Vehicle collision detection processing method and device, storage medium and terminal

Abstract

The application discloses a kind of vehicle collision detection processing method and device, storage medium, terminal, it is related to intelligent driving technical field, main purpose is to solve the problem of low efficiency of existing vehicle collision detection processing. Including: in the difference between the driving direction angle of vehicle and the reference direction angle of reference path is greater than preset direction threshold condition, the expansion direction of the vehicle is determined based on the difference;Obtain the expansion parameter of the vehicle, and according to the expansion direction, the vehicle is expanded based on the expansion parameter, and the vehicle profile information after expansion is obtained;Collision detection of the vehicle is carried out based on the vehicle profile information, the collision result of the vehicle is determined, to carry out path planning according to the collision result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, in particular to a vehicle collision detection processing method and device, a storage medium and a terminal. BACKGROUND

[0002] With the rapid development of intelligent driving technology, the control of the vehicle driving process is becoming more and more refined. Among them, collision detection needs to be performed during the turning driving of the vehicle to plan a route to avoid obstacles, so as to realize automatic control of the vehicle to avoid collision.

[0003] At present, the existing vehicle in the garage or multi-bend scene, such as continuous U-shaped bend, continuous right-angle bend, usually plans a reference path of the vehicle based on the longitudinal path planning strategy, and performs collision detection to control the vehicle to drive according to the reference path. However, in the scene of large-curvature turning and continuous turning, the actual orientation of the vehicle is greatly different from the path orientation of the planned reference path, and in the scene of whether collision occurs between the expected longitudinal direction and the obstacle, the collision detection may fail, and reasonable stopping cannot be performed in time, which greatly increases the risk of vehicle collision, thereby greatly reducing the processing efficiency of vehicle collision detection. SUMMARY

[0004] Therefore, the present application provides a vehicle collision detection processing method and device, a storage medium and a terminal, which mainly aims to solve the problem of low processing efficiency of existing vehicle collision detection.

[0005] According to one aspect of the present application, a vehicle collision detection processing method is provided, comprising:

[0006] When the difference between the driving orientation angle of the vehicle and the reference orientation angle of the reference path is greater than a preset orientation threshold condition, the inflation direction of the vehicle is determined based on the difference;

[0007] Obtain the inflation parameter of the vehicle, and perform inflation processing on the vehicle based on the inflation parameter in the inflation direction to obtain the inflated vehicle contour information;

[0008] Perform collision detection on the vehicle based on the vehicle contour information to determine the collision result of the vehicle, and perform path planning according to the collision result.

[0009] Further, before obtaining the inflation parameter of the vehicle, the method further comprises:

[0010] Obtain the driving speed of the vehicle, and determine the longitudinal inflation parameter matched with the driving speed based on a preset speed inflation mapping relationship;

[0011] determine a lateral inflation parameter matched with the driving orientation angle based on a preset angle inflation mapping relationship;

[0012] The preset speed inflation mapping relationship includes a linear smooth mapping relationship between different driving speeds and different longitudinal inflation coefficients, and the preset angle inflation mapping relationship includes a linear balance mapping relationship between different driving angles and different lateral inflation coefficients.

[0013] Further, the inflation direction includes a vehicle right side inflation direction and a vehicle left side inflation direction, and the determining the inflation direction of the vehicle based on the difference value includes:

[0014] When the difference value is greater than a preset difference threshold, the inflation direction of the vehicle is determined as the vehicle left side inflation direction;

[0015] When the difference value is less than the preset difference threshold, the inflation direction of the vehicle is determined as the vehicle right side inflation direction.

[0016] Further, the performing inflation processing on the vehicle based on the inflation parameter according to the inflation direction to obtain the inflated vehicle contour information includes:

[0017] extending and inflating the vehicle contour information of the vehicle based on the longitudinal inflation parameter and the lateral inflation parameter according to the vehicle left side inflation direction to obtain the inflated vehicle contour information;

[0018] extending and inflating the vehicle contour information of the vehicle based on the longitudinal inflation parameter and the lateral inflation parameter according to the vehicle right side inflation direction to obtain the inflated vehicle contour information.

[0019] Further, before the determining the inflation direction of the vehicle based on the difference value, the method further includes:

[0020] obtaining a trajectory frame of the vehicle, and determining the reference orientation angle based on that at least one trajectory point in the trajectory frame is located in a tangent direction of the reference path;

[0021] identifying vehicle contour information of the vehicle from the trajectory frame, and determining a driving orientation angle of the vehicle according to a geometric shape of the vehicle contour information;

[0022] determining a difference value between the driving orientation angle and the reference orientation angle.

