the second width and the front wheel steering angle of the candidate obstacle in real time through sensors such as laser radar and camera in the vehicle.

[0132] Afterwards, the vehicle-mounted terminal may determine the second heading angle of the candidate obstacle according to the traveling direction of the candidate obstacle and the front wheel steering angle.

[0133] Based on this, the vehicle-mounted terminal can construct a first bounding box corresponding to the target vehicle according to the first length, the first width, the first heading angle and the first position information, that is, restore the true shape of the target vehicle at the first position information.

[0134] The vehicle-mounted terminal can construct a second bounding box corresponding to the candidate obstacle according to the second length, the second width, the second heading angle and the second position information, that is, restore the real shape of the candidate obstacle at the second position information.

[0135] Based on this, the vehicle-mounted terminal can perform collision detection processing according to the first bounding box and the second bounding box to obtain a collision detection result between the target vehicle and the candidate obstacle.

[0136] In one embodiment of the present application, the vehicle-mounted terminal can implement step S403 by the following steps, which are described in detail as follows:

[0137] Performing intersection detection on the first bounding box and the second bounding box according to a polygon intersection judgment algorithm to obtain a bounding box intersection detection result;

[0138] If the bounding box intersection detection result is that there is intersection, then determining the collision detection result is that there is collision;

[0139] If the bounding box intersection detection result is no intersection, then the collision detection result is determined to be no collision.

[0140] In practical applications, polygon intersection judgment algorithms include but are not limited to fast elimination algorithms, vector cross-product straddle algorithms, and ray algorithms.

[0141] In this embodiment, the vehicle terminal can detect whether there is an edge-to-edge intersection between the first bounding box and the second bounding box based on the polygon intersection judgment algorithm, that is, at least one edge of the first bounding box intersects with at least one edge of the second bounding box, thereby obtaining a bounding box intersection detection result.

[0142] It should be noted that the bounding box intersection detection results include but are not limited to intersection and no intersection.

[0143] Based on this, when the vehicle-mounted terminal detects that the bounding box intersection detection result is intersection, it indicates that there is an overlap between the first bounding box and the second bounding box. Therefore, the vehicle-mounted terminal can determine that the collision detection result between the target vehicle and the candidate obstacle is collision.

[0144] When the vehicle-mounted terminal detects that the bounding box intersection detection result is no intersection, it means that there is no overlapping part between the first bounding box and the second bounding box. Therefore, the vehicle-mounted terminal can determine that the collision detection result between the target vehicle and the candidate obstacle is no collision.

[0145] In S105 , if the collision detection result is a collision, the candidate obstacle is determined as a predicted obstacle for the target vehicle.

[0146] In the embodiment of the present application, when the vehicle-mounted terminal detects that the collision detection result between the target vehicle and the candidate obstacle is a collision, it means that there is indeed a collision risk between the target vehicle and the candidate obstacle. Therefore, the vehicle-mounted terminal can determine the candidate obstacle as the predicted obstacle of the target vehicle.

[0147] Based on this, after determining the predicted obstacle of the target vehicle, the on-board terminal can control the target vehicle to detour according to the distance between the target vehicle and the predicted obstacle and the driving direction of the predicted obstacle to avoid collision with the predicted obstacle.

[0148] From the above, it can be seen that the obstacle prediction method for a vehicle provided by the embodiment of the present application detects candidate obstacles on the road that have a risk of collision with the target vehicle when the target vehicle is traveling on the road; detects the first motion information of the candidate obstacle, and the relative speed between the candidate obstacle and the target vehicle; predicts the first position information of the target vehicle and the second position information of the candidate obstacle when the target vehicle collides with the candidate obstacle based on the first motion information, the second motion information of the target vehicle, and the relative speed; uses the bounding box algorithm to perform collision detection processing based on the first position information and the second position information to obtain a collision detection result; if the collision detection result is a collision, the candidate obstacle is determined as the predicted obstacle of the target vehicle. The embodiment of the present application can first predict the position where the vehicle and the candidate obstacle collide, and then perform collision detection on the vehicle and the candidate obstacle at the position to determine the final obstacle corresponding to the vehicle. Compared with the prior art that performs collision detection based only on distance, the prediction accuracy of the obstacle is improved.

