CN117508232A - Track prediction method, device, equipment and medium for vehicle surrounding obstacle - Google Patents
Track prediction method, device, equipment and medium for vehicle surrounding obstacle Download PDFInfo
- Publication number
- CN117508232A CN117508232A CN202311763153.7A CN202311763153A CN117508232A CN 117508232 A CN117508232 A CN 117508232A CN 202311763153 A CN202311763153 A CN 202311763153A CN 117508232 A CN117508232 A CN 117508232A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- score
- steering
- driving lane
- candidate driving
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000015654 memory Effects 0.000 claims description 26
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
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
- B60W60/00272—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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/04—Traffic conditions
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of track prediction and discloses a track prediction method, a device, equipment and a medium for surrounding obstacles of a vehicle.
Description
Technical Field
The invention relates to the technical field of track prediction, in particular to a track prediction method, device, equipment and medium for surrounding obstacles of a vehicle.
Background
The core module of the unmanned system comprises sensing, prediction, regulation, high-precision positioning and the like. The prediction module is mainly responsible for predicting a future time track of a vehicle, a pedestrian and other obstacles according to the result of environmental perception, and issuing the prediction result to the decision planning or control module for use. Therefore, the real-time and accuracy of the trajectory prediction results of the surrounding obstacles will directly determine the safety of the unmanned vehicle and the traffic participants.
Currently, track prediction has comparatively determined scene studies such as lane change track prediction, crossroad track prediction, etc. in a structured road scene, and high-precision map information is referred to as prediction information for these specific scenes. However, in a park road scene, the road is complex in structure type, a high-precision map accurate to a lane level cannot be provided, and obstacles such as vehicles, electric vehicles, pedestrians around an unmanned vehicle do not travel on a structured road, so that the track prediction of the obstacles is very complex.
Therefore, the method for accurately predicting the obstacle track on the park road has great practical demands and practical significance.
Disclosure of Invention
In view of the above, the present invention provides a method, apparatus, device and medium for predicting a track of an obstacle around a vehicle, so as to solve the problem that in a road scene with a complex structure, the track of the obstacle cannot be accurately predicted.
In a first aspect, the present invention provides a trajectory prediction method of a vehicle surrounding obstacle, the method comprising:
when detecting that an obstacle positioned at an intersection exists around a vehicle, acquiring a plurality of candidate driving lanes and pose information of the obstacle;
for each candidate driving lane, based on track information and pose information of the current candidate driving lane, obtaining a lateral distance and a course angle deviation between the obstacle and the current candidate driving lane, and determining relative steering of the current candidate driving lane relative to the obstacle;
determining a steering score of the obstacle in each candidate driving lane based on the corresponding lateral distance of each candidate driving lane;
determining a track score of the current candidate driving lane according to the corresponding lateral distance, course angle deviation, relative steering and steering scores of the obstacles of the current candidate driving lane for each candidate driving lane;
and obtaining the driving track of the obstacle according to the track score and the pose information of each candidate driving lane.
When the situation that the obstacle located at the intersection exists around the vehicle is detected, the transverse distance, the course angle deviation, the relative steering and the steering score of the obstacle corresponding to each candidate driving lane are calculated through obtaining the plurality of candidate driving lanes and the pose information of the obstacle, the driving intention of the obstacle is quantitatively analyzed through the steering score of the obstacle, the track score of each candidate driving lane is obtained according to the transverse distance, the course angle deviation and the steering score of the relative steering and the steering score of the obstacle corresponding to each candidate driving lane, and the driving track of the obstacle is generated according to the track score and the pose information of each candidate driving lane, so that the driving track of the obstacle is predicted, guidance is provided for unmanned path planning and obstacle avoidance of a vehicle, and collision and friction between the unmanned vehicle and the obstacle are avoided.
In an alternative embodiment, the lateral distance comprises lateral distances at a plurality of moments in time; determining a track score of the current candidate driving lane according to the corresponding lateral distance, course angle deviation, relative steering and steering score of the obstacle of the current candidate driving lane, comprising:
obtaining a lateral distance variance value according to the lateral distances of the current candidate driving lane at a plurality of moments;
obtaining a target steering score and a steering matching score of the current candidate driving lane according to the relative steering and the steering score of the obstacle;
and obtaining the track score of the current candidate driving lane according to the transverse distance variance value, the course angle deviation, the target steering score and the steering matching score.
Therefore, the track score of the current candidate driving lane can be accurately calculated through the transverse distance variance value, the course angle deviation, the target steering score and the steering matching score, and the candidate driving lane is quantitatively evaluated so as to provide guidance for the selection of the possible target driving lane of the obstacle.
In an alternative embodiment, obtaining the track score of the current candidate driving lane according to the lateral distance variance value, the course angle deviation, the target steering score and the steering matching score includes:
and calculating the product of the course angle deviation and the preset proportion, and summing the product, the lateral distance variance value, the target steering score and the opposite number of the steering matching score to obtain the track score of the current candidate driving lane.
In an alternative embodiment, the obtaining the target steering score and the steering matching score of the current candidate driving lane according to the steering score of the relative steering and the obstacle comprises:
updating the steering score of the obstacle based on the relative steering to obtain a target steering score of the current candidate driving lane; the relative steering includes straight, left and right turns;
determining the driving intention of the obstacle according to the steering score of the obstacle; the travel intents include straight, left turn, and right turn;
the travel intention of the obstacle is compared with the relative steering, and a steering matching score of the current candidate travel lane is calculated based on the comparison result and the target steering score.
The target steering score and the steering matching score of the current candidate traveling lane are thus obtained from the steering scores of the relative steering and the obstacle, and the candidate traveling lane is evaluated by taking the traveling intention of the obstacle, the relative steering of the lane, and the degree of matching of the lane relative steering and the traveling intention of the obstacle.
In an alternative embodiment, obtaining the driving track of the obstacle according to the track score and the pose information of each candidate driving lane includes:
according to the track score of each candidate driving lane, determining the candidate driving lane with the minimum track score as a target driving lane of the obstacle;
and generating a driving track of the obstacle based on the position and the course angle of the obstacle in the target driving lane and the pose information.
The candidate driving lane with the minimum track score is determined to be the target driving lane of the obstacle, and the driving track of the obstacle is generated based on the target driving lane and the position and course angle of the obstacle in the pose information, so that the driving track prediction of the obstacle for a period of time in the future is realized, and references and guidance are provided for the path planning and obstacle avoidance of the unmanned vehicle.
In an alternative embodiment, the pose information includes pose information of the obstacle at a plurality of moments in time; for each candidate driving lane, based on the track information and the pose information of the current candidate driving lane, obtaining the lateral distance and the course angle deviation between the obstacle and the current candidate driving lane, and determining the relative steering of the current candidate driving lane relative to the obstacle, including:
for each candidate driving lane, a lateral distance between the obstacle and the current candidate driving lane at each time is obtained based on pose information of the obstacle at a plurality of times and track information of the current candidate driving lane.
And the transverse distance between the obstacle and the current candidate driving lane at each moment is obtained through the pose information of the obstacle at a plurality of moments and the track information of the current candidate driving lane, so that the position change between the obstacle and the lane is analyzed.
In an alternative embodiment, determining a steering score for an obstacle in each candidate travel lane based on a corresponding lateral distance for each candidate travel lane includes:
for each candidate driving lane, according to the transverse distance of the current candidate driving lane at a plurality of moments, traversing to calculate the difference between the transverse distance at the last moment and the transverse distance at each moment, and calculating the steering score of the obstacle in the current candidate driving lane according to the difference.
The steering score of the obstacle in the candidate driving lane is thus obtained by the lateral distances between the obstacle and the candidate driving lane at a plurality of moments, in order to analyze the steering intention of the obstacle at a later time.
In a second aspect, the present invention provides a trajectory prediction device of a vehicle surrounding obstacle, the device comprising:
an acquisition module for acquiring a plurality of candidate driving lanes and pose information of an obstacle when the obstacle located at the intersection exists around the vehicle;
the first processing module is used for obtaining the lateral distance and the course angle deviation between the obstacle and the current candidate driving lane based on the track information and the pose information of the current candidate driving lane aiming at each candidate driving lane, and determining the relative steering of the current candidate driving lane relative to the obstacle;
a second processing module for determining a steering score of the obstacle in each candidate driving lane based on the corresponding lateral distance of each candidate driving lane;
the third processing module is used for determining the track score of the current candidate driving lane according to the corresponding transverse distance, course angle deviation, relative steering and steering score of the obstacle of the current candidate driving lane for each candidate driving lane;
and the fourth processing module is used for obtaining the driving track of the obstacle according to the track score and the pose information of each candidate driving lane.
In a third aspect, the present invention provides a computer device comprising: the vehicle-surrounding obstacle trajectory prediction method according to the first aspect or any one of the embodiments thereof is provided with a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to thereby perform the trajectory prediction method of the vehicle-surrounding obstacle according to the first aspect or any one of the embodiments thereof.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon computer instructions for causing a computer to execute the trajectory prediction method of the vehicle-surrounding obstacle of the first aspect or any one of its corresponding embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a trajectory prediction method of a vehicle surrounding obstacle according to an embodiment of the present invention;
FIG. 2 is a schematic illustration of an intersection region according to an embodiment of the present invention;
fig. 3 is a flowchart of a trajectory prediction method of another vehicle surrounding obstacle according to an embodiment of the present invention;
FIG. 4 is a schematic illustration of the location of an obstacle and a candidate driving lane according to an embodiment of the invention;
fig. 5 is an application diagram of a trajectory prediction method of a vehicle surrounding obstacle according to an embodiment of the present invention;
fig. 6 is a block diagram of a configuration of a trajectory predicting device of a vehicle surrounding obstacle according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
According to an embodiment of the present invention, there is provided a trajectory prediction method embodiment of a vehicle surrounding obstacle, it being noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in an order different from that herein.
In this embodiment, a track prediction method for a vehicle surrounding obstacle is provided, which may be used for a computer device or an electronic device for predicting a track of a vehicle surrounding obstacle, such as a vehicle-mounted computer, a vehicle controller, etc., fig. 1 is a flowchart of a track prediction method for a vehicle surrounding obstacle according to an embodiment of the present invention, as shown in fig. 1, and the flowchart includes the following steps:
in step S101, when it is detected that an obstacle located at an intersection exists around a vehicle, a plurality of candidate driving lanes and pose information of the obstacle are acquired.
Specifically, the map is constructed by collecting the intersection area of the park as shown in fig. 2, the area is a polygonal area, and when the unmanned vehicle detects that an obstacle exists in the vicinity of the intersection area, pose information (including positions and course angles at a plurality of continuous moments) of the obstacle and candidate driving lanes for the obstacle to possibly drive next are obtained for a period of time, so that the driving track of the obstacle for a period of time in the future is predicted, and data guidance and reference are provided for path planning of the self-vehicle, and collision and friction with the obstacle around the vehicle are avoided. The obstacle may be a moving object such as a vehicle, a bicycle, or a pedestrian.
Step S102, for each candidate driving lane, based on the track information and the pose information of the current candidate driving lane, obtaining the lateral distance and the course angle deviation between the obstacle and the current candidate driving lane, and determining the relative steering of the current candidate driving lane relative to the obstacle.
Specifically, the lateral distance between the obstacle and the current candidate driving lane refers to a vertical lateral distance between the obstacle and the center line of the current candidate driving lane, and according to the positions of a plurality of continuous moments included in the obstacle pose information, the lateral distances respectively corresponding to the obstacle at the plurality of continuous moments can be obtained, so that the driving intention of the obstacle can be analyzed, and a basis is provided for the selection of the candidate driving lane.
Specifically, the relative steering (straight, left, right) of the lane may be determined based on the relative position of the lane and the obstacle. Taking two points closest to the vehicle in the track points of the candidate driving lanes and the last point along the driving direction of the vehicle in the track points of the candidate driving lanes, if the error of the orientation angle of the two closest points and the last point is smaller than a certain angle, considering the relative steering as straight running, otherwise judging the left and right orientations according to the vector relation among the three points, and detailed description of the related art can be referred to and will not be repeated here.
Specifically, the heading angle deviation α between the obstacle and the current candidate travel lane may be calculated according to the following formula:
α＝θ ve h-lane
wherein θ veh Represents the heading angle, theta, of the obstacle lane Indicating the heading angle of the lane.
Step S103, determining a steering score of the obstacle in each candidate driving lane based on the corresponding lateral distance of each candidate driving lane.
Specifically, the steering score of the obstacle in the corresponding candidate driving lane can be calculated through the corresponding transverse distances of the obstacle at a plurality of continuous moments, so that the driving intention of the obstacle is quantitatively analyzed, and a basis is provided for the selection of the candidate driving lane.
Step S104, for each candidate driving lane, determining the track score of the current candidate driving lane according to the corresponding lateral distance, heading angle deviation, relative steering and steering score of the obstacle of the current candidate driving lane.
Specifically, the track score of the candidate travel lane is calculated from several aspects of the lateral distance, the heading angle deviation, the relative steering of the lane, and the travel intention of the obstacle, thereby evaluating the candidate travel lane.
Step S105, the driving track of the obstacle is obtained according to the track score and the pose information of each candidate driving lane.
Specifically, after the track score of each candidate driving lane is obtained, the lane most likely to be driven by the obstacle in a period of time in the future can be determined, and then the driving track of the obstacle can be generated along the track position of the selected driving lane according to the current position and the course angle of the obstacle, so that guidance is provided for unmanned path planning and obstacle avoidance of the vehicle.
According to the track prediction method for the obstacles around the vehicle, when the obstacles located at the intersection are detected to exist around the vehicle, the corresponding lateral distance, heading angle deviation, relative steering and steering scores of the obstacles are calculated through the plurality of candidate driving lanes and pose information of the obstacles, the driving intention of the obstacles is quantitatively analyzed through the steering scores of the obstacles, track scores of the candidate driving lanes are obtained, the driving track of the obstacles is generated according to the track scores and the pose information of the candidate driving lanes, and therefore the driving track of the obstacles is predicted, and guidance is provided for unmanned path planning and obstacle avoidance of a vehicle.
In this embodiment, a track prediction method for a vehicle surrounding obstacle is provided, which may be used for a computer device or an electronic device for predicting a track of a vehicle surrounding obstacle, such as a vehicle-mounted computer, a vehicle controller, etc., and fig. 3 is a flowchart of a track prediction method for a vehicle surrounding obstacle according to an embodiment of the present invention, as shown in fig. 3, and the flowchart includes the following steps:
in step S301, when it is detected that an obstacle located at an intersection exists around the vehicle, a plurality of candidate driving lanes and pose information of the obstacle are acquired. Please refer to step S101 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S302, for each candidate driving lane, based on the track information and the pose information of the current candidate driving lane, obtaining the lateral distance and the course angle deviation between the obstacle and the current candidate driving lane, and determining the relative steering of the current candidate driving lane relative to the obstacle.
Specifically, the pose information includes pose information of the obstacle at a plurality of times, and for each candidate traveling lane, a lateral distance between the obstacle and the current candidate traveling lane at each time is obtained based on the pose information of the obstacle at the plurality of times and track information of the current candidate traveling lane.
In some alternative embodiments, as shown in fig. 4, the position of the obstacle at a certain moment is denoted as P (x 0, y 0), two points closest to the obstacle are selected on the lane line of the current candidate driving lane, and the positions of the two points are denoted as a (x 1, y 1) and B (x 2, y 2), so the following relationship exists:
the lateral distance d between the obstacle and the current candidate driving lane can be calculated according to the following formula:
and the transverse distance between the obstacle and the current candidate driving lane at each moment is obtained through the pose information of the obstacle at a plurality of moments and the track information of the current candidate driving lane, so that the position change between the obstacle and the lane is analyzed.
Step S303, determining a steering score of the obstacle in each candidate driving lane based on the corresponding lateral distance of each candidate driving lane.
Specifically, for each candidate driving lane, a difference between the lateral distance at the last time and the lateral distance at each time is calculated by traversing according to the lateral distances of the current candidate driving lane at a plurality of times, and a steering score of an obstacle in the current candidate driving lane is calculated according to the difference.
In some optional embodiments, the transverse distance at the last moment is recorded as dl, the transverse distances di corresponding to a plurality of moments within a certain time (for example, within 2 s) are traversed, when the difference of dl-di is greater than a certain threshold (which can be set according to practical application requirements, for example, 0.2 m), the steering score value is increased by ki (dl-di), and the steering score is obtained by traversing the transverse distances corresponding to all moments, wherein ki represents a proportionality coefficient, and the value can be set according to practical scenes.
The steering score of the obstacle in the candidate driving lane is thus obtained by the lateral distances between the obstacle and the candidate driving lane at a plurality of moments, in order to analyze the steering intention of the obstacle at a later time.
Step S304, for each candidate driving lane, determining the track score of the current candidate driving lane according to the corresponding lateral distance, heading angle deviation, relative steering and steering score of the obstacle of the current candidate driving lane.
Specifically, the lateral distance includes lateral distances at a plurality of moments, and the step S204 includes:
step S3041, obtaining a lateral distance variance value according to the lateral distances of the current candidate driving lane at a plurality of moments.
Specifically, the average value of the lateral distances at a plurality of times within a certain time (for example, within 2 seconds) can be calculated according to the following formula
Where n represents the number of times.
Then, according to the average value of the transverse distances d at a plurality of moments in a certain timeCalculating the lateral distance variance value sigma according to the following formula 2 ：
And step S3042, obtaining a target steering score and a steering matching score of the current candidate driving lane according to the relative steering and the steering score of the obstacle.
In some alternative embodiments, step S3042 includes:
and a step a1, updating the steering score of the obstacle based on relative steering to obtain a target steering score of the current candidate driving lane, wherein the relative steering comprises straight, left and right turning.
Specifically, if the relative steering is left-handed, inverting the steering score of the obstacle to obtain a target steering score; if the relative steering is straight, directly taking the steering score of the obstacle as a target steering score; if the relative turn is a right turn, the absolute value of the turn score of the obstacle is taken as the target turn score.
And a step a2 of determining the driving intention of the obstacle according to the steering score of the obstacle, wherein the driving intention comprises straight running, left turning and right turning.
Specifically, comparing the steering score of the obstacle with a preset threshold, and if the steering score is smaller than the preset left turn threshold, the driving intention of the obstacle is left turn; if the steering score is larger than a preset right turn threshold, the driving intention of the obstacle is right turn; otherwise, the driving intention of the obstacle is straight. For example, the preset left-turn threshold may be-0.02, the preset right-turn threshold may be 0.02, and may be actually set according to a specific application scenario, which is not limited by the present invention.
And a step a3 of comparing the driving intention of the obstacle with the relative steering, and calculating a steering matching score of the current candidate driving lane based on the comparison result and the target steering score.
Specifically, if the traveling intention of the obstacle does not match the relative turn, for example, the traveling intention of the obstacle is left turn and the relative turn is right turn, the target turn score is reduced by a certain proportion, resulting in a turn match score. For example, the turn match score is a target turn score/2.
The target steering score and the steering matching score of the current candidate traveling lane are thus obtained from the steering scores of the relative steering and the obstacle, and the candidate traveling lane is evaluated by taking the traveling intention of the obstacle, the relative steering of the lane, and the degree of matching of the lane relative steering and the traveling intention of the obstacle.
And step S3043, obtaining the track score of the current candidate driving lane according to the transverse distance variance value, the course angle deviation, the target steering score and the steering matching score.
Specifically, the product of the course angle deviation and the preset proportion is calculated, and the product, the lateral distance variance value, the target steering score and the opposite number of the steering matching score are summed to obtain the track score of the current candidate driving lane.
In some alternative embodiments, the track score S for the current candidate driving lane may be calculated according to the following formula:
S＝k*α+σ 2 +D-V
where k represents a preset ratio, D represents a target steering score, and V represents a steering match score. Illustratively, k may be 0.3, which is not limiting to the invention.
Therefore, the track score of the current candidate driving lane can be accurately calculated through the transverse distance variance value, the course angle deviation, the target steering score and the steering matching score, and the candidate driving lane is quantitatively evaluated so as to provide guidance for the selection of the possible target driving lane of the obstacle.
Step S305, the driving track of the obstacle is obtained according to the track score and the pose information of each candidate driving lane.
Specifically, the step S305 includes:
in step S3051, the candidate driving lane having the smallest track score is determined as the target driving lane of the obstacle, based on the track score of each candidate driving lane.
Step S3052, generating a travel track of the obstacle based on the target travel lane and the position and heading angle of the obstacle in the pose information.
Specifically, after determining the most likely target driving lane of the obstacle, the driving track of the obstacle is generated from the current position of the obstacle along the heading angle direction and the position of the track point of the target driving lane. It should be noted that the lateral distance of the travel locus from the obstacle, i.e., the lateral distance between the obstacle and the target travel lane.
The candidate driving lane with the minimum track score is determined to be the target driving lane of the obstacle, and the driving track of the obstacle is generated based on the target driving lane and the position and course angle of the obstacle in the pose information, so that the driving track prediction of the obstacle for a period of time in the future is realized, and references and guidance are provided for the path planning and obstacle avoidance of the unmanned vehicle.
According to the track prediction method for the obstacles around the vehicle, when the obstacles located at the intersection are detected to exist around the vehicle, the corresponding lateral distance, heading angle deviation, relative steering and steering scores of the obstacles are calculated through the plurality of candidate driving lanes and pose information of the obstacles, the driving intention of the obstacles is quantitatively analyzed through the steering scores of the obstacles, the track score of each candidate driving lane is obtained, the candidate driving lane with the minimum track score is determined to be the target driving lane of the obstacle, the driving track of the obstacle is generated based on the positions and heading angles of the obstacles in the target driving lane and the pose information, the future driving track prediction of the obstacle is realized, guidance is provided for unmanned path planning and obstacle avoidance of the vehicle, and collision and friction with the obstacle are avoided.
The following describes in detail the trajectory prediction method of the obstacle around the vehicle of the present invention with reference to a specific application example, as shown in fig. 5, which includes the steps of:
1. and acquiring information such as the position, the speed, the course angle and the like of the obstacle, and map information of an intersection area where the obstacle is located, wherein the map information is used for pre-acquiring lane lines where the obstacle is likely to travel.
2. And calculating the transverse distance and course angle error of the obstacle and the pre-acquisition lane line, and calculating the transverse distance average value and the transverse distance variance value based on the transverse distance within a certain time.
3. And determining the relative steering of the pre-acquisition lane line relative to the obstacle and the driving intention of the obstacle according to the calculated transverse distance and course angle error of the obstacle and the pre-acquisition lane line.
4. And combining the obtained information such as the transverse distance variance value, the relative steering of the lane lines relative to the obstacle, the driving intention of the obstacle and the like, calculating the track score of the pre-collected lane lines, and selecting the lane line with the smallest track score as the lane line with the most possibility of selecting the driving of the obstacle, thereby carrying out the track prediction of the obstacle.
The present embodiment also provides a track prediction device for a vehicle surrounding obstacle, which is used to implement the foregoing embodiments and preferred embodiments, and will not be described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The present embodiment provides a trajectory prediction device of a vehicle surrounding obstacle, as shown in fig. 6, including:
an acquisition module 601, configured to acquire a plurality of candidate driving lanes and pose information of an obstacle when it is detected that the obstacle located at the intersection exists around the vehicle;
the first processing module 602 is configured to obtain, for each candidate driving lane, a lateral distance and a heading angle deviation between the obstacle and the current candidate driving lane based on the track information and the pose information of the current candidate driving lane, and determine a relative steering of the current candidate driving lane with respect to the obstacle;
a second processing module 603 for determining a steering score of the obstacle in each candidate driving lane based on the corresponding lateral distance of each candidate driving lane;
a third processing module 604, configured to determine, for each candidate driving lane, a track score of the current candidate driving lane according to a lateral distance, a heading angle deviation, a relative steering, and a steering score of an obstacle corresponding to the current candidate driving lane;
the fourth processing module 605 is configured to obtain a driving track of the obstacle according to the track score and the pose information of each candidate driving lane.
In some alternative embodiments, the pose information includes pose information of the obstacle at a plurality of moments in time; the first processing module 602 includes:
the first processing unit is used for obtaining the transverse distance between the obstacle and the current candidate driving lane at each moment based on pose information of the obstacle at a plurality of moments and track information of the current candidate driving lane for each candidate driving lane.
In some alternative embodiments, the second processing module 603 includes:
and the second processing unit is used for traversing and calculating the difference value between the transverse distance at the last moment and the transverse distance at each moment according to the transverse distances of the current candidate driving lane at a plurality of moments for each candidate driving lane, and calculating the steering score of the obstacle in the current candidate driving lane according to the difference value.
In some alternative embodiments, the lateral distance comprises lateral distances at a plurality of times; the third processing module 604 includes:
the third processing unit is used for obtaining a lateral distance variance value according to the lateral distances of a plurality of moments corresponding to the current candidate driving lane;
a fourth processing unit, configured to obtain a target steering score and a steering matching score of the current candidate driving lane according to the relative steering and the steering score of the obstacle;
and the fifth processing unit is used for obtaining the track score of the current candidate driving lane according to the transverse distance variance value, the course angle deviation, the target steering score and the steering matching score.
In some alternative embodiments, the fourth processing unit comprises:
a first processing subunit, configured to update a steering score of the obstacle based on the relative steering, and obtain a target steering score of the current candidate driving lane; the relative steering includes straight, left and right turns;
a second processing subunit for determining a driving intention of the obstacle according to the steering score of the obstacle; the travel intents include straight, left turn, and right turn;
and a third processing subunit for comparing the driving intention of the obstacle with the relative steering, and calculating a steering matching score of the current candidate driving lane based on the comparison result and the target steering score.
In some alternative embodiments, the fifth processing unit comprises:
and the fourth processing subunit is used for calculating the product of the course angle deviation and the preset proportion, and summing the product, the transverse distance deviation value, the target steering score and the opposite number of the steering matching score to obtain the track score of the current candidate driving lane.
In some alternative embodiments, the fourth processing module 605 includes:
a sixth processing unit configured to determine, as a target travel lane of the obstacle, a candidate travel lane having the smallest track score according to the track score of each candidate travel lane;
and a seventh processing unit for generating a travel track of the obstacle based on the target travel lane and the position and heading angle of the obstacle in the pose information.
Further functional descriptions of the above respective modules and units are the same as those of the above corresponding embodiments, and are not repeated here.
The trajectory prediction device of the obstacle around the vehicle in the present embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit ) circuit, a processor and a memory that execute one or more software or a fixed program, and/or other devices that can provide the above functions.
The embodiment of the invention also provides computer equipment, which is provided with the track prediction device of the obstacle around the vehicle shown in the figure 6.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a computer device according to an alternative embodiment of the present invention, as shown in fig. 7, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 10 is illustrated in fig. 7.
The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.
Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform the methods shown in implementing the above embodiments.
The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.
The computer device also includes a communication interface 30 for the computer device to communicate with other devices or communication networks.
The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (10)
1. A track prediction method of a vehicle surrounding obstacle, characterized by comprising:
when detecting that an obstacle positioned at an intersection exists around a vehicle, acquiring a plurality of candidate driving lanes and pose information of the obstacle;
for each candidate driving lane, obtaining a lateral distance and a course angle deviation between the obstacle and the current candidate driving lane based on track information and pose information of the current candidate driving lane, and determining relative steering of the current candidate driving lane relative to the obstacle;
determining a steering score for the obstacle in each candidate travel lane based on the corresponding lateral distance of each candidate travel lane;
determining a track score of the current candidate driving lane according to the corresponding lateral distance, course angle deviation, relative steering and the steering score of the obstacle of the current candidate driving lane aiming at each candidate driving lane;
and obtaining the driving track of the obstacle according to the track score of each candidate driving lane and the pose information.
2. The method of claim 1, wherein the lateral distance comprises lateral distances at a plurality of moments in time; the determining the track score of the current candidate driving lane according to the corresponding lateral distance, course angle deviation, relative steering and the steering score of the obstacle of the current candidate driving lane comprises the following steps:
obtaining a lateral distance variance value according to the lateral distances of the current candidate driving lane at a plurality of moments;
obtaining a target steering score and a steering matching score of the current candidate driving lane according to the relative steering and the steering score of the obstacle;
and obtaining the track score of the current candidate driving lane according to the transverse distance variance value, the course angle deviation, the target steering score and the steering matching score.
3. The method of claim 2, wherein the deriving a trajectory score for the current candidate travel lane based on the lateral distance variance value, the heading angle deviation, the target steering score, and the steering match score comprises:
and calculating the product of the course angle deviation and a preset proportion, and summing the product, the transverse distance deviation value, the target steering score and the opposite number of the steering matching score to obtain the track score of the current candidate driving lane.
4. The method of claim 2, wherein the deriving the target steering score and the steering match score for the current candidate driving lane based on the relative steering and the steering score for the obstacle comprises:
updating the steering score of the obstacle based on the relative steering to obtain a target steering score of the current candidate driving lane; the relative steering includes straight, left and right turns;
determining a driving intention of the obstacle according to the steering score of the obstacle; the travel intents include straight, left turn, and right turn;
comparing the driving intention of the obstacle with the relative steering, and calculating a steering matching score of the current candidate driving lane based on the comparison result and the target steering score.
5. The method according to claim 1, wherein the obtaining the travel track of the obstacle according to the track score of each candidate travel lane and the pose information includes:
according to the track score of each candidate driving lane, determining the candidate driving lane with the minimum track score as the target driving lane of the obstacle;
and generating a driving track of the obstacle based on the target driving lane and the position and course angle of the obstacle in the pose information.
6. The method of claim 1, wherein the pose information comprises pose information of an obstacle at a plurality of moments in time; the method for obtaining the lateral distance and the course angle deviation between the obstacle and the current candidate driving lane based on the track information and the pose information of the current candidate driving lane and determining the relative steering of the current candidate driving lane relative to the obstacle comprises the following steps:
for each candidate driving lane, based on pose information of the obstacle at a plurality of moments and track information of the current candidate driving lane, a lateral distance between the obstacle and the current candidate driving lane at each moment is obtained.
7. The method of claim 2 or 5, wherein determining a steering score for the obstacle in each candidate travel lane based on the corresponding lateral distance of each candidate travel lane comprises:
for each candidate driving lane, according to the transverse distance of the current candidate driving lane at a plurality of moments, traversing to calculate the difference between the transverse distance at the last moment and the transverse distance at each moment, and calculating the steering score of the obstacle in the current candidate driving lane according to the difference.
8. A trajectory prediction device of a vehicle surrounding obstacle, characterized by comprising:
an acquisition module, configured to acquire a plurality of candidate driving lanes and pose information of an obstacle located at an intersection when detecting that the obstacle exists around a vehicle;
the first processing module is used for obtaining the transverse distance and the course angle deviation between the obstacle and the current candidate driving lane based on the track information and the pose information of the current candidate driving lane for each candidate driving lane, and determining the relative steering of the current candidate driving lane relative to the obstacle;
a second processing module for determining a steering score of the obstacle in each candidate driving lane based on the corresponding lateral distance of each candidate driving lane;
the third processing module is used for determining the track score of the current candidate driving lane according to the corresponding transverse distance, the course angle deviation, the relative steering and the steering score of the obstacle of the current candidate driving lane;
and the fourth processing module is used for obtaining the running track of the obstacle according to the track score of each candidate running lane and the pose information.
9. A computer device, comprising:
a memory and a processor communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the trajectory prediction method of the vehicle-surrounding obstacle according to any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon computer instructions for causing a computer to execute the trajectory prediction method of the obstacle around the vehicle according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311763153.7A CN117508232A (en) | 2023-12-19 | 2023-12-19 | Track prediction method, device, equipment and medium for vehicle surrounding obstacle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311763153.7A CN117508232A (en) | 2023-12-19 | 2023-12-19 | Track prediction method, device, equipment and medium for vehicle surrounding obstacle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117508232A true CN117508232A (en) | 2024-02-06 |
Family
ID=89762841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311763153.7A Pending CN117508232A (en) | 2023-12-19 | 2023-12-19 | Track prediction method, device, equipment and medium for vehicle surrounding obstacle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117508232A (en) |
-
2023
- 2023-12-19 CN CN202311763153.7A patent/CN117508232A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3699048B1 (en) | Travelling track prediction method and device for vehicle | |
| CN113267199B (en) | Method and device for planning driving track | |
| CN109760675B (en) | Method, device, storage medium and terminal equipment for predicting vehicle track | |
| CN111301409A (en) | Parking path planning method and device, vehicle and storage medium | |
| US11520340B2 (en) | Traffic lane information management method, running control method, and traffic lane information management device | |
| JP2019204509A (en) | Determination of driving route for automatic driving for avoiding moving obstacle | |
| CN110834630A (en) | Vehicle driving control method and device, vehicle and storage medium | |
| JP2018197964A (en) | Control method of vehicle, and device thereof | |
| CN115127576B (en) | Path planning method, device, chip, terminal, electronic equipment and storage medium | |
| CN118235180A (en) | Method and device for predicting drivable lane | |
| CN114475656B (en) | Travel track prediction method, apparatus, electronic device and storage medium | |
| CN113899378A (en) | Lane changing processing method and device, storage medium and electronic equipment | |
| CN114264307A (en) | Route generation method, apparatus, vehicle and storage medium | |
| CN116476840B (en) | Variable-lane driving method, device, equipment and storage medium | |
| CN117227714A (en) | Control method and system for turning avoidance of automatic driving vehicle | |
| CN117508232A (en) | Track prediction method, device, equipment and medium for vehicle surrounding obstacle | |
| US20230053243A1 (en) | Hybrid Performance Critic for Planning Module's Parameter Tuning in Autonomous Driving Vehicles | |
| CN115892076A (en) | Lane obstacle screening method and device and domain controller | |
| CN113753038A (en) | Trajectory prediction method and apparatus, electronic device and storage medium | |
| CN115257801A (en) | Trajectory planning method and device, server and computer readable storage medium | |
| WO2024216768A1 (en) | Vehicle path planning method and apparatus, and vehicle | |
| CN113327456A (en) | Lane structure detection method and device | |
| JP7558091B2 (en) | Driving support method and driving support device | |
| CN114475650B (en) | Vehicle driving behavior determination method, device, equipment and medium | |
| RU2789921C2 (en) | Method and device for control of self-driving car |
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 |