[0023] Further, the performing collision detection on the vehicle based on the vehicle contour information to determine a collision result of the vehicle includes:

[0024] obtaining obstacle contour information of an obstacle in the trajectory frame of the vehicle;

[0025] Based on the overlap between the vehicle outline information and the obstacle outline information, it is determined whether a collision has occurred between the vehicle and the obstacle;

[0026] Under the condition that there is an overlap between the obstacle outline information and the vehicle outline information, it is determined that a collision is expected to occur between the vehicle and the obstacle within the time range of the corresponding trajectory frame;

[0027] If there is no overlap between the obstacle outline information and the vehicle outline information, it is determined that no collision is expected between the vehicle and the obstacle within the time range corresponding to the trajectory frame.

[0028] Furthermore, the method also includes:

[0029] If a collision is expected between the vehicle and the obstacle based on the expanded vehicle outline information, then longitudinal trajectory planning is performed based on the expanded trajectory points corresponding to the vehicle outline information, and path boundary constraints are determined based on the vehicle outline information, and lateral trajectory planning is performed according to the path boundary constraints.

[0030] According to another aspect of the present invention, a processing apparatus for vehicle collision detection is provided, comprising:

[0031] The determination module is used to determine the expansion direction of the vehicle based on the difference when the difference between the driving orientation angle of the vehicle and the reference orientation angle of the reference path is greater than a preset orientation threshold.

[0032] The acquisition module is used to acquire the expansion parameters of the vehicle, and to expand the vehicle according to the expansion direction and based on the expansion parameters to obtain the expanded vehicle outline information.

[0033] The detection module is used to perform collision detection on the vehicle based on the vehicle outline information, determine the collision result of the vehicle, and perform path planning according to the collision result.

[0034] Furthermore, the determining module is specifically used to acquire the vehicle's driving speed and determine a longitudinal expansion parameter matching the driving speed based on a preset speed expansion mapping relationship; and to determine a lateral expansion parameter matching the driving orientation angle based on a preset angle expansion mapping relationship; wherein the preset speed expansion mapping relationship includes a linear smooth mapping relationship between different driving speeds and different longitudinal expansion coefficients, and the preset angle expansion mapping relationship includes a linear balanced mapping relationship between different driving angles and different lateral expansion coefficients.

[0035] Furthermore, the expansion direction includes the expansion direction on the right side of the vehicle and the expansion direction on the left side of the vehicle, and the determining module includes:

[0036] The first determining unit is configured to determine the expansion direction of the vehicle as the left expansion direction of the vehicle when the difference is greater than a preset difference threshold.

[0037] The second determining unit is used to determine the expansion direction of the vehicle as the right-side expansion direction when the difference is less than a preset difference threshold.

[0038] Furthermore, the acquisition module is specifically used to extend and expand the vehicle outline information of the vehicle according to the left expansion direction of the vehicle, based on the longitudinal expansion parameter and the lateral expansion parameter, to obtain the expanded vehicle outline information; and to extend and expand the vehicle outline information of the vehicle according to the right expansion direction of the vehicle, based on the longitudinal expansion parameter and the lateral expansion parameter, to obtain the expanded vehicle outline information.

[0039] Furthermore, the acquisition module is also used to acquire the trajectory frame of the vehicle, and determine the reference orientation angle based on the tangent direction of at least one trajectory point in the trajectory frame being located on the reference path;

[0040] The determining module is further configured to identify the vehicle outline information of the vehicle from the trajectory frame, and determine the driving orientation angle of the vehicle based on the geometric shape of the vehicle outline information.

[0041] The determining module is also used to determine the difference between the driving orientation angle and the reference orientation angle.

[0042] Furthermore, the detection module includes:

[0043] The acquisition unit is used to acquire obstacle contour information of obstacles in the trajectory frame of the vehicle;

[0044] The first determining unit is used to determine whether a collision has occurred between the vehicle and the obstacle based on the overlap relationship between the vehicle outline information and the obstacle outline information;

[0045] The second determining unit is used to determine, under the condition that there is an overlap between the obstacle outline information and the vehicle outline information, that a collision is expected to occur between the vehicle and the obstacle within the time range of the corresponding trajectory frame;

[0046] The third determining unit is used to determine, under the condition that there is no overlap between the obstacle outline information and the vehicle outline information, that the vehicle and the obstacle are not expected to collide within the time range of the corresponding trajectory frame.

[0047] Furthermore, the device also includes:

[0048] The planning module is used to determine the expected collision between the vehicle and the obstacle based on the expanded vehicle contour information, then perform longitudinal trajectory planning based on the expanded trajectory points corresponding to the vehicle contour information, and determine the path boundary constraints based on the vehicle contour information, and perform lateral trajectory planning according to the path boundary constraints.

[0049] According to one aspect of the present invention, a vehicle is provided, including the aforementioned vehicle collision detection processing device.

[0050] According to another aspect of the present invention, a storage medium is provided, wherein at least one executable instruction is stored therein, the executable instruction causing a processor to perform an operation corresponding to the vehicle collision detection processing method described above.