[0149] See also Figure 6 , Figure 6 Another embodiment of the present application provides a method for predicting vehicle obstacles. Figure 1 Corresponding embodiment, in this embodiment, step S104 specifically includes S501-S502, and correspondingly, step S105 specifically includes S503-S504, which are described in detail as follows:

[0150] In S501, according to the bounding box algorithm, a third bounding box of the target vehicle at each of the first position coordinates is obtained, and a fourth bounding box of the candidate obstacle at each of the second position coordinates is obtained.

[0151] It should be noted that, in this embodiment, the first position information is composed of the first position coordinates of the target vehicle at each moment within the set collision duration, and correspondingly, the second position information is composed of the second position coordinates of the candidate obstacle at each moment within the set collision duration.

[0152] Based on this, the vehicle-mounted terminal can construct a third bounding box corresponding to the target vehicle at each moment according to the bounding box algorithm, with the first position coordinates at each moment as the center; and construct a fourth bounding box corresponding to the candidate obstacle at each moment with the second position coordinates at each moment as the center.

[0153] In S502, collision detection processing is performed on the third bounding box and the fourth bounding box at the same time to obtain the collision detection results at the respective times.

[0154] In this embodiment, at any time, the vehicle terminal can perform collision detection on the third bounding box corresponding to the target vehicle at that time and the fourth bounding box corresponding to the candidate obstacle to obtain the collision detection result between the target vehicle and the candidate obstacle at that time.

[0155] Specifically, the vehicle-mounted terminal may detect whether there is an overlapping portion between the third bounding box and the fourth bounding box, so as to detect whether a collision occurs between the target vehicle and the candidate obstacle.

[0156] When the vehicle-mounted terminal detects that there is an overlapping part between the above-mentioned third bounding box and the fourth bounding box, it can determine that the collision detection result between the target vehicle and the candidate obstacle is a collision. When the vehicle-mounted terminal detects that there is no overlapping part between the above-mentioned third bounding box and the fourth bounding box, it can determine that the collision detection result between the target vehicle and the candidate obstacle is no collision.

[0157] In S503, if the collision detection result at the target time is a collision, the collision distance between the target vehicle and the predicted obstacle is calculated according to the current driving time of the target vehicle and the target time; wherein the target time is any time within the collision duration.

[0158] In this embodiment, when the vehicle-mounted terminal detects that the collision detection result at the target time is a collision, it means that there is indeed a risk of collision between the target vehicle and the candidate obstacle at the target time. That is to say, the vehicle-mounted terminal can determine that the candidate obstacle is a predicted obstacle. Therefore, in order to successfully avoid the collision, the vehicle-mounted terminal can calculate the collision distance between the target vehicle and the predicted obstacle based on the current driving time of the target vehicle and the target time.

[0159] It should be noted that the current driving time refers to the time when the target vehicle detects the candidate obstacle.

[0160] In this embodiment, the vehicle-mounted terminal can calculate the driving time of the target vehicle based on the current driving time of the target vehicle and the target time. The vehicle-mounted terminal can then obtain the current speed of the target vehicle and calculate the collision distance between the target vehicle and the predicted obstacle based on the current speed and driving time.

[0161] In S504, the target vehicle is controlled to decelerate according to the current driving time, the target time and the collision distance.

[0162] In this embodiment, the vehicle-mounted terminal calculates the driving time of the target vehicle based on the current driving time of the target vehicle and the target time, which is the predicted collision time between the target vehicle and the predicted obstacle. Therefore, the vehicle-mounted terminal can control the speed of the target vehicle in real time according to the predicted collision time and collision distance, that is, reduce the speed of the target vehicle in real time according to the predicted collision time and collision distance to avoid collision.

[0163] From the above, it can be seen that the vehicle obstacle prediction method provided by this embodiment obtains the third bounding box of the target vehicle at each first position coordinate and obtains the fourth bounding box of the candidate obstacle at each second position coordinate according to the bounding box algorithm; performs collision detection processing on the third bounding box and the fourth bounding box at the same time to obtain the collision detection results at each time; if the collision detection result at the target time is a collision, the collision distance between the target vehicle and the predicted obstacle is calculated according to the current driving time and the target time of the target vehicle; and the target vehicle is controlled to decelerate according to the current driving time, the target time and the collision distance. The method provided by this embodiment can control the target vehicle to decelerate in real time and flexibly according to the current driving time, the target time and the collision distance of the target vehicle, thereby improving the success rate of the target vehicle in avoiding collisions, thereby reducing the risk of collision damage to the target vehicle, and further ensuring the safety of the target vehicle and the personnel using the target vehicle.

