CN117252296A

CN117252296A - Track prediction method, device and system, electronic equipment and automatic driving vehicle

Info

Publication number: CN117252296A
Application number: CN202311091380.XA
Authority: CN
Inventors: 刘金鑫; 李文博; 彭亮; 陈泰然; 包帅
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-08-28
Filing date: 2023-08-28
Publication date: 2023-12-19

Abstract

The disclosure provides a track prediction method, a track prediction device, a track prediction system, electronic equipment and an automatic driving vehicle, and relates to the technical field of computers, in particular to the technical fields of intelligent transportation, automatic driving and the like. The specific implementation scheme is as follows: obtaining predicted motion parameters of an interactive vehicle, wherein the interactive vehicle is a vehicle with an interactive relation with a target vehicle; acquiring an initial predicted track of an interactive vehicle, wherein the initial predicted track of the interactive vehicle comprises a plurality of initial track coordinates of the interactive vehicle, and the plurality of initial track coordinates are arranged based on time sequence; and obtaining a track prediction result of the interactive vehicle based on the predicted motion parameters of the interactive vehicle and the initial predicted track of the interactive vehicle, wherein the track prediction result of the interactive vehicle is used for planning the running track of the target vehicle. According to the technical scheme provided by the disclosure, the track prediction result of the interactive vehicle can be more accurate, and the running track of the target vehicle is more reasonable.

Description

Track prediction method, device and system, electronic equipment and automatic driving vehicle

Technical Field

The disclosure relates to the field of computer technology, and in particular to the technical fields of intelligent transportation, automatic driving and the like.

Background

The automatic driving decision and planning is a core module of the automatic driving system and is mainly responsible for generating a feasible, reasonable and safe driving track of the automatic driving vehicle in the current traffic environment, and the feasible, reasonable and safe driving track is sent to a vehicle bottom layer control module for execution, so that the automatic driving decision and planning method has an important effect on processing uncertainty of upper layer sensing information of the automatic driving system and guaranteeing driving safety of the automatic driving vehicle. In the prior art, the determination mode of the running track of the automatic driving vehicle mainly comprises the following steps: the travel locus of the autonomous vehicle is predicted from the predicted locus of all surrounding obstacles. However, the above-described processing manner does not consider the interaction relationship between the autonomous vehicle and the surrounding vehicles, and thus may cause inaccuracy in the predicted trajectory of the interaction vehicles around the autonomous vehicle, and may further cause unreasonability in the predicted travel trajectory of the autonomous vehicle.

Disclosure of Invention

The disclosure provides a track prediction method, a track prediction device, a track prediction system, electronic equipment and an automatic driving vehicle.

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

obtaining predicted motion parameters of an interactive vehicle, wherein the interactive vehicle is a vehicle with an interactive relation with a target vehicle;

Acquiring an initial predicted track of the interactive vehicle, wherein the initial predicted track of the interactive vehicle comprises a plurality of initial track coordinates of the interactive vehicle, and the plurality of initial track coordinates are arranged based on time sequence;

and obtaining a track prediction result of the interactive vehicle based on the predicted motion parameters of the interactive vehicle and the initial predicted track of the interactive vehicle, wherein the track prediction result of the interactive vehicle is used for planning the running track of the target vehicle.

According to a second aspect of the present disclosure, there is provided a trajectory prediction apparatus including:

the motion parameter acquisition module is used for acquiring predicted motion parameters of the interactive vehicle, wherein the interactive vehicle is a vehicle with an interactive relation with the target vehicle;

the system comprises an initial predicted track acquisition module, a first control module and a second control module, wherein the initial predicted track acquisition module is used for acquiring an initial predicted track of the interactive vehicle, the initial predicted track of the interactive vehicle comprises a plurality of initial track coordinates of the interactive vehicle, and the plurality of initial track coordinates are arranged based on time sequence;

the track prediction result acquisition module is used for acquiring a track prediction result of the interactive vehicle based on the predicted motion parameters of the interactive vehicle and the initial predicted track of the interactive vehicle, wherein the track prediction result of the interactive vehicle is used for planning the running track of the target vehicle.

According to a third aspect of the present disclosure, there is provided a trajectory prediction system comprising: the track prediction device is used for obtaining predicted motion parameters of the interactive vehicle, wherein the interactive vehicle is a vehicle with an interactive relation with the target vehicle; acquiring an initial predicted track of the interactive vehicle, wherein the initial predicted track of the interactive vehicle comprises a plurality of initial track coordinates of the interactive vehicle, and the plurality of initial track coordinates are arranged based on time sequence; and obtaining a track prediction result of the interactive vehicle based on the predicted motion parameters of the interactive vehicle and the initial predicted track of the interactive vehicle, wherein the track prediction result of the interactive vehicle is used for planning the running track of the target vehicle.

According to a fourth 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 trajectory prediction method of the first aspect described above.

According to a fifth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the trajectory prediction method of the foregoing first aspect.

According to a sixth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the trajectory prediction method of the first aspect described above.

According to a seventh aspect of the present disclosure, there is provided an autonomous vehicle comprising the electronic device of the fourth aspect described above.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

According to the technical scheme, the predicted motion parameters of the interactive vehicle with the interactive relation with the target vehicle can be obtained, and the track prediction result of the interactive vehicle is obtained by processing again based on the predicted motion parameters of the interactive vehicle and the initial predicted track of the interactive vehicle. Therefore, the initial track prediction of the interactive vehicle is further combined with the predicted motion parameters of the interactive vehicle to obtain the track prediction result of the interactive vehicle, so that the track prediction result of the interactive vehicle is more accurate, and the running track of the target vehicle is more reasonable.

Drawings

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

FIG. 1 is a flow chart of a trajectory prediction method provided according to an embodiment of the present disclosure;

FIG. 2 is a schematic block diagram of a trajectory prediction device provided in accordance with an embodiment of the present disclosure;

FIG. 3 is yet another schematic block diagram of a trajectory prediction device provided in accordance with an embodiment of the present disclosure;

FIG. 4 is a schematic block diagram of a trajectory prediction system provided in accordance with an embodiment of the present disclosure;

FIG. 5 is yet another schematic block diagram of a trajectory prediction system provided in accordance with an embodiment of the present disclosure;

FIG. 6 is yet another schematic block diagram of a trajectory prediction system provided in accordance with an embodiment of the present disclosure;

fig. 7 is a block diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one 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.

An embodiment of a first aspect of the present disclosure provides a track prediction method, as shown in fig. 1, including:

s101, obtaining predicted motion parameters of an interactive vehicle, wherein the interactive vehicle is a vehicle with an interactive relation with a target vehicle;

s102, acquiring an initial predicted track of the interactive vehicle, wherein the initial predicted track of the interactive vehicle comprises a plurality of initial track coordinates of the interactive vehicle, and the plurality of initial track coordinates are arranged based on time sequence;

and S103, obtaining a track prediction result of the interactive vehicle based on the predicted motion parameters of the interactive vehicle and the initial predicted track of the interactive vehicle, wherein the track prediction result of the interactive vehicle is used for planning the running track of the target vehicle.

The target vehicle may be an autonomous vehicle.

The track prediction method can be implemented by the electronic equipment. The electronic device may be a device mounted on the target vehicle, such as a terminal having computing and/or processing capabilities, for example. The electronic device may also be a device capable of communicating with the target vehicle, where the communication may be a wired communication or a wireless communication, and the electronic device may be any of a terminal, a server, and the like, for example.

By adopting the technical scheme, the predicted motion parameters of the interactive vehicle with the interactive relation with the target vehicle can be obtained, and the track prediction result of the interactive vehicle is obtained by processing again based on the predicted motion parameters of the interactive vehicle and the initial predicted track of the interactive vehicle. Therefore, the initial track prediction of the interactive vehicle is further combined with the predicted motion parameters of the interactive vehicle to obtain the track prediction result of the interactive vehicle, so that the track prediction result of the interactive vehicle is more accurate, and the running track of the target vehicle is more reasonable.

In some possible embodiments, the obtaining the predicted motion parameter of the interactive vehicle may include: identifying an interaction scene corresponding to the position of the target vehicle; determining an interactive vehicle of the target vehicle according to the identified interactive scene; and acquiring predicted motion parameters of the interactive vehicle according to the determined interactive vehicle of the target vehicle.

The interaction scene may include any one of a parallel import scene and a main and auxiliary road import scene, and may also be other interaction scenes, which are not limited herein.

The method for identifying the interaction scene corresponding to the position of the target vehicle can comprise the following steps: acquiring road information corresponding to the position of the target vehicle; and identifying an interaction scene according to the road information corresponding to the position of the target vehicle. Wherein the road information may be at least one of a picture, map information, etc. reflecting a road scene around the target vehicle.

The way of obtaining the road information corresponding to the location of the target vehicle is various, and is not limited herein. For example, when the road information is map information, acquiring the road information corresponding to the position where the target vehicle is located may include: acquiring a position of the target vehicle by a positioning device of the target vehicle such as a GPS or the like; and obtaining road information corresponding to the position of the target vehicle according to the map information corresponding to the position of the target vehicle. For another example, when the road information is a picture, the road image of the position of the target vehicle may be acquired according to a sensor, such as a camera, a vehicle recorder, or the like, mounted on the target vehicle, and the road information corresponding to the position of the target vehicle may be acquired based on the road image of the position of the target vehicle.

The determining the interactive vehicle of the target vehicle according to the identified interactive scene may specifically include: determining an interaction range according to the identified interaction scene; and determining all vehicles in the interaction range as interaction vehicles. After determining the interactive vehicle, the identity of the interactive vehicle may be obtained.

The method for determining the interaction range according to the identified interaction scene is not limited herein. For example, when the interactive scene is identified as a parallel convergence scene, determining a first front preset range and a first rear preset range on adjacent lanes of the target vehicle as a first interactive range; the adjacent lanes of the target vehicle are lanes outside the lanes where the target vehicle is located in the two adjacent lanes in the parallel entry scene. For another example, when the interaction scene is identified as the main and auxiliary road remittance scene, a second front preset range and a second rear preset range on adjacent lanes of the target vehicle are determined as the second interaction range, wherein the adjacent lanes of the target vehicle are lanes other than the lanes where the target vehicle is located in the adjacent two lanes under the main and auxiliary road remittance scene. The first front preset range and the second front preset range may be the same or different. The first rear preset range and the second rear preset range may be the same or different. The first interaction range may be the same as or different from the second interaction range.

The determining all vehicles within the interaction range as the interaction vehicles may be: vehicles within the interaction range are identified and all vehicles within the interaction range are determined to be interacting vehicles.

The obtaining, according to the determined interactive vehicle of the target vehicle, a predicted motion parameter of the interactive vehicle may be: acquiring physical motion parameters of the interactive vehicle; inputting physical motion parameters of the interactive vehicle into an interactive decision model to obtain an interactive behavior decision result of the interactive decision model output target vehicle; and obtaining the predicted motion parameters of the interactive vehicle based on the interactive behavior decision result of the target vehicle.

The interactive behavior decision result of the target vehicle may be: at least one of a behavior decision of the target vehicle, a predicted behavior of the interactive vehicle. In the case that the interactive behavior decision result of the target vehicle is a behavior decision of the target vehicle, the interactive behavior decision result of the target vehicle may be: the target vehicle may choose to overtake, the target vehicle may choose to avoid, or may choose to make other behavior decisions of the target vehicle, which is not limited herein. In the case that the interactive behavior decision result of the target vehicle is the predicted behavior of the interactive vehicle, the interactive behavior decision result of the target vehicle may be: one of predicting that the interactive vehicle selects overtaking, predicting that the interactive vehicle selects avoiding, and predicting that the interactive vehicle selects not to avoid, and other predicted behaviors of the interactive vehicle can be also used, and the method is not limited herein.

The interactive decision model can be obtained by training in the electronic equipment, or can be arranged in the electronic equipment after training in other electronic equipment is completed. The interactive decision model training mode is not limited herein.

The obtaining the predicted motion parameter of the interactive vehicle based on the interactive behavior decision result of the target vehicle may include: and obtaining the predicted acceleration in the predicted motion parameters of the interactive vehicle based on the interactive behavior decision result of the target vehicle.

For example, when the interactive behavior decision result of the target vehicle is that the interactive vehicle is predicted to select overtaking, based on the current speeds of the interactive vehicle and the target vehicle, the current relative distance between the interactive vehicle and the target vehicle, and a preset overtaking time, the predicted acceleration of the interactive vehicle is obtained based on an overtaking principle (the distance traveled by the interactive vehicle in the preset overtaking time is equal to the sum of the current relative distance between the interactive vehicle and the target vehicle plus the distance traveled by the target vehicle in the preset overtaking time).

For another example, when the interactive behavior decision result of the target vehicle is that the interactive vehicle is predicted to select avoidance, based on the current speeds of the interactive vehicle and the target vehicle, the current relative distance between the interactive vehicle and the target vehicle, and a preset avoidance time, based on an avoidance principle (the distance traveled by the target vehicle in the preset avoidance time is equal to the sum of the current relative distance between the interactive vehicle and the target vehicle plus the distance traveled by the interactive vehicle in the preset avoidance time), the predicted acceleration of the interactive vehicle is obtained.

For another example, when the interactive behavior decision result of the target vehicle is that the interactive vehicle is predicted to choose not to avoid, the predicted acceleration of the interactive vehicle is obtained to be 0.

Optionally, the predicted motion parameters of the interactive vehicle may further include: a duration threshold, the duration threshold being preset or preconfigured.

The initial predicted track of the interactive vehicle includes a plurality of initial track coordinates of the interactive vehicle, where the plurality of initial track coordinates are arranged based on a time sequence, and may refer to: the initial predicted trajectory of the interactive vehicle may be a set of a plurality of initial trajectory coordinates of the interactive vehicle, in which each initial trajectory coordinate is arranged in chronological order.

Accordingly, the processing after the electronic device obtains the initial predicted track of the interactive vehicle may further include: taking the time of acquiring the initial predicted track of the interactive vehicle as an initial time, and acquiring a plurality of predicted times based on a plurality of preconfigured time intervals and the initial time; and establishing a corresponding relation between each initial track coordinate contained in the initial predicted track of the interactive vehicle and each predicted time according to the sequence of the plurality of predicted times. That is, on the electronic device side, the plurality of initial track coordinates corresponds to a plurality of predicted times, and different initial track coordinates correspond to different predicted times.

For example, assume that the electronic device is preconfigured with 80 time intervals of 0.1 second, 0.2 second, 0.3 second, 0.4 second, … 7.9.9 second, 8 seconds, respectively; the electronic equipment sets the moment of receiving the 80 initial track coordinates as initial moment, takes the initial moment as 0 th second, and further obtains 80 predicted times of 0.1 th second, 0.2 th second, 0.3 th second, 0.4 th second, … th 7.9 th second and 8 th second respectively; assuming that the initial predicted track of the interactive vehicle includes 80 initial track coordinates, on the electronic device side, the 80 initial track coordinates are in one-to-one correspondence with 80 predicted times.

It should be noted that, in the above example, the differences between the adjacent two time intervals of the plurality of time intervals are the same, and the differences between the adjacent two time intervals of the plurality of time intervals may be different, and the present invention is not limited thereto.

There are various ways to obtain the initial predicted trajectory of the interactive vehicle, and the method is not limited herein. For example, the initial predicted trajectory of the interactive vehicle may be acquired with the interactive vehicle as an obstacle in such a manner that the predicted trajectory of the obstacle is acquired.

According to the scheme, the initial predicted track of the interactive vehicle is represented in the form of the scattered point coordinates, so that the electronic equipment can conveniently carry out subsequent processing, the plurality of initial track coordinates are arranged according to time sequence, the driving behavior of the interactive vehicle is met, and the subsequent processing can be more reasonable.

In some possible embodiments, the obtaining the track prediction result of the interactive vehicle based on the predicted motion parameter of the interactive vehicle and the initial predicted track of the interactive vehicle includes: taking a first initial track coordinate in the initial predicted track of the interactive vehicle as a reference track coordinate, and taking one or more remaining initial track coordinates except the first initial track coordinate in the initial predicted track of the interactive vehicle as one or more track coordinates to be adjusted; taking a first predicted time in a plurality of predicted times as a predicted arrival time of the reference track coordinate, wherein a time interval between each predicted time in the plurality of predicted times and an initial time is preconfigured, and the initial time is a time when an initial predicted track of the interactive vehicle is acquired; obtaining the predicted arrival time of the interactive vehicle to each track coordinate to be adjusted in the one or more track coordinates to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted motion parameter; obtaining a predicted track coordinate corresponding to each predicted time in the plurality of predicted times based on the predicted arrival time of the reference track coordinate and the predicted arrival time of each track coordinate to be adjusted; and generating a track prediction result of the interactive vehicle based on the predicted track coordinates corresponding to each prediction time.

For example, assume that the initial predicted track of the interactive vehicle includes 80 initial track coordinates, where the 80 initial track coordinates correspond to 80 predicted times one by one, the initial time is 0 th second, and the 80 predicted times are 0.1 th second, 0.2 th second, 0.3 th second, 0.4 th second, … th 7.9 th second, and 8 th second, respectively; the initial track coordinate corresponding to 0.1 second is the first initial track coordinate in the initial predicted track of the interactive vehicle, that is, the initial track coordinate corresponding to 0.1 second is the reference track coordinate, the 0.1 th second is the predicted arrival time of the reference track coordinate, and the initial track coordinates corresponding to 0.2 th to 8 th seconds are the track coordinates to be adjusted.

The obtaining the predicted arrival time of the interactive vehicle to reach each of the one or more track coordinates to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted motion parameter may be: and obtaining the predicted arrival time of the interactive vehicle to each track coordinate to be adjusted in the one or more track coordinates to be adjusted based on the predicted arrival time of the reference track coordinate, the predicted driving speed of the interactive vehicle corresponding to the predicted arrival time of the reference track coordinate and the predicted acceleration in the predicted motion parameter.

Optionally, the generating the track prediction result of the interactive vehicle based on the predicted track coordinates corresponding to each prediction time may include: and directly taking the predicted track coordinates corresponding to each predicted time as track prediction results of the interactive vehicles.

And directly taking the predicted track coordinates corresponding to each predicted time as track prediction results of the interactive vehicle, wherein the predicted track coordinates refer to: and sequencing the predicted track coordinates corresponding to each predicted time according to the sequence of the predicted times to obtain all sequenced predicted track coordinates, and directly taking all sequenced predicted track coordinates as track prediction results of the interactive vehicle. Here, all the predicted track coordinates in the track prediction result of the interactive vehicle may form a set, an array, or the like.

Optionally, the generating the track prediction result of the interactive vehicle based on the predicted track coordinates corresponding to each prediction time may include: and taking the predicted track coordinates corresponding to each predicted time as track prediction results of the interactive vehicle.

The taking the predicted track coordinates corresponding to each predicted time as the track prediction result of the interactive vehicle may be: and sequencing the predicted track coordinates corresponding to each predicted time according to the sequence of the predicted times to obtain sequenced predicted track coordinates and the predicted time corresponding to the sequenced predicted track coordinates, and taking the sequenced predicted track coordinates and the predicted time corresponding to the sequenced predicted track coordinates as track prediction results of the interactive vehicle.

In this case, the predicted track coordinates may be taken as the track prediction result of the interactive vehicle, and the predicted time corresponding to each predicted track coordinate may be added to the track prediction result of the interactive vehicle, so that the predicted track coordinates in the track prediction result of the interactive vehicle may be verified during the subsequent processing, for example, if the predicted track coordinates in a certain predicted time are lost, the predicted track coordinates in the predicted time may be obtained by interpolation based on the predicted track coordinates before and after the lost predicted track coordinates, so as to reduce the influence caused by the lost predicted track coordinates.

According to the technical scheme, the initial track coordinates of the interactive vehicle, which are included in the initial predicted track, are divided into the reference track coordinates and the track coordinates to be adjusted; and aiming at the track coordinates to be adjusted, obtaining the predicted arrival time corresponding to each track coordinate to be adjusted based on the predicted motion parameters, and obtaining the predicted track coordinate corresponding to each predicted time according to the reference track coordinate, the predicted time corresponding to the reference track coordinate, each track coordinate to be adjusted and the predicted arrival time corresponding to each track coordinate to be adjusted, thereby obtaining the track prediction result of the interactive vehicle. Thus, the initial predicted track of the interactive vehicle can be further adjusted based on the predicted motion parameters of the interactive vehicle, so that the track prediction result of the interactive vehicle can be obtained more accurately.

In some possible embodiments, the predicted motion parameters include a predicted acceleration and a duration threshold; the obtaining the predicted arrival time of the interactive vehicle to each of the one or more track coordinates to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted motion parameter includes: extracting current track coordinates to be adjusted based on the arrangement sequence of the track coordinates to be adjusted; determining the predicted arrival time of the interactive vehicle at the current track coordinate to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted acceleration; calculating the predicted driving speed of the interactive vehicle reaching the current track coordinate to be adjusted based on the predicted acceleration under the condition that the predicted arrival time of the current track coordinate to be adjusted is greater than or equal to the duration threshold value; determining one or more remaining track coordinates to be adjusted after the current track coordinates to be adjusted from the one or more track coordinates to be adjusted; and determining the predicted arrival time of the interactive vehicle to each of the one or more remaining track coordinates to be adjusted based on the arrangement sequence of the one or more remaining track coordinates to be adjusted and the predicted driving speed.

The extracting the current track coordinates to be adjusted based on the arrangement sequence of the one or more track coordinates to be adjusted may refer to: and sequentially extracting current track coordinates to be adjusted from the first track coordinates to be adjusted based on the arrangement sequence of the one or more track coordinates to be adjusted.

The determining, based on the predicted arrival time of the reference track coordinate and the predicted acceleration, the predicted arrival time of the interactive vehicle reaching the current track coordinate to be adjusted may be: and inputting the predicted driving speed of the interactive vehicle reaching the reference track coordinate, the predicted arrival time of the interactive vehicle reaching the reference track coordinate, the predicted acceleration and the current track coordinate to be adjusted into a uniform acceleration motion model to obtain the predicted arrival time of the interactive vehicle reaching the current track coordinate to be adjusted. The model of the uniform acceleration motion may include one or more algorithms suitable for uniform acceleration motion, without limitation.

After determining the predicted arrival time of the interactive vehicle at the current track coordinate to be adjusted, the method may include: and under the condition that the predicted arrival time of the current track coordinates to be adjusted is smaller than the duration threshold, continuing to execute the process of extracting the current track coordinates to be adjusted based on the arrangement sequence of the one or more track coordinates to be adjusted, and determining the predicted arrival time of the interactive vehicle to reach the current track coordinates to be adjusted based on the predicted arrival time of the reference track coordinates and the predicted acceleration, which is not repeated here.