[0051] According to another aspect of the present invention, a terminal is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0052] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-described vehicle collision detection processing method.

[0053] By employing the above-described technical solutions, the technical solutions provided by the embodiments of the present invention have at least the following advantages:

[0054] This invention provides a vehicle collision detection processing method, apparatus, storage medium, and terminal. Compared with existing technologies, this invention determines the vehicle's expansion direction based on the difference between the vehicle's driving orientation angle and the reference orientation angle of the reference path, provided the difference exceeds a preset orientation threshold. It then acquires the vehicle's expansion parameters and expands the vehicle according to the expansion direction and the expansion parameters to obtain expanded vehicle contour information. Based on this contour information, it performs collision detection to determine the collision result, and then performs path planning according to the collision result. This achieves efficient collision avoidance in high-curvature turns and continuous turns, significantly reducing the possibility of collisions between the vehicle and obstacles, meeting the need for reasonable vehicle braking, and thus improving the efficiency and accuracy of vehicle collision detection processing.

[0055] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0056] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0057] Figure 1 A flowchart of a vehicle collision detection processing method provided by an embodiment of the present invention is shown;

[0058] Figure 2 A flowchart of another vehicle collision detection processing method provided by an embodiment of the present invention is shown;

[0059] Figure 3 This diagram illustrates the expansion direction of the left side of a vehicle according to an embodiment of the present invention.

[0060] Figure 4 This diagram illustrates the expansion direction of the right side of a vehicle according to an embodiment of the present invention.

[0061] Figure 5 A flowchart of another vehicle collision detection processing method provided by an embodiment of the present invention is shown;

[0062] Figure 6 This diagram illustrates a vehicle-obstacle overlap collision according to an embodiment of the present invention.

[0063] Figure 7 A block diagram of a vehicle collision detection processing device provided in an embodiment of the present invention is shown;

[0064] Figure 8 A schematic diagram of the structure of a terminal provided in an embodiment of the present invention is shown. Detailed Implementation

[0065] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0066] For vehicles in underground parking garages or multi-curved scenarios, such as consecutive U-turns or right-angle turns, a reference path is typically planned based on longitudinal path planning strategies, followed by collision detection to control the vehicle to follow the reference path. However, in scenarios with sharp curves or continuous turns, the actual orientation of the vehicle differs significantly from the orientation of the planned reference path. In scenarios where a collision with an obstacle is anticipated longitudinally, collision detection may fail, preventing timely and appropriate braking and greatly increasing the risk of a collision, thus significantly reducing the efficiency of vehicle collision detection. This invention provides a vehicle collision detection method, such as... Figure 1 As shown, the method includes:

[0067] 101. When the difference between the vehicle's driving orientation angle and the reference orientation angle of the reference path is greater than a preset orientation threshold, the expansion direction of the vehicle is determined based on the difference.

[0068] In this embodiment of the invention, during intelligent driving, the current executing entity can be an autonomous driving processor controlling the vehicle, a processor configured on the vehicle, or a cloud server matching the vehicle. The current executing entity performs path planning for the vehicle to achieve autonomous driving control. After path planning, a reference path is generated, allowing the current executing entity to control the vehicle to travel along this path. The reference orientation angle of the reference path is the tangent direction at the path position point. Since the actual driving path may not perfectly match the reference path, the vehicle's driving orientation angle is the forward direction determined based on the vehicle's outline during actual driving. Of course, if the vehicle travels exactly according to the reference path, the driving orientation angle at the path position point is the same as the reference orientation angle. However, if the vehicle veers off course, a judgment is made based on the driving orientation angle and the reference orientation angle. Specifically, if the difference between the vehicle's driving orientation angle and the reference orientation angle of the reference path is greater than a preset orientation threshold, the vehicle's expansion direction is determined based on this difference, thereby enabling vehicle collision detection. The preset orientation threshold is the maximum yaw orientation angle of the pre-set device, which can be 20 degrees, 10 degrees, etc., and is not specifically limited in this embodiment of the invention. Furthermore, to improve collision detection accuracy, the expansion direction is determined based on this difference so that the current executing entity can expand the vehicle's contour information. At this time, the expansion direction includes the expansion direction to the right of the vehicle and the expansion direction to the left of the vehicle, and expansion processing is performed according to this expansion direction; is not specifically limited in this embodiment of the invention.

[0069] It should be noted that the vehicles in the autonomous driving scenario are those equipped with automatic control systems, including passenger cars and commercial vehicles. Common passenger car models include, but are not limited to, sedans, SUVs, and multi-person commercial vehicles. Common commercial vehicle models include, but are not limited to, pickup trucks, minivans, dump trucks, cargo trucks, tractor units, trailers, and mining vehicles. In this case, the vehicles can achieve autonomous driving based on the automatic control system.

