Vehicle collision detection method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides a vehicle collision detection method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring first travel information of a first vehicle, i.e., a predicted trajectory of the first vehicle and a bounding box of the first vehicle; on the basis of the first travel information and a predicted trajectory and a specified distance of a target vehicle, determining a collision risk area between the target vehicle and the first vehicle; detecting a first positional relationship between the bounding box of the first vehicle and the collision risk area, and a second positional relationship between the position of the target vehicle and the collision risk area; and on the basis of the first positional relationship and the second positional relationship, detecting whether there is a risk of collision between the target vehicle and the first vehicle. The technical solution of the present disclosure can determine a trajectory collision area between autonomous driving vehicles, efficiently and rapidly detect vehicle collisions, and shorten the time in vehicle collision detection, thereby providing a trajectory planning basis for the autonomous driving vehicles in advance.

Description

Vehicle collision detection method, device, electronic device and storage medium Technical Field

[0001] The present disclosure relates to the fields of unmanned driving and vehicle technology, and more particularly to a vehicle collision detection method, device, electronic device, and storage medium. Background Art

[0002] Ensuring the safe operation of autonomous vehicles is crucial for autonomous mines. Due to the complex nature of mine operations, the constantly changing working environment, and the presence of numerous open areas, rapid and effective trajectory collision detection between autonomous vehicles and other vehicles is essential to ensure safety within a specific area. This facilitates more effective decision-making regarding subsequent vehicle actions.

[0003] The existing trajectory collision detection is computationally time-consuming and requires high computing power, which cannot meet the real-time requirements of the decision-making and planning module in the unmanned driving scenario of mines. Summary of the Invention

[0004] The embodiments of the present disclosure at least provide a vehicle collision detection method, device, electronic device, and storage medium.

[0005] In a first aspect, an embodiment of the present disclosure provides a vehicle collision detection method, comprising:

[0006] Acquire first driving information of a first vehicle; wherein the first driving information includes: a predicted trajectory of the first vehicle and a bounding box of the first vehicle;

[0007] determining a collision risk area between the target vehicle and the first vehicle based on the first driving information and second driving information of the target vehicle, wherein the second driving information includes a predicted trajectory and a specified distance of the target vehicle;

[0008] detecting a first positional relationship between a bounding box of the first vehicle and the collision risk area, and a second positional relationship between a position of the target vehicle and the collision risk area;

[0009] Based on the first positional relationship and the second positional relationship, it is detected whether there is a collision risk between the target vehicle and the first vehicle.

[0010] In an optional implementation manner, the obtaining the first driving information of the first vehicle includes: obtaining the first driving information in a Cartesian coordinate system;

[0011] The determining, based on the first driving information and the second driving information of the target vehicle, a collision risk area between the target vehicle and the first vehicle includes:

[0012] Projecting the first driving information from a Cartesian coordinate system to a Frenet coordinate system to obtain projected first driving information; wherein the Frenet coordinate system is a Frenet coordinate system constructed based on the predicted trajectory of the target vehicle;

[0013] Based on the projected first driving information and the second driving information, a collision risk area between the target vehicle and the first vehicle is determined.

[0014] In an optional implementation manner, obtaining the first driving information of the first vehicle includes:

[0015] The first driving information is obtained according to a preset period; wherein the preset period is determined based on a preset time interval or a preset driving distance.

[0016] In an optional implementation, determining a collision risk area between the target vehicle and the first vehicle based on the first driving information and the second driving information of the target vehicle includes:

[0017] If it is determined based on the first driving information of the current cycle and the first driving information of the previous cycle that the predicted trajectory of the first vehicle has not changed, determining the collision risk area of ​​the current cycle based on the collision risk area determined by the first driving information of the previous cycle;

[0018] or,

[0019] If it is determined based on the first driving information of the current cycle and the first driving information of the previous cycle that the predicted trajectory of the first vehicle has changed, a new collision risk area is determined as the collision risk area of ​​the current cycle based on the first driving information of the current cycle and the second driving information.

[0020] In an optional implementation, detecting whether there is a collision risk between the target vehicle and the first vehicle based on the first position relationship and the second position relationship includes:

[0021] When it is determined based on the first positional relationship that any corner point of the bounding box of the first vehicle is located within the collision risk area, and when it is determined based on the second positional relationship that the target vehicle is located within the collision risk area at a target moment, it is determined that there is a collision risk between the target vehicle and the first vehicle; wherein the target moment is the moment when any corner point is located within the collision risk area.

[0022] In an optional implementation, determining a collision risk area between the target vehicle and the first vehicle based on the first driving information and the second driving information of the target vehicle includes:

[0023] determining a predicted driving area of ​​the first vehicle based on the predicted trajectory of the first vehicle and a bounding box of the first vehicle;

[0024] The collision risk area is determined according to intersection information between the predicted driving area and a target driving area of ​​the target vehicle, wherein the target driving area is determined based on the second driving information and the designated distance.

[0025] In an optional embodiment, determining the collision risk area based on intersection information between the predicted driving area and the target driving area of ​​the target vehicle includes:

[0026] Determining a first intersection point and a last intersection point between the predicted driving area and the target driving area along a traveling direction of the target vehicle or the first vehicle;

[0027] The collision risk area is determined based on an area between the first intersection and the last intersection in the target driving area.

[0028] In an optional implementation, determining the collision risk area based on the target driving area between the first intersection and the last intersection includes:

[0029] Determine a target area enclosed by a first perpendicular line passing through the first intersection and perpendicular to an area boundary of the target driving area, a second perpendicular line passing through the last intersection and perpendicular to the area boundary, and the area boundary;

[0030] The collision risk area is determined according to the target area.

[0031] In an optional embodiment, determining the collision risk area based on intersection information between the predicted driving area and the target driving area of ​​the target vehicle includes:

[0032] Based on the position of the first origin of the vehicle coordinate system of the target vehicle and the position of the second origin of the coordinate system of the positioning sensor of the target vehicle, the target area is corrected to obtain the collision risk area after correction, wherein the target area is a part of the target driving area determined based on the intersection information.

