CN113104041B

CN113104041B - Driving track prediction method and device, electronic equipment and storage medium

Info

Publication number: CN113104041B
Application number: CN202110502033.6A
Authority: CN
Inventors: 郑保山; 孙轩; 李天琪; 兰洪祥; 黄建筑
Original assignee: Horizon Shanghai Artificial Intelligence Technology Co Ltd
Current assignee: Horizon Shanghai Artificial Intelligence Technology Co Ltd
Priority date: 2021-05-08
Filing date: 2021-05-08
Publication date: 2022-11-04
Anticipated expiration: 2041-05-08
Also published as: CN113104041A

Abstract

A lane line reference line of a vehicle in the driving process is determined, an initial predicted track of the vehicle driving track is obtained according to state information of the vehicle, a weight parameter is calculated, the lane line reference line and the initial predicted track are subjected to weighted fusion according to the weight parameter, a final predicted track of the vehicle driving track is obtained, the final predicted track of the vehicle driving track is obtained through the weighted fusion of the lane line reference line and the initial predicted track, and the advantages of the lane line reference line and the initial predicted track are integrated, so that the accuracy of each position of the final predicted track of the vehicle driving track is improved, the future driving track is predicted more accurately, a judgment basis is provided for an auxiliary driving system, the accuracy of the auxiliary driving system is improved, the probability of potential safety hazards is reduced, and the driving safety is improved.

Description

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

Technical Field

The present disclosure relates to a driving assistance or automatic driving technology, and more particularly, to a driving trajectory prediction method, a trajectory prediction apparatus, an electronic device, and a computer-readable storage medium.

Background

The driving assistance technology is an active safety technology which can effectively improve the safety of the vehicle during running, and the prediction of the running area of the vehicle plays an important role in a driving assistance system. The prediction of the driving area of the vehicle can influence the selection of a target vehicle and is directly related to the performance of driving auxiliary systems such as a front collision early warning system, a self-adaptive cruise control system, an automatic emergency braking system and the like.

In many conventional predictions of the travel area of a vehicle, the travel path of the vehicle is predicted based on chassis information such as the steering wheel angle, yaw rate, and vehicle speed of the vehicle. The predicted travelling path predicted by the method has the problem that the accuracy is obviously reduced along with the increase of the distance, and meanwhile, the acquisition of the vehicle chassis information is obtained based on the measurement of the sensor, and the sensor has measurement errors, so that the calculated result has errors, the predicted travelling path (particularly at a close distance) can sway left and right, and the predicted travelling path is unstable.

Disclosure of Invention

The present disclosure is proposed to solve the above technical problems. The embodiment of the disclosure provides a driving track prediction method, a track prediction device, an electronic device and a computer readable storage medium, wherein a lane line reference line of a vehicle in a driving process is determined, an initial predicted track of a driving track of the vehicle is obtained according to state information of the vehicle, a weight parameter is calculated, the lane line reference line and the initial predicted track are subjected to weighted fusion according to the weight parameter to obtain a final predicted track of the driving track of the vehicle, the final predicted track of the driving track of the vehicle is obtained by utilizing the weighted fusion of the lane line reference line and the initial predicted track, and the advantages of the lane line reference line and the initial predicted track are integrated, so that the accuracy of the final predicted track of the driving track of the vehicle is improved.

According to an aspect of the present disclosure, there is provided a driving trajectory prediction method, including: determining a lane line reference line of a vehicle in the driving process; obtaining an initial predicted track of the vehicle driving track according to the state information of the vehicle; calculating weight parameters of the track points on the lane line reference line and the track points on the initial predicted track based on the track points on the lane line reference line and the distance between the track points on the initial predicted track and the current position of the vehicle; and based on the weight parameters, carrying out weighted fusion on the lane line reference line and the initial predicted track to obtain a final predicted track of the vehicle driving track.

According to another aspect of the present disclosure, there is provided a driving trajectory prediction apparatus including: the determining module is used for determining a lane line reference line of the vehicle in the driving process; the acquisition module is used for acquiring an initial predicted track of the vehicle driving track according to the state information of the vehicle; the calculation module is used for calculating weight parameters of the track points on the lane line reference line and the track points on the initial prediction track based on the track points on the lane line reference line and the distance between the track points on the initial prediction track and the current position of the vehicle; and the fusion module is used for weighting and fusing the lane line reference line and the initial predicted track based on the weight parameter to obtain a final predicted track of the vehicle driving track.

According to another aspect of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing any of the trajectory prediction methods described above.

According to another aspect of the present disclosure, there is provided an electronic device including: a processor; a memory for storing the processor-executable instructions; the processor is configured to execute any one of the trajectory prediction methods described above.

The embodiment of the disclosure provides a driving track prediction method, a track prediction device, an electronic device and a computer readable storage medium, wherein a lane line reference line of a vehicle in a driving process is determined, an initial predicted track of the driving track of the vehicle is obtained according to state information of the vehicle, a weight parameter is calculated, the lane line reference line and the initial predicted track are subjected to weighted fusion according to the weight parameter to obtain a final predicted track of the driving track of the vehicle, the final predicted track of the driving track of the vehicle is obtained by utilizing the weighted fusion of the lane line reference line and the initial predicted track, and the advantages of the lane line reference line and the initial predicted track are integrated to improve the accuracy of the final predicted track of the driving track of the vehicle.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent by describing in more detail embodiments of the present disclosure with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the principles of the disclosure and not to limit the disclosure. In the drawings, like reference numbers generally indicate like parts or steps.

Fig. 1 is a schematic application scenario diagram of a driving trajectory prediction system according to an exemplary embodiment of the present disclosure.

Fig. 2 is a schematic flowchart of a driving trajectory prediction method according to an exemplary embodiment of the present disclosure.

Fig. 3 is a flowchart illustrating a method for calculating a weight parameter according to an exemplary embodiment of the disclosure.

Fig. 4 is a flowchart illustrating a method for obtaining a final predicted trajectory according to another exemplary embodiment of the present disclosure.

Fig. 5 is a schematic structural diagram of a driving trajectory prediction apparatus according to an exemplary embodiment of the present disclosure.

Fig. 6 is a schematic structural diagram of a driving trajectory prediction apparatus according to another exemplary embodiment of the present disclosure.

Fig. 7 is a block diagram of an electronic device provided in an exemplary embodiment of the present disclosure.

Detailed Description

Hereinafter, example embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.

Summary of the application

The present disclosure may be applied to any technical field using autonomous driving or assisted driving. For example, the embodiments of the present disclosure may be applied to a vehicle with a driving assistance function, which is used to avoid a similar traffic accident or minimize the severity of the accident when the accident occurs, during the driving of the vehicle, a traffic accident may be caused by an emergency such as a sudden change of a driving lane of the vehicle or a sudden change of a driving lane of another vehicle. However, the implementation of the driving assistance function needs to be based on the prediction of the future driving track of the vehicle, that is, the implementation of the driving assistance function is based on the prediction of the future driving track of the vehicle, so as to determine whether the vehicle has a safety hazard (i.e., whether there is a possibility of a traffic accident) on the future driving track, and thus take corresponding measures, such as a front collision warning, an adaptive cruise control, an automatic emergency braking, and the like, according to the occurrence state and the occurrence probability of the safety hazard.

Generally, a method for predicting the future trajectory of a vehicle, such as a forward collision warning system, an adaptive cruise control system, and an automatic emergency braking system, is to calculate the real-time turning radius of the vehicle based on the real-time chassis information (including steering wheel angle, yaw rate, real-time vehicle speed, etc.) of the vehicle, and fit to obtain a curve as the future trajectory of the vehicle. The method for predicting the future driving track is based on real-time chassis information, and equipment such as a sensor for acquiring the chassis information has certain time delay or error, so that the prediction precision is not high, the chassis information is changed in real time, namely the acquired chassis information at two adjacent moments is likely to have great difference, so that a curve obtained by fitting is also great difference, the future driving track of the vehicle is uncertain in left and right swing, an auxiliary driving system is difficult to accurately take correct measures, in addition, the error between the curve obtained by fitting and the real track of the vehicle is increased along with the increase of the distance from the vehicle, and the prediction result at a position far away from the vehicle is inaccurate.

In order to determine the accurate intervention time of the assistant driving system, the accuracy of the future predicted driving track needs to be higher, so that the assistant driving system can be ensured to intervene at a proper time to avoid potential safety hazards or reduce the severity of accidents, and the problem of reduction of driving comfort caused by misoperation of the assistant driving system can be avoided.

In view of the above technical problems, the basic concept of the present disclosure is to provide a driving trajectory prediction method, a trajectory prediction device, an electronic device, and a computer-readable storage medium, in which a lane line reference line of a vehicle during driving is determined, an initial predicted trajectory of the vehicle driving trajectory is obtained according to state information of the vehicle, a weight parameter is calculated, the lane line reference line and the initial predicted trajectory are weighted and fused according to the weight parameter to obtain a final predicted trajectory of the vehicle driving trajectory, the final predicted trajectory of the vehicle driving trajectory is obtained by weighting and fusing the lane line reference line and the initial predicted trajectory, and advantages of the lane line reference line and the initial predicted trajectory are integrated to improve accuracy of each position of the final predicted trajectory of the vehicle driving trajectory, so as to more accurately predict a future driving trajectory, provide a basis for an auxiliary driving system, improve accuracy of the auxiliary driving system, further reduce probability of occurrence of potential safety hazards, and improve driving safety.

Having described the general principles of the present disclosure, various non-limiting embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings.

Exemplary System

The present disclosure may be applied to any autonomous or assisted driving system, such as the aforementioned forward collision warning system, adaptive cruise control system, automatic emergency braking system, and the like. Fig. 1 is a schematic application scenario diagram of a driving trajectory prediction system according to an exemplary embodiment of the present disclosure. As shown in fig. 1, a lane line reference line image may be acquired by an image acquisition device such as a camera and a lane line reference line (a vertical solid line in fig. 1) may be extracted from the lane line reference line image by an algorithm; and an initial predicted trajectory (a dashed trajectory in fig. 1) is predicted based on the state information of the vehicle (i.e., the current state of the vehicle during running, such as the vehicle speed, direction, etc.); and then carrying out weighted fusion according to the lane line reference line and the initial predicted track to obtain a final predicted track (a solid line track in fig. 1) of the vehicle running track. Because the lane line is an important reference line of the vehicle in the driving process, when the lane is not changed and the like, the vehicle usually can drive in the current lane (namely, the vehicle drives between two lane lines of the current lane), the lane line reference line can have a better reference meaning for the prediction of the long-range track of the vehicle, but has a poorer prediction effect on the short-range track, because the vehicle does not strictly drive according to the lane line in the driving process, if the driving track predicted by the lane line reference line is not smooth enough, the vehicle may have larger jitter. The initial predicted track obtained according to the state information of the vehicle is based on the state of the vehicle at the current moment, the initial predicted track is smooth, and the prediction precision for short distance is high, so that the lane line reference line and the initial predicted track are fused, the advantages of the lane line reference line and the initial predicted track can be integrated, the accuracy of each position (including short distance and long distance) of the final predicted track of the vehicle driving track is improved, the future driving track is predicted more accurately, a judgment basis is provided for an auxiliary driving system, the accuracy of the auxiliary driving system is improved, the probability of potential safety hazards is reduced, and the driving safety is improved.

Exemplary method

Fig. 2 is a schematic flowchart of a driving trajectory prediction method according to an exemplary embodiment of the present disclosure. The present embodiment may be applied to an electronic device, for example, a vehicle control unit of a vehicle with an automatic driving or driving assistance function, as shown in fig. 2, including the following steps:

step 110: and determining a lane line reference line of the vehicle in the driving process.

The vehicle in the present disclosure refers to a vehicle having an automatic driving or driving assistance function, and the vehicle usually travels in one lane (not including a traveling state during lane change) no matter whether a road is a straight line or a curved line, so that the vehicle can travel in the respective lanes by using a lane line as a reference line during traveling, thereby ensuring smooth and safe traffic. In the embodiment of the disclosure, a lane line reference line where a vehicle is located in a driving process is determined, and the lane line reference line is used as a basis for predicting the driving track of the vehicle, that is, the extending direction curve of the lane line is used as a reference line to predict the future driving track of the vehicle.

Step 120: and obtaining an initial predicted track of the vehicle driving track according to the state information of the vehicle.

The state information may include driving state parameters of the vehicle within the lane line, such as an offset amount of the vehicle within the current lane, an angle of the lane line reference line at the vehicle with the vehicle speed direction, a curvature of the vehicle driving track, a rate of change of the curvature. The offset of the vehicle in the current lane is the offset distance between the vehicle and the center line of the current lane (i.e. the above lane line reference line), the included angle between the lane line reference line and the vehicle speed direction at the vehicle is the offset angle between the vehicle driving instantaneous direction and the lane line reference line, the curvature of the vehicle driving track is the bending degree of the vehicle driving track, and the change rate of the curvature is the curvature derivation. The method comprises the steps of collecting real-time state information in the running process of a vehicle according to a sensor of a vehicle chassis, and obtaining an initial predicted track of the vehicle track according to the collected state information, namely predicting the future track of the vehicle according to the instantaneous state in the running process of the vehicle so as to obtain a smooth initial predicted track based on the instantaneous state.

Step 130: and respectively calculating the weight parameters of the track points on the lane line reference line and the track points on the initial prediction track based on the distances between the track points on the lane line reference line and the track points on the initial prediction track and the current position of the vehicle.

Since the initial predicted trajectory is accurate and smooth when the distance from the current position of the vehicle is close, and the accuracy of the initial predicted trajectory is reduced when the distance from the current position of the vehicle is far (even the initial predicted trajectory is completely different from the actual driving trajectory), it is necessary to fuse the initial predicted trajectory and the lane line reference line to improve the accuracy of the final predicted trajectory. Specifically, after the initial predicted trajectory and the lane line reference line are obtained, a plurality of trajectory points may be selected from the initial predicted trajectory and the lane line reference line, for example, a plurality of trajectory points may be respectively selected at equal intervals on the initial predicted trajectory and the lane line reference line, and the weight parameters of the initial predicted trajectory and the lane line reference line are calculated based on the trajectory points, or the trajectory points may be used as data for weighted fusion of the initial predicted trajectory and the lane line reference line. And calculating to obtain the weights of the track points on the initial prediction track and the track points on the lane line reference line according to the distances between the track points on the initial prediction track and the current position of the vehicle, wherein the track points on the lane line reference line and the track points on the initial prediction track are corresponding track points, the corresponding track points are a pair of track points which are equal in coordinates along the extending direction of the lane line and are respectively positioned on the initial prediction track and the lane line reference line, and namely the corresponding track points are equal in distance from the current position of the vehicle along the extending direction of the lane line. For example, the weight of a track point on the initial predicted track is inversely related to the distance value from the track point to the current position of the vehicle, and the weight of a track point on the lane line reference line is positively related to the distance value from the track point to the current position of the vehicle.

Step 140: and weighting and fusing the lane line reference line and the initial predicted track based on the weight parameters to obtain the final predicted track of the vehicle driving track.

Based on the set weight parameters, the lane line reference line and the corresponding track points in the initial predicted track are subjected to weighted fusion to obtain a plurality of track points on the final predicted track, then the final predicted track of the vehicle driving track can be obtained based on the plurality of track points on the final predicted track, and for example, the plurality of track points on the final predicted track are fitted to obtain the final predicted track.

The method comprises the steps of determining a lane line reference line of a vehicle in the driving process, obtaining an initial predicted track of the vehicle track according to state information of the vehicle, calculating a weight parameter, performing weighted fusion on the lane line reference line and the initial predicted track according to the weight parameter to obtain a final predicted track of the vehicle track, obtaining the final predicted track of the vehicle track by performing weighted fusion on the lane line reference line and the initial predicted track, and integrating the advantages of the lane line reference line and the initial predicted track to improve the accuracy of each position of the final predicted track of the vehicle track, so that the future track is predicted more accurately, a judgment basis is provided for an auxiliary driving system, the accuracy of the auxiliary driving system is improved, the probability of potential safety hazards is reduced, and the driving safety is improved.

In one embodiment, the lane line reference line image may be acquired by a camera disposed in front of the vehicle. By arranging the camera, the lane line reference line image in front of the vehicle can be accurately and effectively tracked and acquired in real time, and the lane line reference line acquired by the camera can be identified by using an image identification unit or module (such as an image identification chip arranged in a vehicle control unit) so as to extract the information of the lane line reference line and provide accurate lane line reference line information for subsequent driving track prediction.

In one embodiment, if the vehicle does not switch lanes, acquiring information of two lane lines of the lane where the vehicle is located currently, and acquiring a lane line reference line according to the information of the two lane lines; if the vehicle switches lanes, calculating the information of the two lane lines of the lane after the vehicle switches according to the information of the two lane lines of the lane where the vehicle is currently located, and obtaining a lane line reference line according to the information of the two lane lines of the lane after the vehicle switches. When the vehicle switches lanes, the lane after switching needs to be used as the driving lane of the vehicle, so that the future driving track of the vehicle can be accurately predicted only by obtaining the lane line reference line according to the lane after switching.

In one embodiment, the two lane lines of the lane in which the vehicle is located may be averaged to obtain the lane line reference line. Since each lane includes two lane lines, left and right, and it is safest that the vehicle travels near the middle position within the lane, the vehicle also generally travels near the middle position within the lane. Therefore, the curve of the middle position of the lane can be obtained by averaging the two lane lines of the lane, the driving track of the vehicle can be more accurately predicted by taking the curve as the reference line of the lane lines, and the driving safety can be ensured as much as possible.

In one embodiment, the initial predicted trajectory may be a cubic polynomial curve; and the polynomial coefficients of the cubic polynomial curve are from low to high according to the degree: offset, tangent of angle, half of curvature, rate of change of curvature. I.e. the initial predicted trajectory is y = p ₀ +p ₁ *x+p ₂ *x ² +p ₃ *x ³ Wherein p is ₀ As an offset, p ₁ Tangent value, p, of the angle between the lane line and the speed direction ₂ Is one half of the real-time curvature, p ₃ Is the rate of change of curvature. The initial prediction track is set to be a cubic polynomial curve, so that the initial prediction track can meet the requirements of smoothness, and can be close to a straight line as much as possible to reduce the difference between the initial prediction track and a lane line reference line. The present application is in view of the followingThe method has the advantages that a cubic polynomial curve is selected while the vehicle track is required to be predicted and the calculation difficulty is met, and it should be understood that the initial predicted track can be set to be a cubic polynomial curve or a higher-order polynomial curve.

In one embodiment, the initial predicted trajectory may be obtained from the state information using a kalman filter. The Kalman filter is a device which utilizes a linear system state equation and carries out optimal estimation on the system state through inputting and outputting observation data of the system. Because the observation data includes the influence of noise and interference in the system, kalman filtering is a data processing technology for removing noise and restoring real data. According to the embodiment of the disclosure, the real-time state information of the vehicle is acquired in real time through the sensors and other devices of the vehicle, and the real-time state information contains noise interference, namely, a certain error exists between the real-time state information and the real state information of the vehicle, so that the real-time state information can be filtered by constructing a Kalman filter, the noise interference is eliminated or reduced, and the prediction precision is improved.

Fig. 3 is a schematic flowchart of a method for calculating a weight parameter according to an exemplary embodiment of the present disclosure. As shown in fig. 3, the step 130 may include the following sub-steps:

step 131: and setting a first weight of the first sampling point based on any first sampling point on the initial predicted track.

The method comprises the steps of obtaining a plurality of first sampling points on an initial prediction track, setting a corresponding first weight for each first sampling point, and determining the first weight of each sampling point according to the distance between the sampling point and the current position of a vehicle.

Step 132: setting a second weight of a second sampling point on the lane line reference line based on the second sampling point corresponding to the first sampling point; and if the distance between the position of the first sampling point and the position of the corresponding second sampling point and the vehicle is less than a first preset distance, the first weight is greater than the second weight, and otherwise, the first weight is less than or equal to the second weight.

A plurality of second sampling points corresponding to the plurality of first sampling points are acquired on the lane line reference line, the distances between the first sampling points and the corresponding second sampling points and the vehicle are equal or approximately equal in the embodiment, and a plurality of second weights are set for the plurality of second sampling points. The setting of the first weight and the second weight may satisfy the following rule: and if the distance between the position of the first sampling point and the position of the corresponding second sampling point and the vehicle is less than a first preset distance, the first weight is greater than the second weight, otherwise, the first weight is less than or equal to the second weight. Setting a first weight of a first sampling point on the initial prediction track to be larger than a second weight of a second sampling point on a corresponding lane line reference line for a sampling point with a distance to the vehicle being smaller than a first preset distance; otherwise, setting a first weight of the first sampling point on the initial prediction track to be less than or equal to a second weight of the second sampling point on the corresponding lane line reference line, wherein the first preset distance can be selected according to the requirements of the actual application scene. Namely, when the distance between the initial predicted track and the current position of the vehicle is close, the weight of the initial predicted track is larger, the weight of the lane line reference line is smaller, and when the distance between the initial predicted track and the current position of the vehicle is farther, the weight of the initial predicted track is smaller, the weight of the lane line reference line is larger, so that the accuracy of the final predicted track when the distance between the final predicted track and the current position of the vehicle is close and farther can be higher.

In an embodiment, a sum of the first weight and the corresponding second weight is a predetermined constant. I.e. the sum of the first weight of the first sample point and the second weight of the corresponding second sample point is a predetermined constant, e.g. 1, etc. After the first weight is obtained, the second weight can be simply calculated according to the preset constant, so that the calculation speed is increased on the premise of ensuring the accuracy of the final predicted track.

In an embodiment, the weight of the kth point on the initial prediction trajectory may be calculated in a specific manner:

wherein N is an integer greater than 3;

correspondingly, the weight of the k-th point on the lane line reference line is 1-omega (k).

Fig. 4 is a flowchart illustrating a method for obtaining a final predicted trajectory according to another exemplary embodiment of the present disclosure. As shown in fig. 4, step 140 may include the following sub-steps:

step 141: and respectively and correspondingly taking N points on the lane line reference line and the initial prediction track.

The number of the first sampling points on the obtained initial prediction track and the number of the second sampling points on the corresponding lane line reference line can be specifically selected according to the requirements of an actual application scene, in order to accurately reflect the accuracy of each position on the predicted driving track, N points can be respectively and correspondingly taken on the lane curve and the initial prediction curve at equal intervals, namely N points are respectively and correspondingly taken on the lane curve and the initial prediction curve according to a second preset distance, wherein the second preset distance can be selected according to the requirements of the actual application scene, the number N of the selected sampling points can also be selected according to the requirements of the actual application scene, the number of the sampling points cannot be too small to ensure that the sampling points can accurately reflect the information of the lane line reference line and the initial prediction track, and overfitting cannot be caused by too much number, for example, one sampling point can be selected every 10 meters, and N =13.

Step 142: and respectively carrying out weighted summation on the N points on the lane line reference line and the corresponding N points on the initial prediction track to obtain N fusion points.

Based on the respective weights of the N sampling points on the lane line reference line and the corresponding N sampling points on the initial prediction track, the N sampling points on the lane line reference line and the corresponding N sampling points on the initial prediction track are respectively subjected to weighted summation to obtain N fusion points, namely each fusion point is obtained through the weighted summation of the corresponding two sampling points.

Step 143: and fitting to obtain a final predicted track according to the N fusion points.

And after N fused points are obtained, fitting the N fused points to obtain a final predicted track. In order to ensure better fusion of the lane line reference line and the initial predicted trajectory, the acquired lane line reference line may also be fitted according to the expression form of the initial predicted trajectory to form a cubic polynomial, and the final predicted trajectory obtained by fitting may also be subjected to a least square method to obtain a cubic polynomial. By acquiring the multiple fusion points and fitting the multiple fusion points to obtain the final predicted trajectory, the calculation process can be simplified, and the accuracy of the final predicted trajectory can be ensured.

In an embodiment, if the vehicle does not switch lanes, the expression of the k-th fusion point may specifically be: x (k) = x ₁ (k)＝x ₂ (k)，y(k)＝ω(k)*y ₁ (k)+(1-ω(k))*y ₂ (k) In that respect Wherein, (x (k), y (k)) is the coordinate value of the k-th fusion point in the observation coordinate system, (x) ₁ (k)，y ₁ (k) (x) is a coordinate value of the kth point on the initial predicted trajectory in the observation coordinate system ₂ (k)，y ₂ (k) Is a coordinate value of the k-th point on the lane line reference line in the observation coordinate system. The observation coordinate system is a coordinate system established according to the current direction of the vehicle by taking the current position of the vehicle as a coordinate origin, the k-th fusion point is calculated through the coordinate value of the k-th point on the initial prediction track under the observation coordinate system and the coordinate value of the k-th point on the lane line reference line under the observation coordinate system, and the final prediction track is obtained by fitting according to the plurality of fusion points, so that the calculation process can be simplified. When the vehicle does not change lanes, the transverse coordinates (the coordinates of the driving direction) of the vehicle are directly obtained by weighting the predicted initial track and the lane line reference line, and the prediction accuracy can be ensured.

In an embodiment, if the vehicle switches lanes, the expression of the k-th fusion point may specifically be: x (k) = x ₁ (k)＝x ₂ (k)，y(k)＝ω(k)*y ₁ (k)+(1-ω(k))*y ₂ (k) + c0+ L/2. Wherein c0 is the offset of the vehicle in the current lane, L is the lane width, and the domestic value is generally 3.5 meters. When the vehicle changes lanes, the longitudinal coordinate of the vehicle needs to be added with the width information of the lane, so that the vehicle can change lanes stably and can run safely in the lane after lane changing.

Exemplary devices

Fig. 5 is a schematic structural diagram of a driving trajectory prediction apparatus according to an exemplary embodiment of the present disclosure. As shown in fig. 5, the trajectory prediction device 40 includes: the determining module 41 is used for determining a lane line reference line of the vehicle in the driving process; the obtaining module 42 is configured to obtain an initial predicted trajectory of a vehicle trajectory according to the state information of the vehicle; a calculating module 43, configured to calculate weight parameters of the track points on the lane line reference line and the track points on the initial predicted track based on the track points on the lane line reference line and the distance between the track points on the initial predicted track and the current position of the vehicle; and the fusion module 44 is configured to perform weighted fusion on the lane line reference line and the initial predicted trajectory based on the weight parameter to obtain a final predicted trajectory of the vehicle trajectory.

The driving track prediction device provided by the disclosure determines a lane line reference line of a vehicle in a driving process through a determination module 41, obtains an initial predicted track of a vehicle driving track according to state information of the vehicle through an acquisition module 42, calculates a weight parameter through a calculation module 43, and performs weighted fusion on the lane line reference line and the initial predicted track through a fusion module 44 according to the weight parameter to obtain a final predicted track of the vehicle driving track.

In an embodiment, the determining module 41 may be further configured to: if the vehicle does not switch lanes, acquiring information of two lane lines of the lane where the vehicle is located currently, and acquiring a lane line reference line according to the information of the two lane lines; if the vehicle switches lanes, calculating the information of the two lane lines of the lane after the vehicle switches according to the information of the two lane lines of the lane where the vehicle is currently located, and obtaining a lane line reference line according to the information of the two lane lines of the lane after the vehicle switches.

In an embodiment, the determining module 41 may be further configured to: the two lane lines of the lane in which the vehicle is located may be averaged to obtain a lane line reference line.

In an embodiment, the obtaining module 42 may be further configured to: the initial prediction track is a cubic polynomial curve; and the polynomial coefficients of the cubic polynomial curve are respectively from low to high according to the degree: offset, tangent of angle, half of curvature, rate of change of curvature. I.e. the initial predicted trajectory is y = p ₀ +p ₁ *x+p ₂ *x ² +p ₃ *x ³ Wherein p is ₀ As an offset, p ₁ Tangent value, p, of the angle between the lane line and the speed direction ₂ Is one half of the real-time curvature, p ₃ Is the rate of change of curvature.

In an embodiment, the obtaining module 42 may be further configured to: and obtaining an initial prediction track according to the state information by using a Kalman filter.

Fig. 6 is a schematic structural diagram of a driving trajectory prediction apparatus according to another exemplary embodiment of the present disclosure. As shown in fig. 6, the calculation module 43 may include sub-modules: a first setting unit 431 configured to set a first weight of any first sample point on the initial predicted trajectory; a second setting unit 432 for setting a second weight of a second sampling point on the lane line reference line, the second sampling point corresponding to the first sampling point; and if the distance between the position of the first sampling point and the position of the corresponding second sampling point and the vehicle is less than a first preset distance, the first weight is greater than the second weight, and otherwise, the first weight is less than or equal to the second weight.

In an embodiment, the calculation module 43 may be further configured to: the sum of the first weight and the corresponding second weight is a preset constant.

In an embodiment, the calculation module 43 may be further configured to: the specific calculation method of the weight of the kth point on the initial prediction trajectory may be as follows:

wherein N is an integer greater than 3;

the weight of the corresponding k-th point on the lane line reference line is 1-omega (k).

In one embodiment, as shown in FIG. 6, the fusion module 44 may include sub-modules: the sampling unit 441 is configured to correspondingly take N points on the lane line reference line and the initial prediction track, where N is an integer greater than 3; a fusion unit 442, configured to perform weighted summation on the N points on the lane line reference line and the N points corresponding to the initial predicted trajectory, respectively, to obtain N fusion points; and a fitting unit 443, configured to fit to obtain a final predicted trajectory according to the N fusion points.

In an embodiment, the fusion module 44 may be further configured to: if the vehicle does not switch lanes, the expression of the k-th fusion point may specifically be: x (k) = x ₁ (k)＝x ₂ (k)，y(k)＝ω(k)*y ₁ (k)+(1-ω(k))*y ₂ (k) In that respect Wherein, (x (k), y (k)) is the coordinate value of the k-th fusion point in the observation coordinate system, (x) ₁ (k)，y ₁ (k) Is the coordinate value of the k-th point on the initial predicted trajectory in the observation coordinate system, (x) ₂ (k)，y ₂ (k) Is a coordinate value of the kth point on the lane line reference line in the observation coordinate system.

In an embodiment, the fusion module 44 may be further configured to: if the vehicle switches lanes, the expression of the k-th fusion point may specifically be: x (k) = x ₁ (k)＝x ₂ (k)，y(k)＝ω(k)*y ₁ (k)+(1-ω(k))*y ₂ (k) + c0+ L/2. Wherein c0 is the offset of the vehicle in the current lane, L is the lane width, and the domestic value is generally 3.5 meters.

Exemplary electronic device

Next, an electronic apparatus according to an embodiment of the present disclosure is described with reference to fig. 7. The electronic device may be either or both of the first device and the second device, or a stand-alone device separate from them, which stand-alone device may communicate with the first device and the second device to receive the acquired input signals therefrom.

FIG. 7 illustrates a block diagram of an electronic device in accordance with an embodiment of the disclosure.

As shown in fig. 7, the electronic device 10 includes one or more processors 11 and memory 12.

The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by processor 11 to implement the trajectory prediction methods of the various embodiments of the present disclosure described above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.

In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other form of connection mechanism (not shown).

For example, when the electronic device is a first device or a second device, the input means 13 may be a camera or a video camera for capturing an input signal of an image. When the electronic device is a stand-alone device, the input means 13 may be a communication network connector for receiving the acquired input signals from the first device and the second device.

The input device 13 may also include, for example, a keyboard, a mouse, and the like.

The output device 14 may output various information including the determined distance information, direction information, and the like to the outside. The output devices 14 may include, for example, a display, speakers, printer, and a communication network and its connected remote output devices, among others.

Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present disclosure are shown in fig. 7, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device 10 may include any other suitable components depending on the particular application.

Exemplary computer program product and computer-readable storage Medium

In addition to the above-described methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the trajectory prediction method according to various embodiments of the present disclosure described in the "exemplary methods" section above of this specification.

The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform steps in a trajectory prediction method according to various embodiments of the present disclosure described in the "exemplary methods" section above of this specification.

The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable 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.

The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure will be described in detail with reference to specific details.

The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably herein. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".

It is also noted that in the apparatus, devices, and methods of the present disclosure, various components or steps may be broken down and/or re-combined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.

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

The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims

1. A driving track prediction method is applied to a vehicle and comprises the following steps:

determining a lane line reference line of the vehicle in the driving process;

obtaining an initial predicted track of the vehicle running track according to state information representing the vehicle running state;

setting a first weight of any first sampling point on the initial prediction track and a second weight of a second sampling point corresponding to the first sampling point on the lane line reference line based on the track point on the lane line reference line and the distance between the track point on the initial prediction track and the current position of the vehicle; the first weight is larger than the second weight under the condition that the distance between the position of the first sampling point and the position of the corresponding second sampling point and the current position of the vehicle is smaller than a first preset distance; and

and weighting and fusing the lane line reference line and the initial predicted track based on the first weight and the second weight to obtain a final predicted track of the vehicle trajectory.

2. The trajectory prediction method according to claim 1, further comprising:

and under the condition that the distance between the position of the first sampling point and the position of the corresponding second sampling point and the current position of the vehicle is greater than a first preset distance, the first weight is less than or equal to the second weight.

3. The trajectory prediction method according to claim 2, wherein a sum of the first weight and the corresponding second weight is a preset constant.

4. The trajectory prediction method according to claim 1, wherein determining a lane line reference line of the vehicle during travel comprises:

if the vehicle does not switch lanes, acquiring information of two lane lines of the lane where the vehicle is located currently; and

and obtaining the lane line reference line according to the information of the two lane lines.

5. The trajectory prediction method according to claim 1, wherein determining a lane line reference line of the vehicle during travel comprises:

if the vehicle switches lanes, calculating two lane line information of the lanes switched by the vehicle according to the two lane line information of the current lane; and

and obtaining the lane line reference line according to the information of the two lane lines after the lane is switched.

6. The trajectory prediction method according to claim 2, wherein the state information includes an offset amount of the vehicle in a current lane, an angle of the lane line reference line with a vehicle speed direction at the current vehicle, a curvature of the vehicle travel trajectory, and a rate of change of the curvature.

7. The trajectory prediction method of claim 1, wherein the weighted fusion of the lane line reference line and the initial predicted trajectory to obtain a final predicted trajectory of the vehicle trajectory comprises:

respectively and correspondingly taking N points on the lane line reference line and the initial prediction track;

respectively carrying out weighted summation on the N points on the lane line reference line and the corresponding N points on the initial prediction track to obtain N fusion points; and

fitting to obtain the final predicted track according to the N fusion points;

wherein N is an integer greater than 3.

8. A driving track prediction device is applied to a vehicle and comprises:

the determining module is used for determining a lane line reference line of the vehicle in the driving process;

the acquisition module is used for acquiring an initial predicted track of the vehicle running track according to state information representing the running state of the vehicle;

the calculation module is used for setting a first weight of any first sampling point on the initial prediction track and a second weight of a second sampling point corresponding to the first sampling point on the lane line reference line based on the track point on the lane line reference line and the distance between the track point on the initial prediction track and the current position of the vehicle; the first weight is larger than the second weight under the condition that the distance between the position of the first sampling point and the position of the corresponding second sampling point and the current position of the vehicle is smaller than a first preset distance; and

and the fusion module is used for performing weighted fusion on the lane line reference line and the initial predicted track based on the first weight and the second weight to obtain a final predicted track of the vehicle driving track.

9. A computer-readable storage medium, the storage medium storing a computer program for executing the trajectory prediction method according to any one of claims 1 to 7.

10. An electronic device, the electronic device comprising:

a processor;

a memory for storing the processor-executable instructions;

the processor is configured to perform the trajectory prediction method of any one of claims 1 to 7.