[0070] 102. Obtain the expansion parameters of the vehicle, and expand the vehicle according to the expansion direction and based on the expansion parameters to obtain the expanded vehicle outline information.

[0071] In this embodiment of the invention, since the expansion direction includes the expansion direction to the right of the vehicle and the expansion direction to the left of the vehicle, in order to accurately expand the vehicle, the expansion parameters of the vehicle are first obtained. These expansion parameters include longitudinal expansion parameters and lateral expansion parameters. Then, based on the expansion direction, the vehicle contour is expanded according to the longitudinal expansion parameters and the lateral expansion parameters respectively, to obtain the expanded vehicle contour information. Specifically, since longitudinal planning of the vehicle is to plan the path length in the vehicle's forward direction, the longitudinal expansion parameters can be determined based on speed, and this embodiment of the invention does not impose specific limitations on this. Since lateral planning is to plan the path position of the vehicle in the left and right directions, the lateral expansion parameters can be determined based on angle, and this embodiment of the invention does not impose specific limitations on this.

[0072] It should be noted that the expansion process in this embodiment of the invention is to extend or lengthen the vehicle outline according to the expansion parameters in the expansion direction, thereby increasing the lateral and longitudinal outline lengths to complete the expansion process.

[0073] 103. Based on the vehicle outline information, perform collision detection on the vehicle, determine the collision result of the vehicle, and perform path planning according to the collision result.

[0074] In this embodiment of the invention, in order to improve the accuracy and effectiveness of collision detection, after the vehicle expansion is completed, collision detection is performed based on the obtained vehicle contour information to determine the collision result. Based on this collision result, the vehicle path planning is re-performed, which greatly improves the collision detection effect when the vehicle is in a scenario with large curvature turns or continuous turns.

[0075] In another embodiment of the invention, for further definition and explanation, such as Figure 2 As shown, before obtaining the expansion parameters of the vehicle, the method further includes:

[0076] 201. Obtain the vehicle's driving speed and determine the longitudinal expansion parameter that matches the driving speed based on a preset speed expansion mapping relationship;

[0077] 202. Determine the lateral expansion parameters that match the driving orientation angle based on the preset angle expansion mapping relationship.

[0078] To perform vehicle expansion based on expansion parameters and meet the requirements of speed and effectiveness in vehicle trajectory planning, longitudinal and lateral expansion parameters are predetermined. Specifically, the current executing entity obtains the actual driving speed of the vehicle and then determines the longitudinal expansion parameter based on a preset speed expansion mapping relationship. This preset speed expansion mapping relationship includes a linear and smooth mapping relationship between different driving speeds and different longitudinal expansion coefficients. Preferably, when the driving speed is between 0 m / s and 10 m / s, it linearly corresponds to longitudinal expansion parameters between 0 m and 1 m, i.e., 0 m / s corresponds to 0 m, and 1 m / s corresponds to 0.1 m, thus reflecting linear balance characteristics and ensuring that the vehicle contour expands smoothly during the expansion process. In addition, after obtaining the driving orientation angle, the current execution entity determines the lateral expansion parameters based on the preset angle expansion mapping relationship. The preset angle expansion mapping relationship includes a linear balance mapping relationship between different driving angles and different lateral expansion coefficients. Preferably, when the driving angle is 0° to 20°, it linearly corresponds to the lateral expansion parameters 0m to 1m, that is, 0° corresponds to 0m and 1° corresponds to 2m, thereby reflecting the linear balance characteristics and making the vehicle outline expand smoothly during the expansion process.

[0079] It should be noted that the current execution entity is pre-configured with preset speed expansion mapping relationships and preset angle expansion mapping relationships. The corresponding lateral expansion parameters and longitudinal expansion parameters can be pre-determined according to different driving speeds and driving orientation angles, so that they can be directly obtained when expansion processing is required. Alternatively, they can be matched based on the vehicle's real-time driving speed and driving orientation angle for acquisition; this embodiment of the invention does not impose specific limitations.

[0080] In another embodiment of the invention, for further definition and explanation, the step of determining the expansion direction of the vehicle based on the difference includes:

[0081] If the difference is greater than a preset difference threshold, the expansion direction of the vehicle is determined to be the left expansion direction of the vehicle.

[0082] If the difference is less than a preset difference threshold, the expansion direction of the vehicle is determined to be the expansion direction of the right side of the vehicle.

[0083] To accurately inflate the vehicle, the inflation direction is determined by subtracting a reference angle from the driving angle. This difference is then compared to a preset threshold to determine the required inflation direction. The preset threshold can be configured based on inflation requirements, such as 10° or 15°, to determine the inflation direction. For example, if the difference between the driving angle and the reference angle is greater than 10°, the inflation direction is determined to be to the left; if it is less than 10°, the inflation direction is determined to be to the right. The vehicle is then inflated according to this determined direction. Of course, if the difference equals the preset threshold, no inflation is required; this embodiment of the invention does not impose specific limitations on this.

[0084] In another embodiment of the invention, for further definition and explanation, the step of expanding the vehicle according to the expansion direction and based on the expansion parameters to obtain the expanded vehicle contour information includes:

[0085] According to the expansion direction on the left side of the vehicle, the vehicle outline information is extended and expanded based on the longitudinal expansion parameter and the lateral expansion parameter to obtain the expanded vehicle outline information.

[0086] According to the expansion direction on the right side of the vehicle, the vehicle outline information is extended and expanded based on the longitudinal expansion parameters and the lateral expansion parameters to obtain the expanded vehicle outline information.

[0087] To achieve high efficiency in collision detection and improve the accuracy of vehicle contour expansion based on dilation processing, the vehicle contour information is extended and expanded using longitudinal and lateral dilation parameters in different expansion directions during the dilation process. In a specific implementation scenario, such as... Figure 3 As shown, the direction of vehicle expansion

[0088] If the expansion direction is to the left of the vehicle, then based on the longitudinal expansion parameters and the lateral expansion parameters, the vehicle contour information, such as the solid line portion, is extended and expanded to obtain the vehicle contour information, such as the dashed line portion.

[0089] That is, the vehicle length in the vehicle outline information is expanded forward according to the longitudinal expansion parameter, and the vehicle width in the vehicle outline information is expanded to the right according to the lateral expansion parameter. This embodiment of the invention does not impose specific limitations. In another specific implementation scenario, such as... Figure 4 As shown, the vehicle expands in the direction of its right side.

[0090] In terms of expansion direction, the vehicle contour information, such as the solid line portion of the contour, is extended and expanded based on the longitudinal expansion parameters and the lateral expansion parameters to obtain the vehicle contour information, such as the dashed line portion. That is, the vehicle length in the vehicle contour information is extended forward according to the longitudinal expansion parameters, and the vehicle width in the vehicle contour information is extended to the left according to the lateral expansion parameters. This embodiment of the invention does not make specific limitations.

[0091] In another embodiment of the invention, for further definition and explanation, before determining the expansion direction of the vehicle based on the difference, the method further includes: 5 acquiring a trajectory frame of the vehicle, and determining the reference orientation angle based on the tangent direction of at least one trajectory point in the trajectory frame located on the reference path;

[0092] The vehicle outline information of the vehicle is identified from the trajectory frame, and the driving orientation angle of the vehicle is determined based on the geometric shape of the vehicle outline information.

[0093] Determine the difference between the driving orientation angle and the reference orientation angle.

[0094] In this embodiment of the invention, to improve the accuracy and effectiveness of collision detection by determining whether to expand the vehicle based on the driving orientation angle and the reference orientation angle, the current executing entity pre-acquires the vehicle's trajectory frame to determine the reference orientation angle and the driving orientation angle. The trajectory frame is the frame content obtained by scanning and capturing images in a coordinate system constructed based on the distance along the trajectory and the distance from the trajectory centerline. The preferred coordinate system is the Frennett coordinate system; that is, the trajectory frame captured in the Frennett coordinate system is obtained. From this trajectory frame, the trajectory points of the vehicle traveling along the reference trajectory can be obtained. For example, a reference trajectory can be formed by including at least eight trajectory points; however, this embodiment of the invention does not impose a specific limitation. Furthermore, since the reference trajectory is obtained through path planning, when determining the reference orientation angle, the orientation angle at the current moment can be determined directly based on the tangent direction of the reference path. For example, a trajectory point on the reference trajectory is selected, and the tangent direction is determined based on this trajectory point. If the vehicle deviates from the reference trajectory, the orientation angle can be determined based on the trajectory point with the smallest distance from the reference trajectory; this embodiment of the invention does not impose a specific limitation. Meanwhile, since the trajectory frame contains image information of the vehicle's outline, the orientation angle can be determined based on the vehicle's geometry at the current moment. For example, if the vehicle's geometry is determined to be rectangular based on the outline information, the orientation angle can be calculated by determining the horizontal direction of the long side of the vehicle's outline. This embodiment of the invention does not impose specific limitations. In this embodiment of the invention, since the angle is determined based on the driving orientation and reference orientation, a reference angle can be selected in the Freunrt coordinate system, and the difference can be calculated based on the driving orientation, the corresponding driving orientation angle determined by the reference orientation, and the reference orientation angle. This embodiment of the invention does not impose specific limitations.

