Vehicle collision prediction method, device, electronic device, medium and vehicle

Abstract

The present disclosure provides a vehicle collision prediction method, device, electronic device, medium and vehicle, which relate to the field of computer technology, and in particular to the fields of intelligent transportation and autonomous driving. The scheme is: obtain a first predicted trajectory of a first vehicle and a second predicted trajectory of a target object; determine a first predicted collision point set based on the first predicted trajectory and the second predicted trajectory. For each predicted collision point: determine the avoidance action parameters of the target object at the predicted collision point at least according to the collision moment corresponding to the predicted collision point; determine whether the avoidance action parameters meet the executable conditions; in response to determining that the avoidance action parameters meet the executable conditions, update the first predicted collision point set; in response to determining that the updated first predicted collision point set includes at least one predicted collision point, predict that the first vehicle will collide with the target object.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, in particular to the field of intelligent transportation and autonomous driving technology, and specifically to a vehicle collision prediction method, device, electronic device, computer-readable storage medium, computer program product, vehicle and edge computing device. Background Art

[0002] Vehicle collisions are common traffic accidents that may cause economic losses and casualties. With the continuous development of autonomous driving technology, how to reduce or avoid collision accidents of autonomous vehicles has received more and more attention. Autonomous vehicles can rely on computer vision, radar, and global positioning systems to achieve autonomous driving functions. During the driving process of autonomous vehicles, in order to reduce or avoid collision accidents, it is usually necessary to accurately predict possible collisions so as to slow down and avoid or detour in time.

[0003] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0004] The present disclosure provides a vehicle collision prediction method, apparatus, electronic device, computer-readable storage medium, computer program product, vehicle, and edge computing device.

[0005] According to one aspect of the present disclosure, a vehicle collision prediction method is provided. The method includes: obtaining a first predicted trajectory of a first vehicle; obtaining a second predicted trajectory of a target object; and determining a first predicted collision point set based on the first predicted trajectory and the second predicted trajectory. The first predicted collision point set includes at least one predicted collision point and a collision moment corresponding to each predicted collision point. For each predicted collision point in the first predicted collision point set: determining an avoidance action parameter of the target object at the predicted collision point at least according to the collision moment corresponding to the predicted collision point, the avoidance action parameter indicating that the target object can avoid the expected collision with the first vehicle when moving in a manner that satisfies the parameter; determining whether the avoidance action parameter satisfies an executable condition; and updating the first predicted collision point set in response to determining that the avoidance action parameter satisfies the executable condition. The method also includes predicting that the first vehicle will collide with the target object in response to determining that the updated first predicted collision point set includes at least one predicted collision point.

[0006] According to another aspect of the present disclosure, a vehicle collision prediction device is provided. The device includes a first acquisition unit, a second acquisition unit, a predicted collision point set determination unit, an avoidance action parameter determination unit, a judgment unit, an update unit, and a collision prediction unit. The first acquisition unit is configured to acquire a first predicted trajectory of a first vehicle; the second acquisition unit is configured to acquire a second predicted trajectory of a target object; the predicted collision point set determination unit is configured to determine a first predicted collision point set based on the first predicted trajectory and the second predicted trajectory. The first predicted collision point set includes at least one predicted collision point and a collision moment corresponding to each predicted collision point. For each predicted collision point in the first predicted collision point set: the avoidance action parameter determination unit is configured to determine an avoidance action parameter of the target object at the predicted collision point at least according to the collision moment corresponding to the predicted collision point, the avoidance action parameter indicating that the target object can avoid the expected collision with the first vehicle when moving in a manner that satisfies the parameter; the judgment unit is configured to determine whether the avoidance action parameter satisfies an executable condition; and the update unit is configured to update the first predicted collision point set in response to determining that the avoidance action parameter satisfies the executable condition. And the collision prediction unit is configured to predict that the first vehicle will collide with the target object in response to determining that the updated first predicted collision point set includes at least one predicted collision point.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned vehicle collision prediction method.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the above-mentioned vehicle collision prediction method.

[0009] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements the above-mentioned vehicle collision prediction method when executed by a processor.

[0010] According to yet another aspect of the present disclosure, a vehicle is provided, the vehicle comprising the electronic device according to the above.

[0011] According to another aspect of the present disclosure, an edge computing device is provided, which includes the electronic device according to the above.

[0012] According to one or more embodiments of the present disclosure, the accuracy of vehicle collision prediction can be improved.

[0013] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0015] Figure 1 A schematic diagram showing an exemplary system in which the various methods described herein may be implemented according to an embodiment of the present disclosure;

[0016] Figure 2 A flow chart of a vehicle collision prediction method according to an embodiment of the present disclosure is shown;

[0017] Figure 3 A flowchart showing a partial process of a vehicle collision prediction method according to an embodiment of the present disclosure;

[0018] Figure 4 A flowchart showing a partial process of a vehicle collision prediction method according to an embodiment of the present disclosure;

[0019] Figure 5 A flowchart showing a partial process of a vehicle collision prediction method according to an embodiment of the present disclosure;

[0020] Figure 6 A scene diagram showing a method for predicting a vehicle collision according to an embodiment of the present disclosure can be implemented;

[0021] Figure 7 A structural block diagram of a vehicle collision prediction device according to an embodiment of the present disclosure is shown; and

[0022] Figure 8 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0023] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0024] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0025] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0026] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0027] As mentioned above, in order to ensure the driving safety of autonomous vehicles, it is necessary to accurately predict possible collisions. The present disclosure proposes a vehicle collision prediction method, device, electronic device, computer-readable storage medium, computer program product, vehicle and edge computing device. Using the predicted trajectories of the vehicle and the target object, a set of predicted collision points is determined; according to the collision moment corresponding to the predicted collision point, the avoidance action parameters are determined; and it is determined whether the avoidance action parameters meet the executable conditions, and when the executable conditions are met, the predicted collision point set is updated; when there are still predicted collision points in the updated predicted collision point set, it is predicted that the vehicle will collide. In this way, the accuracy of collision prediction can be improved.

[0028] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0029] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes a motor vehicle 110 , a server 120 , and one or more communication networks 130 coupling the motor vehicle 110 to the server 120 .

[0030] In an embodiment of the present disclosure, the motor vehicle 110 may include a computing device according to an embodiment of the present disclosure and / or be configured to perform a method according to an embodiment of the present disclosure.

[0031] The server 120 may run one or more services or software applications that can execute the vehicle collision prediction method according to the embodiment of the present disclosure. In some embodiments, the server 120 may also provide other services or software applications, which may include non-virtual environments and virtual environments. Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. A user of the motor vehicle 110 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0032] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0033] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0034] In some embodiments, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from motor vehicle 110. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of motor vehicle 110.

[0035] The network 130 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including, but not limited to, TCP / IP, SNA, IPX, etc. By way of example only, one or more networks 130 may be a satellite communications network, a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (including, for example, Bluetooth, WiFi), and / or any combination of these and other networks.

[0036] The system 100 may also include one or more databases 150. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 150 may be used to store information such as audio files and video files. The data repository 150 may reside in various locations. For example, the data repository used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The data repository 150 may be of different types. In some embodiments, the data repository used by the server 120 may be a database, such as a relational database. One or more of these databases may store, update, and retrieve data to and from the database in response to a command.

[0037] In some embodiments, one or more of the databases 150 may also be used by an application to store application data. The databases used by the application may be different types of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0038] The motor vehicle 110 may include a sensor 111 for sensing the surrounding environment. The sensor 111 may include one or more of the following sensors: a visual camera, an infrared camera, an ultrasonic sensor, a millimeter wave radar, and a laser radar (LiDAR). Different sensors may provide different detection accuracy and range. The camera may be installed at the front, rear, or other location of the vehicle. The visual camera may capture the situation inside and outside the vehicle in real time and present it to the driver and / or passengers. In addition, by analyzing the images captured by the visual camera, information such as traffic light indications, intersection conditions, and the operating status of other vehicles may be obtained. The infrared camera may capture objects under night vision conditions. Ultrasonic sensors may be installed around the vehicle to measure the distance of objects outside the vehicle from the vehicle using the characteristics of strong ultrasonic directionality. Millimeter wave radars may be installed at the front, rear, or other location of the vehicle to measure the distance of objects outside the vehicle from the vehicle using the characteristics of electromagnetic waves. Laser radars may be installed at the front, rear, or other location of the vehicle to detect object edges and shape information, thereby identifying and tracking objects. Due to the Doppler effect, the radar device may also measure the speed change of the vehicle and the moving object.

[0039] The motor vehicle 110 may also include a communication device 112. The communication device 112 may include a satellite positioning module capable of receiving satellite positioning signals (e.g., Beidou, GPS, GLONASS, and GALILEO) from satellites 141 and generating coordinates based on these signals. The communication device 112 may also include a module for communicating with a mobile communication base station 142, and the mobile communication network may implement any suitable communication technology, such as GSM / GPRS, CDMA, LTE, and other current or evolving wireless communication technologies (e.g., 5G technology). The communication device 112 may also have a vehicle-to-vehicle or vehicle-to-everything (V2X) module, which is configured to implement, for example, vehicle-to-vehicle (V2V) communication with other vehicles 143 and vehicle-to-infrastructure (V2I) communication with infrastructure 144. In addition, the communication device 112 may also have a module configured to communicate with a user terminal 145 (including but not limited to a smartphone, a tablet computer, or a wearable device such as a watch) by, for example, using a wireless LAN or Bluetooth of the IEEE802.11 standard. Using the communication device 112, the motor vehicle 110 may also access the server 120 via the network 130.

[0040] The motor vehicle 110 may also include a control device 113. The control device 113 may include a processor that communicates with various types of computer-readable storage devices or media, such as a central processing unit (CPU) or a graphics processing unit (GPU), or other dedicated processors. The control device 113 may include an automatic driving system for automatically controlling various actuators in the vehicle. The automatic driving system is configured to control the powertrain, steering system, and braking system of the motor vehicle 110 (not shown) via multiple actuators in response to inputs from multiple sensors 111 or other input devices to control acceleration, steering, and braking, respectively, without human intervention or limited human intervention. Some processing functions of the control device 113 can be implemented through cloud computing. For example, some processing can be performed using an on-board processor, while other processing can be performed using computing resources in the cloud. The control device 113 can be configured to perform a method according to the present disclosure. In addition, the control device 113 can be implemented as an example of a computing device on the motor vehicle side (client) according to the present disclosure.

[0041] Figure 1 The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0042] Figure 2 A flow chart of a vehicle collision prediction method 200 according to an embodiment of the present disclosure is shown.

[0043] like Figure 2 As shown, the method 200 includes:

[0044] Step S210, obtaining a first predicted trajectory of a first vehicle;

[0045] Step S220, obtaining a second predicted trajectory of the target object;

[0046] Step S230: Determine a first predicted collision point set based on the first predicted trajectory and the second predicted trajectory. The first predicted collision point set includes at least one predicted collision point and a collision moment corresponding to each predicted collision point.

[0047] For each predicted collision point in the first predicted collision point set, the method 200 further includes:

[0048] Step S240: determining an avoidance action parameter of the target object at the predicted collision point at least according to the collision moment corresponding to the predicted collision point. The avoidance action parameter indicates that the target object can avoid the expected collision with the first vehicle when moving in a manner that satisfies the parameter;

[0049] Step S250, determining whether the avoidance action parameters meet the executable conditions; and

[0050] Step S260: In response to determining that the avoidance action parameters meet the executable condition, updating the first predicted collision point set.

[0051] The method 200 further includes step S270 , predicting that the first vehicle will collide with the target object in response to determining that the updated first predicted collision point set includes at least one predicted collision point.

[0052] The method 200 may be performed by a first vehicle, for example, and the first vehicle may be the motor vehicle 110 described above. In some examples, the target object may be a fixed obstacle (eg, a street lamp, a guardrail), a pedestrian, or another moving vehicle around the first vehicle.

[0053] In step S210, the trajectory of the first vehicle planned according to the navigation route may be obtained as the first predicted trajectory. For example, the first predicted trajectory may be determined according to the coordinates of each position on the navigation route in the high-precision map.

[0054] In step S220, the second predicted trajectory may be received from other vehicles by means of inter-vehicle communication. For example, if the target object is another vehicle in motion, the other vehicle may transmit its planned second predicted trajectory to the first vehicle by means of inter-vehicle communication. In some other examples, the target object may be a stationary fixed obstacle (such as a guardrail), and the first vehicle may sense the motion state of the target object by means of a camera or radar and further calculate the second predicted trajectory of the target object by means of a computer (in the case where the target object is a fixed obstacle, the second predicted trajectory is a fixed point).

[0055] In step S230, one or more intersection points of the first predicted trajectory and the second predicted trajectory may be determined, and the one or more intersection points may all be used as predicted collision points. Exemplarily, three intersection points may be included between the first predicted trajectory and the second predicted trajectory, and the three intersection points may be predicted collision point a, predicted collision point b, and predicted collision point c, respectively. Each predicted collision point has a corresponding collision moment. For example, the predicted collision moment of collision point a is 1 second, which means that the first vehicle may collide with the target object at the predicted collision point a after 1 second. For example, the predicted collision moment of collision point b is 2 seconds, which means that the first vehicle may collide with the target object at the predicted collision point b after 2 seconds. For example, the predicted collision moment of collision point c is 3 seconds, which means that the first vehicle may collide with the target object at the predicted collision point c after 3 seconds.

[0056] In step S240, for each predicted collision point in the first predicted collision point set, the avoidance action parameters of the target object at the predicted collision point can be determined according to the collision time corresponding to the predicted collision point. For example, for predicted collision point c, the avoidance action parameters (such as turning radius or braking acceleration) of the target object at the predicted collision point c within 3 seconds are determined according to the collision time corresponding to the predicted collision point c. For example, the avoidance action parameters of the target object can be determined to be 5m / s 2 Braking acceleration, which means that in the next 3 seconds, if the target object moves at 5m / s 2 If the vehicle brakes with a braking acceleration of , the expected collision with the first vehicle can be avoided.

[0057] The executable condition may be a range of evasive actions that are allowed to be performed by the target object. For example, considering the safety risks that the evasive action itself may bring (for example, the target object may slip or roll over during evasion), performing evasive actions within the allowed range may prevent the target object from causing the above safety risks.

[0058] When determining the avoidance action parameters (5m / s 2 When the braking acceleration meets the executable conditions, it means that under the current circumstances, the target object can 2 The braking acceleration is used to decelerate the vehicle to avoid the expected collision with the first vehicle. Therefore, the first predicted collision point set can be updated, and the updated first predicted collision point set can include, for example, predicted collision point a and predicted collision point b.

[0059] In step S270 , in response to determining that the updated first predicted collision point set includes at least one predicted collision point (eg, including predicted collision point a and predicted collision point b), it can be predicted that the first vehicle will collide with the target object.

[0060] Therefore, the predicted collision point c that is further predicted not to collide can be removed from the first predicted collision point set, while the predicted collision points (predicted collision point a and predicted collision point b) that are further predicted to collide are retained in the first predicted collision point set, which can improve the accuracy of collision prediction.

[0061] According to some embodiments, step S220, obtaining a second predicted trajectory of the target object may include: obtaining current position information and motion state information of the target object; and determining the second predicted trajectory of the target object according to the position information and the motion state information.

[0062] For example, the first vehicle can use a visual perception module or a radar perception module to obtain the current position information and motion state information of the target object. The position information can be the coordinates of the target object in the high-precision map, and the motion state information can include one or more of the target object's motion speed, acceleration, and steering angle. Based on the current coordinates, speed, and acceleration of the target object, a second predicted trajectory of the target object in the future can be calculated.

[0063] Therefore, when the second predicted trajectory provided by the target object cannot be obtained from the target object (for example, the target object is a pedestrian), the second predicted trajectory can be determined by the position information and motion state information of the target object.

[0064] Figure 3 The flowchart shows a partial process of the vehicle collision prediction method 200 according to an embodiment of the present disclosure.

[0065] According to some embodiments, the first predicted trajectory may include a plurality of first predicted coordinates of the first vehicle within a preset time period and the time corresponding to each first predicted coordinate, and the second predicted trajectory includes a plurality of second predicted coordinates of the target object within the preset time period and the time corresponding to each second predicted coordinate. Figure 3 As shown, for each moment, step S230 may include:

[0066] Step S331, determining the distance between the first coordinate and the second coordinate at this moment;

[0067] Step S332, comparing the distance with a distance threshold; and

[0068] Step S333: In response to determining that the distance is less than the distance threshold, determine the predicted collision point coordinates corresponding to the moment according to the first coordinate and the second coordinate.

[0069] In some examples, the first predicted coordinate and the second predicted coordinate may be coordinates in a high-precision map, and the distance between the first coordinate and the second coordinate may be a Euclidean distance.

[0070] The distance threshold may be a threshold pre-set according to the dimensions of the first vehicle, and the distance threshold can provide a safety margin for collision prediction, thereby improving the accuracy of the prediction of a "grazing" collision between the vehicle and the target object. In some examples, when the first vehicle is a large vehicle, the distance threshold may be appropriately increased; when the first vehicle is a small vehicle, the distance threshold may be appropriately decreased.

[0071] According to some embodiments, the above step S333 may include: determining an average value of the first coordinate and the second coordinate as the predicted collision point coordinate corresponding to the moment.

[0072] The average value of the first coordinate and the second coordinate may be an average value of the abscissas and an average value of the ordinates of the first coordinate and the second coordinate in the plane coordinate system.

[0073] According to some embodiments, the method 200 may further include: respectively acquiring the contour information of the first vehicle and the contour information of the target object, and the distance threshold may be determined based on both the contour information of the first vehicle and the contour information of the target object.

[0074] Therefore, when determining the distance threshold, by taking into account the contour information of the first vehicle and the target object, the distance threshold is made more reasonable, thereby further improving the prediction accuracy of the collision. In some examples, the contour information of the first vehicle may be pre-set according to the factory parameters of the first vehicle, and the contour information of the first vehicle may be the width of the windward surface of the first vehicle; and the contour information of the target object may be calculated by the visual perception function of the first vehicle, and the contour information of the target object may be the width of the windward surface of the target object.

[0075] In some examples, the distance threshold may be the sum of the width of the windward surface of the first vehicle, the width of the windward surface of the target object, and a safety margin.

[0076] According to some embodiments, the above step S250, determining whether the avoidance action parameter satisfies the executable condition may include: querying the allowable value of the avoidance action preset for the target object at least according to the collision moment corresponding to the predicted collision point; and comparing the avoidance action parameter with the allowable value. And the above step S260, in response to determining that the avoidance action parameter satisfies the executable condition, updating the first predicted collision point set may include: in response to determining that the avoidance action parameter satisfies the allowable value, removing the predicted collision point from the first predicted collision point set.

[0077] For example, the allowed value of the pre-set evasive action corresponding to the collision time of 3 seconds can be queried, and the allowed value can be 6m / s 2 The permissible value of the evasive action indicates the maximum acceleration that the target object can make within 3 seconds. The permissible value of the evasive action may be pre-set according to the driving performance of the target object or the maximum acceleration of the vehicle permitted by traffic regulations or road conditions.

[0078] Next, when the avoidance action parameters (5m / s 2 Braking acceleration) meets the allowable value (6m / s 2 ), it means that under the current circumstances, the target object can move at a speed of 5m / s 2 The predicted collision point c can be removed from the first predicted collision point set to update the first predicted collision point set.

[0079] According to some embodiments, the evasive action parameter may include an evasive turn radius indicating that the target object can avoid the expected collision if it turns less than the evasive turn radius, and the allowed value includes a turning radius allowed value.

[0080] And the above step S270 may include: in response to determining that the avoidance turning radius is greater than the turning radius allowable value, removing the predicted collision point from the first predicted collision point set.

[0081] The avoidance turning radius being greater than the allowable turning radius value means that the target object is allowed to turn with the avoidance turning radius to avoid the expected collision. The allowable turning radius value may be determined according to the steering performance of the vehicle and the road width.

[0082] For each predicted collision point, the avoidance turning radius of the target object at the predicted collision point is determined, and those predicted collision points where the target object can avoid collision by turning are removed from the first predicted collision point set, so that those predicted collision points where the target object cannot avoid collision by turning are retained in the first predicted collision point set. In this way, the possibility of predicting a situation where no collision will occur as a situation where a collision will occur can be reduced, further improving the accuracy of collision prediction. The remaining predicted collision points in the first predicted collision point set can all be considered to have a higher collision risk.

[0083] Figure 4 The flowchart shows a partial process of the vehicle collision prediction method 200 according to an embodiment of the present disclosure.

[0084] According to some embodiments, Figure 4 As shown, the evasive steering radius can be determined by the following steps:

[0085] Step S410, obtaining the speed of the target object;

[0086] Step S420, determining the angle between the first predicted trajectory and the second predicted trajectory at the predicted collision point;

[0087] Step S430, determining the avoidance steering angular velocity according to the included angle and the collision moment corresponding to the predicted collision point; and

[0088] Step S440: Determine the avoidance turning radius according to the avoidance turning angular velocity and the speed of the target object.

[0089] The speed of the target object can be the absolute speed V of the target object in the high-precision map. obstacle .

[0090] The angle θ between the first predicted trajectory and the second predicted trajectory at the predicted collision point may be an acute angle between the tangent directions of the first predicted trajectory and the second predicted trajectory at the predicted collision point.

[0091] The avoidance steering angular velocity ω may be a ratio of the angle θ to the collision moment.

[0092] Avoid turning radius r avoid Can be the absolute speed V obstacle The ratio of angular velocity ω.

[0093] According to some embodiments, the turning radius allowable value may be determined by the following steps:

[0094] Get the speed of the target object; and

[0095] According to the collision time corresponding to the predicted collision point and the speed of the target object, the turning radius allowable value is queried from the first data table. The first data table respectively maintains the association between the speed of the target object and the turning radius allowable value and the association between the collision time and the turning radius allowable value.

[0096] The speed of the target object can be the absolute speed V of the target object in the high-precision map. obstacle .

[0097] In some examples, the velocity V of the target object obstacle For example, it can be 10m / s, and the collision time corresponding to the predicted collision point can be 3s. In the first data table, the speed value of 10m / s can correspond to the values ​​of multiple collision times, for example, the speed value of 10m / s can correspond to the values ​​of the three collision times of 1s, 2s, and 3s. The value of each collision time can correspond to a turning radius allowable value, for example, corresponding to turning radius allowable values ​​of 10m, 9m, and 8m respectively. Therefore, based on the speed of the target object 10m / s and the collision time 3s, according to the correlation between the two and the turning radius allowable value, the turning radius allowable value of 8m can be queried from the first data table.

[0098] In the first data table, a smaller speed value may correspond to a smaller steering radius allowable value. For example, at the same collision moment, the steering radius allowable value corresponding to a speed of 10m / s may be smaller than the steering radius allowable value corresponding to a speed of 11m / s. This is because the smaller the steering radius allowable value, the more urgent the target object is allowed to turn, and when the speed of the target object increases, the more urgent the turn is not allowed, so as to avoid turning too quickly and causing the target object (such as a vehicle) to slip or roll over. Similarly, in the first data table, a larger collision moment may correspond to a smaller steering radius allowable value. For example, at the same speed value, the steering radius allowable value corresponding to a collision moment of 2s may be smaller than the steering radius allowable value corresponding to a collision moment of 1s. This is because when the collision moment of the target object is smaller, it means that the distance to the collision is closer, and the reaction time of the target object (such as a vehicle) to turn is also shorter. The performance of the target vehicle may not be able to meet the requirements of making a sharp turn in a very short time, so a larger steering radius allowable value can be set. Thus, by setting different steering radius allowable values ​​for different collision moments and different speeds of target objects, the accuracy of collision prediction can be further improved.

[0099] According to some embodiments, the avoidance action parameter may include an avoidance acceleration indicating that the target object can avoid the expected collision when moving at a speed greater than the avoidance acceleration, and the allowable value includes an acceleration allowable value.

[0100] And the above step S270 may include: in response to determining that the avoidance acceleration is less than the acceleration allowable value, removing the predicted collision point from the first predicted collision point set.

[0101] The avoidance acceleration being less than the acceleration allowable value means that the target object is allowed to accelerate or decelerate at the acceleration allowable value to avoid the expected collision. The acceleration allowable value may be determined according to the acceleration and deceleration performance of the vehicle and the road friction factor.

[0102] For each predicted collision point, the avoidance acceleration of the target object at the predicted collision point is determined, and those predicted collision points where the target object can avoid collision by acceleration and deceleration are removed from the first predicted collision point set, so that those predicted collision points where the target object cannot avoid collision by acceleration and deceleration are retained in the first predicted collision point set. In this way, the possibility of predicting a situation where no collision will occur as a situation where a collision will occur can be reduced, further improving the accuracy of collision prediction. The remaining predicted collision points in the first predicted collision point set can all be considered to have a higher collision risk.

[0103] According to some embodiments, the acceleration allowable value may be determined by the following steps:

[0104] Determine the type of target object; and

[0105] According to the collision time corresponding to the predicted collision point and the type of the target object, the acceleration allowable value is queried from the second data table. The second data table maintains the association between the type of the target object and the acceleration allowable value and the association between the collision time and the acceleration allowable value.

[0106] In some examples, the type of the target object may be, for example, a large vehicle, a small vehicle, a bicycle, etc. In the second data table, each type of target object may correspond to multiple collision time values, for example, a large vehicle may correspond to three collision time values ​​of 1s, 2s, and 3s. Each collision time value may correspond to an acceleration allowable value, for example, 6m / s 2 , 7m / s 2 , 8m / s 2 Therefore, based on the type of target object and the collision time 3s, according to the correlation between the two and the acceleration allowable value, the acceleration allowable value can be queried from the second data table to be 8m / s 2 .

[0107] In the second data table, a smaller vehicle model may correspond to a larger acceleration allowable value. For example, at the same collision moment, the acceleration allowable value corresponding to a small vehicle may be greater than the acceleration allowable value corresponding to a large vehicle. This is because a larger vehicle model means a greater vehicle inertia, and due to the limitations of the vehicle braking system itself, a vehicle with a greater inertia tends to have a longer braking distance, so it should correspond to a smaller acceleration allowable value (if the acceleration is too large, a rollover accident may occur). Similarly, in the second data table, a larger collision moment may correspond to a larger acceleration allowable value. For example, under the same vehicle model, the acceleration allowable value corresponding to a collision moment of 2s may be greater than the acceleration allowable value corresponding to a collision moment of 1s. This is because when the collision moment of the target object is smaller, it means that the distance to the collision is closer, the reaction time of the target object (such as a vehicle) for braking is shorter, and the performance of the target vehicle may not be able to meet the emergency braking in a very short time, so a smaller acceleration allowable value can be set. Thus, by setting different acceleration allowable values ​​for different collision moments and different types of target objects, the accuracy of collision prediction can be further improved.

[0108] It will be understood that the second data table may be the same data table as the first data table, or may be a different data table from the first data table.

[0109] According to some embodiments, determining the type of the target object may include the following steps:

[0110] acquiring an image including a target object; and

[0111] The image is subjected to image recognition to determine whether the target object is one of the following preset types: a fixed obstacle, a pedestrian, or a moving second vehicle.

[0112] For example, the first vehicle can capture an image including a target object through a visual perception function, and perform image recognition on the captured image. Fixed obstacles, pedestrians, and the second vehicle in motion can be three preset types. Fixed obstacles can be, for example, buildings, guardrails, etc. Since these obstacles cannot move by themselves, in the second data table, no matter what the value of the collision moment is, the corresponding acceleration allowable value can be set to 0. Pedestrians can avoid with a smaller acceleration before the collision occurs, so at the same collision moment in the second data table, the acceleration allowable value corresponding to the target object type of "pedestrian" can be slightly larger than the acceleration allowable value corresponding to the target object type of "fixed obstacle". Similarly, the second vehicle in motion can avoid with a larger acceleration before the collision occurs, so at the same collision moment in the second data table, the acceleration allowable value corresponding to the target object type of "second vehicle in motion" can be further increased than the target object type of "pedestrian". Therefore, setting different acceleration allowable values ​​for different types of target objects can make the accuracy of the predicted collision points in the first predicted collision point set higher, thereby further improving the collision prediction accuracy.

[0113] Figure 5 The flowchart shows a partial process of the vehicle collision prediction method 200 according to an embodiment of the present disclosure.

[0114] According to some embodiments, Figure 5 As shown, the above step S230 may include:

[0115] Step S531: determining a second predicted collision point set based on the first predicted trajectory and the second predicted trajectory, wherein the second predicted collision point set includes a plurality of predicted collision points and a collision time corresponding to each predicted collision point;

[0116] Step S532, determining a deviation range in front of the first vehicle along the first predicted trajectory, where the deviation range defines an area of ​​a preset area on both sides of the first predicted trajectory; and

[0117] Step S533: Select predicted collision points that fall within the deviation range from the second predicted collision point set, thereby obtaining a first predicted collision point set.

[0118] In some examples, for each moment, a coordinate point (the coordinate point may be a coordinate point on the first predicted trajectory, a coordinate point on the second predicted trajectory, or an average coordinate point of the two) whose distance between the coordinates on the first predicted trajectory at that moment and the coordinates on the second predicted trajectory is less than a distance threshold can be determined as a predicted collision point in the second predicted collision point set.

[0119] In step S532, according to some examples, the deviation range in front of the first vehicle can be a rectangular area with a preset width and a preset length along the forward direction of the first predicted trajectory. The preset width can be a width of 2m offset from the central axis of the first vehicle to both sides; the preset length can be, for example, 10m. Thus, the deviation range defines an area of ​​20mm on both sides of the first predicted trajectory. 2 area.

[0120] Since the collision accuracy predicted by the points not falling within the deviation range is lower than the collision accuracy predicted by the points falling within the deviation range (generally, the closer to the first vehicle, the higher the accuracy of the collision prediction point), by selecting the predicted collision points falling within the deviation range into the first predicted collision point set, and excluding the predicted collision points not falling within the deviation range from the first predicted collision point set, the amount of calculation can be reduced while ensuring the collision prediction accuracy, thereby improving the calculation efficiency.

[0121] According to some embodiments, the lateral deviation distance of the deviation range may gradually decrease from the position of the first vehicle along the first predicted trajectory forward.

[0122] As the collision accuracy corresponding to the predicted collision point decreases along the first predicted trajectory, by gradually reducing the lateral deviation distance of the deviation range and further excluding the collision prediction points far away from the current position of the first vehicle from the first predicted collision point set, the amount of calculation can be further reduced, thereby further improving the calculation efficiency.

[0123] Next we will continue to combine Figure 6 A vehicle collision prediction method according to an embodiment of the present disclosure is described. Figure 6 A scene diagram is shown in which a vehicle collision prediction method 200 according to an embodiment of the present disclosure can be implemented.

[0124] like Figure 6As shown, vehicle 610 is the first vehicle and vehicle 620 is the target object. Along the forward direction of vehicle 610, six hollow dots show the first predicted trajectory of vehicle 610. The six hollow dots are represented by [X1], [X2], [X3], [X4], [X5, 5s], [X6], where X1 to X6 represent the coordinates of each trajectory point, and 5s represents the collision time is 5s. The six hollow triangles show the second predicted trajectory of vehicle 620. The six hollow triangles are represented by [Y1], [Y 2], [Y3], [Y 4], [Y5, 5s], [Y6], where Y1 to Y6 represent the coordinates of each trajectory point, and 5s represents the collision time is 5s.

[0125] First, the first coordinate at each moment can be determined ( Figure 6 The corresponding one in the hollow circle in ) and the second coordinate ( Figure 6 The distance between the corresponding one of the hollow triangles in the figure); comparing the distance with the distance threshold; in this example, since the distance between the fifth hollow circle and the fifth hollow triangle is less than the distance threshold, the average coordinate point 630 of the two is determined to be the predicted collision point.

[0126] Furthermore, since the predicted collision point 630 falls within the deviation range 640 , it means that there is a certain risk of a collision accident occurring at the predicted collision point 630 .

[0127] For the predicted collision point 630, the avoidance turning radius here can be calculated by first obtaining the speed V of the target object. 620 ; Determine the angle θ at the predicted collision point 630 according to the first predicted trajectory and the second predicted trajectory (the two predicted trajectories are shown by dotted lines respectively); calculate the ratio between the angle θ and the collision time 5s to obtain the avoidance steering angular velocity ω; calculate the velocity V 620 The ratio of the angular velocity of the avoidance steering ω to the avoidance steering radius r 620 .

[0128] Then, for the predicted collision point 630, the collision time 5s corresponding to the predicted collision point 630 and the speed V of the target object can be calculated. 620 , query the corresponding turning radius allowable value r from the first data table allow .

[0129] Furthermore, by comparing the avoidance turning radius r 620 The allowable value of turning radius r allow , when the avoidance turning radius r 620 Greater than the allowable value of turning radius r allow , which means that the vehicle 620 can avoid the turning radius r at the predicted collision point 630 620Turning is performed to avoid collision with vehicle 610. Thus, predicted collision point 630 can be removed from the predicted collision point set. Thus, the updated predicted collision point set is empty, and it can be predicted that no collision will occur between vehicle 610 and vehicle 620.

[0130] In some other examples, when the avoidance turn radius r 620 Less than the allowable value of turning radius r allow , which means that the vehicle 620 cannot avoid the turning radius r at the predicted collision point 630. 620 Turning is performed to avoid collision with vehicle 610. Thus, predicted collision point 630 will continue to be retained in the predicted collision point set. Thus, the updated predicted collision point set includes at least one predicted collision point, and it can be predicted that a collision will occur between vehicle 610 and vehicle 620.

[0131] In some other examples, the avoidance acceleration at the predicted collision point 630 may also be calculated in the manner described in method 200 , and whether to remove the predicted collision point 630 from the predicted collision point set may be determined according to a corresponding acceleration threshold.

[0132] It will be understood that for the sake of simplicity of description, Figure 6 In the example, the predicted collision point set includes only one predicted collision point. In more examples, the predicted collision point set may include more predicted collision points, and the above-described method may be used to perform operations on each predicted collision point to predict whether a collision will occur between the vehicle and the target object.

[0133] Figure 7 A structural block diagram of a vehicle collision prediction device 700 according to an embodiment of the present disclosure is shown.

[0134] like Figure 7 As shown, the device 700 includes a first acquisition unit 710, a second acquisition unit 720, a predicted collision point set determination unit 730, an avoidance action parameter determination unit 740, a judgment unit 750, an updating unit 760 and a collision prediction unit 770.

[0135] The first acquisition unit 710 is configured to acquire a first predicted trajectory of a first vehicle;

[0136] The second acquisition unit 720 is configured to acquire a second predicted trajectory of the target object;

[0137] The predicted collision point set determining unit 730 is configured to determine a first predicted collision point set based on the first predicted trajectory and the second predicted trajectory. The first predicted collision point set includes at least one predicted collision point and a collision moment corresponding to each predicted collision point.

[0138] For each predicted collision point in the first predicted collision point set:

[0139] The avoidance action parameter determination unit 740 is configured to determine an avoidance action parameter of the target object at the predicted collision point at least according to the collision moment corresponding to the predicted collision point, the avoidance action parameter indicating that the target object can avoid the expected collision with the first vehicle when moving in a manner satisfying the parameter;

[0140] The determination unit 750 is configured to determine whether the avoidance action parameters meet the executable conditions; and

[0141] The updating unit 760 is configured to update the first predicted collision point set in response to determining that the avoidance action parameters meet the executable condition.

[0142] The collision prediction unit 770 is configured to predict that the first vehicle will collide with the target object in response to determining that the updated first predicted collision point set includes at least one predicted collision point.

[0143] According to an embodiment of the present disclosure, an electronic device, a readable storage medium and a computer program product are also provided.

[0144] According to another aspect of the present disclosure, a vehicle is provided, comprising the electronic device described above.

[0145] According to another aspect of the present disclosure, an edge computing device is also provided. Optionally, the edge computing device may include not only electronic devices but also communication components, and the electronic devices and the communication components may be integrated or separately provided. The electronic devices may obtain data from roadside sensing devices (such as roadside cameras), such as pictures and videos, to perform image and video processing and data calculation, and then transmit the processing and calculation results to the cloud control platform via the communication components.

[0146] Optionally, the edge computing device may also be a road side computing unit (RSCU). Optionally, the electronic device itself may also have the perception data acquisition function and communication function, such as an AI camera. The electronic device can directly perform image and video processing and data calculation based on the acquired perception data, and then transmit the processing and calculation results to the cloud control platform.

[0147] Optionally, the cloud control platform performs processing in the cloud to perform image and video processing and data calculation. The cloud control platform can also be called a vehicle-road collaborative management platform, V2X platform, cloud computing platform, central system, cloud server, etc.

[0148] refer to Figure 8, a block diagram of an electronic device 800 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0149] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0150] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, an output unit 807, a storage unit 808 and a communication unit 809. The input unit 806 can be any type of device that can input information to the electronic device 800. The input unit 806 can receive input digital or character information, and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone and / or a remote control. The output unit 807 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator and / or a printer. The storage unit 808 can include but is not limited to a disk, an optical disk. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver and / or a chipset, such as Bluetooth TM devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0151] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as method 200. For example, in some embodiments, the method 200 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method 200 described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the method 200 in any other appropriate manner (e.g., by means of firmware).

[0152] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0153] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0154] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0155] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0156] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0157] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0158] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0159] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A vehicle collision prediction method, comprising: Obtaining a first predicted trajectory of a first vehicle; Obtaining a second predicted trajectory of the target object; Determining a first predicted collision point set based on the first predicted trajectory and the second predicted trajectory, wherein the first predicted collision point set includes at least one predicted collision point and a collision moment corresponding to each predicted collision point; For each predicted collision point in the first predicted collision point set: determining, at least according to a collision moment corresponding to the predicted collision point, an avoidance action parameter of the target object at the predicted collision point, the avoidance action parameter indicating that the target object can avoid an expected collision with the first vehicle when moving to meet the parameter; Determining whether the avoidance action parameters meet executable conditions; and In response to determining that the avoidance action parameter satisfies the executable condition, updating a first predicted collision point set; and In response to determining that the updated first predicted collision point set includes at least one predicted collision point, predicting that the first vehicle will collide with the target object; Wherein, judging whether the avoidance action parameters meet the executable conditions includes: querying a pre-set allowable value of an evasive action for the target object at least according to the collision moment corresponding to the predicted collision point; and comparing the avoidance action parameter with the allowed value, And wherein, in response to determining that the avoidance action parameter satisfies the executable condition, updating the first predicted collision point set includes: In response to determining that the avoidance action parameter satisfies the allowable value, the predicted collision point is removed from the first predicted collision point set.

2. The method according to claim 1, wherein: The avoidance action parameter includes an avoidance turning radius, the avoidance turning radius indicating that the target object can avoid the expected collision when turning at a radius smaller than the avoidance turning radius, and the allowable value includes a turning radius allowable value; And wherein, in response to determining that the avoidance action parameter satisfies the allowable value, removing the predicted collision point from the first predicted collision point set comprises: In response to determining that the avoidance turning radius is greater than the turning radius allowable value, the predicted collision point is removed from the first predicted collision point set.

3. The method according to claim 2, wherein: The evasive steering radius is determined by: Acquiring the speed of the target object; determining an angle between the first predicted trajectory and the second predicted trajectory at the predicted collision point; Determining an evasive steering angular velocity according to the included angle and a collision moment corresponding to the predicted collision point; as well as The avoidance steering radius is determined according to the avoidance steering angular velocity and the speed of the target object.

4. The method according to claim 2, wherein: The turning radius allowable value is determined by: Acquiring the speed of the target object; and According to the collision moment corresponding to the predicted collision point and the speed of the target object, the allowable value of the turning radius is queried from a first data table, wherein the first data table respectively maintains the association between the speed of the target object and the allowable value of the turning radius and the association between the collision moment and the allowable value of the turning radius.

5. The method according to claim 1, wherein: The avoidance action parameter includes an avoidance acceleration, the avoidance acceleration indicates that the target object can avoid the expected collision when moving at a speed greater than the avoidance acceleration, and the allowable value includes an acceleration allowable value; And wherein, in response to determining that the avoidance action parameter satisfies the allowable value, removing the predicted collision point from the first predicted collision point set comprises: In response to determining that the avoidance acceleration is less than the acceleration allowable value, the predicted collision point is removed from the first predicted collision point set.

6. The method according to claim 5, wherein: The acceleration allowable value is determined in the following manner: determining the type of the target object; and According to the collision moment corresponding to the predicted collision point and the type of the target object, the allowable acceleration value is queried from a second data table, wherein the second data table respectively maintains an association relationship between the type of the target object and the allowable acceleration value and an association relationship between the collision moment and the allowable acceleration value.

7. The method according to claim 6, wherein: Determining the type of the target object includes: acquiring an image including the target object; and Image recognition is performed on the image to determine whether the target object is one of the following preset types: a fixed obstacle, a pedestrian, or a moving second vehicle.

8. The method according to claim 1, wherein: The first predicted trajectory includes a plurality of first predicted coordinates of the first vehicle within a preset time period and a time corresponding to each first predicted coordinate, and the second predicted trajectory includes a plurality of second predicted coordinates of the target object within the preset time period and a time corresponding to each second predicted coordinate, And wherein, based on the first predicted trajectory and the second predicted trajectory, determining a first predicted collision point set comprises: For each moment: Determine the distance between the first predicted coordinate and the second predicted coordinate at the moment; comparing the distance to a distance threshold; and In response to determining that the distance is less than the distance threshold, the predicted collision point coordinates corresponding to the moment are determined according to the first predicted coordinates and the second predicted coordinates.

9. The method according to claim 8, wherein: Determining the predicted collision point coordinates corresponding to the moment according to the first predicted coordinates and the second predicted coordinates includes: An average value of the first predicted coordinates and the second predicted coordinates is determined as the predicted collision point coordinates corresponding to the moment.

10. The method according to claim 8, further comprising: respectively acquiring the contour information of the first vehicle and the contour information of the target object, The distance threshold is determined based on both the contour information of the first vehicle and the contour information of the target object.

11. The method according to claim 1, wherein: Determining a first predicted collision point set based on the first predicted trajectory and the second predicted trajectory includes: Determining a second predicted collision point set based on the first predicted trajectory and the second predicted trajectory, wherein the second predicted collision point set includes a plurality of predicted collision points and a collision moment corresponding to each predicted collision point; Determining a deviation range in front of the first vehicle along the first predicted trajectory, the deviation range defining an area of ​​a preset area on both sides of the first predicted trajectory; and The predicted collision points falling within the deviation range are selected from the second predicted collision point set, thereby obtaining the first predicted collision point set.

12. The method according to claim 11, wherein: From the position of the first vehicle forward along the first predicted trajectory, the lateral deviation distance of the deviation range gradually decreases.

13. A vehicle collision prediction device, comprising a first acquisition unit, a second acquisition unit, a predicted collision point set determination unit, an avoidance action parameter determination unit, a judgment unit, an update unit and a collision prediction unit, wherein: The first acquisition unit is configured to acquire a first predicted trajectory of a first vehicle; The second acquisition unit is configured to acquire a second predicted trajectory of the target object; The predicted collision point set determining unit is configured to determine a first predicted collision point set based on the first predicted trajectory and the second predicted trajectory, wherein the first predicted collision point set includes at least one predicted collision point and a collision moment corresponding to each predicted collision point; For each predicted collision point in the first predicted collision point set: The avoidance action parameter determination unit is configured to determine an avoidance action parameter of the target object at the predicted collision point at least according to a collision moment corresponding to the predicted collision point, the avoidance action parameter indicating that the target object can avoid an expected collision with the first vehicle when moving in a manner satisfying the parameter; The judging unit is configured to judge whether the avoiding action parameters meet the executable condition; and The updating unit is configured to update the first predicted collision point set in response to determining that the avoidance action parameter satisfies the executable condition; and The collision prediction unit is configured to predict that the first vehicle will collide with the target object in response to determining that the updated first predicted collision point set includes at least one predicted collision point; Wherein, judging whether the avoidance action parameters meet the executable conditions includes: querying a pre-set allowable value of an evasive action for the target object at least according to the collision moment corresponding to the predicted collision point; and comparing the avoidance action parameter with the allowed value, And wherein, in response to determining that the avoidance action parameter satisfies the executable condition, updating the first predicted collision point set includes: In response to determining that the avoidance action parameter satisfies the allowable value, the predicted collision point is removed from the first predicted collision point set.

14. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 12.

15. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-12.

16. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

17. A vehicle comprising the electronic device according to claim 14.

18. An edge computing device, comprising the electronic device according to claim 14.

Images