Collision risk identification method and device, electronic equipment and storage medium

By obtaining obstacle position data and vehicle outline point cloud data, determining obstacle prediction motion trajectory and calculating hazard coefficients, the problem of accurate and efficient collision risk identification in the prior art is solved, and more accurate and efficient obstacles are achieved Things recognition and driving decision support.

CN118942279APending Publication Date: 2024-11-12CHONGQING CHANGAN AUTOMOBILE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411015972.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing collision risk identification methods are inaccurate and efficient, making it difficult to accurately and promptly identify the collision risk between vehicles and obstacles.

Method used

By obtaining the location data of the obstacle and the outer contour point cloud data of the vehicle, the predicted motion trajectory of the obstacle is determined, and whether there is a collision risk is determined, the predicted collision point is determined from the predicted motion trajectory, and the hazard coefficient of the obstacle is calculated.

Benefits of technology

Improve the vehicle environment perception ability, accurately and quickly identify and predict collision points, improve the accuracy and efficiency of collision risk identification, and realize the quantification of obstacle hazards, providing more accurate and accurate driving decisions for vehicles to make safer driving decisions. support.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942279A_ABST
    Figure CN118942279A_ABST
Patent Text Reader

Abstract

The invention provides a collision risk identification method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a predicted motion track of an obstacle according to position data of the obstacle; according to the predicted motion trail of the obstacle and the outer contour point cloud data of the vehicle, whether the obstacle has a collision risk to the vehicle is judged; determining a predicted collision point between the obstacle and the vehicle from the predicted movement track of the obstacle under the condition that the obstacle has the collision risk to the vehicle; and determining a danger coefficient of the obstacle according to the predicted collision point. According to the invention, the predicted collision point is determined according to the predicted movement track of the obstacle and the outer contour point cloud data of the vehicle, the predicted collision point can be accurately and rapidly determined, and the accuracy and efficiency of collision risk identification are improved. Besides, the danger coefficient of the obstacle is determined based on the predicted collision point, so that the danger of the obstacle is quantified, and support is provided for making safer and more reasonable driving decisions for subsequent vehicles.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of autonomous driving technology, and in particular to a collision risk identification method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of science and technology, driverless technology is gradually moving from the laboratory to commercial applications, becoming one of the key technologies to change the future mode of transportation. In this process, the path planning and speed planning technologies of driverless vehicles are particularly important, as they are the core to ensure the safe and efficient operation of vehicles.

[0003] In the path planning of unmanned vehicles, environmental perception is the foundation, and obstacle detection and evaluation are important components of environmental perception. In an ideal situation without obstacles, the vehicle can drive smoothly along the center line of the lane. However, in the actual road environment, the presence of obstacles is the norm. These obstacles may be static, such as parked vehicles on the roadside and construction areas, or dynamic, such as pedestrians and other vehicles. The presence of these obstacles not only affects the normal driving of the vehicle, but may also bring safety hazards. Therefore, in order to ensure that the vehicle makes obstacle avoidance decisions in a timely manner and ensure the safety of vehicle driving, it is particularly important to improve the accuracy and efficiency of collision risk identification between the vehicle and obstacles. Summary of the invention

[0004] One of the purposes of the present invention is to provide a collision risk identification method to solve the problems of low collision risk identification accuracy and low efficiency in existing collision risk identification methods, and to improve the accuracy and efficiency of collision risk identification; the second purpose is to provide a collision risk identification device; the third purpose is to provide an electronic device; and the fourth purpose is to provide a storage medium.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A first aspect of an embodiment of the present invention provides a collision risk identification method, the method comprising:

[0007] Obtain the location data of obstacles and the point cloud data of the vehicle's outer contour;

[0008] Determining a predicted motion trajectory of the obstacle according to the position data of the obstacle;

[0009] Determining whether the obstacle poses a collision risk to the vehicle based on the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle;

[0010] In the case where the obstacle poses a risk of collision with the vehicle, determining a predicted collision point between the obstacle and the vehicle from the predicted motion trajectory of the obstacle;

[0011] The risk factor of the obstacle is determined according to the predicted collision point.

[0012] Optionally, obtaining the location data of the obstacle includes:

[0013] Acquire first position data of the obstacle through a sensor on the vehicle, wherein the first position data is position data of the obstacle in a pre-established sensor coordinate system;

[0014] Acquire the position and posture data of the sensor, wherein the position and posture data of the sensor is the position and posture data of the sensor in a pre-established vehicle coordinate system;

[0015] The position data of the obstacle is determined according to the first position data of the obstacle and the position data of the sensor, wherein the position data of the obstacle is the position data of the obstacle in a pre-established vehicle coordinate system.

[0016] Optionally, determining the predicted motion trajectory of the obstacle according to the position data of the obstacle includes:

[0017] Obtaining the location data of the obstacle at the current moment and the location data of the obstacle at the previous moment;

[0018] Obtaining the time difference between the current moment and the previous moment;

[0019] Determine the displacement of the obstacle according to the position data of the obstacle at the current moment and the position data of the obstacle at the previous moment;

[0020] Determining a relative speed of the obstacle with respect to the vehicle according to the displacement of the obstacle and the time difference;

[0021] The predicted motion trajectory of the obstacle is determined according to the relative speed, the preset prediction time and the position data of the obstacle at the current moment.

[0022] Optionally, judging whether the obstacle poses a collision risk to the vehicle according to the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle includes:

[0023] Pre-establishing an obstacle coordinate system of the obstacle, wherein the negative X-axis of the obstacle coordinate system is opposite to the velocity direction of the obstacle;

[0024] Determine a first outer contour point closest to the obstacle according to the position data of the obstacle and the outer contour point cloud data of the vehicle, and determine the first outer contour point as a first candidate collision point, wherein the outer contour point cloud data of the vehicle includes position data of a plurality of the outer contour points;

[0025] Determining a first obstacle trajectory prediction point closest to the first candidate collision point according to the first candidate collision point and the predicted motion trajectory of the obstacle, and determining the first obstacle trajectory prediction point as a first trajectory prediction point, wherein the predicted motion trajectory of the obstacle includes a plurality of the obstacle trajectory prediction points;

[0026] Determining whether the first trajectory prediction point is on the negative X-axis of the obstacle coordinate system;

[0027] If the first trajectory prediction point is located on the negative X-axis of the obstacle coordinate system, it is determined that the obstacle has no collision risk to the vehicle;

[0028] If the first trajectory prediction point is not located on the negative X-axis of the obstacle coordinate system, it is determined that the obstacle poses a collision risk to the vehicle.