[0095] In another embodiment of the invention, for further definition and explanation, such as Figure 5 As shown, the steps for performing collision detection on the vehicle based on the vehicle outline information and determining the collision result of the vehicle include:

[0096] 301. Obtain the obstacle outline information of the obstacles in the trajectory frame of the vehicle;

[0097] 302. Based on the overlap relationship between the vehicle outline information and the obstacle outline information, determine whether a collision has occurred between the vehicle and the obstacle;

[0098] 303. Under the condition that there is an overlap between the obstacle outline information and the vehicle outline information, it is determined that a collision is expected to occur between the vehicle and the obstacle within the time range of the corresponding trajectory frame;

[0099] 304. Under the condition that there is no overlap between the obstacle outline information and the vehicle outline information, it is determined that no collision is expected to occur between the vehicle and the obstacle within the time range of the corresponding trajectory frame.

[0100] To improve the accuracy of collision detection based on the expanded vehicle contour information, the specific steps for collision detection based on vehicle contour information are as follows: First, the obstacle contour information of obstacles in the trajectory frame is acquired, and then the overlap relationship is used to determine whether a collision has occurred. The overlap relationship between the vehicle contour information and the obstacle contour information is determined by overlapping the regions formed by the contour coordinates of the two contours. Figure 6 As shown, if the regions corresponding to the vehicle contour information and the obstacle contour information have at least one overlapping coordinate position, it can be determined that there is an overlapping relationship, and a collision is expected to occur between the vehicle and the obstacle. Furthermore, if the regions corresponding to the vehicle contour information and the obstacle contour information do not have overlapping coordinate positions, it can be determined that there is no overlapping relationship. This embodiment of the invention does not impose specific limitations.

[0101] In another embodiment of the invention, for further definition and explanation, the steps further include:

[0102] If a collision is expected between the vehicle and the obstacle based on the expanded vehicle outline information, then longitudinal trajectory planning is performed based on the expanded trajectory points corresponding to the vehicle outline information, and path boundary constraints are determined based on the vehicle outline information, and lateral trajectory planning is performed according to the path boundary constraints.

[0103] In this embodiment of the invention, to meet the requirements of efficient path planning in collision scenarios, longitudinal trajectory planning is performed based on the expanded vehicle contour information when it is determined that a collision between the vehicle and an obstacle is expected. Furthermore, during the lateral trajectory planning process, the optimization algorithm for lateral trajectory planning can be constrained by path boundary constraints. Further, path boundary constraints are determined using the expanded vehicle contour information; for example, the distance between the center position of the expanded vehicle contour and the reference path is used as a path boundary constraint. Path planning decisions are made using this path boundary constraint, thereby improving the accuracy and effectiveness of the driving path planning.

[0104] This invention provides a method for vehicle collision detection. Compared with existing technologies, this invention determines the vehicle's expansion direction based on the difference between the vehicle's driving orientation angle and the reference orientation angle of the reference path, provided the difference exceeds a preset orientation threshold. The method then acquires the vehicle's expansion parameters and expands the vehicle according to the expansion direction and the expansion parameters to obtain expanded vehicle contour information. Based on this contour information, collision detection is performed to determine the collision result, and path planning is then conducted according to the collision result. This achieves efficient collision avoidance in scenarios with high curvature turns and continuous turns, significantly reducing the possibility of collisions between the vehicle and obstacles, meeting the need for reasonable vehicle braking, and thus improving the efficiency and accuracy of vehicle collision detection.

[0105] Furthermore, as a response to the above Figure 1 The implementation of the method shown in this embodiment of the invention provides a vehicle collision detection processing device, such as... Figure 7 As shown, the device includes:

[0106] The determining module 41 is used to determine the expansion direction of the vehicle based on the difference when the difference between the driving orientation angle of the vehicle and the reference orientation angle of the reference path is greater than a preset orientation threshold.

[0107] The acquisition module 42 is used to acquire the expansion parameters of the vehicle, and expand the vehicle according to the expansion direction and based on the expansion parameters to obtain the expanded vehicle outline information.

[0108] The detection module 43 is used to perform collision detection on the vehicle based on the vehicle outline information, determine the collision result of the vehicle, and perform path planning according to the collision result.

[0109] Furthermore, the determining module is specifically used to acquire the vehicle's driving speed and determine a longitudinal expansion parameter matching the driving speed based on a preset speed expansion mapping relationship; and to determine a lateral expansion parameter matching the driving orientation angle based on a preset angle expansion mapping relationship; wherein the preset speed expansion mapping relationship includes a linear smooth mapping relationship between different driving speeds and different longitudinal expansion coefficients, and the preset angle expansion mapping relationship includes a linear balanced mapping relationship between different driving angles and different lateral expansion coefficients.

[0110] Furthermore, the expansion direction includes the expansion direction on the right side of the vehicle and the expansion direction on the left side of the vehicle, and the determining module includes:

[0111] The first determining unit is configured to determine the expansion direction of the vehicle as the left expansion direction of the vehicle when the difference is greater than a preset difference threshold.

[0112] The second determining unit is used to determine the expansion direction of the vehicle as the right-side expansion direction when the difference is less than a preset difference threshold.