[0164] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0165] Corresponding to the vehicle obstacle prediction method described in the above embodiment, Figure 7 The structure diagram of a vehicle obstacle prediction device provided by an embodiment of the present application is shown. For the convenience of explanation, only the part related to the embodiment of the present application is shown. Figure 7 The vehicle obstacle prediction device 700 includes: a first detection unit 71, a second detection unit 72, a prediction unit 73, a first processing unit 74 and a first determination unit 75. Among them:

[0166] The first detection unit 71 is used to detect candidate obstacles on the road that have a risk of collision with the target vehicle when the target vehicle is traveling on the road.

[0167] The second detection unit 72 is used to detect the first motion information of the candidate obstacle and the relative speed between the candidate obstacle and the target vehicle.

[0168] The prediction unit 73 is used to predict the first position information of the target vehicle and the second position information of the candidate obstacle when the target vehicle collides with the candidate obstacle based on the first motion information, the second motion information of the target vehicle and the relative speed.

[0169] The first processing unit 74 is configured to use a bounding box algorithm to perform collision detection processing according to the first position information and the second position information to obtain a collision detection result.

[0170] The first determination unit 75 is configured to determine the candidate obstacle as a predicted obstacle of the target vehicle if the collision detection result is a collision.

[0171] In one embodiment of the present application, the first detection unit 71 specifically includes: a first acquisition unit, a third detection unit and a second determination unit. Among them:

[0172] The first acquisition unit is used to acquire vehicle obstacle probability information output by the auxiliary driving system of the target vehicle.

[0173] The third detection unit is used to detect vehicle information of other vehicles on the road that are within a preset range from the target vehicle, and to detect distance information between the target vehicle and the other vehicles.

[0174] The second determination unit is used to determine whether the other vehicle becomes the candidate obstacle according to the vehicle obstacle probability information, the vehicle information and the distance information.

[0175] In one embodiment of the present application, the vehicle obstacle probability information includes a first probability value of the existence of the other vehicle and a second probability value of the other vehicle becoming the candidate obstacle, and the vehicle information includes the type, state and movement direction of the other vehicle; the second determination unit specifically includes: a third determination unit, a fourth determination unit and a fifth determination unit. Among them:

[0176] The third determination unit is used to determine a first proportional factor for the other vehicle to become the candidate obstacle according to the type, state and movement direction of the other vehicle if the first probability value is greater than or equal to a first threshold and the second probability value is greater than or equal to a second threshold.

[0177] The fourth determining unit is used to determine a second proportional factor for the other vehicle to become the candidate obstacle according to the distance information between the target vehicle and the other vehicle.

[0178] The fifth determining unit is used to determine whether the other vehicle becomes the candidate obstacle according to the first proportional factor and the second proportional factor.

[0179] In one embodiment of the present application, the first motion information includes the first motion direction of the candidate obstacle, and the second motion information includes the first speed and the second motion direction of the target vehicle; the prediction unit 73 specifically includes: a first calculation unit, a second calculation unit and a third calculation unit. Among them:

[0180] The first calculation unit is used to calculate a second speed of the candidate obstacle according to the first speed and the relative speed.

[0181] The second calculation unit is used to calculate the first position information according to the first speed, the second movement direction and the set collision duration.

[0182] The third calculation unit is used to calculate the second position information according to the second speed, the first moving direction and the collision duration.

[0183] In one embodiment of the present application, the first processing unit 74 specifically includes: a second acquisition unit, a first construction unit, a second construction unit and a second processing unit.

[0184] The second acquisition unit is used to acquire the first length, the first width and the first heading angle of the target vehicle, and to acquire the second length, the second width and the second heading angle of the candidate obstacle.

[0185] The first construction unit is used to construct a first bounding box corresponding to the target vehicle according to the first length, the first width, the first heading angle, and the first position information.

[0186] The second construction unit is used to construct a second bounding box corresponding to the candidate obstacle according to the second length, the second width, the second heading angle, and the second position information.

[0187] The second processing unit is used for performing collision detection processing according to the first bounding box and the second bounding box to obtain the collision detection result.

[0188] In one embodiment of the present application, the second processing unit specifically includes: a fourth detection unit, a sixth determination unit and a seventh determination unit.

[0189] The fourth detection unit is used to perform intersection detection on the first bounding box and the second bounding box according to a polygon intersection judgment algorithm to obtain a bounding box intersection detection result.

[0190] The sixth determination unit is configured to determine that the collision detection result is a collision if the bounding box intersection detection result is an intersection.

[0191] The seventh determination unit is configured to determine that the collision detection result is no collision if the bounding box intersection detection result is no intersection.

[0192] In one embodiment of the present application, the first position information is composed of the first position coordinates of the target vehicle at various times within the set collision duration; the second position information is composed of the second position coordinates of the candidate obstacle at various times within the collision duration; the first processing unit 74 specifically includes: a third acquisition unit and a fifth detection unit. Among them:

[0193] The third acquisition unit is used to acquire, according to the bounding box algorithm, a third bounding box of the target vehicle at each of the first position coordinates, and acquire a fourth bounding box of the candidate obstacle at each of the second position coordinates.

[0194] The fifth detection unit is used to perform collision detection processing on the third bounding box and the fourth bounding box at the same time, and obtain the collision detection results at the respective time.

[0195] Correspondingly, the vehicle obstacle prediction device 700 further includes: a fourth calculation unit and a control unit.

[0196] in:

[0197] The fourth calculation unit is used to calculate the collision distance between the target vehicle and the predicted obstacle according to the current driving time of the target vehicle and the target time if the collision detection result at the target time is a collision; wherein the target time is any time within the collision duration.

[0198] The control unit is used to control the target vehicle to decelerate according to the current driving time, the target time and the collision distance.

[0199] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0200] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by 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 embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0201] Figure 8 This is a schematic diagram of the structure of a vehicle-mounted terminal provided in one embodiment of the present application. Figure 8 As shown, the vehicle terminal 8 of this embodiment includes: at least one processor 80 ( Figure 8 Only one is shown in the figure) a processor, a memory 81, and a computer program 82 stored in the memory 81 and executable on the at least one processor 80, and when the processor 80 executes the computer program 82, the steps in the above-mentioned obstacle prediction method embodiment of any of the vehicles are implemented.

[0202] The vehicle terminal may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will appreciate that Figure 8 It is only an example of the vehicle-mounted terminal 8 and does not constitute a limitation on the vehicle-mounted terminal 8. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0203] The processor 80 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0204] In some embodiments, the memory 81 may be an internal storage unit of the vehicle-mounted terminal 8, such as the memory of the vehicle-mounted terminal 8. In other embodiments, the memory 81 may also be an external storage device of the vehicle-mounted terminal 8, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the vehicle-mounted terminal 8. Further, the memory 81 may also include both the internal storage unit of the vehicle-mounted terminal 8 and an external storage device. The memory 81 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 81 may also be used to temporarily store data that has been output or is to be output.

[0205] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0206] An embodiment of the present application provides a computer program product. When the computer program product runs on a vehicle-mounted terminal, the vehicle-mounted terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0207] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the vehicle-mounted terminal, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0208] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0209] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A vehicle obstacle prediction method, characterized in that: include: When the target vehicle is traveling on a road, detecting candidate obstacles on the road that have a risk of collision with the target vehicle; Detecting first motion information of the candidate obstacle and a relative speed between the candidate obstacle and the target vehicle; Predicting, based on the first motion information, the second motion information of the target vehicle, and the relative speed, first position information of the target vehicle and second position information of the candidate obstacle when the target vehicle collides with the candidate obstacle; Using a bounding box algorithm, performing collision detection processing according to the first position information and the second position information to obtain a collision detection result; If the collision detection result is a collision, the candidate obstacle is determined as a predicted obstacle for the target vehicle.

2. The obstacle prediction method according to claim 1, characterized in that: When the target vehicle is traveling on a road, detecting candidate obstacles on the road that have a risk of collision with the target vehicle includes: Obtaining vehicle obstacle probability information output by the auxiliary driving system of the target vehicle; Detecting vehicle information of other vehicles on the road that are within a preset range from the target vehicle, and detecting distance information between the target vehicle and the other vehicles; Whether the other vehicle becomes the candidate obstacle is determined according to the vehicle obstacle probability information, the vehicle information, and the distance information.

3. The obstacle prediction method according to claim 2, characterized in that: The vehicle obstacle probability information includes a first probability value of the existence of the other vehicle and a second probability value of the other vehicle becoming the candidate obstacle, the vehicle information includes the type, state and movement direction of the other vehicle, and determining the candidate obstacle from the other vehicles according to the vehicle obstacle probability information, the vehicle information and the distance information includes: If the first probability value is greater than or equal to a first threshold value, and the second probability value is greater than or equal to a second threshold value, determining a first proportional factor for the other vehicle to become the candidate obstacle according to the type, state, and movement direction of the other vehicle; Determining, based on the distance information between the target vehicle and the other vehicle, a second proportional factor for the other vehicle to become the candidate obstacle; Whether the other vehicle becomes the candidate obstacle is determined according to the first scale factor and the second scale factor.

4. The obstacle prediction method according to claim 1, characterized in that: The first motion information includes a first motion direction of the candidate obstacle, the second motion information includes a first speed and a second motion direction of the target vehicle, and the predicting, based on the first motion information, the second motion information of the target vehicle, and the relative speed, first position information of the target vehicle and second position information of the candidate obstacle when the target vehicle collides with the candidate obstacle includes: Calculating a second speed of the candidate obstacle according to the first speed and the relative speed; Calculate the first position information according to the first speed, the second movement direction and the set collision duration; The second position information is calculated according to the second speed, the first moving direction and the collision duration.

5. The obstacle prediction method according to any one of claims 1 to 4, characterized in that: The using of the bounding box algorithm to perform collision detection processing according to the first position information and the second position information to obtain a collision detection result includes: Acquire a first length, a first width, and a first heading angle of the target vehicle, and acquire a second length, a second width, and a second heading angle of the candidate obstacle; Constructing a first bounding box corresponding to the target vehicle according to the first length, the first width, the first heading angle, and the first position information; constructing a second bounding box corresponding to the candidate obstacle according to the second length, the second width, the second heading angle, and the second position information; A collision detection process is performed according to the first bounding box and the second bounding box to obtain the collision detection result.

6. The obstacle prediction method according to claim 5, characterized in that: The performing collision detection processing according to the first bounding box and the second bounding box to obtain the collision detection result includes: Performing intersection detection on the first bounding box and the second bounding box according to a polygon intersection judgment algorithm to obtain a bounding box intersection detection result; If the bounding box intersection detection result is that there is intersection, then determining the collision detection result is that there is collision; If the bounding box intersection detection result is no intersection, then the collision detection result is determined to be no collision.

7. The obstacle prediction method according to claim 1, characterized in that: The first position information is composed of the first position coordinates of the target vehicle at each time within the set collision duration; the second position information is composed of the second position coordinates of the candidate obstacle at each time within the collision duration; the collision detection process is performed based on the first position information and the second position information using the bounding box algorithm to obtain a collision detection result, including: According to the bounding box algorithm, a third bounding box of the target vehicle at each of the first position coordinates is obtained, and a fourth bounding box of the candidate obstacle at each of the second position coordinates is obtained; Performing collision detection processing on the third bounding box and the fourth bounding box at the same time to obtain the collision detection results at each time; Accordingly, after determining the candidate obstacle as the predicted obstacle of the target vehicle, the method further includes: If the collision detection result at the target time is a collision, the collision distance between the target vehicle and the predicted obstacle is calculated according to the current driving time of the target vehicle and the target time; wherein the target time is any time within the collision duration; The target vehicle is controlled to decelerate according to the current driving time, the target time and the collision distance.

8. A vehicle obstacle prediction device, characterized in that: include: A first detection unit is used to detect candidate obstacles on the road that have a collision risk with the target vehicle when the target vehicle is traveling on the road; A second detection unit, configured to detect first motion information of the candidate obstacle and a relative speed between the candidate obstacle and the target vehicle; a prediction unit, configured to predict, based on the first motion information, the second motion information of the target vehicle, and the relative speed, first position information of the target vehicle and second position information of the candidate obstacle when the target vehicle collides with the candidate obstacle; A first processing unit, configured to use a bounding box algorithm to perform collision detection processing according to the first position information and the second position information to obtain a collision detection result; The first determining unit is configured to determine the candidate obstacle as a predicted obstacle of the target vehicle if the collision detection result is a collision.

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

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

Images