[0029] Optionally, determining the predicted collision point between the obstacle and the vehicle from the predicted motion trajectory of the obstacle includes:

[0030] Determine, according to the first trajectory prediction point and the outer contour point cloud data of the vehicle, a second outer contour point closest to the first trajectory prediction point, and determine the second outer contour point as a second candidate collision point;

[0031] Determining a second obstacle trajectory prediction point closest to the second candidate collision point according to the second candidate collision point and the predicted motion trajectory of the obstacle, and determining the second obstacle trajectory prediction point as the second trajectory prediction point;

[0032] Acquire the position data of the first trajectory prediction point and the position data of the second trajectory prediction point;

[0033] determining a distance between the first trajectory prediction point and the second trajectory prediction point according to the position data of the first trajectory prediction point and the position data of the second trajectory prediction point;

[0034] If the distance between the first trajectory prediction point and the second trajectory prediction point is less than a preset distance threshold, determining the first trajectory prediction point as a predicted collision point;

[0035] If the distance between the first trajectory prediction point and the second trajectory prediction point is greater than or equal to the distance threshold, a third outer contour point closest to the second trajectory prediction point is determined based on the second trajectory prediction point and the outer contour point cloud data of the vehicle, and the third outer contour point is determined as a third candidate collision point.

[0036] Optionally, the determining the predicted collision point between the obstacle and the vehicle from the predicted motion trajectory of the obstacle includes:

[0037] respectively determining the distances between the outer contour points of the vehicle and the obstacle trajectory prediction points;

[0038] determining a minimum distance based on the distance;

[0039] The obstacle trajectory prediction point corresponding to the shortest distance is determined in the predicted motion trajectory of the obstacle, and the obstacle trajectory prediction point corresponding to the shortest distance is used as the predicted collision point.

[0040] Optionally, determining the risk factor of the obstacle according to the predicted collision point includes:

[0041] Pre-acquiring the position data of the predicted collision point and the obstacle type of the obstacle;

[0042] Establish the corresponding relationship between obstacle type and risk factor in advance;

[0043] Determining the risk coefficient of the obstacle according to the obstacle type of the obstacle and the corresponding relationship between the obstacle type and the risk coefficient;

[0044] Determining a collision distance according to the position data of the obstacle and the position data of the predicted collision point;

[0045] The risk factor of the obstacle is determined according to the relative speed of the obstacle with respect to the vehicle, the risk factor of the obstacle, and the collision distance.

[0046] A second aspect of an embodiment of the present invention provides a collision risk identification device, the device comprising:

[0047] A data acquisition module is used to obtain the location data of obstacles and the point cloud data of the outer contour of the vehicle;

[0048] A trajectory prediction module, used to determine the predicted motion trajectory of the obstacle according to the position data of the obstacle;

[0049] A collision risk judgment module, used to judge whether the obstacle poses a collision risk to the vehicle based on the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle;

[0050] A predicted collision point determination module, configured to determine a predicted collision point between the obstacle and the vehicle from a predicted motion trajectory of the obstacle when the obstacle poses a collision risk to the vehicle;

[0051] The obstacle hazard quantification module is used to determine the hazard coefficient of the obstacle according to the predicted collision point.

[0052] Optionally, the data acquisition module includes:

[0053] The first position data acquisition submodule of the obstacle is used to acquire the first position data of the obstacle through the sensor on the vehicle, wherein the first position data is the position data of the obstacle in a pre-established sensor coordinate system;

[0054] A sensor posture data acquisition submodule, used to acquire the posture data of the sensor, wherein the posture data of the sensor is the posture data of the sensor in a pre-established vehicle coordinate system;

[0055] The obstacle position data acquisition submodule is used to determine the position data of the obstacle according to the first position data of the obstacle and the posture data of the sensor, wherein the position data of the obstacle is the position data of the obstacle in a pre-established vehicle coordinate system.

[0056] Optionally, the trajectory prediction module includes:

[0057] A position data acquisition submodule, used to acquire the position data of the obstacle at the current moment and the position data of the obstacle at the previous moment;

[0058] A time difference acquisition submodule, used to acquire the time difference between the current moment and the previous moment;

[0059] A displacement determination submodule, used to determine the displacement of the obstacle according to the position data of the obstacle at the current moment and the position data of the obstacle at the previous moment;

[0060] A relative speed determination submodule, configured to determine a relative speed of the obstacle relative to the vehicle based on the displacement of the obstacle and the time difference;

[0061] The motion trajectory prediction submodule is used to determine the predicted motion trajectory of the obstacle according to the relative speed, the preset prediction time and the position data of the obstacle at the current moment.

[0062] Optionally, the collision risk judgment module includes:

[0063] An obstacle coordinate system establishment submodule is used to pre-establish an obstacle coordinate system of the obstacle, wherein the negative X-axis of the obstacle coordinate system is opposite to the speed direction of the obstacle;

[0064] A first candidate collision point determination submodule, configured to determine a first outer contour point closest to the obstacle according to the position data of the obstacle and the outer contour point cloud data of the vehicle, and determine the first outer contour point as a first candidate collision point, wherein the outer contour point cloud data of the vehicle includes position data of a plurality of the outer contour points;

[0065] a first obstacle trajectory prediction point determination submodule, configured to determine a first obstacle trajectory prediction point closest to the first candidate collision point according to the first candidate collision point and the predicted motion trajectory of the obstacle, and determine the first obstacle trajectory prediction point as a first trajectory prediction point, wherein the predicted motion trajectory of the obstacle includes a plurality of the obstacle trajectory prediction points;

[0066] A position determination submodule, used to determine whether the first trajectory prediction point is located on the negative X-axis of the obstacle coordinate system;

[0067] a first collision risk judgment submodule, configured to determine that the obstacle has no collision risk to the vehicle if the first trajectory prediction point is located on the negative X-axis of the obstacle coordinate system;

[0068] The second collision risk judgment submodule is used to determine that the obstacle has a collision risk to the vehicle if the first trajectory prediction point is not located on the negative X-axis of the obstacle coordinate system.

[0069] Optionally, the predicted collision point determination module includes:

[0070] A second candidate collision point determination submodule, configured to determine a second outer contour point closest to the first trajectory prediction point according to the first trajectory prediction point and the outer contour point cloud data of the vehicle, and determine the second outer contour point as a second candidate collision point;

[0071] a second obstacle trajectory prediction point determination submodule, configured to determine a second obstacle trajectory prediction point closest to the second candidate collision point according to the second candidate collision point and the predicted motion trajectory of the obstacle, and determine the second obstacle trajectory prediction point as a second trajectory prediction point;

[0072] A trajectory prediction point position data acquisition submodule, used to acquire the position data of the first trajectory prediction point and the position data of the second trajectory prediction point;

[0073] a distance determination submodule for adjacent trajectory prediction points, configured to determine the distance between the first trajectory prediction point and the second trajectory prediction point according to the position data of the first trajectory prediction point and the position data of the second trajectory prediction point;

[0074] a first predicted collision point determination submodule, configured to determine the first trajectory prediction point as a predicted collision point if the distance between the first trajectory prediction point and the second trajectory prediction point is less than a preset distance threshold;

[0075] The third candidate collision point determination submodule is used to determine a third outer contour point closest to the second trajectory prediction point based on the second trajectory prediction point and the outer contour point cloud data of the vehicle if the distance between the first trajectory prediction point and the second trajectory prediction point is greater than or equal to the distance threshold, and determine the third outer contour point as the third candidate collision point.