After determining the predicted arrival time of the interactive vehicle at the current track coordinate to be adjusted, the method may further include: and under the condition that the predicted arrival time of the current track coordinate to be adjusted is greater than or equal to the duration threshold value, calculating the predicted driving speed of the interactive vehicle reaching the current track coordinate to be adjusted based on the predicted acceleration.

The calculating, based on the predicted acceleration, a predicted driving speed of the interactive vehicle reaching the current track coordinate to be adjusted may be: and calculating the predicted driving speed of the interactive vehicle reaching the reference track coordinate, the predicted arrival time of the interactive vehicle reaching the reference track coordinate, the predicted acceleration and the predicted arrival time of the interactive vehicle reaching the current track coordinate to be adjusted to obtain the predicted driving speed of the interactive vehicle reaching the current track coordinate to be adjusted.

The determining, based on the arrangement sequence of the one or more remaining track coordinates to be adjusted and the predicted driving speed, a predicted arrival time of the interactive vehicle to reach each of the one or more remaining track coordinates to be adjusted may be one of:

Inputting a predicted driving speed of the interactive vehicle reaching a current track coordinate to be adjusted, a predicted arrival time of the interactive vehicle reaching the current track coordinate to be adjusted, a j-th residual track coordinate to be adjusted in the one or more residual track coordinates to be adjusted, and obtaining a predicted arrival time of the interactive vehicle reaching the j-th residual track coordinate to be adjusted, wherein j is a positive integer greater than or equal to 1;

and inputting a predicted driving speed of the interactive vehicle reaching the current track coordinate to be adjusted, a predicted arrival time of the interactive vehicle reaching the current track coordinate to be adjusted and the one or more residual track coordinates to be adjusted into a uniform motion model to obtain a predicted arrival time of the interactive vehicle reaching each residual track coordinate to be adjusted in the one or more residual track coordinates to be adjusted.

The constant motion model may include one or more algorithms suitable for constant motion, which are not limited herein.

For example, still in combination with the above example, it is assumed that the initial predicted track of the interactive vehicle includes 80 initial track coordinates, the first initial track coordinate is the reference track coordinate, and all remaining initial track coordinates are track coordinates to be adjusted; the above-mentioned process of obtaining the predicted arrival time of each track coordinate to be adjusted may be: extracting a first track coordinate to be adjusted (an initial track coordinate corresponding to the 0.2 second), and determining the predicted arrival time of the interactive vehicle to reach the first track coordinate to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted acceleration; extracting a second track coordinate to be adjusted (an initial track coordinate corresponding to the 0.3 second), and determining the predicted arrival time of the interactive vehicle to the second track coordinate to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted acceleration; …, extracting an ith track coordinate to be adjusted, determining the predicted arrival time of the interactive vehicle at the ith track coordinate to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted acceleration, and calculating the predicted driving speed of the interactive vehicle at the ith track coordinate to be adjusted based on the predicted acceleration under the condition that the ith track coordinate to be adjusted is greater than or equal to the duration threshold; taking the (i+1) th track coordinate to be adjusted to the seventy-ninth track coordinate to be adjusted as the rest track coordinates to be adjusted; and based on the predicted driving speed of the interactive vehicle reaching the first track coordinate to be adjusted, sequentially determining the predicted arrival time of the interactive vehicle reaching the (i+1) th track coordinate to the seventy-ninth track coordinate to be adjusted, wherein i is a positive integer greater than 1.

According to the technical scheme, the method for accurately obtaining the predicted arrival time of the interactive vehicle to each track coordinate to be adjusted based on the predicted arrival time and the predicted motion parameters of the reference track coordinate under the condition that the predicted motion parameters comprise the predicted acceleration and the duration threshold is provided, and the method is beneficial to accurately obtaining the predicted track coordinates of the interactive vehicle subsequently.

In some possible embodiments, the predicted motion parameter may include only the predicted acceleration, and not the time threshold, that is, the interaction vehicle always makes a uniform acceleration motion to reach each of the one or more trajectory coordinates to be adjusted. The obtaining the predicted arrival time of the interactive vehicle to each of the one or more track coordinates to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted motion parameter includes: extracting current track coordinates to be adjusted based on the arrangement sequence of the track coordinates to be adjusted; determining the predicted arrival time of the interactive vehicle at the current track coordinate to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted acceleration; and then, extracting the current track coordinates to be adjusted based on the arrangement sequence of the track coordinates to be adjusted, until the processing of all the track coordinates to be adjusted is completed.

The predicted arrival time of the interactive vehicle to the current track coordinate to be adjusted is determined based on the predicted arrival time of the reference track coordinate and the predicted acceleration, and is the same as the previous one, i.e. the uniform acceleration motion model is adopted, and details are not repeated here.

In some possible embodiments, the obtaining the predicted track coordinate corresponding to each predicted time in the plurality of predicted times based on the predicted arrival time of the reference track coordinate and the predicted arrival time of each track coordinate to be adjusted includes: establishing a corresponding relation between the track and the time based on the predicted arrival time of the reference track coordinates and the predicted arrival time of each track coordinate to be adjusted; and determining the predicted track coordinates corresponding to each predicted time in the plurality of predicted times based on the corresponding relation between the track and the time.

The establishing a corresponding relationship between the track and the time based on the predicted arrival time of the reference track coordinate and the predicted arrival time of each track coordinate to be adjusted may specifically include: based on the reference track coordinates, the predicted arrival time of the reference track coordinates, the track coordinates to be adjusted and the predicted arrival time of the track coordinates to be adjusted, a corresponding relationship between the track and the time can be established.

The correspondence between the track and the time may be represented by a function or a curve.

For example, when the correspondence between the track and the time is expressed as a function, the function may be established based on each predicted arrival time and its corresponding reference track coordinate or track coordinate to be adjusted, with time as an argument and the coordinate position as an argument. Thus, after the function is established, if the coordinates of a specified prediction time are to be obtained, the predicted trajectory coordinates corresponding to the specified prediction time can be calculated based on the function.

For example, when the correspondence between the track and the time is represented by a curve, the time may be taken as an abscissa, the coordinate position may be taken as an ordinate, each predicted arrival time and the corresponding reference track coordinate or the track coordinate to be adjusted may be set in the coordinate system, and finally each predicted arrival time and the corresponding reference track coordinate or the track coordinate to be adjusted may be connected to form a corresponding curve. In this way, after the curve in the coordinate system is established, when the coordinates of a predetermined prediction time are to be obtained, the predicted trajectory coordinates corresponding to the predetermined prediction time can be directly extracted from the curve.

For example, the predicted motion parameter includes a predicted acceleration and a duration threshold, and the specific processing procedure for obtaining the track prediction result of the interactive vehicle based on the predicted motion parameter of the interactive vehicle and the initial predicted track of the interactive vehicle may be:

assuming that the initial predicted trajectory includes 80 initial trajectory coordinates, respectively (x ₁ ，y ₁ )、(x ₂ ，y ₂ )、(x ₃ ，y ₃ )、…、(x ₈₀ ，y ₈₀ ) The method comprises the steps of carrying out a first treatment on the surface of the The 80 initial trajectory coordinates correspond to the predicted time of 0.1 second, 0.2 second, 0.3 second, …, 8 seconds, respectively. It should be noted that the initial predicted trajectory may also beIndicated in bracketsRepresents x _{inter_obs} Starting from 0 seconds (excluding 0),to 8 seconds of the abscissa in the initial trajectory coordinates;representing y _{inter_obs} Starting from 0 seconds (excluding 0), to the ordinate in the initial trajectory coordinates of 8 seconds, andmay be set to 0.1 seconds. Calculating an arrival (x) based on the predicted acceleration from the second point using a uniform acceleration model ₂ ，y ₂ )、…、(x _i ，y _i ) Is the predicted arrival time t of (2) _arrive Respectively t ₂ Second, …, t _i Second, at the predicted arrival time t _arrive The value t of (2) _i Greater than or equal to the duration threshold t _range (i.e. t _arrive ≥t _range ) The method comprises the steps of carrying out a first treatment on the surface of the Calculate the t _i Second predicted driving speed v _range The method comprises the steps of carrying out a first treatment on the surface of the Based on the t _i Second predicted driving speed v _range Based on the uniform velocity model, the arrival (x _i+1 ，y _i+1 )、…、(x ₈₀ ，y ₈₀ ) Is the predicted arrival time t of (2) _arrive Respectively t _i+1 Second, …, t ₈₀ Second, wherein the second is; based on (x) ₁ ，y ₁ )、(x ₂ ，y ₂ )、(x ₃ ，y ₃ )、…、(x ₈₀ ，y ₈₀ ) Corresponding 0.1 th second, t ₂ Second, …, t _i Second, t _i+1 Second, …, t ₈₀ Second, establishing a corresponding relation between the track and time; based on the corresponding relation between the track and time, the predicted track coordinates (x _new1 ,y _new1 )、(x _new2 ,y _new2 )、(x _new2 ,y _new2 )、…、(x _new80 ,y _new80 ). Wherein, (x) _new1 ,y _new1 ) Equal to (x) ₁ ，y ₁ ). It should be noted that the above 80 predicted track coordinates may also be +.>Indicated in brackets->Representing x_new _{inter_obs} Starting from 0 seconds (excluding 0), to 8 seconds of the abscissa in the predicted trajectory coordinates; />Representing y_new _{inter_obs} Starting from 0 seconds (excluding 0), to the ordinate in the initial trajectory coordinates of 8 seconds, andmay be set to 0.1 seconds.

Through the technical scheme, based on the concept of interpolation, the corresponding relation between the track and the time is established firstly based on the predicted arrival time of the reference track coordinates and the predicted arrival time of each track coordinate to be adjusted; and determining a predicted track coordinate corresponding to each predicted track coordinate in the plurality of predicted times based on the corresponding relation between the track and the time, so that the predicted time corresponding to each predicted track coordinate obtained finally is the predicted time corresponding to each initial track coordinate, thereby enabling the track predicted result of the finally obtained interactive vehicle to be applied to a device (a track planning device mentioned below) for generating the initial predicted track of the interactive vehicle, and facilitating the device to plan the running track of the target vehicle based on the track predicted result of the interactive vehicle.

In the above scheme, the first initial track coordinate and the corresponding predicted time are not adjusted, that is, the obtained first predicted track coordinate is the same as the first initial track coordinate, and the predicted arrival time corresponding to the first predicted track coordinate is the same as the predicted time corresponding to the first initial track coordinate.

In other embodiments, the first initial trajectory coordinate and its corresponding predicted time may be adjusted. Namely: the obtaining a track prediction result of the interactive vehicle based on the predicted motion parameter of the interactive vehicle and the initial predicted track of the interactive vehicle includes: obtaining a predicted arrival time of the interactive vehicle at each initial track coordinate in the plurality of initial track coordinates based on the predicted motion parameters and the speed and position coordinates of the interactive vehicle at an initial time, wherein a time interval between the predicted arrival time of the interactive vehicle at each initial track coordinate and the initial time is preconfigured, and the initial time is a time when an initial predicted track of the interactive vehicle is obtained; obtaining a predicted track coordinate corresponding to each predicted time based on the predicted arrival time of the interactive vehicle at each initial track coordinate and each initial track coordinate; and generating a track prediction result of the interactive vehicle based on the predicted track coordinates corresponding to each prediction time.

The method for acquiring the speed of the interactive vehicle at the initial moment may include: acquiring the speed of the target vehicle at the initial moment and the relative speed of the interactive vehicle and the target vehicle; and determining the speed of the interactive vehicle at the initial moment based on the speed of the target vehicle at the initial moment and the relative speed of the interactive vehicle and the target vehicle. It should be understood that this is only an exemplary illustration, and that in the actual process, if the electronic device is capable of communicating with the interactive vehicle, the speed of the initial moment sent by the interactive vehicle may also be obtained directly, and this embodiment is not limited and exhaustive in all possible ways.

The method for acquiring the position coordinates of the interactive vehicle at the initial moment may include: acquiring the position coordinates of the target vehicle at the initial moment and the relative position coordinates of the interactive vehicle and the target vehicle; and determining the position coordinates of the interactive vehicle at the initial moment based on the position coordinates of the target vehicle at the initial moment and the relative position coordinates of the interactive vehicle and the target vehicle. It should be understood that this is also merely an exemplary illustration, and in the practical process, if the electronic device is capable of communicating with the interactive vehicle, the position coordinates of the interactive vehicle at the initial moment sent by the interactive vehicle may also be directly obtained, which is not limited to and exhaustive of all possible manners in this embodiment.

The predicted motion parameter includes a predicted acceleration and a duration threshold, and the obtaining, based on the predicted motion parameter, a speed and a position coordinate of the interactive vehicle at an initial time, a predicted arrival time of the interactive vehicle reaching each of the plurality of initial trajectory coordinates may include: extracting current initial track coordinates based on the arrangement sequence of the initial track coordinates; determining the predicted arrival time of the interactive vehicle to the current initial track coordinate based on the predicted motion parameter, the speed of the interactive vehicle at the initial moment and the position coordinate; calculating a predicted driving speed of the interactive vehicle to the current initial track coordinate based on the predicted acceleration, the speed of the interactive vehicle at the initial time and the predicted arrival time of the interactive vehicle to the current initial track coordinate when the predicted arrival time of the current initial track coordinate is greater than or equal to the duration threshold; determining one or more remaining initial track coordinates from the plurality of initial track coordinates after the current initial track coordinate; and determining the predicted arrival time of the interactive vehicle to each of the one or more remaining initial trajectory coordinates based on the arrangement sequence of the one or more remaining initial trajectory coordinates and the predicted driving speed.

In the above scheme, the manner of calculating the predicted arrival time and the predicted driving speed is the same as that of the previous method, and will not be described here. By adopting the above scheme, the predicted motion parameters include a predicted acceleration and a duration threshold, and the specific processing procedure for obtaining the track prediction result of the interactive vehicle based on the predicted motion parameters of the interactive vehicle and the initial predicted track of the interactive vehicle may be:

assuming that the initial predicted trajectory includes 80 initial trajectory coordinates, respectively (x ₁ ，y ₁ )、(x ₂ ，y ₂ )、(x ₃ ，y ₃ )、…、(x ₈₀ ，y ₈₀ ) The method comprises the steps of carrying out a first treatment on the surface of the The 80 initial track coordinates respectively correspond to the predicted time of 0.1 second, 0.2 second, 0.3 second, … and 8 thSecond. It should be noted that the initial predicted trajectory may also beIndicated in brackets->Represents x _{inter_obs} Starting from 0 seconds (excluding 0), to 8 seconds of the abscissa in the initial trajectory coordinates;representing y _{inter_obs} Starting from 0 seconds (excluding 0), to the ordinate in the initial trajectory coordinates of 8 seconds, andmay be set to 0.1 seconds. Calculating an arrival (x) based on the predicted acceleration from the first point using a uniform acceleration model ₁ ，y ₁ )、…、(x _i ，y _i ) Is the predicted arrival time t of (2) _arrive Respectively t ₁ Second, …, t _i Second, at the predicted arrival time t _arrive The value t of (2) _i Greater than or equal to the duration threshold t _range (i.e. t _arrive ≥t _range ) The method comprises the steps of carrying out a first treatment on the surface of the Calculate the t _i Second predicted driving speed v _range The method comprises the steps of carrying out a first treatment on the surface of the Based on the t _i Second predicted driving speed v _range Based on the uniform velocity model, the arrival (x _i+1 ，y _i+1 )、…、(x ₈₀ ，y ₈₀ ) Is the predicted arrival time t of (2) _arrive Respectively t _i+1 Second, …, t ₈₀ Second, wherein the second is; based on (x) ₁ ，y ₁ )、(x ₂ ，y ₂ )、(x ₃ ，y ₃ )、…、(x ₈₀ ，y ₈₀ ) Corresponding t ₁ Second, …, t _i Second, t _i+1 Second, …, t ₈₀ Second, establishing a corresponding relation between the track and time; based on the corresponding relation between the track and the time, the prediction of 0.1 th second, 0.2 th second, 0.3 th second, … th second and 8 th second which are respectively corresponding is obtained by utilizing an interpolation principleTrack coordinates (x) _new1 ,y _new1 )、(x _new2 ,y _new2 )、(x _new2 ,y _new2 )、…、(x _new80 ,y _new80 )。

In some possible embodiments, the obtaining the initial predicted trajectory of the interactive vehicle includes: acquiring an initial predicted track of the interactive vehicle from a track planning device; after obtaining the track prediction result of the interactive vehicle, the method further comprises the following steps: and sending the track prediction result of the interactive vehicle to the track planning device, and enabling the track planning device to plan the running track of the target vehicle based on the track prediction result of the interactive vehicle.

The track planning device may be a hierarchical decision and planning framework in the prior art. The layered decision and planning framework in the prior art can disassemble the decision and planning problems of automatic driving one by one, the development of functions of each sub-module is completed in a progressive manner, the tasks of each module are clear and defined, and the layered decision and planning framework is a framework with strong interpretation and is also a main flow decision and planning framework used in the actual landing process of automatic driving. However, the hierarchical decision and planning framework of the prior art is not suitable for vehicle interaction scenarios.

According to the technical scheme, the initial predicted track of the interactive vehicle generated by the track planning device can be obtained from the track planning device, the track prediction result of the interactive vehicle is obtained after the initial predicted track of the interactive vehicle is partially or completely adjusted based on the predicted motion parameters of the interactive vehicle, and the track prediction result of the interactive vehicle is sent to the track planning device, so that the track planning device can plan the running track of the target vehicle based on the track prediction result of the interactive vehicle, and the track planning device can be suitable for vehicle interaction scenes. The independence of the original track planning device is ensured when the vehicle interactivity is introduced, and the huge and redundant of the existing track planning device caused by independently developing the interactive module under the existing track planning device is avoided.

A second aspect of the present disclosure provides a trajectory prediction apparatus 200, as shown in fig. 2, including:

a motion parameter obtaining module 201, configured to obtain a predicted motion parameter of an interactive vehicle, where the interactive vehicle is a vehicle having an interaction relationship with a target vehicle;

an initial predicted track obtaining module 202, configured to obtain an initial predicted track of the interactive vehicle, where the initial predicted track of the interactive vehicle includes a plurality of initial track coordinates of the interactive vehicle, and the plurality of initial track coordinates are arranged based on a time sequence;

The track prediction result obtaining module 203 is configured to obtain a track prediction result of the interactive vehicle based on the predicted motion parameter of the interactive vehicle and the initial predicted track of the interactive vehicle, where the track prediction result of the interactive vehicle is used to plan the driving track of the target vehicle.

In some possible embodiments, the track prediction result obtaining module 203 is configured to take a first initial track coordinate in an initial predicted track of the interactive vehicle as a reference track coordinate, and one or more remaining initial track coordinates in the initial predicted track of the interactive vehicle except for the first initial track coordinate as one or more track coordinates to be adjusted; taking a first predicted time in a plurality of predicted times as a predicted arrival time of the reference track coordinate, wherein a time interval between each predicted time in the plurality of predicted times and an initial time is preconfigured, and the initial time is a time when an initial predicted track of the interactive vehicle is acquired; obtaining the predicted arrival time of the interactive vehicle to each track coordinate to be adjusted in the one or more track coordinates to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted motion parameter; obtaining a predicted track coordinate corresponding to each predicted time in the plurality of predicted times based on the predicted arrival time of the reference track coordinate and the predicted arrival time of each track coordinate to be adjusted; and generating a track prediction result of the interactive vehicle based on the predicted track coordinates corresponding to each prediction time.

In some possible embodiments, the predicted motion parameters include a predicted acceleration and a duration threshold. The track prediction result obtaining module 203 is configured to extract a current track coordinate to be adjusted based on an arrangement sequence of the one or more track coordinates to be adjusted; determining the predicted arrival time of the interactive vehicle at the current track coordinate to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted acceleration; calculating the predicted driving speed of the interactive vehicle reaching the current track coordinate to be adjusted based on the predicted acceleration under the condition that the predicted arrival time of the current track coordinate to be adjusted is greater than or equal to the duration threshold value; determining one or more remaining track coordinates to be adjusted after the current track coordinates to be adjusted from the one or more track coordinates to be adjusted; and determining the predicted arrival time of the interactive vehicle to each of the one or more remaining track coordinates to be adjusted based on the arrangement sequence of the one or more remaining track coordinates to be adjusted and the predicted driving speed.

In some possible embodiments, the track prediction result obtaining module 203 is configured to establish a correspondence between a track and a time based on the predicted arrival time of the reference track coordinate and the predicted arrival time of each track coordinate to be adjusted; and determining the predicted track coordinates corresponding to each predicted time in the plurality of predicted times based on the corresponding relation between the track and the time.

In some possible embodiments, as shown in fig. 3, the trajectory prediction device 200 further includes: and the track prediction result sending module 204 is configured to send the track prediction result of the interactive vehicle to a track planning device after obtaining the track prediction result of the interactive vehicle, and enable the track planning device to plan the driving track of the target vehicle based on the track prediction result of the interactive vehicle. The initial predicted track acquiring module 202 is configured to acquire an initial predicted track of the interactive vehicle from the track planning device.

An embodiment of a third aspect of the present disclosure provides a trajectory prediction system, as shown in fig. 4, including:

the track prediction device 410 is configured to obtain a predicted motion parameter of an interactive vehicle, where the interactive vehicle is a vehicle having an interaction relationship with a target vehicle; acquiring an initial predicted track of the interactive vehicle, wherein the initial predicted track of the interactive vehicle comprises a plurality of initial track coordinates of the interactive vehicle, and the plurality of initial track coordinates are arranged based on time sequence; and obtaining a track prediction result of the interactive vehicle based on the predicted motion parameters of the interactive vehicle and the initial predicted track of the interactive vehicle, wherein the track prediction result of the interactive vehicle is used for planning the running track of the target vehicle.

In some possible embodiments, the system further comprises: track planning means 420 for sending an initial predicted track of the interactive vehicle to the track prediction means; receiving a track prediction result of the interactive vehicle, which is sent by the track prediction device; and planning the running track of the target vehicle based on the track prediction result of the interactive vehicle.

The track prediction device 410 is configured to obtain an initial predicted track of the interactive vehicle from the track planning device; and after the track prediction result of the interactive vehicle is obtained, the track prediction result of the interactive vehicle is sent to the track planning device.

In some possible embodiments, as shown in fig. 5 or 6, the trajectory prediction device 410 may include the following modules: the motion parameter acquisition module 411, the initial predicted track acquisition module 412, the track prediction result acquisition module 413 and the track prediction result transmission module 414.

The motion parameter obtaining module 411, the initial predicted trajectory obtaining module 412, the trajectory prediction obtaining module 413, and the trajectory prediction sending module 414 are the same as the motion parameter obtaining module 201, the initial predicted trajectory obtaining module 202, the trajectory prediction obtaining module 203, and the trajectory prediction sending module 204, respectively, except that they are renumbered. Therefore, the functions of the motion parameter acquisition module 411, the initial predicted trajectory acquisition module 412, the trajectory prediction result acquisition module 413, and the trajectory prediction result transmission module 414 will not be described in detail.

Optionally, as shown in fig. 5 or fig. 6, the trajectory prediction device 410 may further include the following modules:

the interaction scene identification module 415 is configured to identify an interaction scene corresponding to a location where the target vehicle is located;

the interactive vehicle determining module 416 is configured to determine an interactive vehicle of the target vehicle according to the identified interactive scene.

The processing performed by the interactive scene recognition module 415 and the interactive vehicle determination module 416 is described in the relevant steps of the method, and will not be described herein.

In some possible embodiments, the trajectory planning device 420 is configured to project a trajectory prediction result of the interactive vehicle, so as to obtain a trajectory projection of the interactive vehicle; determining a plurality of candidate trajectories for the target vehicle; acquiring an interactive behavior decision result of the target vehicle; pruning a plurality of candidate tracks of the target vehicle based on track projection of the interaction vehicle and the interaction behavior decision result of the target vehicle to obtain a plurality of feasible tracks of the target vehicle; and planning the running track of the target vehicle based on the plurality of feasible tracks.

The track prediction result projection of the interactive vehicle is obtained, namely: and in a coordinate system where the candidate tracks of the target vehicle are located, the track prediction result of the interactive vehicle is expressed, and the track projection of the interactive vehicle is obtained. The projection accuracy can be set according to different requirements.

Wherein, the determining the plurality of candidate trajectories of the target vehicle may specifically include: and according to the current speed and the current acceleration of the target vehicle, sampling possible motion tracks of the target vehicle in a future fixed time domain within a certain acceleration range to obtain a plurality of candidate tracks.

The obtaining the interactive behavior decision result of the target vehicle may be obtained from a track prediction device. The track prediction device can identify an interaction scene corresponding to the position of the target vehicle; determining an interactive vehicle of the target vehicle according to the identified interactive scene; and determining an interactive behavior decision result of the target vehicle according to the determined interactive vehicle of the target vehicle.

The pruning is performed on a plurality of candidate tracks of the target vehicle based on the track projection of the interaction vehicle and the interaction behavior decision result of the target vehicle, so as to obtain a plurality of feasible tracks of the target vehicle, which specifically may include: and pruning the sampling tracks which are not feasible or credible for the automatic driving vehicle based on the track projection of the interactive vehicle and the interactive behavior decision result of the target vehicle to obtain a plurality of feasible tracks of the target vehicle. The obtained multiple feasible tracks of the target vehicle cannot intersect with the track projection of the interactive vehicle, and meanwhile, the interactive behavior decision result of the target vehicle is met. The method comprises the steps that according with the interactive behavior decision result of the target vehicle, when the interactive behavior decision result of the target vehicle is that the target vehicle selects avoidance, a plurality of feasible tracks of the target vehicle need to show an avoidance trend.

The planning the driving track of the target vehicle based on the plurality of feasible tracks may specifically include: and for the plurality of feasible tracks, comprehensively considering the running safety, running efficiency, running comfort and the like of the target vehicle, selecting the optimal running track in the plurality of feasible tracks, and taking the optimal running track in the plurality of feasible tracks as the running track of the target vehicle. For example, each of the plurality of possible trajectories is scored in terms of running safety, running efficiency, and running comfort, a score of each possible trajectory is obtained, and a possible trajectory with the highest score is used as the running trajectory of the target vehicle.

For example, in connection with fig. 5, the trajectory planning device 420 included in the trajectory prediction system may include the following modules:

an initial trajectory prediction module 4210 for generating an initial predicted trajectory of the interactive vehicle, and transmitting the initial predicted trajectory of the interactive vehicle to an initial predicted trajectory acquisition module 412 of the trajectory prediction device 410;

an interactive vehicle track projection module 4221, configured to project a track prediction result of the interactive vehicle to obtain a track projection of the interactive vehicle; receiving the track prediction result of the interactive vehicle sent by the track prediction result sending module 414 of the track prediction device 410;

A candidate trajectory acquisition module 4222 for determining a plurality of candidate trajectories of the target vehicle;

a pruning module 4223, configured to obtain an interaction behavior decision result of the target vehicle from the motion parameter obtaining module 411, and prune a plurality of candidate trajectories of the target vehicle based on the trajectory projection of the interaction vehicle and the interaction behavior decision result of the target vehicle to obtain a plurality of feasible trajectories of the target vehicle;

an optimal trajectory acquisition module 4224 for planning a driving trajectory of the target vehicle based on the plurality of possible trajectories.

In some possible embodiments, the trajectory planning device 420 is configured to obtain an interactive behavior decision result of the target vehicle; constructing a track planning problem of the target vehicle based on the track prediction result of the interaction vehicle and the interaction behavior decision result of the target vehicle; and solving the constructed track planning problem of the target vehicle, and planning the running track of the target vehicle.

The method for obtaining the interactive behavior decision result of the target vehicle may be the same as that described above, and will not be described herein.

The constructing the track planning problem of the target vehicle based on the track prediction result of the interaction vehicle and the interaction behavior decision result of the target vehicle may specifically include: and constructing a track planning problem of the target vehicle based on the track prediction result of the interaction vehicle, the interaction behavior decision result of the target vehicle, the physical motion parameters of the target vehicle and the like. The track planning problem of the target vehicle is mainly that a feasible region formed by the surrounding environment of the target vehicle is built, constraint conditions are built, and key parameters of solving are obtained.

The solving the constructed track planning problem of the target vehicle, and planning the running track of the target vehicle may specifically include: and planning the running track of the target vehicle according to the constructed track planning problem of the target vehicle, so that the running track of the target vehicle can accord with the interactive behavior decision of the target vehicle, and the performance of the target vehicle is better when the target vehicle runs based on the running track.

As shown in fig. 6, the trajectory planning device 420 included in the trajectory prediction system may include the following modules:

a track planning problem building module 4231 for obtaining the interactive behavior decision result of the target vehicle; receiving the track prediction result of the interactive vehicle sent by the track prediction result sending module 414 of the track prediction device 410; constructing a track planning problem of the target vehicle based on the track prediction result of the interaction vehicle and the interaction behavior decision result of the target vehicle;

And an optimal track solving module 4232, configured to solve the constructed track planning problem of the target vehicle, and plan the running track of the target vehicle.

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

Fig. 7 illustrates a schematic block diagram of an example electronic device 700 that may 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 telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary 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 includes a computing unit 701 that can 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 RAM703, various programs and data required for the operation of the electronic device 700 may also be stored. The computing unit 701, the ROM 702, and the RAM703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Various 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, etc.; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, an optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information/data with other devices through a computer network, such as the internet, and/or various telecommunication networks.

The computing unit 701 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above. For example, in some embodiments, the various methods described above may be implemented as a computer software program tangibly embodied on 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 RAM703 and executed by computing unit 701, one or more steps of the various methods described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the methods described above in any other suitable manner (e.g., by means of firmware).

According to yet another embodiment of the present disclosure, an autonomous vehicle is provided, which comprises the electronic device 700 of the above-described embodiment.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On 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, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code 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 code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. 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. The 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 portable 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 pointing device (e.g., a mouse or 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 may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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 (LAIs), wide area networks (WAIs), and the internet.

The computer system may include a client and a server. The client and server are typically 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 incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A trajectory prediction method, comprising:

2. The method of claim 1, wherein the deriving the trajectory prediction result of the interactive vehicle based on the predicted motion parameter of the interactive vehicle and the initial predicted trajectory of the interactive vehicle comprises:

taking a first initial track coordinate in the initial predicted track of the interactive vehicle as a reference track coordinate, and taking one or more remaining initial track coordinates except the first initial track coordinate in the initial predicted track of the interactive vehicle as one or more track coordinates to be adjusted;

taking a first predicted time in a plurality of predicted times as a predicted arrival time of the reference track coordinate, wherein a time interval between each predicted time in the plurality of predicted times and an initial time is preconfigured, and the initial time is a time when an initial predicted track of the interactive vehicle is acquired;

obtaining the predicted arrival time of the interactive vehicle to each track coordinate to be adjusted in the one or more track coordinates to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted motion parameter;

Obtaining a predicted track coordinate corresponding to each predicted time in the plurality of predicted times based on the predicted arrival time of the reference track coordinate and the predicted arrival time of each track coordinate to be adjusted;

and generating a track prediction result of the interactive vehicle based on the predicted track coordinates corresponding to each prediction time.

3. The method of claim 2, wherein the predicted motion parameters include a predicted acceleration and a duration threshold; the obtaining the predicted arrival time of the interactive vehicle to each of the one or more track coordinates to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted motion parameter includes:

extracting current track coordinates to be adjusted based on the arrangement sequence of the track coordinates to be adjusted;

determining the predicted arrival time of the interactive vehicle at the current track coordinate to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted acceleration;

calculating the predicted driving speed of the interactive vehicle reaching the current track coordinate to be adjusted based on the predicted acceleration under the condition that the predicted arrival time of the current track coordinate to be adjusted is greater than or equal to the duration threshold value;

Determining one or more remaining track coordinates to be adjusted after the current track coordinates to be adjusted from the one or more track coordinates to be adjusted;

and determining the predicted arrival time of the interactive vehicle to each of the one or more remaining track coordinates to be adjusted based on the arrangement sequence of the one or more remaining track coordinates to be adjusted and the predicted driving speed.

4. The method of claim 2, wherein the obtaining the predicted track coordinate corresponding to each of the plurality of predicted times based on the predicted arrival time of the reference track coordinate and the predicted arrival time of each track coordinate to be adjusted includes:

establishing a corresponding relation between the track and the time based on the predicted arrival time of the reference track coordinates and the predicted arrival time of each track coordinate to be adjusted;

and determining the predicted track coordinates corresponding to each predicted time in the plurality of predicted times based on the corresponding relation between the track and the time.

5. The method of any of claims 1-4, wherein the obtaining the initial predicted trajectory of the interactive vehicle comprises: acquiring an initial predicted track of the interactive vehicle from a track planning device;

After obtaining the track prediction result of the interactive vehicle, the method further comprises the following steps: and sending the track prediction result of the interactive vehicle to the track planning device, and enabling the track planning device to plan the running track of the target vehicle based on the track prediction result of the interactive vehicle.

6. A trajectory prediction device, comprising:

7. The apparatus of claim 6, wherein the track prediction result obtaining module is configured to take a first initial track coordinate in an initial predicted track of the interactive vehicle as a reference track coordinate, and take one or more remaining initial track coordinates except the first initial track coordinate in the initial predicted track of the interactive vehicle as one or more track coordinates to be adjusted; taking a first predicted time in a plurality of predicted times as a predicted arrival time of the reference track coordinate, wherein a time interval between each predicted time in the plurality of predicted times and an initial time is preconfigured, and the initial time is a time when an initial predicted track of the interactive vehicle is acquired; obtaining the predicted arrival time of the interactive vehicle to each track coordinate to be adjusted in the one or more track coordinates to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted motion parameter; obtaining a predicted track coordinate corresponding to each predicted time in the plurality of predicted times based on the predicted arrival time of the reference track coordinate and the predicted arrival time of each track coordinate to be adjusted; and generating a track prediction result of the interactive vehicle based on the predicted track coordinates corresponding to each prediction time.

8. The apparatus of claim 7, wherein the predicted motion parameters include a predicted acceleration and a duration threshold; the track prediction result obtaining module is used for extracting current track coordinates to be adjusted based on the arrangement sequence of the track coordinates to be adjusted; determining the predicted arrival time of the interactive vehicle at the current track coordinate to be adjusted based on the predicted arrival time of the reference track coordinate and the predicted acceleration; calculating the predicted driving speed of the interactive vehicle reaching the current track coordinate to be adjusted based on the predicted acceleration under the condition that the predicted arrival time of the current track coordinate to be adjusted is greater than or equal to the duration threshold value; determining one or more remaining track coordinates to be adjusted after the current track coordinates to be adjusted from the one or more track coordinates to be adjusted; and determining the predicted arrival time of the interactive vehicle to each of the one or more remaining track coordinates to be adjusted based on the arrangement sequence of the one or more remaining track coordinates to be adjusted and the predicted driving speed.

9. The apparatus of claim 7, wherein the track prediction result obtaining module is configured to establish a corresponding relationship between a track and a time based on the predicted arrival time of the reference track coordinate and the predicted arrival time of each track coordinate to be adjusted; and determining the predicted track coordinates corresponding to each predicted time in the plurality of predicted times based on the corresponding relation between the track and the time.

10. The apparatus according to any one of claims 6-9, the apparatus further comprising:

the track prediction result sending module is used for sending the track prediction result of the interactive vehicle to the track planning device after the track prediction result of the interactive vehicle is obtained, and enabling the track planning device to plan the running track of the target vehicle based on the track prediction result of the interactive vehicle;

the initial predicted track acquisition module is used for acquiring the initial predicted track of the interactive vehicle from the track planning device.

11. A trajectory prediction system, comprising:

the track prediction device is used for obtaining predicted motion parameters of the interactive vehicle, wherein the interactive vehicle is a vehicle with an interactive relation with the target vehicle; acquiring an initial predicted track of the interactive vehicle, wherein the initial predicted track of the interactive vehicle comprises a plurality of initial track coordinates of the interactive vehicle, and the plurality of initial track coordinates are arranged based on time sequence; and obtaining a track prediction result of the interactive vehicle based on the predicted motion parameters of the interactive vehicle and the initial predicted track of the interactive vehicle, wherein the track prediction result of the interactive vehicle is used for planning the running track of the target vehicle.

12. The system of claim 11, further comprising:

track planning means for transmitting an initial predicted track of the interactive vehicle to the track prediction means; receiving a track prediction result of the interactive vehicle, which is sent by the track prediction device; and planning a running track of the target vehicle based on a track prediction result of the interactive vehicle;

the track prediction device is used for acquiring an initial predicted track of the interactive vehicle from the track planning device; and after the track prediction result of the interactive vehicle is obtained, the track prediction result of the interactive vehicle is sent to the track planning device.

13. The system according to claim 12, wherein the trajectory planning device is configured to project a trajectory prediction result of the interactive vehicle to obtain a trajectory projection of the interactive vehicle; determining a plurality of candidate trajectories for the target vehicle; acquiring an interactive behavior decision result of the target vehicle; pruning a plurality of candidate tracks of the target vehicle based on track projection of the interaction vehicle and the interaction behavior decision result of the target vehicle to obtain a plurality of feasible tracks of the target vehicle; and planning the running track of the target vehicle based on the plurality of feasible tracks.

14. The system of claim 12, the trajectory planning device for obtaining interactive behavior decision results of the target vehicle; constructing a track planning problem of the target vehicle based on the track prediction result of the interaction vehicle and the interaction behavior decision result of the target vehicle; and solving the constructed track planning problem of the target vehicle, and planning the running track of the target vehicle.

15. 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 1-5.

16. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-5.

17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-5.

18. An autonomous vehicle comprising the electronic device of claim 15.