CN115675534A

CN115675534A - Vehicle track prediction method and device, electronic equipment and storage medium

Info

Publication number: CN115675534A
Application number: CN202211517080.9A
Authority: CN
Inventors: 孔祥锋; 姚萌; 孙灏
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-11-29
Filing date: 2022-11-29
Publication date: 2023-02-03

Abstract

The disclosure provides a vehicle track prediction method, a vehicle track prediction device, electronic equipment and a storage medium, relates to the field of artificial intelligence, in particular to the technical fields of automatic driving, computer vision, intelligent transportation, voice processing and the like, and can be applied to scenes such as vehicle track prediction. The scheme comprises the following steps: identifying a target vehicle with a detour intention from candidate vehicles in a preset monitoring range of the host vehicle; determining an obstacle set corresponding to a target vehicle; acquiring a speed comparison value of each obstacle and a target vehicle in the obstacle set and distance information between each obstacle and the target vehicle; determining a target obstacle which needs to be bypassed by the target vehicle from the obstacle set based on the speed comparison value and the distance information corresponding to each obstacle; a travel locus of the target vehicle around the target obstacle is predicted. The method can avoid the situation that the unreasonable bypassing track is predicted to a greater extent.

Description

Vehicle track prediction method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly to the technical fields of autopilot, computer vision, intelligent transportation, and speech processing.

Background

In reality, the existing track prediction methods for other vehicles around the main vehicle are based on a deep learning model to infer the running tracks of other vehicles. The deep learning model has high universality and can cover most scenes.

However, for some marginal scenarios, the driving trajectory of other vehicles inferred based on the deep learning model may not be reasonable enough, for example, for other vehicles to bypass a barrier and switch to a vehicle scenario, the driving trajectory output by the deep learning model may cross some hard boundaries, especially because the driving route of the non-motor vehicle is more flexible, and the probability of unreasonableness of the driving trajectory of the non-motor vehicle inferred based on the deep learning model is higher.

Disclosure of Invention

The disclosure provides a vehicle track prediction method, a vehicle track prediction device, an electronic device and a storage medium.

According to a first aspect of the present disclosure, there is provided a vehicle trajectory prediction method, the method comprising:

identifying a target vehicle with a detour intention from candidate vehicles in a preset monitoring range of the main vehicle;

determining an obstacle set corresponding to a target vehicle;

acquiring a speed comparison value of each obstacle and a target vehicle in the obstacle set and distance information between each obstacle and the target vehicle;

determining a target obstacle which needs to be bypassed by the target vehicle from the obstacle set based on the speed comparison value and the distance information corresponding to each obstacle;

a travel locus of the target vehicle around the target obstacle is predicted.

In an embodiment of the present disclosure, the distance information includes a first longitudinal distance and a first lateral distance between the obstacle and the target vehicle; determining a target obstacle which needs to be bypassed by a target vehicle from the obstacle set based on the speed comparison value and the distance information corresponding to each obstacle, wherein the method comprises the following steps:

matching a first longitudinal distance and a speed comparison value corresponding to the obstacle with a preset first bypassing condition, and matching a first transverse distance corresponding to the obstacle with a preset second bypassing condition;

determining the obstacle as a candidate obstacle in response to determining that the obstacle meets the first detonable condition and the second detonable condition;

and determining the candidate obstacle with the minimum corresponding first longitudinal distance as the target obstacle which needs to be bypassed by the target vehicle.

In the disclosed embodiment, the speed comparison value is a speed ratio of the obstacle to the target vehicle, and the first detonable condition includes:

the first longitudinal distance corresponding to the obstacle is larger than a first distance threshold value, and the speed ratio corresponding to the obstacle is smaller than a first preset ratio;

or the first longitudinal distance corresponding to the obstacle is smaller than a first distance threshold value, and the speed ratio corresponding to the obstacle is smaller than a second preset ratio;

wherein, the first preset ratio is smaller than the second preset ratio.

In an embodiment of the present disclosure, the speed comparison value is a speed difference between the obstacle and the target vehicle, and the first detonable condition includes:

the first longitudinal distance corresponding to the obstacle is larger than a first distance threshold, and the speed difference corresponding to the obstacle is larger than a first preset difference;

or the first longitudinal distance corresponding to the obstacle is smaller than a first distance threshold value, and the speed ratio corresponding to the obstacle is smaller than a second preset difference value;

and the first preset difference is greater than the second preset difference.

In an embodiment of the present disclosure, the second detonable condition includes: the first lateral distance corresponding to the obstacle is less than a second distance threshold.

In an embodiment of the present disclosure, predicting a travel track of a target vehicle around a target obstacle includes:

determining a first constraint point based on the motion information of the target vehicle, wherein the position information of the first constraint point is the same as the current position information of the target vehicle, and the speed information corresponding to the first constraint point is the same as the current speed information of the target vehicle;

determining position information of a second constraint point based on the first constraint point, the contour information of the target vehicle and the contour information of the target obstacle, wherein when the target vehicle reaches the second constraint point, a first transverse distance between the target vehicle and the target obstacle is larger than 0;

determining speed information corresponding to a second constraint point based on the speed information corresponding to the first constraint point;

determining at least one other constraint point based on the position information of the second constraint point and the speed information corresponding to the second constraint point;

based on the first constraint point, the second constraint point, and the at least one other constraint point, a travel locus of the target vehicle around the target obstacle is predicted.

In the embodiment of the present disclosure, a longitudinal distance between the second constrained point and the first constrained point is equal to a minimum longitudinal distance between the first constrained point and the target obstacle, where the minimum longitudinal distance is determined based on position information of the first constrained point and contour information of the target obstacle;

and the minimum transverse distance between the second constraint point and the target obstacle is equal to the sum of the preset safety distance and the 0.5-time width value of the target vehicle, wherein the width of the target vehicle is determined based on the contour information of the target vehicle.

In the disclosed embodiment, the speed information includes a speed direction and a speed value; based on the speed information corresponding to the first constraint point, determining the speed information corresponding to the second constraint point, including:

determining the lane direction as a corresponding speed direction of the second constraint point;

determining an included angle between the speed direction corresponding to the first constraint point and the lane direction;

and calculating the speed value corresponding to the second constraint point based on the included angle and the speed value corresponding to the first constraint point.

In embodiments of the present disclosure, at least one other constraint point is on an extension of the corresponding velocity direction of the second constraint point.

In the embodiment of the present disclosure, identifying a target vehicle with a detour intention from candidate vehicles in a preset monitoring range of a host vehicle includes:

acquiring relative motion information of each candidate vehicle in a preset monitoring range of the host vehicle relative to the host vehicle;

and identifying the target vehicle with the detour intention from the preset monitoring range based on the relative motion information corresponding to each candidate vehicle.

In the disclosed embodiment, the relative motion information includes position information of a plurality of consecutive time points of the candidate vehicle;

identifying a target vehicle with a detour intention from a preset monitoring range based on the relative motion information corresponding to each candidate vehicle, wherein the detour intention comprises the following steps:

determining distance variation information of a lateral distance between the candidate vehicle and the host vehicle based on position information of the candidate vehicle at a plurality of consecutive time points;

in response to the distance change information indicating that the candidate vehicle is close to the host vehicle, the candidate vehicle is determined as a target vehicle with a detour intention.

In the disclosed embodiment, in response to the distance change information indicating that the candidate vehicle is close to the host vehicle, determining the candidate vehicle as a target vehicle for which there is a detour intention includes:

in response to determining that the change in distance information indicates that the candidate vehicle is near the host vehicle, calculating a relative lateral velocity of the candidate vehicle with respect to the host vehicle;

in response to determining that the relative lateral speed is greater than a preset speed threshold, the candidate vehicle is determined as the target vehicle with the detour intention.

In the disclosed embodiment, in response to determining that the relative lateral speed is greater than a preset speed threshold, determining the candidate vehicle as the target vehicle with the detour intention includes:

predicting a first time length required by intersection of the target vehicle and the host vehicle in the transverse direction and a second time length required by intersection of the target vehicle and the host vehicle in the longitudinal direction in response to determining that the relative transverse speed is greater than a preset speed threshold;

in response to determining that the first and second time periods satisfy the preset collision time condition, determining the candidate vehicle as the target vehicle with the detour intention.

In an embodiment of the present disclosure, the time-to-collision condition includes: the first time length is smaller than a preset time length threshold value, and the first time length is smaller than a second time length of a preset multiple.

According to a second aspect of the present disclosure, there is provided a vehicle trajectory prediction apparatus including a target vehicle identification module, an obstacle set determination module, an obstacle information acquisition module, a target obstacle determination module, and a travel trajectory prediction module;

the target vehicle identification module is used for identifying a target vehicle with a detour intention from candidate vehicles in a preset monitoring range of the host vehicle;

the obstacle set determining module is used for determining an obstacle set corresponding to the target vehicle;

the obstacle information acquisition module is used for acquiring a speed comparison value of each obstacle and the target vehicle in the obstacle set and distance information between each obstacle and the target vehicle;

the target obstacle determining module is used for determining a target obstacle which needs to be bypassed by the target vehicle from the obstacle set based on the speed comparison value and the distance information corresponding to each obstacle;

and the driving track prediction module is used for predicting the driving track of the target vehicle around the target obstacle.

In an embodiment of the present disclosure, the distance information includes a first longitudinal distance and a first lateral distance between the obstacle and the target vehicle;

the target obstacle determination module is specifically configured to, when determining a target obstacle that the target vehicle needs to detour from the obstacle set based on the speed comparison value and the distance information corresponding to each obstacle, determine:

matching a first longitudinal distance and a speed comparison value corresponding to the obstacle with a preset first detonable condition, and matching a first transverse distance corresponding to the obstacle with a preset second detonable condition;

and determining the candidate obstacle with the minimum corresponding first longitudinal distance as a target obstacle which needs to be bypassed by the target vehicle.

wherein, the first preset ratio is smaller than the second preset ratio.

In the disclosed embodiment, the speed comparison value is a speed difference between the obstacle and the target vehicle, and the first detonable condition includes:

and the first preset difference is greater than the second preset difference.

In an embodiment of the present disclosure, wherein the second detonable condition includes: the first lateral distance corresponding to the obstacle is less than a second distance threshold.

In the disclosed embodiment, the travel track prediction module, when used for predicting the travel track of the target vehicle around the target obstacle, is specifically configured to:

In the embodiment of the present disclosure, a longitudinal distance between the second constraint point and the first constraint point is equal to a minimum longitudinal distance between the first constraint point and the target obstacle, where the minimum longitudinal distance is determined based on the position information of the first constraint point and the contour information of the target obstacle;

In the disclosed embodiment, the speed information includes a speed direction and a speed value; the driving track prediction module is specifically configured to, when determining speed information corresponding to the second constraint point based on the speed information corresponding to the first constraint point:

determining the lane direction as a corresponding speed direction of the second tie point;

In an embodiment of the present disclosure, the target vehicle identification module, when identifying a target vehicle with a detour intention from candidate vehicles in a preset monitoring range of the host vehicle, is specifically configured to:

the target vehicle identification module is specifically configured to, when the target vehicle with the detour intention is identified from the preset monitoring range based on the relative motion information corresponding to each candidate vehicle:

in response to the distance change information indicating that the candidate vehicle is close to the host vehicle, the candidate vehicle is determined as a target vehicle for which there is an intention to detour.

In an embodiment of the disclosure, the target vehicle identification module, when being configured to determine the candidate vehicle as the target vehicle having the detour intention in response to the distance change information indicating that the candidate vehicle is close to the host vehicle, is specifically configured to:

in response to determining that the change-of-distance information indicates that the candidate vehicle is near the host vehicle, calculating a relative lateral velocity of the candidate vehicle with respect to the host vehicle;

In an embodiment of the disclosure, the target vehicle identification module, when being configured to determine the candidate vehicle as the target vehicle having the detour intention in response to determining that the relative lateral speed is greater than a preset speed threshold, is specifically configured to:

predicting a first time period required for the target vehicle to intersect with the host vehicle in the transverse direction and a second time period required for the target vehicle to intersect with the host vehicle in the longitudinal direction in response to determining that the relative transverse speed is greater than a preset speed threshold;

According to a third aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method according to the first aspect.

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method according to the first aspect.

According to a sixth aspect of the present disclosure, there is provided an autonomous vehicle comprising the electronic device provided by the third aspect of the present disclosure.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

The technical scheme provided by the disclosure has the following beneficial effects:

according to the vehicle track prediction method provided by the embodiment of the disclosure, for other vehicles around the unmanned vehicle, the target obstacle which the other vehicles actually need to detour is accurately identified by analyzing the actual interactive relationship between the other vehicles and the corresponding obstacles, and the reasonable detour track is predicted based on the actual interactive relationship between the other vehicles and the target obstacle. It can be seen that the method is not limited to predicting the trajectory of the vehicle based on a preset scene, but predicts the trajectory of the vehicle according to the actual situation faced by the vehicle, which can largely avoid the situation that an unreasonable detour trajectory is predicted, which helps to ensure the driving safety of the unmanned vehicle.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 is a schematic diagram illustrating an application scenario of a vehicle trajectory prediction method provided by the present disclosure;

FIG. 2 illustrates a flow chart diagram of a vehicle trajectory prediction method provided by the present disclosure;

FIG. 3 illustrates an exemplary scenario diagram for determining a target obstacle provided by the present disclosure;

FIG. 4 illustrates a flow chart for predicting a travel path of a target vehicle around a target obstacle provided by the present disclosure;

FIG. 5 illustrates an exemplary scenario diagram for predicting a travel trajectory of a target vehicle around a target obstacle provided by the present disclosure;

FIG. 6 is a schematic diagram of a vehicle trajectory prediction device provided by the present disclosure;

FIG. 7 shows a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It should be understood that in the embodiments of the present disclosure, the character "/" generally indicates that the former and latter associated objects are in an "or" relationship. The terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated.

However, for some marginal scenarios, the driving trajectory of other vehicles inferred based on the deep learning model may not be reasonable enough, for example, for other vehicles to switch around obstacles, the driving trajectory output by the deep learning model may cross some hard boundaries (such as guardrails of a road), and particularly, because the driving route of the non-motor vehicle is more flexible, the probability of unreasonableness of the driving trajectory of the non-motor vehicle inferred based on the deep learning model is higher.

The vehicle track prediction method provided by the embodiment of the disclosure is not limited to predicting the track of the vehicle based on the preset scene, but predicts the track of the vehicle according to the actual situation faced by the vehicle, so that the situation that an unreasonable detour track is predicted can be avoided to a great extent, and the driving safety of the unmanned vehicle can be ensured.

The execution subject of the method may be a terminal device, or a computer, or a server, or may also be other devices with data processing capabilities. The subject matter of the method is not limited in this respect. In some embodiments, the execution subject of the vehicle trajectory prediction method provided by the embodiments of the present disclosure may be a terminal device (such as an on-board computer) on a host vehicle.

Optionally, the terminal device may be a mobile phone, or may be a tablet computer, a wearable device, an in-vehicle device, an Augmented Reality (AR)/Virtual Reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), or the like, and the specific type of the terminal device is not limited in the embodiment of the present disclosure.

In some embodiments, the server may be a single server, or may be a server cluster composed of a plurality of servers. In some embodiments, the server cluster may also be a distributed cluster. The present disclosure is also not limited to a specific implementation of the server.

Fig. 1 is a schematic diagram illustrating an application scenario of a vehicle trajectory prediction method provided by the present disclosure, where, as shown in fig. 1, a host vehicle in the diagram is an automatic driving vehicle, the present disclosure aims to identify a target vehicle having a detour intention around the host vehicle, determine a target obstacle that the target vehicle needs to detour, and predict a running trajectory of the target vehicle that detours the target obstacle, so as to adjust an automatic driving strategy of the host vehicle based on the running trajectory, thereby ensuring driving safety of the host vehicle.

The following exemplifies a vehicle trajectory prediction method provided by the present disclosure.

Fig. 2 shows a schematic flow chart of a vehicle trajectory prediction method provided by the present disclosure, and as shown in fig. 2, the method may mainly include the following steps:

s210: a target vehicle with a detour intention is identified from candidate vehicles in a preset monitoring range of the host vehicle.

In the disclosed embodiment, the host vehicle is equipped with at least one sensor (such as a radar or a camera) by which traveling data of a vehicle within a preset monitoring range of the host vehicle is monitored and acquired. Here, the preset monitoring range may be determined according to actual design requirements. For example, a range in which the distance from the host vehicle is smaller than a preset distance in a lane (left lane or right lane) on the side where the host vehicle is located is taken as a preset monitoring range; or, the range in the lane on one side of the main vehicle and within the preset distance in front of the tail part of the main vehicle is used as the preset monitoring range. Of course, the way of defining the preset monitoring range is not limited thereto.

For ease of understanding and presentation, the present disclosure defines the vehicles of the preset monitoring range of the host vehicle as candidate vehicles, and defines the determined candidate vehicle with the detour intention as a target vehicle. In some embodiments, the candidate vehicle may be further determined according to the type of vehicle, for example, a non-motor vehicle of a preset monitoring range of the host vehicle may be defined as the candidate vehicle, and it is understood that in this case, the determined target vehicle having the detour intention is also the non-motor vehicle.

In the embodiment of the present disclosure, relative movement information of each candidate vehicle in a preset monitoring range of the host vehicle with respect to the host vehicle may be acquired, and a target vehicle with a detour intention may be identified from the preset monitoring range based on the relative movement information corresponding to each candidate vehicle. Here, the relative movement information may be determined based on the traveling data of the candidate vehicle acquired by the sensor of the host vehicle.

The relative motion information of the candidate vehicle to the host vehicle is used as the basis for identifying whether the candidate vehicle has the bypassing intention, so that the identified target vehicles are all vehicles which can influence the running of the host vehicle, the running track is predicted only aiming at the vehicles of the type, and the vehicles which do not influence the running of the host vehicle and have the bypassing intention are ignored, so that the calculation efficiency can be improved, and the effective utilization rate of calculation resources can be improved.

In some embodiments, the relative motion information may include position information for a plurality of consecutive points in time of the candidate vehicle. When a target vehicle with a detour intention is identified from a preset monitoring range, distance change information of a transverse distance between the candidate vehicle and the host vehicle can be determined based on position information of a plurality of continuous time points of the candidate vehicle; in response to the distance change information indicating that the candidate vehicle is close to the host vehicle, the candidate vehicle is determined as a target vehicle with a detour intention.

Specifically, the lateral distance of the candidate vehicle between the host vehicle and each time point may be determined based on the position information of the time point. The distance change information may reflect a change in the lateral distance between the candidate vehicle and the host vehicle at two preceding and subsequent time points, and if the lateral distance becomes smaller with time, it indicates that the candidate vehicle is close to the host vehicle, and at this time, the candidate vehicle may be determined as the target vehicle with the detour intention. It is understood that if the distance change information indicates that the candidate vehicle is not close to the host vehicle, the subsequent steps for the candidate vehicle may be stopped.

In some embodiments, upon determining whether the candidate vehicle is the target vehicle with the detour intention based on the distance change information, it may be further determined whether the candidate vehicle is the target vehicle with the detour intention based on a relative lateral velocity of the candidate vehicle with respect to the host vehicle. Specifically, the disclosed embodiments calculate a relative lateral velocity of the candidate vehicle with respect to the host vehicle after indicating that the candidate vehicle is close to the host vehicle in response to determining the distance change information; in response to determining that the relative lateral velocity is greater than a preset velocity threshold, the candidate vehicle is determined as a target vehicle with an intention to detour. The relative transverse speed of the candidate vehicle relative to the host vehicle is further introduced to serve as a basis for identifying whether the candidate vehicle has the bypassing intention, so that the target vehicle which really has the bypassing intention can be accurately identified, the calculation efficiency is further improved, and the effective utilization rate of calculation resources is improved.

Here, the relative lateral velocity of the candidate vehicle with respect to the host vehicle may be calculated based on position information of a plurality of consecutive time points of the candidate vehicle. The speed threshold may be dependent on the actual design requirements, for example, the speed threshold may be 0.15m/s. When the relative lateral velocity of the candidate vehicle relative to the host vehicle is not greater than a preset velocity threshold, the behavior of the candidate vehicle approaching the host vehicle is determined to belong to the normal operation error of the driver of the candidate vehicle; when the relative lateral velocity of the candidate vehicle with respect to the host vehicle is greater than a preset velocity threshold, the candidate vehicle is determined as a target vehicle for which a detour intention exists.

In some embodiments, in determining whether the candidate vehicle is the target vehicle for which the detour intention exists based on the distance change information and the relative lateral velocity of the candidate vehicle with respect to the host vehicle, a collision time condition may also be set, and it may be determined whether it is the target vehicle for which the detour intention exists further based on the collision time condition.

In particular, embodiments of the present disclosure may predict a first time period required for the target vehicle to intersect with the host vehicle in the lateral direction, a second time period required for the target vehicle to intersect with the host vehicle in the longitudinal direction, in response to determining that the relative lateral velocity is greater than a preset velocity threshold; in response to determining that the first and second time periods satisfy the preset collision time condition, determining the candidate vehicle as the target vehicle with the detour intention. Here, the first duration means: the time required when the minimum lateral distance between the target vehicle and the host vehicle is 0, assuming that both the target vehicle and the host vehicle travel at the current speed; the second time period is: it is assumed that the target vehicle and the host vehicle both travel at the current speed, and the time required when the minimum longitudinal distance between the two is 0.

The method and the device can predict the time length of intersection of the target vehicle and the main vehicle in the transverse direction, and introduce the time length as a basis for identifying whether the candidate vehicle has the detour intention, so that the target vehicle which really has the detour intention can be accurately identified, the calculation efficiency is further improved, and the effective utilization rate of calculation resources is improved.

Here, the collision time condition includes: the first time length is smaller than a preset time length threshold value, and the first time length is smaller than a second time length of a preset multiple. The duration threshold and the preset multiple may be determined according to actual design requirements, for example, the duration threshold may be 8 seconds, and the preset multiple may be 9 times.

S220: and determining an obstacle set corresponding to the target vehicle.

Here, the set of obstacles includes obstacles that the target vehicle may need to detour, and the obstacles may include dynamic obstacles (e.g., a running vehicle and a running pedestrian, etc.) and static obstacles (e.g., a stopped vehicle and a pedestrian, a road barrier, etc.). The embodiment of the disclosure may determine the set of obstacles corresponding to the target vehicle according to the actual situation, for example, all obstacles within a preset distance (for example, 20 meters) in front of the target vehicle may be included in the set of obstacles.

S230: and acquiring a speed comparison value of each obstacle in the obstacle set and the target vehicle and distance information between each obstacle and the target vehicle.

S240: and determining a target obstacle which needs to be bypassed by the target vehicle from the obstacle set based on the speed comparison value and the distance information corresponding to each obstacle.

The speed comparison value between the obstacle and the target vehicle and the distance information between the obstacle and the target vehicle can reflect the actual interactive relation between the target vehicle and the obstacle, and the target obstacle which the target vehicle actually needs to detour can be accurately screened out through the speed comparison value and the distance information.

In some embodiments, the distance information includes a first longitudinal distance and a first lateral distance between the obstacle and the target vehicle. It should be noted that the first longitudinal distance is a minimum longitudinal distance between the obstacle and the target vehicle, and the first transverse distance is a minimum transverse distance between the obstacle and the target vehicle. In the embodiment of the present disclosure, the longitudinal distance represents a distance between two objects in the front-back direction, and the transverse distance represents a distance between two objects in the left-right direction.

When a target obstacle which needs to be bypassed by a target vehicle is determined from an obstacle set based on a speed comparison value and distance information corresponding to each obstacle, a first longitudinal distance and a speed comparison value corresponding to the obstacle can be matched with a preset first bypassing condition, and a first transverse distance corresponding to the obstacle can be matched with a preset second bypassing condition; determining the obstacle as a candidate obstacle in response to determining that the obstacle meets the first detonable condition and the second detonable condition; and determining the candidate obstacle with the minimum corresponding first longitudinal distance as the target obstacle which needs to be bypassed by the target vehicle.

Here, a first circumventable condition may be set for the first longitudinal distance and the speed comparison value, and a second circumventable condition may be set for the first lateral distance, wherein the first circumventable condition may reflect a possibility that the target vehicle circumvents the obstacle in the longitudinal dimension, and the second circumventable condition may reflect a possibility that the target vehicle circumvents the obstacle in the lateral dimension. The necessity of the target vehicle to detour the obstacle is evaluated through the condition of two dimensions, and the target obstacle which the target vehicle needs to detour is accurately determined.

In some embodiments, the speed comparison value is a speed ratio of the obstacle to the target vehicle. The first detonable condition includes two sub-conditions, one sub-condition being: the first longitudinal distance corresponding to the obstacle is greater than a first distance threshold, and the speed ratio corresponding to the obstacle is smaller than a first preset ratio. Another sub-condition is: the first longitudinal distance corresponding to the obstacle is smaller than a first distance threshold value, and the speed ratio corresponding to the obstacle is smaller than a second preset ratio. Here, if an obstacle can satisfy any one of the above sub-conditions, it may be determined that the obstacle meets the first detonable condition. Here, the first preset ratio is smaller than the second preset ratio. The first distance threshold, the first preset ratio and the second preset ratio can be determined according to actual design requirements. Here, the possibility that the target vehicle detours the obstacle in the longitudinal dimension is analyzed by the first longitudinal distance and the speed ratio between the obstacle and the target vehicle, and the degree of necessity for the target vehicle to detour the obstacle can be objectively reflected.

In an embodiment of the present disclosure, the second detonable condition includes: the first lateral distance corresponding to the obstacle is less than a second distance threshold. That is, if the first lateral distance corresponding to an obstacle is smaller than the second distance threshold, it is determined that the obstacle satisfies the second detonable condition. Here, the second distance threshold may be determined according to actual design requirements, and generally, the second distance threshold is a reserved width which is generally used when the vehicle passes through an obstacle. Here, the possibility that the target vehicle detours the obstacle in the lateral dimension is analyzed by the first lateral distance between the obstacle and the target vehicle, and the degree of necessity for the target vehicle to detour the obstacle can be objectively reflected.

Fig. 3 illustrates an exemplary scenario for determining a target obstacle according to the present disclosure, in which the first distance threshold is 5 meters, the second distance threshold is 0.8 meters, the first preset ratio is 0.6, and the second preset ratio is 0.9. In fig. 3, the set of obstacles of the target vehicle includes an obstacle a, an obstacle B, an obstacle C, and an obstacle D, wherein the first lateral distances corresponding to the obstacle B, the obstacle C, and the obstacle D are all no less than 0.8 m, and therefore, none of the obstacle B, the obstacle C, and the obstacle D can be used as candidate obstacles; the corresponding first longitudinal distance of the obstacle A is less than 5 meters, the speed ratio corresponding to the obstacle A is less than 0.9, and the first transverse distance corresponding to the obstacle A is not less than 0.8 meters, that is, the obstacle A simultaneously meets the first detouring condition and the second detouring condition, so the obstacle A can be used as a candidate obstacle. Since obstacle a is the only candidate obstacle, the heredity can directly determine obstacle a as the target obstacle. It can be understood that if more than two candidate obstacles are determined, the corresponding candidate obstacle with the smallest first longitudinal distance needs to be determined as the target obstacle that the target vehicle needs to detour.

In some embodiments, the speed comparison value is a speed difference of the obstacle and the target vehicle. The first detonable condition includes two sub-conditions, one being: the first longitudinal distance corresponding to the obstacle is larger than a first distance threshold value, and the speed difference corresponding to the obstacle is larger than a first preset difference value; another sub-condition is: the first longitudinal distance corresponding to the obstacle is smaller than a first distance threshold, and the speed ratio corresponding to the obstacle is smaller than a second preset difference. Here, if an obstacle can satisfy any one of the above sub-conditions, it may be determined that the obstacle satisfies the first detonable condition. Here, the first preset difference is greater than the second preset difference. The first distance threshold, the first preset difference and the second preset difference can be determined according to actual design requirements.

S250: a travel locus of the target vehicle around the target obstacle is predicted.

After the target obstacle is determined, a travel track of the target vehicle around the target obstacle may be predicted based on the data of the target vehicle, the data of the target obstacle, and the relationship between the target vehicle and the target obstacle. Specifically, a plurality of constraint points may be predicted, and a travel locus passing through the respective constraint points in order is generated, and the target vehicle travels along the travel locus to bypass the target obstacle.

Fig. 4 shows a schematic flowchart of a process for predicting a travel track of a target vehicle around a target obstacle according to the present disclosure, and as shown in fig. 4, the process mainly includes the following steps:

s410: a first constraint point is determined based on the motion information of the target vehicle.

Here, the position information of the first restraint point is the same as the current position information of the target vehicle, and the speed information corresponding to the first restraint point is the same as the current speed information of the target vehicle.

S420: and determining the position information of the second constraint point based on the first constraint point, the contour information of the target vehicle and the contour information of the target obstacle.

Here, the second constraint point is when the following condition is satisfied: when the target vehicle reaches the second restraint point, a first lateral distance between the target vehicle and the target obstacle is greater than 0.

In some embodiments, a corresponding condition may be set for the position of the second constraining point, based on which the position information of the second constraining point is determined. Specifically, the position information of the second constraint point should satisfy the following condition: the longitudinal distance between the second constraint point and the first constraint point is equal to the minimum longitudinal distance between the first constraint point and the target obstacle, wherein the minimum longitudinal distance is determined based on the position information of the first constraint point and the contour information of the target obstacle; and the minimum transverse distance between the second constraint point and the target obstacle is equal to the sum of the preset safety distance and the 0.5-time width value of the target vehicle, wherein the width of the target vehicle is determined based on the contour information of the target vehicle.

It is understood that the current position information of the target vehicle is determinable from data detected by the sensor of the host vehicle, and therefore the position information of the first constraint point is known, the contour information of the target vehicle includes position information of a plurality of points of the target vehicle, and the contour information of the target obstacle includes position information of a plurality of points of the target obstacle. Based on the position information of these known points and the above-mentioned conditions, the position information of the second constraining point can be calculated.

S430: and determining the speed information corresponding to the second constraint point based on the speed information corresponding to the first constraint point.

Here, the speed information includes a speed direction and a speed value. The disclosed embodiments assume that the driving direction of the target vehicle has returned to positive when the target vehicle reaches the second constraint point, i.e. the driving direction of the target vehicle is parallel to the lane direction, under which condition the corresponding speed direction of the second constraint point should be parallel to the lane direction. In S430, a lane direction may be determined as a speed direction corresponding to the second constraint point, an angle between the speed direction corresponding to the first constraint point and the lane direction may be determined, and a speed value corresponding to the second constraint point may be calculated based on the angle and the speed value corresponding to the first constraint point.

S440: and determining at least one other constraint point based on the position information of the second constraint point and the speed information corresponding to the second constraint point.

In S440, at least one other constraint point is on an extension of the corresponding velocity direction of the second constraint point. Here, it may be assumed that the target vehicle is at the second constraint point, and a point reached after traveling for a preset time according to the speed information of the second constraint point is taken as another constraint point, where the specific number of the other constraint points may be determined according to actual design requirements.

S450: based on the first constraint point, the second constraint point, and the at least one other constraint point, a travel locus of the target vehicle around the target obstacle is predicted.

In S450, a travel locus that passes through the first constraint point, the second constraint point, and each of the other constraint points in this order is generated, and the target vehicle travels in accordance with the travel locus to bypass the target obstacle.

According to the embodiment of the disclosure, when the form track is predicted, the contour information of the target vehicle and the contour information of the target obstacle are used, the influence of the sizes of the target vehicle and the target obstacle on the driving path is fully considered, and the unreasonable form track is prevented from being predicted.

Fig. 5 illustrates an exemplary scene schematic diagram for predicting a driving track of a target vehicle around a target obstacle, as shown in fig. 5, taking current position information of the target vehicle as position information of a first constraint point, and taking current speed information of the target vehicle as speed information corresponding to the first constraint point, where the speed information includes a speed direction and a speed value.

Then, the minimum longitudinal distance between the first constraint point and the target obstacle can be determined, and the longitudinal position information of the first constraint point is superposed on the minimum longitudinal distance to obtain the longitudinal position information of the second constraint point. Determining the width of the target vehicle based on the contour information of the target vehicle, and determining that the safety distance is 0.5 m; and superposing the position information of the leftmost boundary of the target obstacle with the safe distance and the width value of 0.5 times of the target vehicle to obtain the transverse position information of the second constraint point.

The velocity value corresponding to the second constraint point can be calculated by the following formula:

speed _modify ＝speed*cosθ

wherein speed _modify And the speed value corresponding to the second constraint point is obtained, speed is the speed value corresponding to the first constraint point, and theta is an included angle between the speed direction corresponding to the first constraint point and the lane direction.

It may be assumed that the target vehicle starts traveling in the lane direction at the speed value corresponding to the second constraint point at the second constraint point, and a point that the target vehicle arrives 4 seconds later is taken as a third constraint point and a point that the target vehicle arrives 8 seconds later is taken as a fourth constraint point.

After the first to fourth constraining points are determined, a running track of the target vehicle around the target obstacle is fitted based on the four constraining points in a manner of a cubic spline curve.

Based on the same principle as the vehicle trajectory prediction method described above, the embodiment of the present disclosure provides a vehicle trajectory prediction device, and fig. 6 shows a schematic diagram of a first vehicle trajectory prediction device provided by the present disclosure. As shown in fig. 6, the vehicle trajectory prediction apparatus 600 includes a target vehicle identification module 610, an obstacle set determination module 620, an obstacle information acquisition module 630, a target obstacle determination module 640, and a travel trajectory prediction module 650.

A target vehicle identification module 610, configured to identify a target vehicle with a detour intention from candidate vehicles in a preset monitoring range of the host vehicle;

an obstacle set determining module 620, configured to determine an obstacle set corresponding to the target vehicle;

the obstacle information acquiring module 630 is configured to acquire a speed comparison value between each obstacle in the obstacle set and the target vehicle, and distance information between each obstacle and the target vehicle;

the target obstacle determining module 640 is configured to determine a target obstacle that the target vehicle needs to detour from the obstacle set based on the speed comparison value and the distance information corresponding to each obstacle;

and a driving track prediction module 650 for predicting a driving track of the target vehicle around the target obstacle.

According to the vehicle track prediction device provided by the embodiment of the disclosure, for other vehicles around the unmanned vehicle, the target obstacle which the other vehicles actually need to detour is accurately identified by analyzing the actual interactive relationship between the other vehicles and the corresponding obstacles, and the reasonable detour track is predicted based on the actual interactive relationship between the other vehicles and the target obstacle. It can be seen that the apparatus is not limited to predicting the trajectory of the vehicle based on a preset scene, but predicts the trajectory of the vehicle according to the actual situation that the vehicle faces, which can largely avoid the occurrence of a situation in which an unreasonable detour trajectory is predicted, which helps to ensure the driving safety of the unmanned vehicle.

the target obstacle determining module 640 is specifically configured to, when the target obstacle determining module is configured to determine, from the obstacle set, a target obstacle that the target vehicle needs to detour, based on the speed comparison value and the distance information corresponding to each obstacle:

or the first longitudinal distance corresponding to the obstacle is smaller than a first distance threshold value, and the speed ratio corresponding to the obstacle is smaller than a second preset ratio value;

wherein, the first preset ratio is smaller than the second preset ratio.

wherein the first preset difference is greater than the second preset difference.

In the disclosed embodiment, the travel track prediction module 650, when used to predict the travel track of the target vehicle around the target obstacle, is specifically configured to:

In the disclosed embodiment, the speed information includes a speed direction and a speed value; when the driving track prediction module 650 is configured to determine speed information corresponding to the second constraint point based on the speed information corresponding to the first constraint point, it is specifically configured to:

In an embodiment of the disclosure, the at least one other constraint point is on an extension of the corresponding speed direction of the second constraint point.

In the embodiment of the present disclosure, the target vehicle identification module 610, when identifying a target vehicle with a detour intention from among candidate vehicles in a preset monitoring range of the host vehicle, is specifically configured to:

the target vehicle identification module 610, when configured to identify a target vehicle with a detour intention from a preset monitoring range based on the relative motion information corresponding to each candidate vehicle, is specifically configured to:

In an embodiment of the disclosure, the target vehicle identification module 610, when being configured to determine the candidate vehicle as the target vehicle having the detour intention in response to the distance change information indicating that the candidate vehicle is close to the host vehicle, is specifically configured to:

In an embodiment of the disclosure, the target vehicle identification module 610, when being configured to determine the candidate vehicle as the target vehicle having the detour intention in response to determining that the relative lateral speed is greater than a preset speed threshold, is specifically configured to:

In the disclosed embodiment, the time-to-collision condition includes: the first time length is smaller than a preset time length threshold value, and the first time length is smaller than a second time length of a preset multiple.

It is understood that the modules of the vehicle trajectory prediction device in the embodiment of the present disclosure have functions of implementing the corresponding steps of the vehicle trajectory prediction method. The function can be realized by hardware, and can also be realized by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above. The modules can be software and/or hardware, and each module can be implemented independently or by integrating a plurality of modules. For the functional description of each module of the vehicle trajectory prediction apparatus, reference may be made to the corresponding description of the vehicle trajectory prediction method, which is not described herein again.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

In an exemplary embodiment, an electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the above embodiments. The electronic device may be the computer or the server described above.

In an exemplary embodiment, the readable storage medium may be a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method according to the above embodiments.

In an exemplary embodiment, the computer program product comprises a computer program which, when being executed by a processor, carries out the method according to the above embodiments.

In an exemplary embodiment, the autonomous vehicle comprises the above-mentioned electronic device, which may be the above-mentioned controller or the first device.

FIG. 7 illustrates a schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may 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 meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 7, the electronic device 700 comprises a computing unit 701, which may perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can be stored. The calculation unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

A number of components in the electronic device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

Computing unit 701 may be a variety of general purpose and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 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, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 701 executes the respective methods and processes described above, such as the vehicle trajectory prediction method. For example, in some embodiments, the vehicle trajectory prediction method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 700 via the ROM 702 and/or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the vehicle trajectory prediction method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the vehicle trajectory prediction method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods 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, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The 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, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here 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 a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, 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, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end 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: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A vehicle trajectory prediction method, the method comprising:

identifying a target vehicle with a detour intention from candidate vehicles in a preset monitoring range of the host vehicle;

determining an obstacle set corresponding to the target vehicle;

acquiring a speed comparison value of each obstacle in the obstacle set and the target vehicle, and distance information between each obstacle and the target vehicle;

predicting a travel track of the target vehicle that bypasses the target obstacle.

2. The method of claim 1, wherein the distance information includes a first longitudinal distance and a first lateral distance between the obstacle and the target vehicle;

the determining, from the obstacle set, a target obstacle that the target vehicle needs to detour based on the speed comparison value and the distance information corresponding to each obstacle includes:

matching the first longitudinal distance and the speed comparison value corresponding to the obstacle with a preset first detouring condition, and matching the first transverse distance corresponding to the obstacle with a preset second detouring condition;

determining the obstacle as a candidate obstacle in response to determining that the obstacle meets the first and second circumventable conditions;

3. The method of claim 2, the speed comparison value being a speed ratio of the obstacle to the target vehicle, the first detonable condition comprising:

the first longitudinal distance corresponding to the obstacle is greater than a first distance threshold, and the speed ratio corresponding to the obstacle is less than a first preset ratio;

or the first longitudinal distance corresponding to the obstacle is smaller than the first distance threshold, and the speed ratio corresponding to the obstacle is smaller than a second preset ratio;

wherein the first preset ratio is smaller than the second preset ratio.

4. The method of claim 2, the speed comparison value being a speed difference of the obstacle and the target vehicle, the first detonable condition comprising:

the first longitudinal distance corresponding to the obstacle is greater than a first distance threshold, and the speed difference corresponding to the obstacle is greater than a first preset difference;

or the first longitudinal distance corresponding to the obstacle is smaller than the first distance threshold, and the speed ratio corresponding to the obstacle is smaller than a second preset difference;

5. The method of claim 2, wherein the second detonable condition comprises: the first lateral distance corresponding to the obstacle is less than a second distance threshold.

6. The method according to any one of claims 1-5, wherein the predicting a travel trajectory of the target vehicle around the target obstacle comprises:

determining position information of a second constraint point based on the first constraint point, the contour information of the target vehicle and the contour information of the target obstacle, wherein when the target vehicle reaches the second constraint point, a first transverse distance between the target vehicle and the target obstacle is greater than 0;

determining speed information corresponding to the second constraint point based on the speed information corresponding to the first constraint point;

predicting a travel trajectory of the target vehicle around the target obstacle based on the first constraint point, the second constraint point, and the at least one other constraint point.

7. The method of claim 6, a longitudinal distance between the second constraint point and the first constraint point being equal to a minimum longitudinal distance between the first constraint point and the target obstacle, wherein the minimum longitudinal distance is determined based on the first constraint point location information and contour information of the target obstacle;

a minimum lateral distance between the second constraint point and the target obstacle is equal to a sum of a preset safety distance and a width value of 0.5 times of the target vehicle, wherein the width of the target vehicle is determined based on the contour information of the target vehicle.

8. The method of claim 6, wherein the speed information comprises a speed direction and a speed value; the determining the speed information corresponding to the second constraint point based on the speed information corresponding to the first constraint point comprises:

and calculating the speed value corresponding to the second constraint point based on the speed values corresponding to the included angle and the first constraint point.

9. A method as defined in claim 8, wherein the at least one other constraint point is on an extension of the second constraint point's corresponding speed direction.

10. The method according to any one of claims 1 to 9, wherein the identifying, from candidate vehicles of a preset monitoring range of the host vehicle, a target vehicle with a detour intention includes:

acquiring relative motion information of each candidate vehicle in a preset monitoring range of a host vehicle relative to the host vehicle;

and identifying a target vehicle with a detour intention from the preset monitoring range on the basis of the relative motion information corresponding to each candidate vehicle.

11. The method of claim 10, wherein the relative motion information includes position information for a plurality of consecutive points in time of the candidate vehicle;

the identifying a target vehicle with a detour intention from the preset monitoring range based on the relative motion information corresponding to each candidate vehicle comprises:

determining distance variation information of a lateral distance between the candidate vehicle and the host vehicle based on position information of a plurality of consecutive time points of the candidate vehicle;

determining the candidate vehicle as a target vehicle with a detour intention in response to the distance change information indicating that the candidate vehicle is close to the host vehicle.

12. The method of claim 11, wherein the determining the candidate vehicle as the target vehicle with the detour intent in response to the distance change information indicating that the candidate vehicle is near the host vehicle comprises:

in response to determining that the change in distance information indicates that the candidate vehicle is near the host, calculating a relative lateral velocity of the candidate vehicle relative to the host;

in response to determining that the relative lateral velocity is greater than a preset velocity threshold, determining the candidate vehicle as a target vehicle with an intent to detour.

13. The method of claim 12, wherein the determining the candidate vehicle as the target vehicle with the detour intent in response to determining that the relative lateral velocity is greater than a preset velocity threshold comprises:

predicting a first period of time required for the target vehicle to intersect with the host vehicle in a lateral direction and a second period of time required for the target vehicle to intersect with the host vehicle in a longitudinal direction in response to determining that the relative lateral velocity is greater than a preset velocity threshold;

in response to determining that the first and second durations satisfy a preset collision time condition, determining the candidate vehicle as a target vehicle with a detour intention.

14. The method of claim 13, wherein the time-to-collision condition comprises: the first time length is less than a preset time length threshold value, and the first time length is less than a preset multiple of the second time length.

15. A vehicle trajectory prediction device, the device comprising:

the target vehicle identification module is used for identifying a target vehicle with a detour intention from candidate vehicles in a preset monitoring range of the main vehicle;

the obstacle information acquisition module is used for acquiring a speed comparison value of each obstacle in the obstacle set and the target vehicle and distance information between each obstacle and the target vehicle;

a target obstacle determination module, configured to determine, from the obstacle set, a target obstacle that the target vehicle needs to detour, based on the speed comparison value and the distance information corresponding to each obstacle;

and the running track prediction module is used for predicting the running track of the target vehicle around the target obstacle.

16. The apparatus of claim 1, wherein the distance information includes a first longitudinal distance and a first lateral distance between the obstacle and the target vehicle;

the target obstacle determining module, when configured to determine a target obstacle that the target vehicle needs to detour from the obstacle set based on the speed comparison value and the distance information corresponding to each obstacle, is specifically configured to:

and determining the candidate obstacle with the minimum first longitudinal distance as a target obstacle which needs to be bypassed by the target vehicle.

17. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor;

wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-14.

18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1-14.

19. A computer program product comprising a computer program which, when executed by a processor, carries out the method according to any one of claims 1-14.

20. An autonomous vehicle comprising the electronic device of claim 17.