[0076] Optionally, the predicted collision point determination module includes:

[0077] A distance calculation submodule, used to respectively determine the distance between the outer contour point of the vehicle and the obstacle trajectory prediction point;

[0078] A shortest distance determination submodule, used to determine the shortest distance according to the distance;

[0079] The second predicted collision point determination submodule is used to determine the obstacle trajectory prediction point corresponding to the shortest distance in the predicted motion trajectory of the obstacle, and use the obstacle trajectory prediction point corresponding to the shortest distance as the predicted collision point.

[0080] Optionally, the obstacle hazard quantification module includes:

[0081] A position data and obstacle type acquisition submodule, used to pre-acquire the position data of the predicted collision point and the obstacle type of the obstacle;

[0082] A corresponding relationship establishment submodule is used to pre-establish the corresponding relationship between obstacle types and risk factors;

[0083] A risk coefficient determination submodule, used to determine the risk coefficient of the obstacle according to the obstacle type of the obstacle and the corresponding relationship between the obstacle type and the risk coefficient;

[0084] A collision distance determination submodule, used to determine the collision distance according to the position data of the obstacle and the position data of the predicted collision point;

[0085] The risk factor determination submodule is used to determine the risk factor of the obstacle according to the relative speed of the obstacle to the vehicle, the risk factor of the obstacle and the collision distance.

[0086] A third aspect of an embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the collision risk identification method as described in the first aspect of the embodiment of the present invention.

[0087] A fourth aspect of an embodiment of the present invention provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the collision risk identification method as described in the first aspect of the embodiment of the present invention are implemented.

[0088] The collision risk identification method provided by the embodiment of the present invention obtains the position data of the obstacle and the outer contour point cloud data of the vehicle; determines the predicted motion trajectory of the obstacle based on the position data of the obstacle; determines whether the obstacle poses a collision risk to the vehicle based on the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle; in the case where the obstacle poses a collision risk to the vehicle, determines the predicted collision point between the obstacle and the vehicle from the predicted motion trajectory of the obstacle; and determines the hazard coefficient of the obstacle based on the predicted collision point. The embodiment of the present invention determines the predicted collision point based on the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle, which not only improves the environmental perception capability of the vehicle, but also can accurately and quickly determine the predicted collision point, thereby improving the accuracy and efficiency of collision risk identification. In addition, the embodiment of the present invention determines the hazard coefficient of the obstacle based on the predicted collision point, thereby quantifying the hazard of the obstacle and providing more accurate support for subsequent vehicles to make safer and more reasonable driving decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0090] Figure 1 is one of the flow charts of a method for identifying collision risks according to an embodiment of the present invention;

[0091] Figure 2 This is a second flow chart of a method for identifying collision risks according to an embodiment of the present invention;

[0092] Figure 3This is a flowchart of a collision risk identification method according to an embodiment of the present invention;

[0093] Figure 4 This is a fourth step flow chart of a collision risk identification method shown in an embodiment of the present invention;

[0094] Figure 5 This is a flowchart of steps of a collision risk identification method shown in one embodiment of the present invention;

[0095] Figure 6 This is a sixth step flow chart of a collision risk identification method shown in an embodiment of the present invention;

[0096] Figure 7 This is a flowchart of the steps of a collision risk identification method shown in an embodiment of the present invention;

[0097] Figure 8 is a device block diagram of a collision risk identification device provided by an embodiment of the present invention;

[0098] Fig. 9 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0099] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0100] Reference Figure 1 , shows a flowchart of the steps of a collision risk identification method provided by an embodiment of the present invention, the method may include:

[0101] Step 101, obtaining the position data of the obstacle and the outer contour point cloud data of the vehicle.

[0102] It should be noted that, in the embodiment of the present invention, in order to predict the motion trajectory of the obstacle, it is necessary to obtain the position data of the obstacle in advance, and the position data of the obstacle is the position data of the obstacle in the pre-established vehicle coordinate system. In order to accurately predict the collision point between the obstacle and the vehicle, it is necessary to obtain the outer contour point cloud data of the vehicle in advance, and the outer contour point cloud data of the vehicle includes the position data of several outer contour points. Specifically, in the 3D digital model of the vehicle, the center of the rear axle of the vehicle is taken as the origin, the front of the vehicle is the positive X axis, the Y axis is perpendicular to the X axis and located at the left of the vehicle, and the Z axis is perpendicular to the X axis or the Y axis and vertically upward as the positive Z axis to establish a vehicle coordinate system; the outer contour line of the vehicle is discretely sampled on the XOY plane of the vehicle coordinate system, that is, along the outer contour line of the vehicle, the coordinates (X, Y) of the points are collected at a certain distance (or angle), and the points are the outer contour points, and the coordinates of the points are the position data of the outer contour points. After completing the discrete sampling of the outer contour line of the vehicle, the position data of several outer contour points can be obtained, and the position data of several outer contour points are the outer contour point cloud data.

[0103] Step 102: determining a predicted motion trajectory of the obstacle based on the position data of the obstacle.

[0104] It should be noted that, in an embodiment of the present invention, after obtaining the position data of the obstacle and the outer contour point cloud data of the vehicle, the movement trajectory of the obstacle in a future period of time is predicted based on the position data of the obstacle at the current moment and the position data of the obstacle at historical moments, so as to obtain the predicted movement trajectory of the obstacle.

[0105] Step 103 , judging whether the obstacle poses a collision risk to the vehicle based on the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle.

[0106] Step 104 : when the obstacle poses a risk of collision with the vehicle, a predicted collision point between the obstacle and the vehicle is determined from the predicted motion trajectory of the obstacle.

[0107] Step 105, determining the risk factor of the obstacle according to the predicted collision point.

[0108] It should be noted that in the embodiment of the present invention, after the predicted motion trajectory of the obstacle is determined, it is determined whether the first trajectory prediction point is on the negative X-axis of the obstacle coordinate system corresponding to the obstacle to determine whether the obstacle is far away from the vehicle or close to the vehicle, and then to evaluate whether the obstacle poses a collision risk to the vehicle. In the case where the obstacle poses a collision risk to the vehicle, the predicted collision point is determined based on the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle, and the hazard coefficient of the obstacle is determined based on the predicted collision point, that is, the hazard of the obstacle is quantified, providing more accurate support for subsequent vehicles to make safer and more reasonable driving decisions.