[0033] In an optional embodiment, the target area is corrected based on the position of the first origin of the vehicle coordinate system of the target vehicle and the position of the second origin of the coordinate system of the positioning sensor of the target vehicle to obtain the collision risk area after correction, including:

[0034] Extending a first boundary of the target area by a first distance along a traveling direction of the target vehicle, and extending a second boundary of the target area by a second distance in a direction opposite to the traveling direction, to obtain the collision risk area;

[0035] Among them, the first distance is the distance between the first origin and the rear of the target vehicle, the second distance is the distance between the first origin and the second origin along the body direction of the target vehicle, the second boundary is the first vertical line passing through the first intersection between the predicted driving area and the target driving area and perpendicular to the area boundary of the target driving area, and the first boundary is the second vertical line passing through the last intersection between the predicted driving area and the target driving area and perpendicular to the area boundary.

[0036] In a second aspect, an embodiment of the present disclosure provides a vehicle collision detection device, comprising:

[0037] An acquiring unit is configured to acquire first driving information of a first vehicle; wherein the first driving information includes: a predicted trajectory of the first vehicle and a bounding box of the first vehicle;

[0038] a determining unit configured to determine a collision risk area between the target vehicle and the first vehicle based on the first driving information and second driving information of the target vehicle, wherein the second driving information includes a predicted trajectory and a specified distance of the target vehicle;

[0039] a first detection unit configured to detect a first positional relationship between a bounding box of the first vehicle and the collision risk area, and a second positional relationship between a position of the target vehicle and the collision risk area;

[0040] The second detection unit is configured to detect whether there is a collision risk between the target vehicle and the first vehicle based on the first position relationship and the second position relationship.

[0041] In a third aspect, an embodiment of the present disclosure further provides an electronic device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the above-mentioned first aspect or any possible implementation of the first aspect are performed.

[0042] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect or any possible implementation of the first aspect are executed.

[0043] In an embodiment of the present disclosure, first, first driving information of a first vehicle is obtained, and then, based on the first driving information and the second driving information of the target vehicle, a collision risk area between the target vehicle and the first vehicle is determined; thereafter, a first positional relationship between the bounding box of the first vehicle in the first driving information and the collision risk area is detected, and a second positional relationship between the position of the target vehicle and the collision risk area is detected; finally, based on the first positional relationship and the second positional relationship, it is detected whether there is a collision risk between the target vehicle and the first vehicle.

[0044] In the above embodiment, by determining the collision risk area between the target vehicle and the first vehicle, and then performing collision detection on the target vehicle and the first vehicle through the first position relationship between the bounding box of the first vehicle and the collision risk area, and the second position relationship between the position of the target vehicle and the collision risk area, vehicle collisions can be detected efficiently and quickly, reducing the time consumption of vehicle collision detection, and providing a trajectory planning basis for the decision-making planning module of the target vehicle, so that the decision-making planning module can make more effective action decisions on the subsequent actions of the autonomous driving vehicle, thereby ensuring safe driving between autonomous driving vehicles in mining scenarios.

[0045] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0047] FIG1 shows a flow chart of a vehicle collision detection method provided by an embodiment of the present disclosure;

[0048] FIG2 shows a schematic diagram of coordinates of a bounding box of a first vehicle in a Cartesian coordinate system provided by an embodiment of the present disclosure;

[0049] FIG3 shows a schematic diagram of determining a trajectory collision area provided by an embodiment of the present disclosure;

[0050] FIG4 shows a flow chart of another vehicle collision detection method provided by an embodiment of the present disclosure;

[0051] FIG5 shows a schematic diagram of a vehicle collision detection method device provided by an embodiment of the present disclosure;

[0052] FIG6 shows a schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the disclosure for which protection is sought, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0054] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0055] The term "and / or" herein simply describes an association relationship, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, and the existence of B alone. In addition, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0056] Ensuring the safe operation of autonomous vehicles is crucial for autonomous mines. Due to the complex nature of mine operations, the constantly changing working environment, and the presence of numerous open areas, rapid and effective trajectory collision detection between autonomous vehicles and other vehicles is essential to ensure safety within a specific area. This facilitates more effective decision-making regarding subsequent vehicle actions.

[0057] The existing trajectory collision detection is computationally time-consuming and requires high computing power, which cannot meet the real-time requirements of the decision-making and planning module in the unmanned driving scenario of mines.

[0058] Based on the above research, the present disclosure provides a vehicle collision detection method, apparatus, electronic device, and storage medium. In an embodiment of the present disclosure, first, first driving information of a first vehicle is obtained. Then, based on the first driving information and second driving information of a target vehicle, a collision risk area between the target vehicle and the first vehicle is determined. Next, a first positional relationship between the bounding box of the first vehicle in the first driving information and the collision risk area is detected, as well as a second positional relationship between the position of the target vehicle and the collision risk area. Finally, based on the first and second positional relationships, whether there is a collision risk between the target vehicle and the first vehicle is detected.

[0059] In the above embodiment, by determining the collision risk area between the target vehicle and the first vehicle, and then performing collision detection on the target vehicle and the first vehicle through the first position relationship between the bounding box of the first vehicle and the collision risk area, and the second position relationship between the position of the target vehicle and the collision risk area, vehicle collisions can be detected efficiently and quickly, reducing the time consumption of vehicle collision detection, and providing a trajectory planning basis for the decision-making planning module of the target vehicle, so that the decision-making planning module can make more effective action decisions on the subsequent actions of the autonomous driving vehicle, thereby ensuring safe driving between autonomous driving vehicles in mining scenarios.

[0060] To facilitate understanding of this embodiment, we first provide a detailed introduction to a vehicle collision detection method disclosed in this embodiment. The vehicle collision detection method provided in this embodiment is generally executed by an electronic device with certain computing capabilities, which can be located on a cloud platform or an unmanned vehicle. In some possible implementations, the vehicle collision detection method can be implemented by a processor invoking computer-readable instructions stored in a memory.

[0061] 1 , which is a flow chart of a vehicle collision detection method provided by an embodiment of the present disclosure, includes steps S101 to S104, wherein:

[0062] S101: Acquire first driving information of a first vehicle; wherein the first driving information includes: a predicted trajectory of the first vehicle and a bounding box of the first vehicle.

[0063] Here, the target vehicle may be a vehicle executing autonomous driving in an unmanned mine scenario, such as a mining truck. The first vehicle may be a vehicle (either a manned vehicle or an unmanned vehicle) that may be at risk of collision with the target vehicle in the unmanned mine scenario. The predicted trajectory in the first driving information includes the coordinates of the position points (i.e., the trajectory point coordinates) and the driving direction.