[0113] Furthermore, the acquisition module is specifically used to extend and expand the vehicle outline information of the vehicle according to the left expansion direction of the vehicle, based on the longitudinal expansion parameter and the lateral expansion parameter, to obtain the expanded vehicle outline information; and to extend and expand the vehicle outline information of the vehicle according to the right expansion direction of the vehicle, based on the longitudinal expansion parameter and the lateral expansion parameter, to obtain the expanded vehicle outline information.

[0114] Furthermore, the acquisition module is also used to acquire the trajectory frame of the vehicle, and determine the reference orientation angle based on the tangent direction of at least one trajectory point in the trajectory frame being located on the reference path;

[0115] The determining module is further configured to identify the vehicle outline information of the vehicle from the trajectory frame, and determine the driving orientation angle of the vehicle based on the geometric shape of the vehicle outline information.

[0116] The determining module is also used to determine the difference between the driving orientation angle and the reference orientation angle.

[0117] Furthermore, the detection module includes:

[0118] The acquisition unit is used to acquire obstacle contour information of obstacles in the trajectory frame of the vehicle;

[0119] The first determining unit is used to determine whether a collision has occurred between the vehicle and the obstacle based on the overlap relationship between the vehicle outline information and the obstacle outline information;

[0120] The second determining unit is used to determine, under the condition that there is an overlap between the obstacle outline information and the vehicle outline information, that a collision is expected to occur between the vehicle and the obstacle within the time range of the corresponding trajectory frame;

[0121] The third determining unit is used to determine, under the condition that there is no overlap between the obstacle outline information and the vehicle outline information, that the vehicle and the obstacle are not expected to collide within the time range of the corresponding trajectory frame.

[0122] Furthermore, the device also includes:

[0123] The planning module is used to determine the expected collision between the vehicle and the obstacle based on the expanded vehicle contour information, then perform longitudinal trajectory planning based on the expanded trajectory points corresponding to the vehicle contour information, and determine the path boundary constraints based on the vehicle contour information, and perform lateral trajectory planning according to the path boundary constraints.

[0124] This invention provides a vehicle collision detection processing device. Compared with the prior art, this invention determines the expansion direction of the vehicle based on the difference between the vehicle's driving orientation angle and the reference orientation angle of the reference path, provided that the difference is greater than a preset orientation threshold. It then acquires the vehicle's expansion parameters and expands the vehicle according to the expansion direction and the expansion parameters to obtain the expanded vehicle contour information. Based on the vehicle contour information, it performs collision detection to determine the collision result, and then performs path planning according to the collision result. This achieves efficient collision avoidance in high-curvature turns and continuous turns, significantly reducing the possibility of collisions between the vehicle and obstacles, meeting the need for reasonable vehicle braking, and thus improving the efficiency and accuracy of vehicle collision detection processing.

[0125] According to one aspect of the present invention, a vehicle is provided, including the above-described vehicle collision detection processing apparatus.

[0126] According to one embodiment of the present invention, a storage medium is provided, the storage medium storing at least one executable instruction, the computer-executable instruction being able to execute the vehicle collision detection processing method in any of the above method embodiments.

[0127] Figure 8 The diagram shows a structural schematic of a terminal according to an embodiment of the present invention. The specific implementation of the terminal is not limited by the specific embodiments of the present invention.

[0128] like Figure 8 As shown, the terminal may include: a processor 502, a communications interface 504, a memory 506, and a communications bus 508.

[0129] The processor 502, communication interface 504, and memory 506 communicate with each other via communication bus 508.

[0130] Communication interface 504 is used to communicate with other network elements such as clients or other servers.

[0131] The processor 502 is used to execute program 510, specifically to execute the relevant steps in the above-described vehicle collision detection processing method embodiment.

[0132] Specifically, program 510 may include program code that includes computer operation instructions.

[0133] Processor 502 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The terminal may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0134] Memory 506 is used to store program 510. Memory 506 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0135] Specifically, program 510 can be used to cause processor 502 to perform the following operations:

[0136] If the difference between the vehicle's driving orientation angle and the reference orientation angle of the reference path is greater than a preset orientation threshold, the expansion direction of the vehicle is determined based on the difference.

[0137] Obtain the expansion parameters of the vehicle, and expand the vehicle according to the expansion direction and based on the expansion parameters to obtain the expanded vehicle outline information;

[0138] Based on the vehicle outline information, collision detection of the vehicle is performed to determine the collision result of the vehicle, and path planning is performed according to the collision result.

[0139] Obviously, those skilled in the art should understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be executable by a computing device.

[0140] The steps are implemented using line-by-line program code, which can then be stored in a storage device and executed by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be implemented as separate integrated circuit modules, or multiple modules or steps can be implemented as a single integrated circuit module. Thus, the invention is not limited to any particular combination of hardware and software.

[0141] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for vehicle collision detection, characterized in that, include: If the difference between the vehicle's driving orientation angle and the reference orientation angle of the reference path is greater than a preset orientation threshold, the expansion direction of the vehicle is determined based on the difference. Obtain the expansion parameters of the vehicle, and expand the vehicle according to the expansion direction and based on the expansion parameters to obtain the expanded vehicle outline information. The expansion process is to extend or lengthen the outline of the vehicle according to the expansion parameters based on the vehicle outline information in the expansion direction to increase the lateral and longitudinal outline lengths, thereby completing the expansion process. Based on the vehicle outline information, collision detection of the vehicle is performed to determine the collision result, and path planning is performed according to the collision result.

2. The method according to claim 1, characterized in that, Before obtaining the expansion parameters of the vehicle, the method further includes: The vehicle's speed is obtained, and a longitudinal expansion parameter matching the speed is determined based on a preset speed expansion mapping relationship. The lateral expansion parameters that match the driving orientation angle are determined based on a preset angle expansion mapping relationship; The preset speed expansion mapping relationship includes a linear smooth mapping relationship between different driving speeds and different longitudinal expansion coefficients, and the preset angle expansion mapping relationship includes a linear balanced mapping relationship between different driving angles and different lateral expansion coefficients.

3. The method according to claim 2, characterized in that, The expansion direction includes the expansion direction on the right side of the vehicle and the expansion direction on the left side of the vehicle. Determining the expansion direction of the vehicle based on the difference includes: If the difference is greater than a preset difference threshold, the expansion direction of the vehicle is determined to be the left expansion direction of the vehicle. If the difference is less than a preset difference threshold, the expansion direction of the vehicle is determined to be the expansion direction of the right side of the vehicle.

4. The method according to claim 3, characterized in that, The step of expanding the vehicle according to the expansion direction and based on the expansion parameters to obtain the expanded vehicle outline information includes: According to the expansion direction on the left side of the vehicle, the vehicle outline information is extended and expanded based on the longitudinal expansion parameter and the lateral expansion parameter to obtain the expanded vehicle outline information. According to the expansion direction on the right side of the vehicle, the vehicle outline information is extended and expanded based on the longitudinal expansion parameters and the lateral expansion parameters to obtain the expanded vehicle outline information.

5. The method according to claim 1, characterized in that, Before determining the expansion direction of the vehicle based on the difference, the method further includes: The trajectory frame of the vehicle is acquired, and the reference orientation angle is determined based on the tangent direction of at least one trajectory point in the trajectory frame being located on the reference path. The vehicle outline information of the vehicle is identified from the trajectory frame, and the driving orientation angle of the vehicle is determined based on the geometric shape of the vehicle outline information. Determine the difference between the driving orientation angle and the reference orientation angle.

6. The method according to claim 1, characterized in that, The step of performing collision detection on the vehicle based on the vehicle outline information and determining the collision result of the vehicle includes: Obtain obstacle contour information from the vehicle's trajectory frame; Based on the overlap between the vehicle outline information and the obstacle outline information, it is determined whether a collision has occurred between the vehicle and the obstacle; Under the condition that there is an overlap between the obstacle outline information and the vehicle outline information, it is determined that a collision is expected to occur between the vehicle and the obstacle within the time range of the corresponding trajectory frame; If there is no overlap between the obstacle outline information and the vehicle outline information, it is determined that no collision is expected between the vehicle and the obstacle within the time range corresponding to the trajectory frame.

7. The method according to claim 6, characterized in that, The method further includes: If a collision is expected between the vehicle and the obstacle based on the expanded vehicle outline information, then longitudinal trajectory planning is performed based on the expanded trajectory points corresponding to the vehicle outline information, and path boundary constraints are determined based on the vehicle outline information, and lateral trajectory planning is performed according to the path boundary constraints.

8. A processing device for vehicle collision detection, characterized in that, include: The determination module is used to determine the expansion direction of the vehicle based on the difference when the difference between the driving orientation angle of the vehicle and the reference orientation angle of the reference path is greater than a preset orientation threshold. The acquisition module is used to acquire the expansion parameters of the vehicle, and to expand the vehicle according to the expansion direction and based on the expansion parameters to obtain the expanded vehicle outline information. The expansion process is to extend or lengthen the outline of the vehicle according to the expansion parameters based on the vehicle outline information in the expansion direction to increase the lateral and longitudinal outline lengths, thereby completing the expansion process. The detection module is used to perform collision detection on the vehicle based on the vehicle outline information, determine the collision result of the vehicle, and perform path planning according to the collision result.

9. A vehicle, characterized in that, The processing device for vehicle collision detection as described in claim 8.

10. A storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the vehicle collision detection processing method as described in any one of claims 1-7.

11. A terminal, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the operation corresponding to the vehicle collision detection processing method as described in any one of claims 1-7.

Images