[0109] The present invention determines the predicted collision point based on the predicted motion trajectory of the obstacle and the point cloud data of the vehicle's outer contour, which not only improves the vehicle's environmental perception ability, but also can accurately and quickly determine the predicted collision point, thereby improving the accuracy and efficiency of collision risk identification. In addition, the embodiment of the present invention determines the danger coefficient of the obstacle based on the predicted collision point, thereby quantifying the danger of the obstacle and providing more accurate support for subsequent vehicles to make safer and more reasonable driving decisions.

[0110] Further, in an embodiment of the present invention, if Figure 2 As shown, step 101 may further include the following steps:

[0111] Step 201 : acquiring first position data of an obstacle through a sensor on a vehicle, wherein the first position data is position data of the obstacle in a pre-established sensor coordinate system.

[0112] It should be noted that, in the embodiment of the present invention, the sensor coordinate system is pre-established. Specifically, the physical center or installation point of the sensor itself is taken as the origin. For example, the origin of the laser radar is the center of its rotation axis, the front of the sensor is the X positive axis, the Y positive axis is perpendicular to the X axis and located to the left of the sensor, and the Z positive axis is perpendicular to the X axis or Y axis and vertically upward to establish the sensor coordinate system.

[0113] The sensors on the vehicle include ultrasonic sensors, radars, etc. The first position data of obstacles around the vehicle are obtained through the sensors installed on the vehicle. Since the first position data of the obstacle is obtained through the sensor, the first position data of the obstacle is the position data of the obstacle in the sensor coordinate system.

[0114] Step 202 , obtaining the position and posture data of the sensor, wherein the position and posture data of the sensor is the position and posture data of the sensor in a pre-established vehicle coordinate system.

[0115] It should be noted that, in the embodiment of the present invention, the pose data of the sensor in a pre-established vehicle coordinate system is acquired in the 3D digital model of the vehicle, and the pose data of the sensor includes the position data and angle data of the sensor.

[0116] Step 203, determining the position data of the obstacle according to the first position data of the obstacle and the position and posture data of the sensor, wherein the position data of the obstacle is the position data of the obstacle in a pre-established vehicle coordinate system.

[0117] It should be noted that, in the embodiment of the present invention, in order to accurately understand the position of the obstacle in the vehicle coordinate system and thus perform an effective collision risk assessment, it is necessary to convert the position data of the obstacle in the sensor coordinate system into the position data of the obstacle in the vehicle coordinate system based on the first position data of the obstacle and the posture data of the sensor. This conversion process can be achieved through a homogeneous transformation matrix.

[0118] The present invention converts the position data of the obstacle in the sensor coordinate system into the position data of the obstacle in the vehicle coordinate system, so that the relative position and distance between the obstacle and the vehicle can be evaluated more intuitively, which helps to more accurately evaluate the collision risk of the obstacle relative to the vehicle, thereby making more reasonable driving decisions.

[0119] Further, in an embodiment of the present invention, if Figure 3 As shown, step 102 may further include the following steps:

[0120] Step 301, obtaining the location data of the obstacle at the current moment and the location data of the obstacle at the previous moment.

[0121] Step 302, obtaining the time difference between the current moment and the previous moment.

[0122] Step 303: Determine the displacement of the obstacle based on the position data of the obstacle at the current moment and the position data of the obstacle at the previous moment.

[0123] Step 304: Determine the relative speed of the obstacle with respect to the vehicle based on the displacement of the obstacle and the time difference.

[0124] Step 305, determining the predicted motion trajectory of the obstacle according to the relative speed, the preset prediction time and the position data of the obstacle at the current moment.

[0125] It should be noted that in the embodiment of the present invention, in order to predict the movement trajectory of the obstacle in the future, it is necessary to obtain the position data of the obstacle at the current moment and the position data of the obstacle at the previous moment in advance. After obtaining the position data of the obstacle at the current moment and the position data of the obstacle at the previous moment, obtain the time difference between the current moment and the previous moment, specifically, the time difference = current moment - previous moment; and determine the displacement of the obstacle based on the position data of the obstacle at the current moment and the position data of the obstacle at the previous moment, specifically, the displacement of the obstacle = the position data of the obstacle at the current moment - the position data of the obstacle at the previous moment. After determining the displacement and time difference of the obstacle, determine the relative speed of the obstacle relative to the vehicle based on the displacement and time difference of the obstacle, specifically, the relative speed of the obstacle relative to the vehicle = displacement of the obstacle / time difference.

[0126] According to the relative speed of the obstacle to the vehicle, the preset prediction time and the position data of the obstacle at the current moment, the position data of the obstacle at the prediction time can be calculated. Specifically, the position data of the obstacle at the prediction time = the position data of the obstacle at the current moment + the relative speed of the obstacle to the vehicle × the prediction time. The predicted motion trajectory of the obstacle can be obtained by connecting the obtained position data of multiple obstacles at the prediction time. For example: the current moment is t, and the prediction time can be t+1, t+2, t+3. According to the relative speed of the obstacle to the vehicle, the moment t+1 and the position data of the obstacle at the moment t, the position data of the obstacle at the moment t+1 is calculated. According to the relative speed of the obstacle to the vehicle, the moment t+2 and the position data of the obstacle at the moment t, the position data of the obstacle at the moment t+2 is calculated. According to the relative speed of the obstacle to the vehicle, the moment t+3 and the position data of the obstacle at the moment t, the position data of the obstacle at the moment t+3 is calculated. By connecting the position data of the obstacle at time t+1, the position data of the obstacle at time t+2, and the position data of the obstacle at time t+3, the predicted movement trajectory of the obstacle between (t+1) and (t+3) in the future can be obtained.

[0127] The present invention determines the predicted motion trajectory of the obstacle based on the relative speed, the preset prediction time and the position data of the obstacle at the current moment, so that the vehicle can predict the movement path of the obstacle in advance, which provides a basis for subsequent vehicles to make accurate decisions based on the predicted obstacle movement trajectory, and further optimizes the driving decision-making process.

[0128] Further, in an embodiment of the present invention, if Figure 4 As shown, step 103 may also include the following steps:

[0129] Step 401 : pre-establishing an obstacle coordinate system of the obstacle, wherein the negative X-axis of the obstacle coordinate system is opposite to the speed direction of the obstacle.

[0130] It should be noted that in the embodiment of the present invention, an obstacle coordinate system corresponding to the obstacle is pre-established. Specifically, the obstacle coordinate system takes the position data of the obstacle as the origin, the speed direction of the obstacle as the positive X axis, the Y positive axis perpendicular to the X axis and located to the left of the obstacle, and the Z positive axis perpendicular to the X axis or the Y axis and vertically upward. The negative X semi-axis of the obstacle coordinate system is opposite to the speed direction of the obstacle.

[0131] Step 402, based on the position data of the obstacle and the outer contour point cloud data of the vehicle, determine the first outer contour point closest to the obstacle, and determine the first outer contour point as the first candidate collision point, wherein the outer contour point cloud data of the vehicle includes the position data of several outer contour points.

[0132] It should be noted that in the embodiment of the present invention, for the position data of any obstacle, the position data of the obstacle is respectively calculated with the position data of several outer contour points to obtain several distances. The several distances are sorted in order from small to large to obtain the sorting result of the distances. The minimum distance is determined according to the sorting result of the distances, and the outer contour point corresponding to the minimum distance is determined from the several outer contour points. The outer contour point corresponding to the minimum distance is the first outer contour point. The distance between the first outer contour point and the obstacle is the shortest, and then the first outer contour point is determined as the first candidate collision point.

[0133] Step 403, determining a first obstacle trajectory prediction point closest to the first candidate collision point according to the first candidate collision point and the predicted motion trajectory of the obstacle, and determining the first obstacle trajectory prediction point as the first trajectory prediction point, wherein the predicted motion trajectory of the obstacle includes a plurality of obstacle trajectory prediction points.

[0134] It should be noted that, in an embodiment of the present invention, the predicted motion trajectory of the obstacle includes several obstacle trajectory prediction points. The position data of the first candidate collision point and the position data corresponding to the several obstacle trajectory prediction points are obtained, and the position data of the first candidate collision point is respectively calculated with the position data corresponding to the several obstacle trajectory prediction points to obtain several distances. The several distances are sorted in order from small to large to obtain the distance sorting result. The minimum distance is determined according to the distance sorting result, and the obstacle trajectory prediction point corresponding to the minimum distance is determined from the several obstacle trajectory prediction points. The obstacle trajectory prediction point corresponding to the minimum distance is the first obstacle trajectory prediction point. The distance between the first obstacle trajectory prediction point and the first candidate collision point is the shortest, and then the first obstacle trajectory prediction point is used as the first trajectory prediction point.

[0135] Step 404 , determining whether the first trajectory prediction point is located on the negative X-axis of the obstacle coordinate system.

[0136] Step 405: If the first trajectory prediction point is located on the negative X-axis of the obstacle coordinate system, it is determined that the obstacle has no collision risk to the vehicle.

[0137] Step 406: If the first trajectory prediction point is not located on the negative X-axis of the obstacle coordinate system, it is determined that the obstacle poses a collision risk to the vehicle.

[0138] It should be noted that, in the embodiment of the present invention, after the first trajectory prediction point is determined, it is determined whether the first trajectory prediction point is located in the negative X-axis of the pre-established obstacle coordinate system. If the first trajectory prediction point is located in the negative X-axis of the obstacle coordinate system, it means that the obstacle is moving away from the vehicle, and it is determined that the obstacle has no collision risk to the vehicle. If the first trajectory prediction point is not located in the negative X-axis of the obstacle coordinate system, it means that the obstacle is approaching the vehicle, and it is determined that the obstacle has a collision risk to the vehicle.

[0139] The present invention determines whether the obstacle is far away from or close to the vehicle by judging whether the first trajectory prediction point is located at the negative X-axis of the obstacle coordinate system corresponding to the obstacle, and then evaluates whether the obstacle poses a collision risk to the vehicle. The present invention can quickly and accurately evaluate whether the obstacle poses a collision risk to the vehicle, which helps subsequent vehicles to quickly take measures, such as deceleration, avoidance or emergency braking, to avoid or reduce potential collision risks.

[0140] Further, in an embodiment of the present invention, if Figure 5 As shown, step 104 may also include the following steps:

[0141] Step 501, according to the first trajectory prediction point and the outer contour point cloud data of the vehicle, determine the second outer contour point closest to the first trajectory prediction point, and determine the second outer contour point as the second candidate collision point.

[0142] It should be noted that, in the embodiment of the present invention, if the obstacle does not pose a collision risk to the vehicle, steps 401-406 need to be repeatedly executed to determine whether other obstacles other than the obstacle pose a collision risk to the vehicle. If the obstacle poses a collision risk to the vehicle, steps 501-506 are continued to be executed to determine the predicted collision point.

[0143] Obtain the position data of the first trajectory prediction point. Calculate the distance between the position data of the first trajectory prediction point and the position data of several outer contour points to obtain several distances. Sort the several distances in ascending order to obtain the distance sorting result. Determine the minimum distance based on the distance sorting result, and determine the outer contour point corresponding to the minimum distance from the several outer contour points. The outer contour point corresponding to the minimum distance is the second outer contour point. The distance between the second outer contour point and the first trajectory prediction point is the shortest, and then the second outer contour point is determined as the second candidate collision point.

[0144] Step 502: Determine a second obstacle trajectory prediction point closest to the second candidate collision point according to the second candidate collision point and the predicted motion trajectory of the obstacle, and determine the second obstacle trajectory prediction point as the second trajectory prediction point.

[0145] It should be noted that, in an embodiment of the present invention, the position data of the second candidate collision point is obtained, and the position data of the second candidate collision point is respectively calculated with the position data corresponding to the respective obstacle trajectory prediction points to obtain a number of distances. The several distances are sorted in order from small to large to obtain a distance sorting result. The minimum distance is determined according to the distance sorting result, and the obstacle trajectory prediction point corresponding to the minimum distance is determined from the several obstacle trajectory prediction points. The obstacle trajectory prediction point corresponding to the minimum distance is the second obstacle trajectory prediction point. The distance between the second obstacle trajectory prediction point and the second candidate collision point is the shortest, and then the second obstacle trajectory prediction point is used as the second trajectory prediction point.

[0146] Step 503: Acquire the position data of the first trajectory prediction point and the position data of the second trajectory prediction point.

[0147] Step 504 : determining the distance between the first trajectory prediction point and the second trajectory prediction point according to the position data of the first trajectory prediction point and the position data of the second trajectory prediction point.

[0148] Step 505: If the distance between the first trajectory prediction point and the second trajectory prediction point is less than a preset distance threshold, the first trajectory prediction point is determined to be a predicted collision point.

[0149] It should be noted that, in the embodiment of the present invention, after the second trajectory prediction point is determined, the position data of the first trajectory prediction point and the position data of the second trajectory prediction point are obtained. According to the position data of the first trajectory prediction point and the position data of the second trajectory prediction point, the distance between the first trajectory prediction point and the second trajectory prediction point is determined. Specifically, the distance between the first trajectory prediction point and the second trajectory prediction point = |position data of the first trajectory prediction point - position data of the second trajectory prediction point|.

[0150] The distance between the first trajectory prediction point and the second trajectory prediction point is compared with a preset distance threshold. If the distance between the first trajectory prediction point and the second trajectory prediction point is less than the preset distance threshold, it means that the distance between the first trajectory prediction point and the second trajectory prediction point is small, and the distance between the first trajectory prediction point and the first candidate collision point is also the shortest, then the first trajectory prediction point is determined to be the predicted collision point.

[0151] Step 506: If the distance between the first trajectory prediction point and the second trajectory prediction point is greater than or equal to the distance threshold, a third outer contour point closest to the second trajectory prediction point is determined based on the second trajectory prediction point and the outer contour point cloud data of the vehicle, and the third outer contour point is determined as the third candidate collision point.

[0152] It should be noted that, in the embodiment of the present invention, if the distance between the first trajectory prediction point and the second trajectory prediction point is greater than or equal to the distance threshold, it means that the distance between the first trajectory prediction point and the second trajectory prediction point is large, then the third outer contour point closest to the second trajectory prediction point is determined according to the second trajectory prediction point and the outer contour point cloud data of the vehicle, and the third outer contour point is determined as the third candidate collision point. According to the third candidate collision point and the predicted motion trajectory of the obstacle, the third obstacle trajectory prediction point closest to the third candidate collision point is determined, and the third obstacle trajectory prediction point is determined as the third trajectory prediction point. That is, steps 501-502 are repeatedly executed, specifically, according to the nth trajectory prediction point and the outer contour point cloud data of the vehicle, the n+1th outer contour point closest to the nth trajectory prediction point is determined, and the n+1th outer contour point is determined as the n+1th candidate collision point. According to the n+1th candidate collision point and the predicted motion trajectory of the obstacle, the n+1th obstacle trajectory prediction point closest to the n+1th candidate collision point is determined, and the n+1th obstacle trajectory prediction point is determined as the n+1th trajectory prediction point. Until the distance between the nth trajectory prediction point and the n+1th trajectory prediction point is less than the preset distance threshold, the distance between the nth trajectory prediction point and the n+1th trajectory prediction point is the shortest, and the distance between the nth trajectory prediction point and the nth candidate collision point is also the shortest, indicating that there is a collision risk to the vehicle when the obstacle is at the nth trajectory prediction point, and the nth trajectory prediction point is used as the predicted collision point.

[0153] The present invention determines the predicted collision point through multiple iterations, so that the determined predicted collision point is the collision position closest to the vehicle, thereby improving the accuracy and efficiency of determining the predicted collision point, and further improving the accuracy of subsequent risk assessment and decision-making.

[0154] Further, in an embodiment of the present invention, if Figure 6 As shown, step 104 may also include the following steps:

[0155] Step 601, respectively determine the distances between the outer contour points of the vehicle and the obstacle trajectory prediction points.

[0156] Step 602, determining the shortest distance according to the distance.

[0157] Step 603: determine the obstacle trajectory prediction point corresponding to the shortest distance in the predicted motion trajectory of the obstacle, and use the obstacle trajectory prediction point corresponding to the shortest distance as the predicted collision point.

[0158] It should be noted that, in an embodiment of the present invention, the outer contour point cloud data of the vehicle includes the position data of several outer contour points, and the predicted motion trajectory of the obstacle includes several obstacle trajectory prediction points. The position data of several outer contour points and the position data of several obstacle trajectory prediction points are obtained respectively. For the position data of any outer contour point and the position data of any obstacle trajectory prediction point, the distance between the position data of the outer contour point and the position data of the obstacle trajectory prediction point is calculated, and then the distance between the position data of several outer contour points and the position data of the obstacle trajectory prediction point can be obtained. The calculated distances are sorted from small to large to obtain a sorting result. According to the sorting result, the nearest distance is determined, and the obstacle trajectory prediction point corresponding to the nearest distance is determined from the predicted motion trajectory of the obstacle, and the obstacle trajectory prediction point corresponding to the nearest distance is used as the predicted collision point. It should be noted that the closer the nearest distance is to 0, the greater the collision risk of the obstacle to the vehicle when it is at the predicted collision point.

[0159] The present invention determines an outer contour point and an obstacle trajectory prediction point from a plurality of outer contour points and a plurality of obstacle trajectory prediction points, the distance between the two points being the shortest, and uses the obstacle trajectory prediction point as the predicted collision point, which helps to accurately identify the predicted collision position, provides a basis for subsequent more accurate risk assessment and decision-making, and thus improves driving safety.

[0160] Further, in an embodiment of the present invention, if Figure 7 As shown, step 105 may also include the following steps:

[0161] Step 701 : Pre-acquire the position data of the predicted collision point and the obstacle type of the obstacle.

[0162] Step 702: Pre-establish a corresponding relationship between obstacle types and risk factors.

[0163] Step 703: Determine the risk coefficient of the obstacle according to the obstacle type of the obstacle and the corresponding relationship between the obstacle type and the risk coefficient.

[0164] Step 704: determine the collision distance based on the position data of the obstacle and the position data of the predicted collision point.

[0165] Step 705, determining the risk factor of the obstacle according to the relative speed of the obstacle to the vehicle, the risk factor of the obstacle, and the collision distance.

[0166] It should be noted that in an embodiment of the present invention, after the predicted collision point is determined, the position data of the predicted collision point and the obstacle type corresponding to the obstacle are obtained, where the obstacle type may include pedestrians, bicycles, motorcycles, cars, trucks, animals, etc.

[0167] For any obstacle type, a risk coefficient is assigned to the obstacle type, which reflects the potential danger of a collision between the vehicle and the obstacle of this type. By matching the obstacle type and the risk coefficient one by one, the corresponding relationship between the obstacle type and the risk coefficient can be obtained, as shown in Table 1.

[0168] Table 1 Correspondence between obstacle types and risk factors

[0169] Obstacle Type pedestrian bike motorcycle car truck animal Risk Factor 0.9 0.7 0.8 0.6 0.7 0.8

[0170] After the corresponding relationship between the obstacle type and the risk coefficient is established, the risk coefficient corresponding to the obstacle type of the current obstacle is determined according to the obstacle type of the current obstacle and the corresponding relationship between the obstacle type and the risk coefficient.

[0171] The collision distance is determined according to the position data of the obstacle and the position data of the predicted collision point. Specifically, the collision distance=|the position data of the obstacle−the position data of the predicted collision point|.

[0172] The risk factor of the obstacle is determined according to the relative speed of the obstacle to the vehicle, the risk factor of the obstacle and the collision distance. Specifically, the risk factor of the obstacle = 1 / (d / v)*c, where d is the collision distance, v is the relative speed of the obstacle to the vehicle, and c is the risk factor corresponding to the obstacle type of the current obstacle. It should be noted that the larger the value of the risk factor, the greater the risk to the vehicle; conversely, the smaller the value of the risk factor, the smaller the risk to the vehicle.

[0173] The present invention calculates the danger coefficient of the obstacle, which takes into account the relative speed of the obstacle to the vehicle, the obstacle type and the collision distance. It not only quantifies the danger of the obstacle, but also conducts a comprehensive assessment of the danger of the obstacle, providing more accurate support for subsequent vehicles to make safer and more reasonable driving decisions.

[0174] Reference Figure 8 , shows a device block diagram of a collision risk identification device provided by an embodiment of the present invention, and the device may include:

[0175] The data acquisition module 801 is used to acquire the location data of obstacles and the outer contour point cloud data of the vehicle;

[0176] A trajectory prediction module 802, used to determine a predicted motion trajectory of an obstacle based on the position data of the obstacle;

[0177] The collision risk judgment module 803 is used to judge whether the obstacle poses a collision risk to the vehicle based on the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle;

[0178] A predicted collision point determination module 804 is used to determine a predicted collision point between the obstacle and the vehicle from the predicted motion trajectory of the obstacle when the obstacle has a collision risk with the vehicle;

[0179] The obstacle hazard quantification module 805 is used to determine the hazard coefficient of the obstacle according to the predicted collision point.

[0180] Optionally, the data acquisition module includes:

[0181] The first position data acquisition submodule of the obstacle is used to acquire the first position data of the obstacle through the sensor on the vehicle, wherein the first position data is the position data of the obstacle in a pre-established sensor coordinate system;

[0182] The sensor posture data acquisition submodule is used to acquire the posture data of the sensor, wherein the posture data of the sensor is the posture data of the sensor in a pre-established vehicle coordinate system;

[0183] The obstacle position data acquisition submodule is used to determine the obstacle position data according to the first obstacle position data and the sensor posture data, wherein the obstacle position data is the obstacle position data in a pre-established vehicle coordinate system.

[0184] Optionally, the trajectory prediction module includes:

[0185] The position data acquisition submodule is used to obtain the position data of the obstacle at the current moment and the position data of the obstacle at the previous moment;

[0186] The time difference acquisition submodule is used to obtain the time difference between the current moment and the previous moment;

[0187] The displacement determination submodule is used to determine the displacement of the obstacle according to the position data of the obstacle at the current moment and the position data of the obstacle at the previous moment;

[0188] A relative speed determination submodule is used to determine the relative speed of the obstacle with respect to the vehicle based on the displacement and time difference of the obstacle;

[0189] The motion trajectory prediction submodule is used to determine the predicted motion trajectory of the obstacle based on the relative speed, the preset prediction time and the position data of the obstacle at the current moment.

[0190] Optionally, the collision risk judgment module includes:

[0191] The obstacle coordinate system establishment submodule is used to pre-establish the obstacle coordinate system of the obstacle, wherein the negative X-axis of the obstacle coordinate system is opposite to the speed direction of the obstacle;

[0192] A first candidate collision point determination submodule is used to determine a first outer contour point closest to the obstacle based on the position data of the obstacle and the outer contour point cloud data of the vehicle, and determine the first outer contour point as the first candidate collision point, wherein the outer contour point cloud data of the vehicle includes the position data of a plurality of outer contour points;

[0193] a first obstacle trajectory prediction point determination submodule, configured to determine a first obstacle trajectory prediction point closest to the first candidate collision point according to the first candidate collision point and the predicted motion trajectory of the obstacle, and determine the first obstacle trajectory prediction point as the first trajectory prediction point, wherein the predicted motion trajectory of the obstacle includes a plurality of obstacle trajectory prediction points;

[0194] A position determination submodule is used to determine whether the first trajectory prediction point is located on the negative X-axis of the obstacle coordinate system;

[0195] A first collision risk judgment submodule, configured to determine that the obstacle has no collision risk to the vehicle if the first trajectory prediction point is located on the negative X-axis of the obstacle coordinate system;

[0196] The second collision risk judgment submodule is used to determine that the obstacle has a collision risk to the vehicle if the first trajectory prediction point is not located on the negative X-axis of the obstacle coordinate system.

[0197] Optionally, the predicted collision point determination module includes:

[0198] A second candidate collision point determination submodule, for determining a second outer contour point closest to the first trajectory prediction point according to the first trajectory prediction point and the outer contour point cloud data of the vehicle, and determining the second outer contour point as a second candidate collision point;

[0199] A second obstacle trajectory prediction point determination submodule, configured to determine a second obstacle trajectory prediction point closest to the second candidate collision point according to the second candidate collision point and the predicted motion trajectory of the obstacle, and determine the second obstacle trajectory prediction point as the second trajectory prediction point;

[0200] A trajectory prediction point position data acquisition submodule, used to acquire position data of a first trajectory prediction point and position data of a second trajectory prediction point;

[0201] a distance determination submodule for adjacent trajectory prediction points, used to determine the distance between the first trajectory prediction point and the second trajectory prediction point according to the position data of the first trajectory prediction point and the position data of the second trajectory prediction point;

[0202] a first predicted collision point determination submodule, configured to determine the first trajectory prediction point as a predicted collision point if the distance between the first trajectory prediction point and the second trajectory prediction point is less than a preset distance threshold;

[0203] The third candidate collision point determination submodule is used to determine a third outer contour point closest to the second trajectory prediction point based on the second trajectory prediction point and the outer contour point cloud data of the vehicle if the distance between the first trajectory prediction point and the second trajectory prediction point is greater than or equal to the distance threshold, and determine the third outer contour point as the third candidate collision point.

[0204] Optionally, the predicted collision point determination module includes:

[0205] A distance calculation submodule, used to determine the distance between the outer contour points of the vehicle and the obstacle trajectory prediction points respectively;

[0206] A closest distance determination submodule, used to determine the closest distance based on the distance;

[0207] The second predicted collision point determination submodule is used to determine the obstacle trajectory prediction point corresponding to the shortest distance in the predicted motion trajectory of the obstacle, and use the obstacle trajectory prediction point corresponding to the shortest distance as the predicted collision point.

[0208] Optionally, the obstacle hazard quantification module includes:

[0209] A position data and obstacle type acquisition submodule, used to pre-acquire the position data of the predicted collision point and the obstacle type of the obstacle;

[0210] A corresponding relationship establishment submodule is used to pre-establish the corresponding relationship between obstacle types and risk factors;

[0211] A risk coefficient determination submodule, used to determine the risk coefficient of the obstacle according to the obstacle type of the obstacle and the corresponding relationship between the obstacle type and the risk coefficient;

[0212] A collision distance determination submodule, used to determine the collision distance based on the position data of the obstacle and the position data of the predicted collision point;

[0213] The risk factor determination submodule is used to determine the risk factor of the obstacle according to the relative speed of the obstacle to the vehicle, the risk factor of the obstacle and the collision distance.

[0214] Reference Fig. 9 , an embodiment of the present invention further provides an electronic device, such as Fig. 9 As shown, it includes a processor 901, a communication interface 902, a memory 903 and a communication bus 904, wherein the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904.

[0215] Memory 903, used for storing computer programs;

[0216] The processor 901 is used to execute the program stored in the memory 903 to implement the following steps:

[0217] Obtain the location data of obstacles and the point cloud data of the vehicle's outer contour;

[0218] Determine the predicted movement trajectory of the obstacle based on the position data of the obstacle;

[0219] Based on the predicted motion trajectory of the obstacle and the point cloud data of the vehicle's outer contour, determine whether the obstacle poses a collision risk to the vehicle;

[0220] In the case where the obstacle poses a risk of collision to the vehicle, determining a predicted collision point between the obstacle and the vehicle from the predicted motion trajectory of the obstacle;

[0221] Determine the danger factor of the obstacle based on the predicted collision point.

[0222] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0223] The communication interface is used for communication between the above terminal and other devices.

[0224] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0225] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0226] In another embodiment provided by the present invention, a computer-readable storage medium is provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the collision risk identification method described in any of the above embodiments.

[0227] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0228] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0229] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0230] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A collision risk identification method, characterized in that: The method comprises: Obtain the location data of obstacles and the point cloud data of the vehicle's outer contour; Determining a predicted motion trajectory of the obstacle according to the position data of the obstacle; Determining whether the obstacle poses a collision risk to the vehicle based on the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle; In the case where the obstacle poses a risk of collision with the vehicle, determining a predicted collision point between the obstacle and the vehicle from the predicted motion trajectory of the obstacle; The risk factor of the obstacle is determined according to the predicted collision point.

2. The method according to claim 1, characterized in that The obtaining of the position data of the obstacle comprises: Acquire first position data of the obstacle through a sensor on the vehicle, wherein the first position data is position data of the obstacle in a pre-established sensor coordinate system; Acquire the position and posture data of the sensor, wherein the position and posture data of the sensor is the position and posture data of the sensor in a pre-established vehicle coordinate system; The position data of the obstacle is determined according to the first position data of the obstacle and the position data of the sensor, wherein the position data of the obstacle is the position data of the obstacle in a pre-established vehicle coordinate system.

3. The method according to claim 1, characterized in that Determining the predicted motion trajectory of the obstacle according to the position data of the obstacle includes: Obtaining the location data of the obstacle at the current moment and the location data of the obstacle at the previous moment; Obtaining the time difference between the current moment and the previous moment; Determine the displacement of the obstacle according to the position data of the obstacle at the current moment and the position data of the obstacle at the previous moment; Determining a relative speed of the obstacle with respect to the vehicle according to the displacement of the obstacle and the time difference; The predicted motion trajectory of the obstacle is determined according to the relative speed, the preset prediction time and the position data of the obstacle at the current moment.

4. The method according to claim 1, characterized in that: The determining, based on the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle, whether the obstacle poses a collision risk to the vehicle comprises: Pre-establishing an obstacle coordinate system of the obstacle, wherein the negative X-axis of the obstacle coordinate system is opposite to the velocity direction of the obstacle; Determine a first outer contour point closest to the obstacle according to the position data of the obstacle and the outer contour point cloud data of the vehicle, and determine the first outer contour point as a first candidate collision point, wherein the outer contour point cloud data of the vehicle includes position data of a plurality of the outer contour points; Determining a first obstacle trajectory prediction point closest to the first candidate collision point according to the first candidate collision point and the predicted motion trajectory of the obstacle, and determining the first obstacle trajectory prediction point as a first trajectory prediction point, wherein the predicted motion trajectory of the obstacle includes a plurality of the obstacle trajectory prediction points; Determining whether the first trajectory prediction point is on the negative X-axis of the obstacle coordinate system; If the first trajectory prediction point is located on the negative X-axis of the obstacle coordinate system, it is determined that the obstacle has no collision risk to the vehicle; If the first trajectory prediction point is not located on the negative X-axis of the obstacle coordinate system, it is determined that the obstacle poses a collision risk to the vehicle.

5. The method according to claim 4, characterized in that Determining the predicted collision point between the obstacle and the vehicle from the predicted motion trajectory of the obstacle includes: Determine, according to the first trajectory prediction point and the outer contour point cloud data of the vehicle, a second outer contour point closest to the first trajectory prediction point, and determine the second outer contour point as a second candidate collision point; Determining a second obstacle trajectory prediction point closest to the second candidate collision point according to the second candidate collision point and the predicted motion trajectory of the obstacle, and determining the second obstacle trajectory prediction point as the second trajectory prediction point; Acquire the position data of the first trajectory prediction point and the position data of the second trajectory prediction point; determining a distance between the first trajectory prediction point and the second trajectory prediction point according to the position data of the first trajectory prediction point and the position data of the second trajectory prediction point; If the distance between the first trajectory prediction point and the second trajectory prediction point is less than a preset distance threshold, determining the first trajectory prediction point as a predicted collision point; If the distance between the first trajectory prediction point and the second trajectory prediction point is greater than or equal to the distance threshold, a third outer contour point closest to the second trajectory prediction point is determined based on the second trajectory prediction point and the outer contour point cloud data of the vehicle, and the third outer contour point is determined as a third candidate collision point.

6. The method according to claim 4, characterized in that The determining the predicted collision point between the obstacle and the vehicle from the predicted motion trajectory of the obstacle comprises: respectively determining the distances between the outer contour points of the vehicle and the obstacle trajectory prediction points; determining a minimum distance based on the distance; The obstacle trajectory prediction point corresponding to the shortest distance is determined in the predicted motion trajectory of the obstacle, and the obstacle trajectory prediction point corresponding to the shortest distance is used as the predicted collision point.

7. The method according to claim 1, characterized in that Determining the risk factor of the obstacle according to the predicted collision point includes: Pre-acquiring the position data of the predicted collision point and the obstacle type of the obstacle; Establish the corresponding relationship between obstacle type and risk factor in advance; Determining the risk coefficient of the obstacle according to the obstacle type of the obstacle and the corresponding relationship between the obstacle type and the risk coefficient; Determining a collision distance according to the position data of the obstacle and the position data of the predicted collision point; The risk factor of the obstacle is determined according to the relative speed of the obstacle with respect to the vehicle, the risk factor of the obstacle, and the collision distance.

8. A collision risk identification device, characterized in that: The device comprises: A data acquisition module is used to obtain the location data of obstacles and the point cloud data of the outer contour of the vehicle; A trajectory prediction module, used to determine the predicted motion trajectory of the obstacle according to the position data of the obstacle; A collision risk judgment module, used to judge whether the obstacle poses a collision risk to the vehicle based on the predicted motion trajectory of the obstacle and the outer contour point cloud data of the vehicle; A predicted collision point determination module, configured to determine a predicted collision point between the obstacle and the vehicle from a predicted motion trajectory of the obstacle when the obstacle poses a collision risk to the vehicle; The obstacle hazard quantification module is used to determine the hazard coefficient of the obstacle according to the predicted collision point.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.