[0064] In an embodiment of the present disclosure, the target vehicle may request the first driving information of the first vehicle from the control center; alternatively, the target vehicle and the first vehicle may obtain corresponding driving information through a collaborative device installed on the vehicles, for example, the target vehicle may request the first driving information from the first vehicle through the collaborative device.

[0065] Autonomous driving equipment in mining scenarios typically has a pre-planned driving trajectory and records it in a control center. Furthermore, autonomous driving equipment in mining scenarios can periodically report its own driving trajectory to the control center. At this point, the target vehicle can request the control center for the first driving information of the first vehicle.

[0066] In the embodiment of the present disclosure, along the predicted trajectory of the first vehicle, a trajectory point can be determined at every preset length, and the coordinates of the trajectory point are the coordinates of the position point; then, a bounding box of the first vehicle is constructed for the trajectory point.

[0067] S102: Determine a collision risk area between the target vehicle and the first vehicle based on the first driving information and second driving information of the target vehicle, wherein the second driving information includes a predicted trajectory and a specified distance of the target vehicle.

[0068] Here, the collision risk area may be understood as an area where there is a collision risk between the first vehicle and the target vehicle. For example, the collision risk area may be an intersecting driving area of ​​the first vehicle and the target vehicle.

[0069] Here, the predicted trajectory of the target vehicle includes the coordinates of the target vehicle's location point and the target vehicle's driving direction; the specified distance can be a safe distance of the target vehicle, wherein the safe distance can be understood as a safe driving distance of the target vehicle, and the safe distance can be determined by the target vehicle's capability boundary; or associated with the target vehicle's attributes, including: vehicle type, operation type, vehicle size and other information of the target vehicle.

[0070] In addition, the specified distance may also be other specified fixed or adjustable distances. For example, the specified distance may be any distance greater than the safety distance.

[0071] S103: Detecting a first positional relationship between the bounding box of the first vehicle and the collision risk area, and a second positional relationship between the position of the target vehicle and the collision risk area.

[0072] Here, the first positional relationship between the bounding box of the first vehicle and the collision risk area may include the following relationship: the corner points of the bounding box are located within the collision risk area, or the corner points of the bounding box are located outside the collision risk area. The second positional relationship between the position of the target vehicle and the collision risk area may include the following relationship: the target vehicle is located within the collision risk area, or the target vehicle is located outside the collision risk area.

[0073] In the embodiment of the present disclosure, while detecting the first positional relationship between the bounding box of the first vehicle and the collision risk area, the second positional relationship between the position of the target vehicle and the collision risk area may be detected.

[0074] S104: Detecting whether there is a collision risk between the target vehicle and the first vehicle based on the first position relationship and the second position relationship.

[0075] In the above embodiment, by determining the collision risk area between the target vehicle and the first vehicle, and then performing collision detection on the target vehicle and the first vehicle through the first position relationship between the bounding box of the first vehicle and the collision risk area, and the second position relationship between the position of the target vehicle and the collision risk area, vehicle collisions can be detected efficiently and quickly, reducing the time consumption of vehicle collision detection, and providing a trajectory planning basis for the decision-making planning module of the target vehicle, so that the decision-making planning module can make more effective action decisions on the subsequent actions of the autonomous driving vehicle, thereby ensuring safe driving between autonomous driving vehicles in mining scenarios.

[0076] The above steps will be described in detail below in conjunction with specific implementation methods.

[0077] In an embodiment of the present disclosure, before obtaining the first driving information of the first vehicle, all vehicles in the driving area where the target vehicle is located can be obtained as alternative vehicles; at this time, there may be vehicles in a stationary state among the alternative vehicles, or there may be vehicles that have no trajectory collision with the target vehicle.

[0078] Here, the static vehicles among the alternative vehicles can be removed; then, the predicted trajectories of the remaining alternative vehicles are obtained; and the trajectory position relationship between the predicted trajectory and the driving trajectory of the target vehicle is determined; wherein, if it is determined that the trajectory position relationship satisfies any of the following, it is determined that the alternative vehicle is not the first vehicle: the predicted trajectory is parallel to the driving trajectory of the target vehicle, the trajectory of the predicted trajectory after turning at the turning point is a driving trajectory away from the target vehicle, and the trajectory end point of the predicted trajectory is not within the safe driving area of ​​the target vehicle.

[0079] If the trajectory position relationship is determined to satisfy any of the above conditions, the predicted trajectory is determined to be an invalid trajectory. In this case, the candidate vehicle can be eliminated and the eliminated candidate vehicle is determined to be the first vehicle. If the trajectory position is determined to not satisfy any of the above conditions and the candidate vehicle is not a static vehicle, the candidate vehicle is determined to be the first vehicle that meets the collision detection requirements.

[0080] The above implementation can screen out vehicles that may collide with the target vehicle's driving trajectory, thereby reducing the computational complexity of trajectory collision detection and further ensuring the real-time requirements of trajectory planning.

[0081] After the first vehicle is determined, first driving information of the first vehicle may be obtained, specifically including: obtaining the first driving information in a Cartesian coordinate system.

[0082] In an embodiment of the present disclosure, a predicted trajectory of the first vehicle in a Cartesian coordinate system can be obtained; thereafter, in the Cartesian coordinate system, based on the coordinates of the position point in the predicted trajectory, the driving direction, and the attributes of the first vehicle (e.g., size, type), the corner point positions of the bounding box of the first vehicle corresponding to the position point can be solved. For example, the bounding box of the first vehicle as shown in FIG2 can be obtained. For example, as shown in FIG2, the corner points of the bounding box are the points shown as (x1, y1), (x2, y2), (x3, y3), and (x4, y4).

[0083] After acquiring the first driving information in a Cartesian coordinate system, a collision risk area between the target vehicle and the first vehicle may be determined based on the first driving information and the second driving information of the target vehicle, specifically comprising the following steps:

[0084] First, projecting the first driving information from a Cartesian coordinate system to a Frenet coordinate system to obtain projected first driving information; wherein the Frenet coordinate system is a Frenet coordinate system constructed based on the predicted trajectory of the target vehicle;

[0085] Secondly, based on the projected first driving information and the second driving information, a collision risk area between the target vehicle and the first vehicle is determined.

[0086] As can be seen from the above description, the first driving information of the first vehicle is driving information obtained in a Cartesian coordinate system. At this time, it is necessary to transform the first driving information in the Cartesian coordinate system into a Frenet coordinate system constructed based on the driving trajectory of the target vehicle to obtain the projected first driving information.

[0087] After obtaining the projected first driving information, it can be determined whether there is any projected first driving information with a large projection error, wherein if there is any, the projected first driving information with a large projection error is deleted.

[0088] For example, it may be determined whether the bounding box of the first vehicle after projection is deformed. If it is determined that the deformation of the bounding box of the first vehicle after projection is significant, the first driving information corresponding to the bounding box of the first vehicle may be deleted. For another example, it may be determined that the positional error of the coordinates of a position point in the predicted trajectory of the first vehicle after projection is significant. If it is determined that the positional error of the coordinates of the position point after projection is significant, the first driving information corresponding to the bounding box of the first vehicle may be deleted.

[0089] After deleting the severely deformed projected first driving information, a collision risk area between the target vehicle and the first vehicle may be determined based on the remaining projected first driving information and the second driving information.

[0090] In the above embodiment, by projecting the first driving information into the Frenet coordinate system and performing trajectory collision detection in the Frenet coordinate system, the detection process can be simplified, thereby achieving fast and accurate trajectory collision detection.

[0091] In the disclosed embodiment, in addition to obtaining the first driving information in a Cartesian coordinate system, the first driving information may also be obtained in other coordinate systems, for example, in a polar coordinate system. The first driving information obtained in the polar coordinate system is then projected from the polar coordinate system to the Frenet coordinate system.

[0092] In the embodiment of the present disclosure, the above step S101 of obtaining the first driving information of the first vehicle includes the following steps:

[0093] The first driving information is obtained according to a preset period; wherein the preset period is determined based on a preset time interval or a preset driving distance.

[0094] In an embodiment of the present disclosure, first driving information of a first vehicle may be acquired at a preset period. After acquiring the first driving information in each period, a collision risk area between the target vehicle and the first vehicle may be determined based on the first driving information acquired each time and the second driving information of the target vehicle. A first positional relationship between a bounding box of the first vehicle and the collision risk area, as well as a second positional relationship between the position of the target vehicle and the collision risk area, may be detected. Based on the first positional relationship and the second positional relationship, whether there is a collision risk between the target vehicle and the first vehicle may be detected.

[0095] Here, the preset period can be determined based on a preset time interval or a preset driving distance. The preset time interval can be a time interval selected by relevant technicians based on experience; it can also be a time interval determined based on the driving speed of the first vehicle or the target vehicle. This disclosure does not specifically limit the length of the preset time interval, which is subject to practicality. The preset driving distance can be the driving distance of the target vehicle, that is, the first driving information of the first vehicle is obtained every time the target vehicle travels the preset driving distance.

[0096] Since the trajectory of the first vehicle is not fixed, it may be replanned as obstacles in the driving environment of the first vehicle change. Therefore, through the above processing method, the first driving information of the first vehicle can be dynamically obtained, so that the collision risk area can be detected more accurately.

[0097] In an optional embodiment, the step S102 determines the collision risk area between the target vehicle and the first vehicle based on the first driving information and the second driving information of the target vehicle, including the following situations:

[0098] Case 1:

[0099] If it is determined based on the first driving information of the current cycle and the first driving information of the previous cycle that the predicted trajectory of the first vehicle has not changed, the collision risk area of ​​the current cycle is determined based on the collision risk area determined based on the first driving information of the previous cycle.

[0100] Here, the predicted trajectory from the first driving information of the current cycle can be compared with the predicted trajectory from the first driving information of the previous cycle. If the two predicted trajectories are found to be identical, or if the two predicted trajectories have the same driving direction, it can be determined that the predicted trajectory of the first vehicle has not changed. In this case, the collision risk area determined from the first driving information of the previous cycle can be used as the collision risk area for the current cycle.

[0101] If the predicted trajectory of the first vehicle has not changed, it can be determined that the area intersection between the predicted driving area of ​​the first vehicle and the safe driving area of ​​the target vehicle has not changed. At this time, the collision risk area determined by the first driving information of the previous cycle can be directly used as the collision risk area of ​​the current cycle.

[0102] This processing method can further simplify the vehicle collision detection process, thereby improving the efficiency of vehicle collision detection and meeting the needs of autonomous driving scenarios with high real-time requirements.

[0103] Case 2:

[0104] If it is determined based on the first driving information of the current cycle and the first driving information of the previous cycle that the predicted trajectory of the first vehicle has changed, a new collision risk area is determined as the collision risk area of ​​the current cycle based on the first driving information of the current cycle and the second driving information.

[0105] Here, the predicted trajectory in the first driving information of the current cycle can be compared with the predicted trajectory in the first driving information of the previous cycle. If the comparison shows that the driving directions of the two predicted trajectories are different, a new collision risk area can be determined based on the first driving information and the second driving information of the current cycle, and then the new collision risk area can be used as the collision risk area of ​​the current cycle.

[0106] During its travel, the first vehicle may replan its trajectory due to obstructions. This may cause the first vehicle's direction to change, and the intersection between the first vehicle's predicted driving area and the target vehicle's safe driving area to change accordingly. Therefore, to more accurately detect vehicle collisions, it is necessary to determine a new collision risk area based on the first and second driving information from the current cycle, thereby ensuring the accuracy of vehicle collision detection.

[0107] In an optional embodiment, step S102 determines the collision risk area between the target vehicle and the first vehicle based on the first driving information and the second driving information of the target vehicle, and specifically includes the following steps:

[0108] Step S11, determining a predicted driving area of ​​the first vehicle based on the predicted trajectory of the first vehicle and the bounding box of the first vehicle;

[0109] Step S12: determining the collision risk area according to the intersection information between the predicted driving area and the target driving area of ​​the target vehicle, wherein the target driving area is determined based on the second driving information and the designated distance.

[0110] In an embodiment of the present disclosure, as shown in FIG3 , a predicted driving area as shown in FIG3 may be obtained based on the predicted trajectory of the first vehicle and the bounding box of the first vehicle.

[0111] In a specific implementation, a driving area can be determined along the driving direction of the predicted trajectory with the boundary of the bounding box of the first vehicle as the boundary, i.e., the predicted driving area of ​​the first vehicle as shown in Figure 3. Alternatively, a driving area can be determined along the driving direction of the predicted trajectory with the width of the bounding box of the first vehicle as the area width, i.e., the predicted driving area of ​​the first vehicle as shown in Figure 3.

[0112] Here, as shown in FIG3 , a target driving area of ​​the target vehicle, also called a safe driving area of ​​the target vehicle, may be determined based on the designated distance and the second driving information of the target vehicle.

[0113] In specific implementation, an area with a specified width and a boundary parallel to the vehicle boundary of the target vehicle can be determined as the target driving area; wherein the body of the target vehicle is completely contained in the target driving area, and the distance from the center point of the target vehicle to the area boundary of the target driving area is equal.

[0114] After the predicted driving area and the target driving area as shown in FIG3 are determined, the intersection information between the predicted driving area and the target driving area may be determined, thereby determining the collision risk area based on the intersection information.

[0115] In the embodiment of the present disclosure, in addition to determining the collision risk area in the manner described in the above steps S11 and S12, the collision risk area may also be determined in the following manner:

[0116] Determine the first bounding box (referred to as the first bounding box) and the last bounding box (referred to as the last bounding box) that intersects the target driving area in the bounding box of the first vehicle; then, determine the intersection points of the first bounding box and the last bounding box with the target driving area, respectively, which are recorded as intersection points A; thereafter, determine the intersection point between the extension lines of the bounding box boundaries parallel to the area boundary of the predicted driving area in the first bounding box and the last bounding box and the area boundary of the predicted driving area, which are recorded as intersection points B; determine the maximum intersection point and the minimum intersection point of intersection points A and B; and determine the collision risk area based on the area between the maximum intersection point and the minimum intersection point in the target driving area.

[0117] In the embodiment of the present disclosure, according to the method described in the above steps S11 and S12, after the intersection information is determined, the collision risk area can be determined according to the intersection information.

[0118] In an optional embodiment, all intersection information between the predicted driving area and the target driving area may be determined; wherein the intersection information includes the coordinates of each intersection; and further, the collision risk area may be determined based on all intersection information.

[0119] In specific implementation, the intersection with the largest coordinates and the intersection with the smallest coordinates can be determined from all the intersection information; then, the collision risk area is determined based on the area between the largest intersection and the intersection with the smallest coordinates in the target driving area.

[0120] In specific implementation, the collision risk area can also be determined based on the area surrounded by all intersection information in the target driving area. For example, as shown in FIG3 , the collision risk area can be determined based on the quadrilateral A'B'CD.

[0121] During specific implementation, the regional shape of the collision risk area may also be determined, and then the collision risk area may be determined based on the regional shape and all intersection information.

[0122] In the embodiment of the present disclosure, the intersection point of the area boundaries of the two driving areas can be calculated using a straight line intersection algorithm; the intersection point of the two driving areas can also be calculated using a area intersection algorithm.

[0123] In another optional embodiment, determining the collision risk area according to the intersection information between the predicted driving area and the target driving area of ​​the target vehicle specifically includes the following steps:

[0124] First, along the traveling direction of the target vehicle or the first vehicle, determining a first intersection point and a last intersection point between the predicted driving area and the target driving area;

[0125] Secondly, the collision risk area is determined based on an area between the first intersection and the last intersection in the target driving area.

[0126] In an embodiment of the present disclosure, the first intersection point (i.e., the first intersection point, such as point A' shown in FIG3 ) and the last intersection point, such as point C shown in FIG3 , between the area boundary of the predicted driving area and the area boundary of the target driving area can be determined along the driving direction of the target vehicle.

[0127] In specific implementation, the intersection point with the smallest coordinates between the target driving area and area boundary 1 can be determined as the first intersection point along the driving direction of the target vehicle; then, the intersection point with the largest coordinates between the target driving area and area boundary 2 can be determined as the last intersection point along the driving direction.

[0128] In addition, a first intersection point (ie, the first intersection point) between the area boundary of the predicted driving area and the area boundary of the target driving area may be determined along the driving direction of the first vehicle.

[0129] Finally, the collision risk area may be determined based on an area between the first intersection and the last intersection in the target driving area.

[0130] In an optional embodiment, a target area can be determined, which is surrounded by a first perpendicular line passing through the first intersection and perpendicular to the area boundary of the target driving area, a second perpendicular line passing through the last intersection and perpendicular to the area boundary, and the area boundary; then, the collision risk area is determined based on the target area.

[0131] As shown in Figure 3, the first perpendicular line passing through the first intersection and perpendicular to the target driving area boundary is A'B', and the second perpendicular line passing through the last intersection and perpendicular to the area boundary is CD. In this case, the area enclosed by A'B', B'C, CD, and DA' can be used as the target area, and the collision risk area can be determined based on this target area.

[0132] In another optional embodiment, the distance A between the first intersection and the last intersection can be determined, and then, a rectangle with a length of distance A and a width of the specified distance is determined as the target area in the target driving area with the first intersection or the last intersection as the vertex; then, the collision risk area is determined based on the target area.

[0133] After determining the target area, it is necessary to correct the target area to obtain the collision risk area.

[0134] In an optional embodiment, the above step of determining the collision risk area based on the intersection information between the predicted driving area and the target driving area of ​​the target vehicle specifically includes the following steps:

[0135] Based on the position of the first origin of the vehicle coordinate system of the target vehicle and the position of the second origin of the coordinate system of the positioning sensor of the target vehicle, the target area is corrected to obtain the collision risk area after correction, wherein the target area is a part of the target driving area determined based on the intersection information.

[0136] In order to more accurately determine the trajectory collision area, it is necessary to compensate the target area according to the position of the origin coordinates of the coordinate system of the positioning sensor in the target vehicle. For example, if the positioning sensor is located at the front end of the vehicle, then through coordinate conversion, the position of the origin coordinates of the positioning sensor's coordinate system can be converted to the origin position of the vehicle coordinate system of the target vehicle, for example, the center point of the rear axle of the target vehicle. Next, determine the distance between the origin position of the vehicle coordinate system of the target vehicle (i.e., the position of the first origin) and the position of the origin coordinates of the coordinate system of the positioning sensor (i.e., the position of the second origin), and correct the target area to obtain the collision risk area after correction.

[0137] During specific implementation, the target area may be expanded in the target driving area based on the distance between the first origin and the second origin, thereby achieving compensation for the target area.

[0138] In an optional embodiment, based on the position of the first origin of the vehicle coordinate system of the target vehicle and the position of the second origin of the coordinate system of the positioning sensor of the target vehicle, the target area is corrected to obtain the collision risk area, which specifically includes the following steps:

[0139] Extending a first boundary of the target area by a first distance along a traveling direction of the target vehicle, and extending a second boundary of the target area by a second distance in a direction opposite to the traveling direction, to obtain the collision risk area;

[0140] Among them, the first distance is the distance between the first origin and the rear of the target vehicle, the second distance is the distance between the first origin and the second origin along the body direction of the target vehicle, the first boundary is a first vertical line passing through the first intersection between the predicted driving area and the target driving area and perpendicular to the area boundary of the target driving area, and the second boundary is a second vertical line passing through the last intersection between the predicted driving area and the target driving area and perpendicular to the area boundary.

[0141] Here, the first boundary is boundary CD shown in Figure 3, and the second boundary is boundary A'B' shown in Figure 3. The first distance is distance e shown in Figure 3, and the second distance is distance S shown in Figure 3. The first intersection is point A', and the last intersection is point C. In this case, the first boundary is the second perpendicular line passing through the last intersection C and perpendicular to the region boundary, and the second boundary is the first perpendicular line passing through the first intersection A' and perpendicular to the region boundary.

[0142] As shown in FIG3 , after determining the target area, the first boundary can be extended by a first distance e along the traveling direction, and then extended by a second distance S in the opposite direction of the traveling direction. The area obtained after the extension is the actual collision risk area.

[0143] In the above embodiment, the collision risk area can be determined more quickly and accurately, thereby providing a trajectory planning basis for the decision-making planning module of the target vehicle in advance, so that the decision-making planning module can make more effective action decisions for the subsequent actions of the autonomous driving vehicle.

[0144] In the embodiment of the present disclosure, after detecting a first positional relationship between the bounding box of the first vehicle and the collision risk area, and a second positional relationship between the position of the target vehicle and the collision risk area, detecting whether there is a collision risk between the target vehicle and the first vehicle based on the first positional relationship and the second positional relationship specifically includes the following steps:

[0145] When it is determined based on the first positional relationship that any corner point of the bounding box of the first vehicle is located within the collision risk area, and when it is determined based on the second positional relationship that the target vehicle is located within the collision risk area at a target moment, it is determined that there is a collision risk between the target vehicle and the first vehicle; wherein the target moment is the moment when any corner point is located within the collision risk area.

[0146] In an embodiment of the present disclosure, if at the same moment (for example, the target moment) at least one corner point of the bounding box of the first vehicle is determined to be located within the collision risk area based on the first positional relationship, and the target vehicle is also located within the collision risk area, it can be determined that the first vehicle and the target vehicle are both located within the collision risk area. At this time, there is a collision risk between the target vehicle and the first vehicle.

[0147] This processing method can quickly and efficiently detect vehicle collisions, thereby reducing the time consumption of vehicle collision detection.

[0148] The above process will be described below with reference to Figure 4. As shown in Figure 4, the method includes the following steps:

[0149] S1: Screen candidate vehicles within the driving area where the target vehicle is located to obtain a first vehicle.

[0150] Here, a first vehicle that meets the collision detection requirement may be determined among the candidate vehicles; wherein the collision detection requirement is used to indicate that the candidate vehicle is in a moving state and the driving trajectory of the candidate vehicle is valid.

[0151] S2: Acquire first driving information of a first vehicle in a Cartesian coordinate system; wherein the first driving information includes a predicted trajectory and a bounding box of the first vehicle.

[0152] Here, the main task is to solve the corner points of the bounding box of the first vehicle corresponding to the position point in the predicted trajectory in the Cartesian coordinate system, the coordinates and orientation, and the attributes of the first vehicle (for example, size, type). For example, the bounding box of the first vehicle obtained is shown in Figure 2. Among them, (x1, y1), (x2, y2), (x3, y3), and (x4, y4) are the corner points obtained.

[0153] S3: Perform SL projection on the first driving information.

[0154] At this time, the first driving information is projected from the Cartesian coordinate system to the Frenet coordinate system to obtain the projected first driving information; wherein the Frenet coordinate system is a Frenet coordinate system constructed based on the predicted trajectory of the target vehicle.

[0155] S4: Determine whether the error of the projected first driving information meets the preset error requirement; if so, execute step S5; otherwise, return to execute step S2, that is, continue to construct the bounding box of the first vehicle for the next position point coordinate.

[0156] S5: Determine whether the predicted trajectory of the first vehicle has changed; if so, execute step S7; otherwise, execute step S6.

[0157] Whether the corner points of the bounding box of the first vehicle after projecting the first driving information of the current cycle and the first driving information of the previous cycle are located within the safe driving area.

[0158] S6: Determine a collision risk area in a current cycle based on the collision risk area determined by the first driving information in a previous cycle.

[0159] S7: Based on the first driving information and the second driving information of the current period, a new collision risk area is determined as the collision risk area of ​​the current period.

[0160] During specific implementation, the predicted driving area of ​​the first vehicle can be determined based on the predicted trajectory of the first vehicle and the bounding box of the first vehicle; the first intersection and the last intersection between the predicted driving area and the target driving area can be determined along the traveling direction of the target vehicle or the first vehicle; and the collision risk area can be determined based on the area between the first intersection and the last intersection in the target driving area.

[0161] S8: Detecting a first positional relationship between the bounding box of the first vehicle and the collision risk area, and a second positional relationship between the position of the target vehicle and the collision risk area.

[0162] S9: When it is determined based on the first positional relationship that any corner point of the bounding box of the first vehicle is located in the collision risk area, and it is determined based on the second positional relationship that the target vehicle is located in the collision risk area at the target moment, it is determined that there is a collision risk between the target vehicle and the first vehicle; wherein the target moment is the moment when any corner point is located in the collision risk area.

[0163] In the above embodiment, by determining the collision risk area between the target vehicle and the first vehicle, and then performing collision detection on the target vehicle and the first vehicle through the first position relationship between the bounding box of the first vehicle and the collision risk area, and the second position relationship between the position of the target vehicle and the collision risk area, vehicle collisions can be detected efficiently and quickly, reducing the time consumption of vehicle collision detection, and providing a trajectory planning basis for the decision-making planning module of the target vehicle, so that the decision-making planning module can make more effective action decisions on the subsequent actions of the autonomous driving vehicle, thereby ensuring safe driving between autonomous driving vehicles in mining scenarios.

[0164] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0165] Based on the same inventive concept, a vehicle collision detection device corresponding to the vehicle collision detection method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned vehicle collision detection method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0166] 5 , which is a schematic diagram of a vehicle collision detection device provided by an embodiment of the present disclosure, the device includes: an acquisition unit 51 , a determination unit 52 , a first detection unit 53 and a second detection unit 54 ; wherein,

[0167] An acquiring unit 51 is configured to acquire first driving information of a first vehicle; wherein the first driving information includes: a predicted trajectory of the first vehicle and a bounding box of the first vehicle;

[0168] a determining unit 52 configured to determine a collision risk area between the target vehicle and the first vehicle based on the first driving information and second driving information of the target vehicle, wherein the second driving information includes a predicted trajectory and a specified distance of the target vehicle;

[0169] A first detection unit 53 is configured to detect a first positional relationship between a bounding box of the first vehicle and the collision risk area, and a second positional relationship between a position of the target vehicle and the collision risk area;

[0170] The second detection unit 54 is configured to detect whether there is a collision risk between the target vehicle and the first vehicle based on the first position relationship and the second position relationship.

[0171] In a possible implementation manner, the acquiring unit 51 is further configured to: acquire the first driving information in a Cartesian coordinate system;

[0172] The determining unit 52 is further configured to:

[0173] Projecting the first driving information from a Cartesian coordinate system to a Frenet coordinate system to obtain projected first driving information; wherein the Frenet coordinate system is a Frenet coordinate system constructed based on the predicted trajectory of the target vehicle;

[0174] Based on the projected first driving information and the second driving information, a collision risk area between the target vehicle and the first vehicle is determined.

[0175] In a possible implementation, the acquiring unit 51 is further configured to:

[0176] The first driving information is obtained according to a preset period; wherein the preset period is determined based on a preset time interval or a preset driving distance.

[0177] In a possible implementation manner, the determining unit 52 is further configured to:

[0178] If it is determined based on the first driving information of the current cycle and the first driving information of the previous cycle that the predicted trajectory of the first vehicle has not changed, determining the collision risk area of ​​the current cycle based on the collision risk area determined by the first driving information of the previous cycle;

[0179] or,

[0180] If it is determined based on the first driving information of the current cycle and the first driving information of the previous cycle that the predicted trajectory of the first vehicle has changed, a new collision risk area is determined as the collision risk area of ​​the current cycle based on the first driving information of the current cycle and the second driving information.

[0181] In a possible implementation, the first detection unit 53 is further configured to:

[0182] When it is determined based on the first positional relationship that any corner point of the bounding box of the first vehicle is located within the collision risk area, and when it is determined based on the second positional relationship that the target vehicle is located within the collision risk area at a target moment, it is determined that there is a collision risk between the target vehicle and the first vehicle; wherein the target moment is the moment when any corner point is located within the collision risk area.

[0183] In a possible implementation manner, the determining unit 52 is further configured to:

[0184] determining a predicted driving area of ​​the first vehicle based on the predicted trajectory of the first vehicle and a bounding box of the first vehicle;

[0185] The collision risk area is determined according to intersection information between the predicted driving area and a target driving area of ​​the target vehicle, wherein the target driving area is determined based on the second driving information and the designated distance.

[0186] In a possible implementation manner, the determining unit 52 is further configured to:

[0187] Determining a first intersection point and a last intersection point between the predicted driving area and the target driving area along a traveling direction of the target vehicle or the first vehicle;

[0188] The collision risk area is determined based on an area between the first intersection and the last intersection in the target driving area.

[0189] In a possible implementation manner, the determining unit 52 is further configured to:

[0190] Determine a target area enclosed by a first perpendicular line passing through the first intersection and perpendicular to an area boundary of the target driving area, a second perpendicular line passing through the last intersection and perpendicular to the area boundary, and the area boundary;

[0191] The collision risk area is determined according to the target area.

[0192] In a possible implementation manner, the determining unit 52 is further configured to:

[0193] Based on the position of the first origin of the vehicle coordinate system of the target vehicle and the position of the second origin of the coordinate system of the positioning sensor of the target vehicle, the target area is corrected to obtain the collision risk area after correction, wherein the target area is a part of the target driving area determined based on the intersection information.

[0194] In a possible implementation manner, the determining unit 52 is further configured to:

[0195] Extending a first boundary of the target area by a first distance along a traveling direction of the target vehicle, and extending a second boundary of the target area by a second distance in a direction opposite to the traveling direction, to obtain the collision risk area;

[0196] Among them, the first distance is the distance between the first origin and the rear of the target vehicle, the second distance is the distance between the first origin and the second origin along the body direction of the target vehicle, the second boundary is the first vertical line passing through the first intersection between the predicted driving area and the target driving area and perpendicular to the area boundary of the target driving area, and the first boundary is the second vertical line passing through the last intersection between the predicted driving area and the target driving area and perpendicular to the area boundary.

[0197] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference can be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0198] Corresponding to the vehicle collision detection method in FIG1 , an embodiment of the present disclosure further provides an electronic device 600 . FIG6 is a schematic structural diagram of the electronic device 600 provided in an embodiment of the present disclosure, including:

[0199] Processor 61, memory 62, and bus 63; memory 62 is used to store execution instructions, including internal memory 621 and external memory 622; the internal memory 621 is also called internal memory, which is used to temporarily store operation data in the processor 61 and data exchanged with external memory 622 such as a hard disk. The processor 61 exchanges data with the external memory 622 through the internal memory 621. When the electronic device 600 is running, the processor 61 communicates with the memory 62 via the bus 63, so that the processor 61 executes the following instructions:

[0200] Acquire first driving information of a first vehicle; wherein the first driving information includes: a predicted trajectory of the first vehicle and a bounding box of the first vehicle;

[0201] determining a collision risk area between the target vehicle and the first vehicle based on the first driving information and second driving information of the target vehicle, wherein the second driving information includes a predicted trajectory and a specified distance of the target vehicle;

[0202] detecting a first positional relationship between a bounding box of the first vehicle and the collision risk area, and a second positional relationship between a position of the target vehicle and the collision risk area;

[0203] Based on the first positional relationship and the second positional relationship, it is detected whether there is a collision risk between the target vehicle and the first vehicle.

[0204] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program executes the steps of the vehicle collision detection method described in the above method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0205] The embodiments of the present disclosure also provide a computer program product, which carries program code. The instructions included in the program code can be used to execute the steps of the vehicle collision detection method described in the above method embodiment. For details, please refer to the above method embodiment and will not be repeated here.

[0206] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0207] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and devices described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0208] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0209] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0210] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0211] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure shall be subject to the scope of protection of the claims.

Claims

1. A vehicle collision detection method, comprising: Acquire first driving information of a first vehicle; wherein the first driving information includes: a predicted trajectory of the first vehicle and a bounding box of the first vehicle; determining a collision risk area between the target vehicle and the first vehicle based on the first driving information and second driving information of the target vehicle, wherein the second driving information includes a predicted trajectory and a specified distance of the target vehicle; detecting a first positional relationship between a bounding box of the first vehicle and the collision risk area, and a second positional relationship between a position of the target vehicle and the collision risk area; Based on the first positional relationship and the second positional relationship, it is detected whether there is a collision risk between the target vehicle and the first vehicle.

2. The method according to claim 1, wherein The obtaining of first driving information of the first vehicle includes: Acquiring the first driving information in a Cartesian coordinate system; The determining, based on the first driving information and the second driving information of the target vehicle, a collision risk area between the target vehicle and the first vehicle includes: Projecting the first driving information from a Cartesian coordinate system to a Frenet coordinate system to obtain projected first driving information; wherein the Frenet coordinate system is a Frenet coordinate system constructed based on the predicted trajectory of the target vehicle; Based on the projected first driving information and the second driving information, a collision risk area between the target vehicle and the first vehicle is determined.

3. The method according to claim 1 or 2, wherein: The obtaining of first driving information of the first vehicle includes: The first driving information is obtained according to a preset period; wherein the preset period is determined based on a preset time interval or a preset driving distance.

4. The method according to claim 3, wherein: The determining, based on the first driving information and the second driving information of the target vehicle, a collision risk area between the target vehicle and the first vehicle includes: If it is determined based on the first driving information of the current cycle and the first driving information of the previous cycle that the predicted trajectory of the first vehicle has not changed, determining the collision risk area of the current cycle based on the collision risk area determined by the first driving information of the previous cycle; or, If it is determined based on the first driving information of the current cycle and the first driving information of the previous cycle that the predicted trajectory of the first vehicle has changed, a new collision risk area is determined as the collision risk area of the current cycle based on the first driving information of the current cycle and the second driving information.

5. The method according to claim 1, wherein The detecting, based on the first position relationship and the second position relationship, whether there is a collision risk between the target vehicle and the first vehicle includes: When it is determined based on the first positional relationship that any corner point of the bounding box of the first vehicle is located within the collision risk area, and when it is determined based on the second positional relationship that the target vehicle is located within the collision risk area at a target moment, it is determined that there is a collision risk between the target vehicle and the first vehicle; wherein the target moment is the moment when any corner point is located within the collision risk area.

6. The method according to claim 1, wherein The determining, based on the first driving information and the second driving information of the target vehicle, a collision risk area between the target vehicle and the first vehicle includes: determining a predicted driving area of the first vehicle based on the predicted trajectory of the first vehicle and a bounding box of the first vehicle; The collision risk area is determined according to intersection information between the predicted driving area and a target driving area of the target vehicle, wherein the target driving area is determined based on the second driving information and the designated distance.

7. The method according to claim 6, wherein: The determining the collision risk area according to the intersection information between the predicted driving area and the target driving area of the target vehicle includes: Determining a first intersection point and a last intersection point between the predicted driving area and the target driving area along a traveling direction of the target vehicle or the first vehicle; The collision risk area is determined based on an area between the first intersection and the last intersection in the target driving area.

8. The method according to claim 7, wherein: The determining the collision risk area based on the target driving area between the first intersection and the last intersection includes: Determine a target area enclosed by a first perpendicular line passing through the first intersection and perpendicular to an area boundary of the target driving area, a second perpendicular line passing through the last intersection and perpendicular to the area boundary, and the area boundary; The collision risk area is determined according to the target area.

9. The method according to claim 6, 7 or 8, wherein The determining the collision risk area according to the intersection information between the predicted driving area and the target driving area of the target vehicle includes: Based on the position of the first origin of the vehicle coordinate system of the target vehicle and the position of the second origin of the coordinate system of the positioning sensor of the target vehicle, the target area is corrected to obtain the collision risk area after correction, wherein the target area is a part of the target driving area determined based on the intersection information.

10. The method according to claim 9, wherein: The correcting the target area based on the position of the first origin of the vehicle coordinate system of the target vehicle and the position of the second origin of the coordinate system of the positioning sensor of the target vehicle to obtain the collision risk area after correction includes: Extending a first boundary of the target area by a first distance along a traveling direction of the target vehicle, and extending a second boundary of the target area by a second distance in a direction opposite to the traveling direction, to obtain the collision risk area; Among them, the first distance is the distance between the first origin and the rear of the target vehicle, the second distance is the distance between the first origin and the second origin along the body direction of the target vehicle, the second boundary is the first vertical line passing through the first intersection between the predicted driving area and the target driving area and perpendicular to the area boundary of the target driving area, and the first boundary is the second vertical line passing through the last intersection between the predicted driving area and the target driving area and perpendicular to the area boundary.

11. A vehicle collision detection device, comprising: An acquiring unit is configured to acquire first driving information of a first vehicle; wherein the first driving information includes: a predicted trajectory of the first vehicle and a bounding box of the first vehicle; a determining unit configured to determine a collision risk area between the target vehicle and the first vehicle based on the first driving information and second driving information of the target vehicle, wherein the second driving information includes a predicted trajectory and a specified distance of the target vehicle; a first detection unit configured to detect a first positional relationship between a bounding box of the first vehicle and the collision risk area, and a second positional relationship between a position of the target vehicle and the collision risk area; The second detection unit is configured to detect whether there is a collision risk between the target vehicle and the first vehicle based on the first position relationship and the second position relationship.

12. An electronic device comprising: A processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate via the bus. When the machine-readable instructions are executed by the processor, the steps of the vehicle collision detection method according to any one of claims 1 to 10 are performed.

13. A computer-readable storage medium having a computer program stored thereon, wherein the computer program is operable to execute the steps of the vehicle collision detection method according to any one of claims 1 to 10 when executed by a processor.

Images