CN114228746A

CN114228746A - Method and device for predicting vehicle motion trail

Info

Publication number: CN114228746A
Application number: CN202210050559.XA
Authority: CN
Inventors: 颜学术; 李继扬
Original assignee: Beijing Jingwei Hirain Tech Co Ltd
Current assignee: Beijing Jingwei Hirain Tech Co Ltd
Priority date: 2022-01-17
Filing date: 2022-01-17
Publication date: 2022-03-25
Anticipated expiration: 2042-01-17
Also published as: CN114228746B

Abstract

The invention provides a method and a device for predicting a vehicle motion trail.A mean kinematics parameter is determined by utilizing the acquired absolute motion state of a specified target vehicle, and the motion trail to be processed is predicted according to the mean kinematics parameter; predicting to obtain an initial driving intention based on the motion trail to be processed and the historical motion trail of the specified target vehicle; determining the lane type of a lane where the specified target vehicle is located, and determining obstacle vehicle information; carrying out filtering processing on the initial driving intention by utilizing the type of the road line and the information of the obstacle vehicle to obtain a final driving intention and determining a transverse target position according to the final driving intention; and predicting the vehicle motion track of the specified target vehicle by using the transverse target position and the average kinematic parameter. The method has low requirement on hardware computing power, and can quickly locate which link is abnormal, so that the abnormity is solved in time to improve safety.

Description

Method and device for predicting vehicle motion trail

Technical Field

The invention relates to the technical field of vehicles, in particular to a method and a device for predicting a vehicle motion trail.

Background

In order to ensure the driving safety during the driving of an intelligent vehicle (i.e., a vehicle having an automatic driving function of L2 or higher), it is necessary to recognize the movement trajectory of the vehicle around the vehicle, for example, the cut-in/cut-out behavior of the vehicle around the vehicle into the lane of the vehicle.

At present, the method for identifying the motion track of a vehicle mainly comprises the following steps: and training by a machine learning algorithm to obtain a prediction model for predicting the movement locus through a large amount of acquired driving data. On one hand, however, the parameter quantity related to the prediction model is huge, and the performance requirement on a computing platform carrying the prediction model is also high, namely, the application of the prediction model requires high hardware computing power, and the hardware computing power of mass-produced intelligent vehicles cannot meet the performance requirement of the application prediction model; on the other hand, when the calculation result of the prediction model is abnormal, the difficulty of analyzing the abnormal reason from the prediction model is high, so that the abnormality cannot be solved in time, and the safety is poor.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and an apparatus for predicting a vehicle motion trajectory, so as to solve the problems of a conventional vehicle motion trajectory prediction method, such as high requirement on hardware computation power and poor safety.

In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:

the first aspect of the embodiments of the present invention discloses a method for predicting a vehicle motion trajectory, which is applied to a device for predicting a vehicle motion trajectory, and the method includes:

determining a designated target vehicle from the detected target vehicles;

determining to obtain an average kinematic parameter by using the absolute motion state of the specified target vehicle collected in a plurality of historical periods, and predicting a motion track to be processed of the specified target vehicle based on the average kinematic parameter, wherein the average kinematic parameter is used for describing the average motion state of the specified target vehicle in the plurality of historical periods;

calculating a normalized mean value of the motion characteristic vector of the specified target vehicle based on the motion track to be processed and the historical motion track of the specified target vehicle;

mapping the normalized mean value to a preset value interval to obtain a driving intention value, and predicting according to the driving intention value to obtain an initial driving intention;

scanning the surrounding environment of the specified target vehicle to obtain the lane type of the lane where the specified target vehicle is located and obtain the obstacle vehicle information in the lane adjacent to the lane where the specified target vehicle is located;

filtering the initial driving intention by using the lane line type and the obstacle vehicle information, and predicting to obtain a final driving intention;

determining a lateral target position based on the final travel intent;

and predicting the vehicle motion track of the specified target vehicle from the current position to the target position by using the transverse target position and the average kinematic parameter.

Preferably, determining to obtain an average kinematic parameter by using the absolute kinematic state of the specified target vehicle collected in a plurality of history cycles, and predicting the trajectory of motion to be processed of the specified target vehicle based on the average kinematic parameter, includes:

determining a time interval of a plurality of history periods;

dividing the absolute motion state of the specified target vehicle acquired in the plurality of historical periods by the time interval to obtain an average kinematic parameter;

and processing the average kinematic parameters by using a kinematic model, and predicting the motion trail to be processed of the specified target vehicle.

Preferably, calculating a normalized mean value of the motion feature vector of the designated target vehicle based on the motion trajectory to be processed and a pre-stored historical motion trajectory of the designated target vehicle, includes:

combining the motion trail to be processed with the pre-stored historical motion trail of the specified target vehicle to obtain an input motion trail;

calculating the horizontal position of the center line of the lane center line and the course angle of the lane line corresponding to the input motion track by using a lane line expression;

for the vehicle transverse position and the vehicle course angle of the specified target vehicle in the input motion track, calculating a transverse position deviation between the vehicle transverse position and the central line transverse position, and calculating a course angle deviation between the vehicle course angle and the road line course angle;

dividing the transverse position deviation by lane width to normalize the transverse position deviation, averaging all the normalized transverse position deviations, and determining to obtain a normalized average value of the transverse position deviation;

dividing the course angle deviation by the maximum course angle of the specified target vehicle to normalize the course angle deviation, averaging all the normalized course angle deviations, and determining to obtain a normalized average of the course angle deviations, wherein the maximum course angle of the specified target vehicle is obtained by calculation based on the vehicle speed of the specified target vehicle.

Preferably, the mapping the normalized mean value to a preset value interval to obtain a driving intention value, and predicting an initial driving intention according to the driving intention value includes:

mapping the normalized mean value of the transverse position deviation to a preset value interval by using a nonlinear mapping function obtained based on an S-shaped function to obtain a first driving intention value, and mapping the normalized mean value of the course angle deviation to the preset value interval to obtain a second driving intention value;

predicting that the initial driving intention is a left lane change intention if the first driving intention value and the second driving intention value satisfy a left lane change rule, wherein the left lane change rule is that: the first driving intention value is within a first left lane change value interval, and the second driving intention value is within a second left lane change value interval;

predicting that the initial driving intention is a right lane change intention if the first driving intention value and the second driving intention value satisfy a right lane change rule, wherein the right lane change rule is that: the first driving intention value is within a first right lane change value interval, and the second driving intention value is within a second right lane change value interval;

predicting an initial travel intent as a lane-keeping intent if the first travel intent value and the second travel intent value do not satisfy the left lane-change rule and the first travel intent value and the second travel intent value do not satisfy the right lane-change rule.

Preferably, the specifying the type of the lane in which the target vehicle is located includes: the lane line type of the left lane line and the lane line type of the right lane line; the lane line types are as follows: lane lines that are allowed to change lanes or lane lines that are not allowed to change lanes.

Preferably, the initial driving intention is a left lane-changing intention, a right lane-changing intention or a lane-keeping intention;

performing filtering processing on the initial driving intention by using the lane type and the obstacle vehicle information, and predicting to obtain a final driving intention, wherein the method comprises the following steps:

determining a lane change condition that is satisfied by the specified target vehicle by using the lane line type and the obstacle vehicle information, wherein the lane change condition at least comprises: a first condition for indicating that a right-hand lane change is permitted, a second condition for indicating that a left-hand lane change is permitted;

predicting a final travel intention as a lane keeping intention when the specified target vehicle does not satisfy the second condition in a case where the initial travel intention is a left lane change intention; predicting that the final driving intention is a left lane changing intention when the specified target vehicle satisfies the second condition;

predicting a final travel intention as a lane keeping intention when the specified target vehicle does not satisfy the first condition in a case where the initial travel intention is a right lane change intention; predicting that the final travel intention is a right lane change intention when the specified target vehicle satisfies the first condition.

Preferably, the final driving intention is a left lane-changing intention, a right lane-changing intention or a lane-keeping intention;

determining a lateral target position based on the final travel intent, comprising:

determining the transverse position of the center line of a lane adjacent to the left of the lane where the specified target vehicle is located as a transverse target position under the condition that the final driving intention is a left lane changing intention;

determining the transverse position of the center line of a lane adjacent to the right of the lane where the specified target vehicle is located as a transverse target position under the condition that the final driving intention is a right lane changing intention;

and in the case that the final driving intention is the intention of keeping the lane, determining the transverse position of the center line of the lane where the specified target vehicle is positioned as a transverse target position.

Preferably, predicting a vehicle motion trajectory of the specified target vehicle from a current position to a target position using the lateral target position and the average kinematic parameter includes:

generating a transverse moving track of the specified target vehicle moving to the transverse target position by using a preset track generation mode;

generating a longitudinal movement track of the specified target vehicle according to the average kinematic parameters;

and predicting the vehicle motion track from the current position to the target position of the specified target vehicle by combining the transverse moving track and the longitudinal moving track.

Preferably, the preset track generation mode is an equal proportion attenuation mode or a polynomial curve fitting mode;

when the trajectory generation method is the equal proportional attenuation method, the data point at the k-th time in the generated transverse movement trajectory is y_k＝αy_k-1，y_kIs the difference between the lateral position of the specified target vehicle and the lateral target position at the k-th time, 0<α<1；

The data point at the k-th time in the generated longitudinal movement track is

x_kIs the longitudinal position of the specified target vehicle at the k-th time, v is the velocity, a is the acceleration, T is the length of the fixed period, v at the k-th time is v_k＝v_k-1+aT；

In the predicted vehicle motion trail, the trail position of the target appointed vehicle at the k-th time is (x)_k，y_k)。

A second aspect of the embodiments of the present invention discloses an apparatus for predicting a vehicle movement locus, the apparatus being mounted in a vehicle, the apparatus including:

a first determination unit configured to determine a specified target vehicle from among all the detected target vehicles;

the processing unit is used for determining and obtaining an average kinematic parameter by using the absolute motion state of the specified target vehicle collected in a plurality of historical periods, and predicting a motion track to be processed of the specified target vehicle based on the average kinematic parameter, wherein the average kinematic parameter is used for describing the average motion state of the specified target vehicle in the plurality of historical periods;

the calculation unit is used for calculating a normalized mean value of the motion characteristic vector of the specified target vehicle based on the motion track to be processed and the historical motion track of the specified target vehicle;

the first prediction unit is used for mapping the normalized mean value to a preset value interval to obtain a driving intention value and predicting to obtain an initial driving intention according to the driving intention value;

the scanning unit is used for scanning the surrounding environment of the specified target vehicle, obtaining the lane type of the lane where the specified target vehicle is located, and obtaining the obstacle vehicle information in the lane adjacent to the lane where the specified target vehicle is located;

the second prediction unit is used for carrying out filtering processing on the initial driving intention by utilizing the road line type and the obstacle vehicle information to predict and obtain a final driving intention;

a second determination unit for determining a lateral target position based on the final travel intention;

and a third prediction unit, configured to generate a vehicle motion trajectory of the specified target vehicle from the current position to the target position using the lateral target position and the average kinematic parameter.

Based on the method and the device for predicting the vehicle motion trail provided by the embodiment of the invention, the method comprises the following steps: determining a designated target vehicle; determining to obtain average kinematic parameters by using the absolute motion states of the specified target vehicle collected in a plurality of historical periods, and predicting a motion track to be processed of the specified target vehicle based on the average kinematic parameters; calculating a normalized mean value of the motion characteristic vector of the specified target vehicle based on the motion track to be processed and the historical motion track of the specified target vehicle; mapping the normalized mean value to a preset value interval to obtain a driving intention value, and predicting according to the driving intention value to obtain an initial driving intention; scanning the surrounding environment of the specified target vehicle to obtain the lane type of the lane where the specified target vehicle is located and obtain the obstacle vehicle information in the lane adjacent to the lane where the specified target vehicle is located; filtering the initial driving intention by using the type of the road line and the information of the obstacle vehicle, and predicting to obtain a final driving intention; determining a lateral target position based on the final driving intent; and predicting a vehicle motion track of the specified target vehicle from the current position to the target position by using the transverse target position and the average kinematic parameter. By adopting the scheme, the driving intention is obtained by calculating the historical motion trail and other parameters of the appointed target vehicle, the motion trail of the vehicle is predicted according to the driving intention, the used parameters for predicting the motion trail of the vehicle are less, and the requirement on hardware computing power is lower; and the vehicle motion track is predicted in a hierarchical mode, when the prediction result is abnormal, which link is abnormal can be quickly positioned, and the abnormity is timely solved to improve the safety.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a flowchart of a method for predicting a motion trajectory of a vehicle according to an embodiment of the present invention;

FIG. 2 is a schematic diagram illustrating a definition of an inertial reference coordinate system and a vehicle coordinate system according to an embodiment of the present invention;

FIG. 3 is a diagram illustrating a non-linear mapping function according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of scanning the surroundings of a given target vehicle, as provided by an embodiment of the present invention;

FIG. 5 is a flowchart of calculating a normalized mean value according to an embodiment of the present invention;

FIG. 6 is a schematic diagram illustrating a vehicle motion trajectory prediction method according to an embodiment of the present invention;

fig. 7 is a block diagram of a device for predicting a motion trajectory of a vehicle according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

As known in the background art, a prediction model for predicting a motion trajectory is usually obtained by training with a machine learning algorithm. However, the parameter quantity related to the prediction model is huge, the requirement on hardware computing power of the intelligent vehicle is high, and when the calculation result of the prediction model is abnormal, the difficulty in analyzing the abnormal reason from the prediction model is high, so that the abnormality cannot be solved in time, and the safety is poor.

Therefore, the embodiment of the invention provides a method and a device for predicting a vehicle motion trail, wherein a driving intention is obtained by calculating a historical motion trail and other parameters of a specified target vehicle, the vehicle motion trail is predicted according to the driving intention, and the parameters used for predicting the vehicle motion trail are fewer, so that the requirement on hardware computing power is reduced; and the vehicle motion track is predicted in a hierarchical mode, when the prediction result is abnormal, which link is abnormal can be quickly positioned, and the abnormity is timely solved to improve the safety.

Referring to fig. 1, a flowchart of a method for predicting a vehicle motion trajectory according to an embodiment of the present invention is shown, where the method is applied to an apparatus for predicting a vehicle motion trajectory, and the method includes:

step S101: a designated target vehicle is determined from the detected target vehicles.

In addition, a sensing system is installed in the vehicle, and the vehicle can detect each target vehicle and detect target information of each target vehicle through the sensing system during driving, for example: and detecting information such as the position, the speed, the acceleration, the course angle and the category of the target vehicle.

In the process of specifically implementing the step S101, according to a preset screening rule, a designated target vehicle is screened from all detected target vehicles, and the designated target vehicle is a target vehicle for which the vehicle motion trajectory needs to be predicted.

In some specific embodiments, from among all the detected target vehicles, a target vehicle whose lateral distance from the vehicle is less than a first threshold value and whose longitudinal distance from the vehicle is less than a second threshold value is determined as the designated target vehicle. That is, for a certain target vehicle, if the lateral distance of the target vehicle from the vehicle is less than a first threshold value, and the longitudinal distance of the target vehicle from the vehicle is less than a second threshold value, the target vehicle can be determined to be the designated target vehicle.

It should be noted that the above manner of determining the designated target vehicle according to the lateral distance and the longitudinal distance from the vehicle is only one example of screening out the designated target vehicle, and the screening rule for screening out the designated target vehicle may also be defined according to other requirements, and the specific content of the screening rule is not limited in the embodiment of the present invention.

Step S102: and determining to obtain an average kinematic parameter by using the absolute motion state of the specified target vehicle collected in a plurality of historical periods, and predicting the motion track to be processed of the specified target vehicle based on the average kinematic parameter.

As can be seen from the above, the sensing system can acquire the target information of the target vehicle, specifically, the target information acquired by the sensing system defines the relative motion state under the coordinate system of the vehicle (the coordinate system is referred to as the host vehicle coordinate system), for example: the speed acquired by the sensing system is a relative speed, and the acceleration acquired is a relative acceleration. In practical application, the acquired relative motion state of the target vehicle needs to be converted into an absolute motion state, and the specific conversion mode is as follows: obtaining chassis information (including vehicle speed, acceleration, yaw rate and the like) of a vehicle (namely, a host vehicle) through a vehicle-mounted bus; according to the obtained chassis information, the relative motion state of the target vehicle in the host vehicle coordinate system is converted into the absolute motion state in the inertial reference coordinate system, and finally the absolute motion states (such as absolute speed, absolute acceleration and the like) of the target vehicle and the vehicle can be obtained.

It should be noted that the inertial reference coordinate system refers to a geodetic coordinate system coinciding with the origin of the vehicle coordinate system at the current time, please refer to fig. 2, and fig. 2 is a schematic diagram illustrating the definitions of the inertial reference coordinate system and the vehicle coordinate system; in fig. 2, the relative motion state of the specified target vehicle in the host vehicle coordinate system is converted to the absolute motion state in the inertial reference coordinate system. Note that, in fig. 2, reference numerals 101 to 104 represent lane lines, reference numeral 200 represents a specified target vehicle, and reference numeral 300 represents a vehicle (i.e., a host vehicle).

It can be understood that, in the solution provided in the embodiment of the present invention, the related computation task is executed according to a certain fixed period, for example, the fixed period T ═ 20 ms; the absolute motion state of the specified target vehicle is acquired in each history period.

It should be noted that the average kinematic parameters are used to describe the average motion state of the specified target vehicle in a plurality of history periods. In the process of implementing step S102 specifically, average kinematic parameters (such as average speed and average yaw rate) may be determined by using the absolute motion states of the specified target vehicle collected in a plurality of history cycles, so as to effectively suppress abnormal data caused in the real-time detection process.

Specifically, a time interval of a plurality of history periods is determined, the time interval being the sum of the plurality of history periods, for example: assuming that N history periods are provided, and the length of each history period is T, the time interval of the N history periods is T ═ NT; the absolute motion state of the specified target vehicle acquired in the plurality of history periods is divided by the time interval to obtain an average kinematic parameter. For example: and dividing the displacement acquired in the plurality of historical periods by the time interval to obtain the average speed. Another example is: and dividing the angle variation acquired in the plurality of historical periods by the time interval to obtain the average yaw rate.

After the average kinematic parameters of the specified target vehicle are obtained through calculation, the average kinematic parameters are processed through a kinematic model, and a to-be-processed motion trajectory (also called as a to-be-processed motion trajectory sequence) of the specified target vehicle is obtained through prediction, or in other words, the to-be-processed motion trajectory of the specified target vehicle is generated.

The kinematic model may be a Constant angular velocity (CTRV) model, a Constant angular velocity (CTRA) model, a Constant acceleration (CTRA) model, or the like; specifically, recursion from the k-th period to the k + 1-th period is performed by using a kinematic model based on the average kinematic parameter of the specified target vehicle, so that the to-be-processed motion track of the specified target vehicle is generated.

It is understood that, since the kinematic model can only reflect the motion state for a short time, the time length of the generated motion trajectory to be processed should be less than a certain value (e.g., less than 0.5 s).

Step S103: and calculating the normalized mean value of the motion characteristic vector of the specified target vehicle based on the motion track to be processed and the historical motion track of the specified target vehicle.

It should be noted that, during actual running, the historical motion track of the specified target vehicle in the inertial reference coordinate system in the past period is recorded in real time, and the time length of the historical motion track may be customized, for example: the time length of the historical motion trail can be defined as 1 second to 3 seconds according to the general lane changing time.

In the process of implementing step S103 specifically, a normalized mean value of the motion feature vector of the specified target vehicle is calculated by using the motion trajectory to be processed and the historical motion trajectory of the specified target vehicle. It is understood that the motion feature vector includes, but is not limited to: a lateral position deviation between a vehicle lateral position of a target vehicle and a center line lateral position of a lane center line (a lane center line of a lane where the target vehicle is located is specified), and a heading angle deviation between a vehicle heading angle of the target vehicle and a lane line heading angle of the lane center line are specified.

Normalizing the transverse position deviation and calculating a mean value based on the width of a lane where the specified target vehicle is located to obtain a normalized mean value of the transverse position deviation; and normalizing the course angle deviation and calculating the mean value based on the maximum course angle of the specified target vehicle to obtain the normalized mean value of the course angle deviation.

How to calculate the normalized mean of the lateral position deviation and the normalized mean of the heading angle deviation is described in detail in fig. 5 of the following embodiments.

Step S104: and mapping the normalized mean value to a preset value interval to obtain a driving intention value, and predicting according to the driving intention value to obtain an initial driving intention.

In the process of implementing the step S104 specifically, mapping the normalized mean value of the motion feature vector to a preset value interval by using a nonlinear mapping function to obtain a driving intention value, and predicting to obtain an initial driving intention according to the driving intention value; the predetermined value interval may be an interval of [ -1,1 ].

In some embodiments, the nonlinear mapping function is determined in advance by using an S-type function, and specifically, the S-type function is scaled and translated to obtain the nonlinear mapping function; the sigmoid function may be a sigmoid function, a tanh function, and the like.

Taking the tanh function as an example, how to determine the process of obtaining the nonlinear mapping function is illustrated. the tanh function is given by equation (1). The tanh function is scaled and translated, and the resulting nonlinear mapping function is as in equation (2).

The tanh function is scaled and translated, and the resulting nonlinear mapping function is as in equation (2).

In the above equations (1) and (2), x is an argument, a is a scaling coefficient, and b is a translation coefficient. In practical application, x in the formula (2) is a normalized mean value of the motion feature vector, and f (x) in the formula (2) is a value obtained by mapping the normalized mean value to a preset value interval.

In some embodiments, the normalized mean of the lateral position deviation is mapped to a preset value interval to obtain a first driving intention value, and the normalized mean of the course angle deviation is mapped to a preset value interval to obtain a second driving intention value, by using a nonlinear mapping function obtained based on an S-type function.

For example: referring to fig. 3, fig. 3 is a schematic diagram of a non-linear mapping function, and after mapping the normalized mean value into a preset value interval of [ -1,1], a corresponding driving intention value can be obtained; when the driving intention value is in a left lane change value interval (namely, a value interval indicated by LLC), the initial driving intention is a left lane change intention; when the driving intention value is in the right lane change value interval (namely, the value interval indicated by the RLC), the driving intention value indicates that the initial driving intention is the right lane change intention; the driving intention value is not in the left lane change value section nor in the right lane change value section (i.e., in the value section indicated by LK), and indicates that the initial driving intention is the intention to keep the lane. The left channel change interval in fig. 3 may be-0.6 to-1, and the right channel change interval may be 0.6 to 1.

After the normalized mean value of the lateral position deviation and the normalized mean value of the course angle deviation are respectively mapped to a preset value interval, under the condition that the first driving intention value and the second driving intention value meet a left lane changing rule, the initial driving intention is predicted to be a left lane changing intention, wherein the left lane changing rule is as follows: the first driving intent value is within a first left lane change value interval and the second driving intent value is within a second left lane change value interval.

And under the condition that the first driving intention value and the second driving intention value meet a right lane changing rule, predicting that the initial driving intention is a right lane changing intention, wherein the right lane changing rule is as follows: the first driving intent value is within a first right lane change value interval and the second driving intent value is within a second right lane change value interval.

In a case where the first travel intention value and the second travel intention value do not satisfy the left lane change rule, and in a case where the first travel intention value and the second travel intention value do not satisfy the right lane change rule, the initial travel intention is predicted as the lane keeping intention.

Step S105: the method comprises the steps of scanning the surrounding environment of an appointed target vehicle, obtaining the type of a lane where the appointed target vehicle is located, and obtaining obstacle vehicle information in a lane adjacent to the lane where the appointed target vehicle is located.

In some embodiments, specifying the lane type of the lane in which the target vehicle is located includes: the lane line type of the left lane line and the lane line type of the right lane line; the lane type is: lane lines that allow lane change (e.g., dashed lines) or lane lines that do not allow lane change (e.g., solid lines).

In the process of implementing step S105 specifically, the surroundings of the specified target vehicle are scanned, such as: scanning the lane type of a lane where the specified target vehicle is located, and scanning obstacle vehicle information in lanes (adjacent left lanes and/or right lanes) adjacent to the lane where the specified target vehicle is located; obtaining a lane type of a lane where the specified target vehicle is located, and obtaining obstacle vehicle information in a lane adjacent to the lane where the specified target vehicle is located, the obstacle vehicle information indicating at least: whether an obstacle vehicle exists in a lane adjacent to the lane in which the specified target vehicle is located.

In some embodiments, the lateral and longitudinal ranges of the surroundings of the designated target vehicle may be defined as practical; the lateral range of the surrounding environment is defined as the width of the lane where the specified target vehicle is located plus the width of the left and right adjacent lanes, for example: the width of a lane where the specified target vehicle is located is L, and lanes adjacent to the left and the right of the lane where the specified target vehicle is located are L, so that the transverse range of the surrounding environment is limited to 3L; the longitudinal range of the surrounding environment may be adaptively adjusted according to the vehicle speed vx of the specified target vehicle, for example: the upper threshold value dis _ y _ low of the longitudinal range of the ambient environment is k × vx, the lower threshold value dis _ y _ high of the longitudinal range of the ambient environment is m × vx, the longitudinal range of the ambient environment is a range formed by dis _ y _ low and dis _ y _ high, wherein k and m are adjustment coefficients, and k and m can be adjusted according to the vehicle type and the sensitivity level set by the system.

Step S106: and carrying out filtering processing on the initial driving intention by using the type of the road line and the information of the obstacle vehicle, and predicting to obtain the final driving intention.

In the process of implementing step S106 specifically, after obtaining the lane type of the lane where the specified target vehicle is located by scanning and obtaining the obstacle vehicle information by scanning, determining a lane change condition that is satisfied by the specified target vehicle by using the lane type and the obstacle vehicle information, where the lane change condition at least includes: a first condition for indicating that a right-hand lane change is allowed, and a second condition for indicating that a left-hand lane change is allowed. Wherein, the first condition may specifically be: the lane line type of the lane line on the right side of the lane where the specified target vehicle is located is a broken line (namely the lane line which can be changed), and no obstacle vehicle exists in the lane adjacent to the right side of the lane where the specified target vehicle is located; the second condition may specifically be: the lane line type of the lane line on the left side of the lane where the specified target vehicle is located is a broken line, and no obstacle vehicle is located in the lane adjacent to the left side of the lane where the specified target vehicle is located.

In the case where the initial travel intention is a left lane change intention, when the specified target vehicle does not satisfy the second condition (i.e., cannot change lanes to the left), predicting that the final travel intention is a lane keeping intention; when the specified target vehicle satisfies the second condition (i.e., can change lane to the left), it is predicted that the final travel intention is a left lane change intention.

In the case where the initial travel intention is a right lane change intention, when the specified target vehicle does not satisfy the first condition (i.e., cannot change lanes to the right), predicting that the final travel intention is a lane keeping intention; if the specified target vehicle satisfies the first condition (i.e., changes lane to the right), it is predicted that the final travel intention is a right lane change intention.

For example: referring to fig. 4, fig. 4 is a schematic diagram of scanning the surroundings of a designated target vehicle, wherein

numbers

201 and 202 represent lane lines, number 400 represents an obstacle vehicle, and number 500 represents the designated target vehicle.

As shown in fig. 4, the lane line type of the lane line on the right side of the lane in which the specified target vehicle is located is a solid line, and an obstacle vehicle is present in the lane adjacent to the left side of the lane in which the specified target vehicle is located; in the case where the initial travel intention is a left lane change intention, since an obstacle vehicle is present in a lane adjacent to the left of the lane in which the specified target vehicle is located (i.e., the lane change to the left is not possible), it is predicted that the final travel intention of the specified target vehicle is a lane-keeping intention (i.e., an in-lane-keeping intention). Meanwhile, as for the scanned ambient environment mentioned in the above step S105, as can be seen from fig. 4, the vertical range of the ambient environment (the environment scanning area in fig. 4) is a range formed by dis _ y _ low and dis _ y _ high.

Step S107: the lateral target position is determined based on the final travel intent.

As can be seen from the above step S106, the final driving intention is a left lane change intention, a right lane change intention, or a lane keeping intention; in the process of specifically implementing step S107, based on the final travel intention, a lateral target position is determined in the lane line Frenet coordinate system, the lateral target position being: and specifying the position to be reached by the transverse motion of the target vehicle.

In some embodiments, in the case that the final driving intention is a left lane-changing intention, determining a center line transverse position of a lane adjacent to the left of the lane where the specified target vehicle is located as a transverse target position; determining the transverse position of the center line of a lane adjacent to the right of the lane where the specified target vehicle is located as a transverse target position under the condition that the final driving intention is a right lane changing intention; in the case where the final travel intention is an intention to keep the lane, a center line lateral position of the lane in which the specified target vehicle is located is determined as a lateral target position.

Step S108: and predicting a vehicle motion track of the specified target vehicle from the current position to the target position by using the transverse target position and the average kinematic parameter.

In the process of implementing step S108 specifically, a lateral movement trajectory that specifies that the target vehicle moves to the lateral target position is generated by using a preset trajectory generation manner, which includes but is not limited to: an equal proportion attenuation mode, a polynomial curve fitting mode and the like; in the case of the proportional attenuation method, the data point at the k-th time in the traverse trajectory is shown in formula (3).

y_k＝αy_k-1 (3)

In the formula (3), y_kFor the difference between the lateral position of the designated target vehicle and the lateral target position at the k-th time, 0<α<1, the smaller alpha, the smaller y_kThe faster the attenuation, i.e. the faster the change in the lateral position of the designated target vehicle, α may in particular be in the range of 0.90 to 0.99.

It is understood that the acceleration of the specified target vehicle in the longitudinal direction is set to be constant, and the longitudinal movement trajectory of the specified target vehicle, in which the data point at the k-th time is as in equation (4), is generated based on the average kinematic parameter determined in step S102.

In the formula (4), x_kThe longitudinal position of the target vehicle is specified at the k-th time, v is the velocity, a is the acceleration, and T is the length of the fixed period. The calculation of v at the k-th time is as in equation (5).

v_k＝v_k-1+aT (5)

And (3) predicting to obtain a vehicle motion track from the current position to the target position of the specified target vehicle by using the formulas (3) to (5) and combining the transverse movement track and the longitudinal movement track, wherein the track position of the specified target vehicle at the k-th moment in the vehicle motion track is marked as (x)_k，y_k)。

As can be seen from the above contents of step S101 to step S108, the method for predicting a vehicle motion trajectory according to the embodiment of the present invention predicts a vehicle motion trajectory of a specific target vehicle in two layers. The first layer is a driving intention prediction layer, the motion characteristics of the specified target vehicle relative to the lane line are obtained through calculation by continuously observing the motion state of the specified target vehicle acquired in the history period, and the final driving intention of the specified target vehicle is judged by considering the dynamic information (whether an obstacle vehicle exists) and the static information (the lane line type of the lane line) of the surrounding environment where the specified target vehicle is located. The second layer is a vehicle motion track prediction layer, and the vehicle motion track of the specified target vehicle in a certain period of time in the future is predicted by specifying the final driving intention of the target vehicle.

In the embodiment of the invention, the driving intention is obtained by calculating the historical motion trail and other parameters of the specified target vehicle, and the motion trail of the vehicle is predicted according to the driving intention, so that the parameters used for predicting the motion trail of the vehicle are less, and the requirement on hardware calculation force is lower; and the vehicle motion track is predicted in a hierarchical mode, when the prediction result is abnormal, which link is abnormal can be quickly positioned, and the abnormity is timely solved to improve the safety.

In the above-mentioned embodiment of the present invention, referring to fig. 5, the process of calculating the normalized mean of the lateral position deviation and the normalized mean of the heading angle deviation in step S103 in fig. 1 shows a flowchart of calculating the normalized mean provided in the embodiment of the present invention, which includes the following steps:

step S501: and combining the motion trail to be processed with the pre-stored historical motion trail of the specified target vehicle to obtain an input motion trail.

In the process of specifically implementing step S501, the historical motion trajectory of the specified target vehicle and the predicted to-be-processed motion trajectory are combined to obtain an input motion trajectory.

Step S502: and calculating the transverse position of the central line of the lane corresponding to the input motion track and the course angle of the lane by using the lane line expression.

The lane center line corresponding to the input motion trajectory is the lane center line of the lane line where the specified target vehicle is located; the lane line expression includes: a left lane line expression and a right lane line expression.

In some embodiments, the left lane line expression is as in equation (6) and the right lane line expression is as in equation (7).

y_l＝c_0l+c_1lx+c_2lx²+c_3lx³ (6)

y_r＝c_0r+c_1rx+c_2rx²+c_3rx³ (7)

In equation (6), x is the longitudinal position of the designated target vehicle in the coordinate system of the vehicle, and y_lA transverse position of a left lane line for specifying a longitudinal position of a target vehicle under a vehicle coordinate system, c_0l、c_1l、c_2lAnd c_3lA 3 rd order polynomial coefficient for the left lane line of the lane line on which the specified target vehicle is located. In equation (7), x is the longitudinal position of the designated target vehicle in the coordinate system of the vehicle, and y_rA transverse position of a right lane line for specifying a longitudinal position of a target vehicle under a host vehicle coordinate system, c_0r、c_1r、c_2rAnd c_3rA 3 rd order polynomial coefficient for the right lane line of the lane line on which the specified target vehicle is located.

Specifying the target vehicle in conjunction with equation (6) and equation (7)The transverse position of the central line of the lane line is y_cAs in equation (8); the track line course angle theta of the central line of the lane_cAs shown in formula (9).

y_c＝(y_l+y_r)/2 (8)

θ_c≈c₁+2c₂x+3c₃x² (9)

In formula (9), c₁＝(c_1l+c_1r)/2，c₂＝(c_2l+c_2r)/2，c₃＝(c_3l+c_3r)/2。

Step S503: for a vehicle transverse position and a vehicle course angle of a specified target vehicle in the input motion trajectory, calculating a transverse position deviation between the vehicle transverse position and a center line transverse position, and calculating a course angle deviation between the vehicle course angle and a road line course angle.

It should be noted that the input motion trajectory includes a plurality of trajectory points, and each trajectory point corresponds to a vehicle lateral position and a vehicle heading angle of the specified target vehicle.

For a vehicle transverse position and a vehicle course angle of a specified target vehicle corresponding to a certain track point, calculating a transverse position deviation dy (namely a transverse position deviation vector) between the vehicle transverse position and a central line transverse position through a formula (10), and calculating a course angle deviation d theta (namely a course angle deviation vector) between the vehicle course angle and a road line course angle through a formula (11).

dy＝y_t-y_c (10)

dθ＝θ_t-θ_c (11)

In the formula (10), y_tVehicle lateral position, y, corresponding to a certain track point_cIs the centerline transverse position. In formula (11), θ_tFor a vehicle heading angle, θ, corresponding to a certain track point_cIs the course angle of the road.

Through the formula (10) and the formula (11), the transverse position deviation between the transverse position of the vehicle corresponding to each track point in the input motion track and the transverse position of the central line can be calculated and obtained, and the course angle deviation between the course angle of the vehicle corresponding to each track point in the input motion track and the course angle of the road line can be calculated and obtained; namely, a plurality of lateral position deviations and a plurality of heading angle deviations are calculated.

Step S504: and dividing the transverse position deviation by the lane width to normalize the transverse position deviation, averaging all the normalized transverse position deviations, and determining to obtain a normalized average value of the transverse position deviation.

In the process of specifically implementing step S504, the lateral position deviation is normalized according to the lane width of the lane where the specified target vehicle is located, which is obtained by real-time detection, to obtain a normalized value of the lateral position deviation. Specifically, the lateral position deviation is normalized by dividing the lateral position deviation by the lane width, and the normalized value of the lateral position deviation is dy _ norm — dy/L, where dy is the lateral position deviation and L is the lane width.

As can be seen from the above, each track point in the input motion trajectory is calculated to obtain a corresponding lateral position deviation, and after the lateral position deviation is normalized, a normalized value of the lateral position deviation corresponding to each track point, that is, a plurality of normalized values of the lateral position deviation, can be obtained.

And averaging all the normalized transverse position deviations, or averaging the normalized values of all the transverse position deviations, and determining to obtain the normalized average value of the transverse position deviations.

Step S505: and dividing the course angle deviation by the maximum course angle of the specified target vehicle to normalize the course angle deviation, averaging all the normalized course angle deviations, and determining to obtain a normalized average value of the course angle deviation.

It should be noted that the maximum heading angle of the specified target vehicle is calculated based on the vehicle speed of the specified target vehicle. Specifically, the maximum lateral acceleration of the specified target vehicle is set, and the maximum heading angle is calculated in real time according to the vehicle speed of the specified target vehicle.

In the process of implementing step S505 specifically, the course angle deviation is normalized according to the maximum course angle of the specified target vehicle obtained by real-time calculation, so as to obtain a normalized value of the course angle deviation. Specifically, the course angle deviation is divided by the maximum course angle of the specified target vehicle to normalize the course angle deviation, and a normalized value d theta _ norm of the course angle deviation is obtained, wherein d theta is the course angle deviation, and theta is the maximum course angle.

According to the above contents, each track point in the input motion track is calculated to obtain a corresponding course angle deviation, and after the course angle deviation is normalized, a normalized value of the course angle deviation corresponding to each track point can be obtained, so that a plurality of normalized values of the course angle deviations can be obtained.

And averaging all the normalized course angle deviations, or averaging the normalized values of all the course angle deviations, and determining to obtain the normalized average value of the course angle deviations.

In the embodiment of the invention, the motion trail to be processed and the historical motion trail are combined to obtain the input motion trail. And calculating the normalized mean value of the transverse position deviation and the course angle deviation according to the lane line expression and the input motion track. Determining a driving intention by using the calculated normalized mean value, and predicting a vehicle motion track based on the driving intention and information of the surrounding environment, wherein the parameters used for predicting the vehicle motion track are less, and the requirement on hardware computing power is lower; and the vehicle motion track is predicted in a hierarchical mode, when the prediction result is abnormal, which link is abnormal can be quickly positioned, and the abnormity is timely solved to improve the safety.

To better explain the contents of the method for predicting the vehicle motion trail in the above embodiments, a schematic diagram of a method for predicting the vehicle motion trail shown in fig. 6 is used for illustration.

Referring to fig. 6, chassis information of a vehicle (i.e., a host vehicle) is acquired through a vehicle-mounted bus 601, information such as a vehicle speed, an acceleration, a yaw rate, and the like of the host vehicle is acquired, and the acquired information is sent to a lane-change intention calculation module 603.

Detecting lane line information through a sensing system 602 and sending the lane line information to a vehicle motion track generation module 604 and a lane change intention calculation module 603; the method comprises the steps of screening out a specified target vehicle from detected target vehicles through a sensing system 602, sending current environment information of the specified target vehicle to a lane change intention calculation module 603, and sending historical information of the specified target vehicle, such as historical position, historical speed and the like, to a vehicle motion track generation module 604 and the lane change intention calculation module 603, wherein the historical information of the historical position, the historical speed and the like is acquired in a historical period.

The lane-change intention calculation module 603 calculates a lane-change intention (i.e., the above-mentioned final travel intention) of the specified target vehicle according to the received information and sends it to the vehicle motion trajectory generation module 604; the vehicle motion trajectory generation module 604 predicts the vehicle motion trajectory of the specified target vehicle based on the received information.

For details of the data processing in fig. 6, reference may be made to the contents shown in fig. 1 to fig. 5 in the above embodiments of the present invention, and details are not repeated here.

Corresponding to the method for predicting the vehicle motion trail provided by the embodiment of the invention, referring to fig. 7, the embodiment of the invention also provides a structural block diagram of a device for predicting the vehicle motion trail, wherein the device is mounted on a vehicle and comprises: a first determination unit 701, a processing unit 702, a calculation unit 703, a first prediction unit 704, a scanning unit 705, a second prediction unit 706, a second determination unit 707, and a third prediction unit 708;

a first determination unit 701 for determining a specified target vehicle from among the detected target vehicles.

In a specific implementation, the first determining unit 701 is specifically configured to: from all the detected target vehicles, the target vehicle with the transverse distance from the vehicle smaller than a first threshold value and the longitudinal distance from the vehicle smaller than a second threshold value is determined as the designated target vehicle.

The processing unit 702 is configured to determine to obtain an average kinematic parameter by using the absolute motion state of the specified target vehicle acquired in multiple history periods, and predict a to-be-processed motion trajectory of the specified target vehicle based on the average kinematic parameter.

It should be noted that the average kinematic parameters are used to describe the average motion state of the specified target vehicle in a plurality of history periods.

In a specific implementation, the processing unit 702 is specifically configured to: determining a time interval of a plurality of history periods; dividing the absolute motion state of the specified target vehicle collected in a plurality of historical periods by a time interval to obtain an average kinematic parameter; and processing the average kinematic parameters by using a kinematic model, and predicting the motion trail to be processed of the specified target vehicle.

The calculating unit 703 is configured to calculate a normalized mean value of the motion feature vector of the specified target vehicle based on the motion trajectory to be processed and the historical motion trajectory of the specified target vehicle.

The first prediction unit 704 is configured to map the normalized mean value to a preset value interval to obtain a driving intention value, and predict an initial driving intention according to the driving intention value.

The scanning unit 705 is configured to scan the surrounding environment of the specified target vehicle, obtain the lane type of the lane where the specified target vehicle is located, and obtain the obstacle vehicle information in the lane adjacent to the lane where the specified target vehicle is located.

In some embodiments, specifying the lane type of the lane in which the target vehicle is located includes: the lane line type of the left lane line and the lane line type of the right lane line; the lane type is: lane lines that are allowed to change lanes or lane lines that are not allowed to change lanes.

And a second prediction unit 706, configured to perform filtering processing on the initial driving intention by using the lane type and the obstacle vehicle information, and predict a final driving intention.

In a specific implementation, the initial driving intent is a left lane-changing intent, a right lane-changing intent, or a lane-keeping intent; the second prediction unit 706 is specifically configured to: determining a lane change condition which is met by a specified target vehicle by using the lane line type and the obstacle vehicle information, wherein the lane change condition at least comprises the following steps: a first condition for indicating that a right-hand lane change is permitted, a second condition for indicating that a left-hand lane change is permitted;

in the case where the initial travel intention is a left lane change intention, predicting that the final travel intention is a lane keeping intention when the specified target vehicle does not satisfy the second condition; predicting that the final driving intention is a left lane changing intention when the specified target vehicle meets the second condition;

in the case where the initial travel intention is a right lane change intention, predicting that the final travel intention is a lane keeping intention when the specified target vehicle does not satisfy the first condition; when the specified target vehicle satisfies the first condition, the final travel intention is predicted as the right lane change intention.

A second determination unit 707 for determining the lateral target position based on the final travel intention.

In a specific implementation, the final driving intent is a left lane-changing intent, a right lane-changing intent, or a lane-keeping intent; the second determination unit 707 is specifically configured to: determining the transverse position of the center line of a lane adjacent to the left of the lane where the specified target vehicle is located as a transverse target position under the condition that the final driving intention is a left lane changing intention; determining the transverse position of the center line of a lane adjacent to the right of the lane where the specified target vehicle is located as a transverse target position under the condition that the final driving intention is a right lane changing intention; in the case where the final travel intention is an intention to keep the lane, a center line lateral position of the lane in which the specified target vehicle is located is determined as a lateral target position.

A third prediction unit 708 for generating a vehicle motion trajectory specifying the target vehicle from the current position to the target position using the lateral target position and the average kinematic parameter.

In a specific implementation, the third prediction unit 708 is specifically configured to: generating a transverse moving track for the specified target vehicle to move to a transverse target position by using a preset track generation mode; generating a longitudinal movement track of the appointed target vehicle according to the average kinematics parameter; and predicting to obtain the vehicle motion track of the specified target vehicle from the current position to the target position by combining the transverse moving track and the longitudinal moving track.

In some embodiments, the preset trajectory generation mode is an equal proportion attenuation mode or a polynomial curve fitting mode; when the trajectory generation method is the equal proportional attenuation method, the generated lateral movement trajectorySee formula (3) above for the contents of the data points in (1); the contents of the data points in the generated longitudinal movement trajectory are referred to the above formula (4) and formula (5); combining the above equations (3) to (5), the trajectory position of the target designated vehicle at the k-th time in the predicted vehicle motion trajectory is (x)_k，y_k)。

Preferably, with reference to fig. 7, the calculation unit 703 includes: the combination subunit, the first calculation subunit, the second calculation subunit, the first processing subunit and the second processing subunit, and the execution principle of each subunit is as follows:

and the combination subunit is used for combining the motion trail to be processed and the pre-stored historical motion trail of the specified target vehicle to obtain an input motion trail.

The first calculating subunit is used for calculating the transverse position of the central line of the lane central line and the course angle of the lane central line corresponding to the input motion track by using a lane line expression;

and the second calculation subunit is used for calculating the transverse position deviation between the transverse position of the vehicle and the transverse position of the central line and calculating the course angle deviation between the course angle of the vehicle and the course angle of the road line for the vehicle transverse position and the vehicle course angle of the specified target vehicle in the input motion track.

And the first processing subunit is used for dividing the transverse position deviation by the lane width to normalize the transverse position deviation, averaging all the normalized transverse position deviations, and determining to obtain a normalized average value of the transverse position deviation.

And the second processing subunit is used for dividing the course angle deviation by the maximum course angle of the specified target vehicle to normalize the course angle deviation, averaging all the normalized course angle deviations, determining the normalized average of the course angle deviation, and calculating the maximum course angle of the specified target vehicle based on the speed of the specified target vehicle.

Accordingly, the first prediction unit 704 is specifically configured to: mapping the normalized mean value of the transverse position deviation to a preset value interval by using a nonlinear mapping function obtained based on an S-shaped function to obtain a first driving intention value, and mapping the normalized mean value of the course angle deviation to the preset value interval to obtain a second driving intention value;

and under the condition that the first driving intention value and the second driving intention value meet a left lane changing rule, predicting that the initial driving intention is a left lane changing intention, wherein the left lane changing rule is as follows: the first driving intention value is in a first left lane change value interval, and the second driving intention value is in a second left lane change value interval;

and under the condition that the first driving intention value and the second driving intention value meet a right lane changing rule, predicting that the initial driving intention is a right lane changing intention, wherein the right lane changing rule is as follows: the first driving intention value is in the first right lane change value interval, and the second driving intention value is in the second right lane change value interval;

In summary, embodiments of the present invention provide a method and an apparatus for predicting a vehicle motion trajectory, where a driving intention is obtained by calculating a historical motion trajectory and other parameters of a specified target vehicle, and then a vehicle motion trajectory is predicted according to the driving intention, and the predicted vehicle motion trajectory uses fewer parameters and has a lower requirement on hardware computation force; and the vehicle motion track is predicted in a hierarchical mode, when the prediction result is abnormal, which link is abnormal can be quickly positioned, and the abnormity is timely solved to improve the safety.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of predicting a vehicle motion locus, the method being applied to an apparatus for predicting a vehicle motion locus mounted in a vehicle, the method comprising:

determining a designated target vehicle from the detected target vehicles;

determining a lateral target position based on the final travel intent;

2. The method according to claim 1, wherein determining an average kinematic parameter using the absolute kinematic state of the designated target vehicle collected in a plurality of history periods, and predicting a trajectory of motion to be processed of the designated target vehicle based on the average kinematic parameter comprises:

determining a time interval of a plurality of history periods;

3. The method of claim 1, wherein calculating a normalized mean of motion feature vectors of the designated target vehicle based on the to-be-processed motion trajectory and a pre-stored historical motion trajectory of the designated target vehicle comprises:

4. The method of claim 3, wherein mapping the normalized mean value to a preset value interval to obtain a driving intention value, and predicting an initial driving intention according to the driving intention value comprises:

5. The method of claim 1, wherein the specifying the type of lane line of the lane in which the target vehicle is located comprises: the lane line type of the left lane line and the lane line type of the right lane line; the lane line types are as follows: lane lines that are allowed to change lanes or lane lines that are not allowed to change lanes.

6. The method of claim 1, wherein the initial driving intent is a left lane change intent, a right lane change intent, or a lane keeping intent;

7. The method of claim 1, wherein the final driving intent is a left lane change intent, a right lane change intent, or a lane keeping intent;

8. The method of any one of claims 1 to 7, wherein predicting a vehicle motion trajectory of the given target vehicle from a current position to a target position using the lateral target position and the average kinematic parameter comprises:

9. The method according to claim 8, wherein the preset trajectory generation mode is an equal proportion attenuation mode or a polynomial curve fitting mode;

when the trajectory generation method is the equal proportional attenuation method, the data point at the k-th time in the generated transverse movement trajectory is y_k＝αy_k-1，y_kAt the k-th timeDifference between the lateral position of the specified target vehicle and the lateral target position, 0<α<1；

The data point at the k-th time in the generated longitudinal movement track is

10. An apparatus for predicting a motion trajectory of a vehicle, the apparatus being mounted in a vehicle, the apparatus comprising: