CN115465295B - Method and device for predicting future track of intersection vehicle, vehicle and storage medium - Google Patents

Method and device for predicting future track of intersection vehicle, vehicle and storage medium Download PDF

Info

Publication number
CN115465295B
CN115465295B CN202211116954.XA CN202211116954A CN115465295B CN 115465295 B CN115465295 B CN 115465295B CN 202211116954 A CN202211116954 A CN 202211116954A CN 115465295 B CN115465295 B CN 115465295B
Authority
CN
China
Prior art keywords
passable
path
target vehicle
paths
intention
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202211116954.XA
Other languages
Chinese (zh)
Other versions
CN115465295A (en
Inventor
贺刚
汪哲文
邱利宏
张鸿杰
周晓宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Changan Automobile Co Ltd
Original Assignee
Chongqing Changan Automobile Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chongqing Changan Automobile Co Ltd filed Critical Chongqing Changan Automobile Co Ltd
Priority to CN202211116954.XA priority Critical patent/CN115465295B/en
Publication of CN115465295A publication Critical patent/CN115465295A/en
Application granted granted Critical
Publication of CN115465295B publication Critical patent/CN115465295B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • B60W60/00276—Planning or execution of driving tasks using trajectory prediction for other traffic participants for two or more other traffic participants
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • B60W60/00272—Planning or execution of driving tasks using trajectory prediction for other traffic participants relying on extrapolation of current movement
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • B60W60/00274—Planning or execution of driving tasks using trajectory prediction for other traffic participants considering possible movement changes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/408—Radar; Laser, e.g. lidar
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4044—Direction of movement, e.g. backwards
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to a method and a device for predicting future tracks of vehicles at an intersection, the vehicles and a storage medium, wherein the method comprises the following steps: determining a plurality of passable paths at the current intersection; calculating at least one driving parameter from the target vehicle to each passable path according to the path information of each passable path; and determining a passable path with a driving intention based on at least one driving parameter, predicting a plurality of predicted driving tracks of the target vehicle, determining a cost function of each predicted driving track, obtaining an optimal predicted driving track in the plurality of predicted driving tracks, and taking the optimal predicted driving track as a predicted result of a future track. The method and the device can be used for predicting the future planned track of the road-side vehicle, are simple and reliable in calculation, do not need to depend on a large amount of data, have low calculation force requirements, and can comprehensively consider the comfort, timeliness and safety of the track.

Description

Method and device for predicting future track of intersection vehicle, vehicle and storage medium
Technical Field
The application relates to the technical field of automatic driving, in particular to a method and a device for predicting future tracks of vehicles at an intersection, the vehicles and a storage medium.
Background
The automatic driving system has great dependence on the surrounding environment of the vehicle, such as a map and a target vehicle, the position of the target vehicle must be accurately identified to effectively avoid collision, the safety of the vehicle and passengers is ensured, when the target vehicle runs in a relatively regular environment, the movement track of the target vehicle can be easily predicted, but if the target vehicle runs at an intersection with a plurality of passable directions, the running direction of the target is difficult to accurately judge, and the future track of the target is difficult to predict.
In the related art, a data-driven machine learning algorithm can be adopted to predict the intention and judge the track at the vehicle intersection by establishing a model, however, the related art needs to rely on a large amount of data to improve the accuracy of the model, has higher requirements on data and calculation force, and is difficult to actively correct to obtain a desired result when the model output is inconsistent with the self-expectation, so that the improvement is needed.
Disclosure of Invention
The application provides a method, a device, a vehicle and a storage medium for predicting future tracks of vehicles at an intersection, which are used for solving the technical problems that in the related art, a large amount of data is needed to be relied on to improve the accuracy of a model, the requirements on data and calculation force are high, and the model output is difficult to actively correct when not consistent with the self expectation.
An embodiment of a first aspect of the present application provides a method for predicting a future track of a vehicle at an intersection, including the steps of: determining a plurality of passable paths at the current intersection; calculating at least one driving parameter from the target vehicle to each passable path according to the path information of each passable path; and determining a passable path with a running intention based on the at least one running parameter, predicting a plurality of predicted running tracks of the target vehicle, determining a cost function of each predicted running track, obtaining an optimal predicted running track in the plurality of predicted running tracks, and taking the optimal predicted running track as a predicted result of a future track.
According to the technical means, the intersection information can be processed into the running of a plurality of paths, a plurality of predicted running tracks of the target vehicle are predicted based on the trafficable paths with the running intention, and then the optimal predicted running track is obtained, so that the future planning track of the intersection vehicle is predicted, the calculation is simple and reliable, a large amount of data is not needed, the calculation force requirement is low, and the comfort, timeliness and safety of the track can be comprehensively considered.
Optionally, in one embodiment of the present application, the determining, based on the at least one driving parameter, a passable path with a driving intention includes: predicting the nearest passable path to the target vehicle after a preset time period based on the at least one running parameter, wherein if a plurality of the nearest passable paths exist and one passable path has a passable vehicle, the one passable path is the passable path with the running intention; if the nearest passable paths are multiple and at least two passable paths have passing vehicles, determining the passable paths with the driving intention according to the steering intention of the target vehicle; if the nearest passable path is a plurality of passable paths, the at least two passable paths have passing vehicles and the steering intention does not exist, taking a path closest to the original path of the target vehicle as the passable path with the driving intention; if the nearest passable path is a plurality of passable paths and no passable path exists for passing vehicles, determining the passable path with the driving intention according to the steering intention of the target vehicle; if the latest passable path is a plurality of passable paths, no passable path has a passable vehicle and no steering intention exists, determining the passable path with the driving intention according to the current state of the passable street lamp at the current intersection; and if the nearest passable path is a plurality of passable paths, no passable path exists in a passable vehicle, no steering intention exists, and the current state is not perceived, taking a path closest to the original path of the target vehicle as the passable path with the driving intention.
According to the technical means, the intersection information can be processed into a plurality of paths, and judgment of the passable paths can be performed based on different conditions.
Optionally, in one embodiment of the present application, the taking the path closest to the original path of the target vehicle as the passable path with the driving intention includes: acquiring a fitting curve of the original path; and calculating the distance between the passable path and the fitting curve, and taking the path with the smallest square mean value of the distance as the nearest path.
According to the technical means, the embodiment of the application can obtain the nearest path through calculation, and the calculation is simple and reliable without consuming a large amount of calculation force.
Optionally, in one embodiment of the present application, the predicting a plurality of predicted travel tracks of the target vehicle includes: establishing a Frenet coordinate system based on the passable path with the driving intention; and solving a track equation of a preset 5-degree polynomial based on the Frenet coordinate system and at least one running parameter of the passable path with the running intention to obtain a plurality of predicted running tracks with different prediction times.
According to the technical means, the embodiment of the application can utilize a 5-degree polynomial planning method, so that the prediction of a plurality of running tracks in a prediction time range is obtained.
Optionally, in an embodiment of the present application, the formula of the cost function is:
where w t represents the weight of the time dimension, w s represents the weight of the comfort dimension, d (t)' represents the comfort and safety of the target motion, and t represents time.
According to the technical means, the optimal target prediction track can be obtained through the embodiment of the application and the cost function.
An embodiment of a second aspect of the present application provides a device for predicting a future track of an intersection vehicle, including: the determining module is used for determining a plurality of passable paths at the current intersection; the calculation module is used for calculating at least one running parameter from the target vehicle to each passable path according to the path information of each passable path; and the prediction module is used for determining a passable path with a running intention based on the at least one running parameter, predicting a plurality of predicted running tracks of the target vehicle, determining a cost function of each predicted running track, obtaining an optimal predicted running track in the plurality of predicted running tracks, and taking the optimal predicted running track as a predicted result of a future track.
Optionally, in one embodiment of the present application, the prediction module includes: the prediction unit is used for predicting the nearest passable path to the target vehicle after a preset time period based on the at least one running parameter, wherein when a plurality of the nearest passable paths exist and one passable path has a passable vehicle, the one passable path is the passable path with the running intention; when the plurality of nearest passable paths exist and at least two passable paths have passing vehicles, determining the passable paths with the driving intention according to the steering intention of the target vehicle; when the nearest passable path is a plurality of passable paths, the at least two passable paths have passing vehicles and the steering intention does not exist, taking a path closest to the original path of the target vehicle as the passable path with the driving intention; when the nearest passable path is a plurality of passable paths and no passable path exists for passing vehicles, determining the passable path with the driving intention according to the steering intention of the target vehicle; when the latest passable path is a plurality of passable paths, no passable path has a passable vehicle and no steering intention exists, determining the passable path with the driving intention according to the current state of the passable street lamp at the current intersection; and when the latest passable path is a plurality of passable paths, no passable path exists in the passable vehicle, no steering intention exists, and the current state is not perceived, taking a path closest to the original path of the target vehicle as the passable path with the driving intention.
Optionally, in one embodiment of the present application, the prediction unit includes: the acquisition subunit is used for acquiring a fitting curve of the original path; and the calculating subunit is used for calculating the distance between the passable path and the fitting curve and taking the path with the smallest square mean value of the distance as the nearest path.
Optionally, in one embodiment of the present application, the prediction module includes: the establishing unit is used for establishing a Frenet coordinate system based on the passable path with the driving intention; and the calculation unit is used for solving a track equation of a preset 5-degree polynomial based on the Frenet coordinate system and at least one running parameter of the passable path with the running intention to obtain the plurality of predicted running tracks with different prediction times.
Optionally, in an embodiment of the present application, the formula of the cost function is:
where w t represents the weight of the time dimension, w s represents the weight of the comfort dimension, d (t)' represents the comfort and safety of the target motion, and t represents time.
An embodiment of a third aspect of the present application provides a vehicle including: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to realize the method for predicting the future track of the crossing vehicle according to the embodiment.
A fourth aspect of the present application provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the method of predicting a future trajectory of an intersection vehicle as above.
The embodiment of the application has the beneficial effects that:
(1) The embodiment of the application can process the intersection information into a plurality of paths, and further obtain the optimal predicted running track through calculation so as to meet the automatic driving requirement;
(2) The embodiment of the application can utilize a 5-degree polynomial planning method to obtain the prediction of a plurality of running tracks in a prediction time range, and obtain the optimal predicted running track based on a cost function, has simple and reliable calculation, does not need to consume a large amount of calculation force, and can comprehensively consider the comfort, timeliness and safety of the track.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flowchart of a method for predicting future trajectories of vehicles at an intersection according to an embodiment of the present application;
FIG. 2 is a schematic illustration of a passable path at an intersection of a method of predicting future trajectories of vehicles at the intersection in accordance with one embodiment of the application;
FIG. 3 is a single-path vehicular prediction schematic diagram of a method of predicting future trajectories of intersection vehicles according to one embodiment of the application;
FIG. 4 is a schematic diagram of a method for predicting future trajectories of intersection vehicles with multiple paths and a target vehicle turning on a right turn light according to one embodiment of the application;
FIG. 5 is a schematic diagram of a path selected to be closest to the original path by a method for predicting future trajectories of vehicles at an intersection according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a plurality of trajectories relative to a reference path plan of a method of predicting a future trajectory of an intersection vehicle in accordance with one embodiment of the present application;
FIG. 7 is a flow chart of a method of predicting future trajectories of vehicles at an intersection in accordance with an embodiment of the present application;
fig. 8 is a schematic structural diagram of a prediction apparatus for future track of an intersection vehicle according to an embodiment of the present application;
fig. 9 is a schematic structural view of a vehicle according to an embodiment of the present application.
Wherein, 10-predicting device of future track of crossing vehicle; 100-determination module, 200-calculation module, 300-prediction module.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
The following describes a method, a device, a vehicle and a storage medium for predicting future trajectories of crossing vehicles according to embodiments of the present application with reference to the accompanying drawings. Aiming at the technical problems that in the related technology mentioned in the background technology center, a large amount of data is required to improve the accuracy of a model, the requirements on data and calculation force are higher, and the model output is not consistent with the self expectation, and active correction is difficult to carry out, the application provides a method for predicting the future track of an intersection vehicle. Therefore, the technical problems that in the related technology, a large amount of data is needed to be relied on to improve the accuracy of the model, the requirements on data and calculation force are high, and when the model output is inconsistent with the self expectation, active correction is difficult to carry out are solved.
Specifically, fig. 1 is a schematic flow chart of a method for predicting a future track of an intersection vehicle according to an embodiment of the present application.
As shown in fig. 1, the method for predicting the future track of the intersection vehicle comprises the following steps:
in step S101, a plurality of traversable paths at the current intersection are determined.
In the actual execution process, the embodiment of the application can process the intersection information into a plurality of paths to determine a plurality of passable paths at the current intersection.
For example, as shown in fig. 2, the embodiment of the present application may convert the map semantics into a form of a plurality of trafficable paths which are understandable by an algorithm according to the information given by the high-precision map, where each path may be composed of a plurality of points, where the original source of the points is the high-precision map, and when the distance between the two points is too large, the embodiment of the present application may perform linear interpolation on the points, so as to ensure that the distance between the two points does not exceed a preset distance, such as 1 meter.
In step S102, at least one travel parameter of the target vehicle to each travelable path is calculated from the path information of each travelable path.
As one possible implementation manner, the embodiment of the present application may calculate at least one driving parameter of the target vehicle to each passable path based on multiple path information, such as calculating tangential and normal positions, speeds, and accelerations of the target vehicle to each path using kalman filtering.
Specifically, the embodiment of the application can obtain the position information of the target vehicle according to the sensor, such as a camera, a radar and the like, and further find the nearest projection point of the target vehicle on each path, thereby obtaining the normal distance of the target vehicle relative to each path according to the projection point and the target position information.
Further, based on the obtained normal distance, the embodiment of the application can obtain the normal speed and acceleration of the target vehicle relative to each path by using a kalman filtering algorithm, wherein the calculation formula can be as follows:
The prediction process comprises the following steps:
xk＝Fk*xk-1+Bk*uk，
the measuring process comprises the following steps:
x′k＝xk+K′*(zk-Hk*xk)，
P′k＝Pk-K′*Hk*Pk，
Wherein x k is a three-dimensional array formed by the normal distance, the speed and the acceleration of the target vehicle, F k is a prediction matrix, B k is a control matrix, u k is a control vector, P k is a covariance matrix, Q k is covariance noise, H k is sensor data dimension, R k is sensor noise, z k is sensor data, and K' is Kalman gain.
Meanwhile, according to the speed information V x and V y of the target vehicle obtained by the sensor, the tangential speed of the target vehicle relative to each path can be obtained by using the Pythagorean theorem, wherein the tangential speed is far greater than the normal speed, and then the tangential acceleration of the target vehicle can be obtained by using Kalman filtering.
In step S103, a passable path with a driving intention is determined based on at least one driving parameter, a plurality of predicted driving trajectories of the target vehicle are predicted, a cost function of each predicted driving trajectory is determined, an optimal predicted driving trajectory among the plurality of predicted driving trajectories is obtained, and the optimal predicted driving trajectory is used as a predicted result of a future trajectory.
In some embodiments, the embodiment of the application can determine the passable path of the target vehicle with the driving intention by using at least one obtained driving parameter, namely the tangential direction, the normal direction position, the speed and the acceleration of the target vehicle to each path, so as to predict a plurality of predicted driving tracks of the target vehicle within a preset duration range, determine a cost function of each predicted driving track, obtain the optimal predicted driving track through the cost function, realize the prediction of the future track of the intersection vehicle by comprehensively considering the comfort, timeliness and safety of the track, and ensure that the obtained predicted track is stable and reliable.
Optionally, in one embodiment of the present application, determining the passable path with the driving intention based on the at least one driving parameter includes: predicting the nearest passable path to the target vehicle after the preset time length based on at least one running parameter, wherein if a plurality of nearest passable paths exist and one passable path has a passing vehicle, one passable path is a passable path with a running intention; if the nearest passable paths are multiple and at least two passable paths have passing vehicles, determining the passable paths with the running intention according to the steering intention of the target vehicle; if the nearest passable paths are a plurality of passable paths, at least two passable paths have passing vehicles and no steering intention exists, taking the path closest to the original path of the target vehicle as the passable path with the driving intention; if the nearest passable paths are multiple and no passable paths exist for passing vehicles, determining the passable paths with the running intention according to the steering intention of the target vehicle; if the latest passable path is a plurality of passable paths, no passable vehicles exist in the passable paths and no steering intention exists, determining the passable path with the driving intention according to the current state of the passing street lamp at the current intersection; if the nearest passable path is a plurality of passable paths, no passable path exists in the passable vehicle, no steering intention exists, and the current state is not perceived, the path closest to the original path of the target vehicle is taken as the passable path with the driving intention.
In the actual execution process, the embodiment of the application can predict the preset time length by utilizing the normal distance, the speed and the acceleration of the target vehicle to each path, for example, the path with the nearest distance to the target vehicle after 2s can be judged as the driving intention of the target vehicle.
If the situation that the distances of a plurality of paths are the same exists at the intersection, the embodiment of the application can correspondingly judge through the following judgment logic:
as shown in fig. 3, when only one of the paths with the same distance has a vehicle passing, the embodiment of the application can default that the target vehicle selects the same path to advance;
as shown in fig. 4, when a plurality of paths with the same distance have vehicles to pass through, if the sensor recognizes that the target vehicle is in a state that the left turn/right turn lamp is turned on, the embodiment of the application can determine that the target vehicle selects the leftmost path when the left turn lamp is turned on, and determine that the target vehicle selects the rightmost path when the right turn lamp is turned on;
As shown in fig. 5, when a plurality of paths with the same distance have vehicles to pass and the sensor recognizes that the target vehicle turns on the turn signal, the embodiment of the application can judge that the target vehicle selects the path closest to the original path to advance;
When no vehicle runs in the paths with the same distances, and at the moment, if the sensor recognizes that the target vehicle is in a state that the left turn light/right turn light is turned on, the embodiment of the application can judge that the target vehicle selects the leftmost path when the left turn light is turned on and judges that the target vehicle selects the rightmost path when the right turn light is turned on;
When no vehicle runs in the paths in the same distance, and at the moment, if the target vehicle does not turn on the steering lamp and the sensor can identify the traffic light state, the embodiment of the application can judge that the target vehicle selects the path in the green light state to advance;
When no vehicle runs in the paths with the same distance, if the target vehicle does not turn on the turn signal lamp and the sensor does not sense the traffic light state, the embodiment of the application can judge that the target vehicle selects the path closest to the original path to advance.
In addition, the embodiment of the application can acquire the actual lane information based on the high-precision map, so as to determine the lane information of the target vehicle, such as left turn/turn lanes, straight lanes, right turn lanes and the like of the target vehicle.
Optionally, in one embodiment of the present application, the path closest to the original path of the target vehicle is taken as a passable path with a traveling intention, including: obtaining a fitting curve of an original path; and calculating the distance between the passable path and the fitted curve, and taking the path with the smallest square mean value of the distance as the nearest path.
The process of using the route closest to the original route of the target vehicle as the passable route having the traveling intention may be as follows:
According to the embodiment of the application, the fitting curve of the original path of the target vehicle can be obtained based on the positioning data points of the target vehicle obtained by the high-precision map, and as shown in fig. 5, the path closest to the original path can be defined as the path with the smallest square average value of the distance of the fitting curve to the history track of the target vehicle.
Optionally, in one embodiment of the present application, predicting a plurality of predicted travel tracks of the target vehicle includes: establishing a Frenet coordinate system based on a passable path with driving intention; and solving a track equation of a preset 5-degree polynomial based on the Frenet coordinate system and at least one running parameter of the passable path with the running intention to obtain a plurality of predicted running tracks with different prediction times.
As a possible implementation manner, the embodiment of the application can establish a Frenet coordinate system according to a predicted path of the target vehicle after predicting the path, uniformly accelerate forward prediction in an arc direction according to the obtained tangential speed and acceleration, and obtain a plurality of predicted driving tracks with different comfortableness and timeliness according to an initial normal distance, speed and acceleration, a normal distance, speed and acceleration at a termination moment, and a predicted time t in a normal direction.
Specifically, as shown in fig. 6, the embodiment of the present application may solve a trajectory equation based on a preset 5 th order polynomial to obtain a5 th order equation including 6 unknowns, and by setting different times t, the embodiment of the present application may obtain predicted trajectories with different comfortableness and timeliness, where the trajectory equation is as follows:
d(t)＝a0+a1*t+a2*t2+a3*t3+a4*t4+a5*t5,
According to the embodiment of the application, all 6 unknowns of a 0～a5 can be solved through 6 known quantities, namely, the predicted track of the target is determined.
Optionally, in one embodiment of the present application, the cost function is formulated as:
where w t represents the weight of the time dimension, w s represents the weight of the comfort dimension, d (t)' represents the comfort and safety of the target motion, and t represents time.
In the actual execution process, the embodiment of the application can further determine the cost function of each predicted running track through the plurality of predicted running tracks of the target vehicle with different predicted times, which are obtained through the steps, so as to obtain the optimal predicted running track in the plurality of predicted running tracks, and take the optimal predicted running track as the predicted result of the future track.
Wherein, the cost function may be as follows:
Wherein w t represents the weight of the time dimension, w s represents the weight of the comfort dimension, the smaller the result obtained by w s is, the better the comprehensiveness of the predicted track is represented, d (t)' represents the comfort and safety of the target motion, and t represents the time.
Meanwhile, after solving, the embodiment of the application can replace the track with the minimum cost function as the predicted track to output, so as to obtain the optimal predicted running track.
The working principle of the method for predicting the future track of the intersection vehicle according to the embodiment of the application is described in detail with reference to fig. 2 to 7.
As shown in fig. 7, an embodiment of the present application may include the steps of:
Step S701: the intersection information is processed into a plurality of paths. According to the embodiment of the application, the map semantics can be converted into a plurality of trafficable paths which can be understood by an algorithm according to the information given by the high-definition map, wherein each path can be composed of a plurality of points, the original sources of the points are the high-definition map, and when the distance between the two points is overlarge, the points can be subjected to linear interpolation, so that the distance between the two points is ensured not to exceed a preset distance, such as 1 meter.
Step S702: motion information of the vehicle relative to the path is calculated. According to the embodiment of the application, the position information of the target vehicle can be obtained according to the sensor, such as a camera, a radar and the like, and then the nearest projection point of the target vehicle on each path is found, so that the normal distance of the target vehicle relative to each path is obtained according to the projection point and the target position information.
Further, based on the obtained normal distance, the embodiment of the application can obtain the normal speed and acceleration of the target vehicle relative to each path by using a kalman filtering algorithm, wherein the calculation formula can be as follows:
The prediction process comprises the following steps:
xk＝Fk*xk-1+Bk*uk，
the measuring process comprises the following steps:
x′k＝xk+K′*(zk-Hk*xk)，
P′k＝Pk-K′*Hk*Pk，
Wherein x k is a three-dimensional array formed by the normal distance, the speed and the acceleration of the target vehicle, F k is a prediction matrix, B k is a control matrix, u k is a control vector, P k is a covariance matrix, Q k is covariance noise, H k is sensor data dimension, R k is sensor noise, z k is sensor data, and K' is Kalman gain.
Meanwhile, according to the speed information V x and V y of the target vehicle obtained by the sensor, the tangential speed of the target vehicle relative to each path can be obtained by using the Pythagorean theorem, wherein the tangential speed is far greater than the normal speed, and then the tangential acceleration of the target vehicle can be obtained by using Kalman filtering.
Step S703: the travel path of the target vehicle is predicted. In the actual execution process, the embodiment of the application can predict the preset time length by utilizing the normal distance, the speed and the acceleration of the target vehicle to each path, for example, the path with the nearest distance to the target vehicle after 2s can be judged as the driving intention of the target vehicle.
If the situation that the distances of a plurality of paths are the same exists at the intersection, the embodiment of the application can correspondingly judge through the following judgment logic:
as shown in fig. 3, when only one of the paths with the same distance has a vehicle passing, the embodiment of the application can default that the target vehicle selects the same path to advance;
as shown in fig. 4, when a plurality of paths with the same distance have vehicles to pass through, if the sensor recognizes that the target vehicle is in a state that the left turn/right turn lamp is turned on, the embodiment of the application can determine that the target vehicle selects the leftmost path when the left turn lamp is turned on, and determine that the target vehicle selects the rightmost path when the right turn lamp is turned on;
As shown in fig. 5, when a plurality of paths with the same distance have vehicles to pass and the sensor recognizes that the target vehicle turns on the turn signal, the embodiment of the application can judge that the target vehicle selects the path closest to the original path to advance;
When no vehicle runs in the paths with the same distances, and at the moment, if the sensor recognizes that the target vehicle is in a state that the left turn light/right turn light is turned on, the embodiment of the application can judge that the target vehicle selects the leftmost path when the left turn light is turned on and judges that the target vehicle selects the rightmost path when the right turn light is turned on;
When no vehicle runs in the paths in the same distance, and at the moment, if the target vehicle does not turn on the steering lamp and the sensor can identify the traffic light state, the embodiment of the application can judge that the target vehicle selects the path in the green light state to advance;
When no vehicle runs in the paths with the same distance, if the target vehicle does not turn on the turn signal lamp and the sensor does not sense the traffic light state, the embodiment of the application can judge that the target vehicle selects the path closest to the original path to advance.
The process of using the route closest to the original route of the target vehicle as the passable route having the traveling intention may be as follows:
The embodiment of the application can obtain the fitting curve of the original path of the target vehicle based on the positioning data points of the target vehicle, and as shown in fig. 5, the embodiment of the application can define the path closest to the original path as the path with the smallest square average value of the fitting curve distance with the history track of the target vehicle.
In addition, the embodiment of the application can acquire the actual lane information based on the high-precision map, so as to determine the lane information of the target vehicle, such as left turn/turn lanes, straight lanes, right turn lanes and the like of the target vehicle.
Step S704: and predicting the possible track of the multi-item target car by using a 5-degree polynomial. According to the method and the device, after the running path of the target vehicle is predicted, a Frenet coordinate system is established according to the path, the forward prediction is uniformly accelerated in the arc direction according to the obtained tangential speed and acceleration, the normal distance, the speed and the acceleration at the normal direction according to the initial normal distance, the initial speed and the initial acceleration, the normal distance, the normal speed and the initial acceleration at the termination moment and the prediction time t, and a plurality of prediction running tracks with different comfortableness and timeliness are obtained based on different prediction times t.
Specifically, as shown in fig. 6, the embodiment of the present application may solve a trajectory equation based on a preset 5 th order polynomial to obtain a5 th order equation including 6 unknowns, and by setting different times t, the embodiment of the present application may obtain predicted trajectories with different comfortableness and timeliness, where the trajectory equation is as follows:
d(t)＝a0+a1*t+a2*t2+a3*t3+a4*t4+a5*t5,
According to the embodiment of the application, all 6 unknowns of a 0～a5 can be solved through 6 known quantities, namely, the predicted track of the target is determined.
Step S705: and selecting the optimal track as a prediction result. According to the embodiment of the application, the cost function of each predicted running track can be determined through the plurality of predicted running tracks of the target vehicle with different predicted times obtained through the steps, so that the optimal predicted running track in the plurality of predicted running tracks is obtained, and the optimal predicted running track is used as a predicted result of a future track.
Wherein, the cost function may be as follows:
Wherein w t represents the weight of the time dimension, w s represents the weight of the comfort dimension, the smaller the result obtained by w s is, the better the comprehensiveness of the predicted track is represented, d (t)' represents the comfort and safety of the target motion, and t represents the time.
Meanwhile, after solving, the embodiment of the application can replace the track with the minimum cost function as the predicted track to output, so as to obtain the optimal predicted running track.
According to the method for predicting the future track of the intersection vehicle, which is provided by the embodiment of the application, intersection information can be processed into a plurality of paths, and the running parameters from the target vehicle to each passable path are calculated according to the path information of each passable path, so that the passable path with the running intention is determined, the plurality of predicted running tracks of the target vehicle are predicted, and the optimal predicted running track is obtained through a cost function, so that the future planning track of the intersection vehicle is predicted, the calculation is simple and reliable, a large amount of data is not needed, the calculation force requirement is low, the comfortableness, the timeliness and the safety of the track can be comprehensively considered, and the driving experience of a user is improved. Therefore, the technical problems that in the related technology, a large amount of data is needed to be relied on to improve the accuracy of the model, the requirements on data and calculation force are high, and when the model output is inconsistent with the self expectation, active correction is difficult to carry out are solved.
Next, a prediction apparatus for future trajectories of intersection vehicles according to an embodiment of the present application will be described with reference to the accompanying drawings.
Fig. 8 is a block diagram schematically illustrating a prediction apparatus for future trajectories of vehicles at an intersection according to an embodiment of the present application.
As shown in fig. 8, the intersection vehicle future trajectory prediction apparatus 10 includes: a determination module 100, a calculation module 200, and a prediction module 300.
Specifically, the determining module 100 is configured to determine a plurality of passable paths at the current intersection.
A calculating module 200, configured to calculate at least one driving parameter from the target vehicle to each passable path according to the path information of each passable path.
The prediction module 300 is configured to determine a passable path with a driving intention based on at least one driving parameter, predict a plurality of predicted driving trajectories of a target vehicle, determine a cost function of each predicted driving trajectory, obtain an optimal predicted driving trajectory among the plurality of predicted driving trajectories, and use the optimal predicted driving trajectory as a predicted result of a future trajectory.
Alternatively, in one embodiment of the application, the prediction module 300 includes: and a prediction unit.
The prediction unit is used for predicting the passable path closest to the target vehicle after the preset time length based on at least one running parameter, wherein when a plurality of the nearest passable paths exist and one passable path has a passable vehicle, one passable path is a passable path with a running intention; when a plurality of nearest passable paths exist and at least two passable paths have passing vehicles, determining the passable paths with the running intention according to the steering intention of the target vehicle; when the nearest passable paths are a plurality of passable paths, at least two passable paths have passing vehicles and steering intention does not exist, taking a path closest to the original path of the target vehicle as a passable path with the driving intention; when the latest passable paths are multiple and no passable paths exist for passing vehicles, determining the passable paths with the running intention according to the steering intention of the target vehicle; when the latest passable paths are multiple, no passable paths have passing vehicles and no steering intention exists, determining passable paths with the driving intention according to the current state of the passing street lamp at the current intersection; when the latest passable path is a plurality of passable paths, no passable path exists in the passable vehicle, no steering intention exists, and the current state is not perceived, the path closest to the original path of the target vehicle is taken as the passable path with the driving intention.
Alternatively, in one embodiment of the present application, the prediction unit 300 includes: the acquisition subunit and the calculation subunit.
The acquisition subunit is used for acquiring the fitting curve of the original path.
And the calculation subunit is used for calculating the distance between the passable path and the fitting curve, and taking the path with the smallest square mean value of the distance as the nearest path.
Alternatively, in one embodiment of the application, the prediction module 300 includes: a setup unit and a calculation unit.
The establishment unit is used for establishing a Frenet coordinate system based on the passable path with the driving intention.
And the calculation unit is used for solving a track equation of a preset 5-degree polynomial based on the Frenet coordinate system and at least one running parameter of the passable path with the running intention to obtain a plurality of predicted running tracks with different prediction times.
Optionally, in one embodiment of the present application, the cost function is formulated as:
where w t represents the weight of the time dimension, w s represents the weight of the comfort dimension, d (t)' represents the comfort and safety of the target motion, and t represents time.
It should be noted that the explanation of the embodiment of the method for predicting the future track of the intersection vehicle is also applicable to the device for predicting the future track of the intersection vehicle in this embodiment, and will not be repeated here.
According to the prediction device for the future track of the intersection vehicle, which is provided by the embodiment of the application, intersection information can be processed into a plurality of paths, and the running parameters from the target vehicle to each passable path are calculated according to the path information of each passable path, so that the passable path with the running intention is determined, the plurality of predicted running tracks of the target vehicle are predicted, and the optimal predicted running track is obtained through the cost function, so that the prediction of the future planning track of the intersection vehicle is realized, the calculation is simple and reliable, a large amount of data is not needed, the calculation force requirement is low, the comfortableness, the timeliness and the safety of the track can be comprehensively considered, and the driving experience of a user is improved. Therefore, the technical problems that in the related technology, a large amount of data is needed to be relied on to improve the accuracy of the model, the requirements on data and calculation force are high, and when the model output is inconsistent with the self expectation, active correction is difficult to carry out are solved.
Fig. 9 is a schematic structural diagram of a vehicle according to an embodiment of the present application. The vehicle may include:
Memory 901, processor 902, and a computer program stored on memory 901 and executable on processor 902.
The processor 902 implements the method for predicting the future track of the intersection vehicle provided in the above embodiment when executing the program.
Further, the vehicle further includes:
A communication interface 903 for communication between the memory 901 and the processor 902.
Memory 901 for storing a computer program executable on processor 902.
Memory 901 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
If the memory 901, the processor 902, and the communication interface 903 are implemented independently, the communication interface 903, the memory 901, and the processor 902 may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (PERIPHERAL COMPONENT, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 9, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 901, the processor 902, and the communication interface 903 are integrated on a chip, the memory 901, the processor 902, and the communication interface 903 may communicate with each other through internal interfaces.
The processor 902 may be a central processing unit (Central Processing Unit, abbreviated as CPU), or an Application SPECIFIC INTEGRATED Circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the application.
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the intersection vehicle future trajectory prediction method as above.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.

Claims (8)

1. The method for predicting the future track of the intersection vehicle is characterized by comprising the following steps of:
determining a plurality of passable paths at the current intersection;
Calculating at least one running parameter from a target vehicle to each passable path according to the path information of each passable path, wherein the running parameter is tangential and normal positions, speeds and accelerations of the target vehicle to each path; and
Determining a passable path with a driving intention based on the at least one driving parameter, predicting a plurality of predicted driving tracks of the target vehicle, determining a cost function of each predicted driving track, obtaining an optimal predicted driving track in the plurality of predicted driving tracks, and taking the optimal predicted driving track as a predicted result of a future track;
the determining a passable path with a driving intention based on the at least one driving parameter includes:
Predicting the nearest passable path to the target vehicle after a preset time period based on the at least one driving parameter, wherein,
If the nearest passable path is a plurality of passable paths and a passable path has a passing vehicle, the passable path is the passable path with the driving intention;
If the nearest passable paths are multiple and at least two passable paths have passing vehicles, determining the passable paths with the driving intention according to the steering intention of the target vehicle;
if the nearest passable path is a plurality of passable paths, the at least two passable paths have passing vehicles and the steering intention does not exist, taking a path closest to the original path of the target vehicle as the passable path with the driving intention;
If the nearest passable path is a plurality of passable paths and no passable path exists for passing vehicles, determining the passable path with the driving intention according to the steering intention of the target vehicle;
if the latest passable path is a plurality of passable paths, no passable path has a passable vehicle and no steering intention exists, determining the passable path with the driving intention according to the current state of the passable street lamp at the current intersection;
If the nearest passable path is a plurality of passable paths, no passable path exists in a passing vehicle, no steering intention exists, and the current state is not perceived, taking a path closest to the original path of the target vehicle as the passable path with the driving intention;
the predicting a plurality of predicted travel tracks of the target vehicle includes:
establishing a Frenet coordinate system based on the passable path with the driving intention;
And solving a track equation of a preset 5-degree polynomial based on the Frenet coordinate system and at least one running parameter of the passable path with the running intention to obtain a plurality of predicted running tracks with different prediction times.
2. The method according to claim 1, wherein the taking the path closest to the original path of the target vehicle as the trafficable path with the traveling intention includes:
acquiring a fitting curve of the original path;
And calculating the distance between the passable path and the fitting curve, and taking the path with the smallest square mean value of the distance as the nearest path.
3. The method of claim 2, wherein the cost function is formulated as:
，
Wherein, The weight representing the dimension of time is given,The weight representing the dimension of comfort is given,Representing comfort and safety of target movement, and t represents time.
4. A prediction apparatus for future trajectories of vehicles at an intersection, comprising:
the determining module is used for determining a plurality of passable paths at the current intersection;
The calculation module is used for calculating at least one running parameter from the target vehicle to each passable path according to the path information of each passable path, wherein the running parameter is tangential and normal position, speed and acceleration of the target vehicle to each path; and
The prediction module is used for determining a passable path with a running intention based on the at least one running parameter, predicting a plurality of predicted running tracks of the target vehicle, determining a cost function of each predicted running track, obtaining an optimal predicted running track in the plurality of predicted running tracks, and taking the optimal predicted running track as a predicted result of a future track;
The prediction module includes:
A prediction unit for predicting a passable path nearest to the target vehicle after a preset time period based on the at least one driving parameter, wherein,
When the nearest passable path is a plurality of passable paths and one passable path has a passing vehicle, the one passable path is the passable path with the driving intention;
When the plurality of nearest passable paths exist and at least two passable paths have passing vehicles, determining the passable paths with the driving intention according to the steering intention of the target vehicle;
When the nearest passable path is a plurality of passable paths, the at least two passable paths have passing vehicles and the steering intention does not exist, taking a path closest to the original path of the target vehicle as the passable path with the driving intention;
when the nearest passable path is a plurality of passable paths and no passable path exists for passing vehicles, determining the passable path with the driving intention according to the steering intention of the target vehicle;
when the latest passable path is a plurality of passable paths, no passable path has a passable vehicle and no steering intention exists, determining the passable path with the driving intention according to the current state of the passable street lamp at the current intersection;
When the nearest passable path is a plurality of passable paths, no passable path exists in a passable vehicle, no steering intention exists, and the current state is not perceived, taking a path closest to an original path of the target vehicle as the passable path with the driving intention;
The establishing unit is used for establishing a Frenet coordinate system based on the passable path with the driving intention;
and the calculation unit is used for solving a track equation of a preset 5-degree polynomial based on the Frenet coordinate system and at least one running parameter of the passable path with the running intention to obtain the plurality of predicted running tracks with different prediction times.
5. The apparatus of claim 4, wherein the prediction unit comprises:
the acquisition subunit is used for acquiring a fitting curve of the original path;
And the calculating subunit is used for calculating the distance between the passable path and the fitting curve and taking the path with the smallest square mean value of the distance as the nearest path.
6. The apparatus of claim 5, wherein the cost function is formulated as:
，
Wherein, The weight representing the dimension of time is given,The weight representing the dimension of comfort is given,Representing comfort and safety of target movement, and t represents time.
7. A vehicle, characterized by comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of predicting future trajectories of intersection vehicles of any one of claims 1-3.
8. A computer-readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor for implementing a method of predicting a future trajectory of an intersection vehicle as claimed in any one of claims 1-3.
CN202211116954.XA 2022-09-14 2022-09-14 Method and device for predicting future track of intersection vehicle, vehicle and storage medium Active CN115465295B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211116954.XA CN115465295B (en) 2022-09-14 2022-09-14 Method and device for predicting future track of intersection vehicle, vehicle and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211116954.XA CN115465295B (en) 2022-09-14 2022-09-14 Method and device for predicting future track of intersection vehicle, vehicle and storage medium

Publications (2)

Publication Number Publication Date
CN115465295A CN115465295A (en) 2022-12-13
CN115465295B true CN115465295B (en) 2024-07-23

Family

ID=84332507

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211116954.XA Active CN115465295B (en) 2022-09-14 2022-09-14 Method and device for predicting future track of intersection vehicle, vehicle and storage medium

Country Status (1)

Country Link
CN (1) CN115465295B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114291116A (en) * 2022-01-24 2022-04-08 广州小鹏自动驾驶科技有限公司 Method and device for predicting track of surrounding vehicle, vehicle and storage medium

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102016217645B4 (en) * 2016-09-15 2023-01-19 Volkswagen Aktiengesellschaft Method for providing information about a probable driving intention of a vehicle
CN109739219B (en) * 2018-12-05 2022-02-11 阿波罗智能技术(北京)有限公司 Method, device and equipment for planning passing path and readable storage medium
CN109582022B (en) * 2018-12-20 2021-11-02 驭势科技（北京）有限公司 Automatic driving strategy decision system and method
CN109976355B (en) * 2019-04-26 2021-12-10 腾讯科技（深圳）有限公司 Trajectory planning method, system, device and storage medium
CN110796856B (en) * 2019-10-16 2022-03-25 腾讯科技（深圳）有限公司 Vehicle lane change intention prediction method and training method of lane change intention prediction network
CN112068545B (en) * 2020-07-23 2022-12-27 哈尔滨工业大学（深圳） Method and system for planning running track of unmanned vehicle at crossroad and storage medium
CN116261649A (en) * 2021-02-26 2023-06-13 华为技术有限公司 Vehicle driving intention prediction method, device, terminal and storage medium
CN114169181A (en) * 2021-12-31 2022-03-11 深圳一清创新科技有限公司 Method and device for target intention recognition and track prediction, unmanned vehicle and medium
CN114475429B (en) * 2022-02-21 2024-03-22 重庆长安汽车股份有限公司 Traffic light reminding method and system combined with user driving intention and automobile

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114291116A (en) * 2022-01-24 2022-04-08 广州小鹏自动驾驶科技有限公司 Method and device for predicting track of surrounding vehicle, vehicle and storage medium

Also Published As

Publication number Publication date
CN115465295A (en) 2022-12-13

Similar Documents

Publication Publication Date Title
CN109583151B (en) Method and device for predicting running track of vehicle
CN109760675B (en) Method, device, storage medium and terminal equipment for predicting vehicle track
US20200369293A1 (en) Autonomous driving apparatus and method
EP3694756B1 (en) Spiral curve based vertical parking planner system for autonomous driving vehicles
CN108340915B (en) Vehicle control device
US11614740B2 (en) Determining speeds for an autonomous vehicle
EP4242998A1 (en) Traffic stream information determination method and apparatus, electronic device and storage medium
JP5565303B2 (en) Driving support device and driving support method
US12036980B2 (en) Course prediction device, computer readable medium, and course prediction method
JP7139992B2 (en) CONTROL MAP INFORMATION EVALUATION DEVICE, CONTROL MAP INFORMATION EVALUATION METHOD, AND CONTROL PROGRAM
WO2020191709A1 (en) A qp spline path and spiral path based reference line smoothing method for autonomous driving
WO2020189056A1 (en) Map data output device
CN115465295B (en) Method and device for predicting future track of intersection vehicle, vehicle and storage medium
US11400955B2 (en) Multi-point enforced based stitch method to connect two smoothed reference lines
CN116443049A (en) Anti-collision method and device for automatic driving vehicle
CN115471524A (en) Intersection pedestrian track prediction method and device
CN117999204A (en) Vehicle control device, vehicle control method, and vehicle control system
EP3985641B1 (en) Travel assistance method and travel assistance device
JP7129269B2 (en) Driving history storage method and driving history storage device
CN113753073B (en) Vehicle speed control method, device, equipment and storage medium
US11242057B2 (en) Method for optimizing three-point turn of autonomous driving vehicles
RU2777141C1 (en) Traffic aid method and traffic aid device
US20240166239A1 (en) Trajectory planning for navigating small objects on road
CN118457598A (en) Method and device for calculating vehicle drivable area, vehicle and storage medium
CN118082882A (en) Vehicle transverse control method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant