CN115727864A - Path prediction method based on visual navigation vehicle and related equipment - Google Patents
Path prediction method based on visual navigation vehicle and related equipment Download PDFInfo
- Publication number
- CN115727864A CN115727864A CN202111021722.1A CN202111021722A CN115727864A CN 115727864 A CN115727864 A CN 115727864A CN 202111021722 A CN202111021722 A CN 202111021722A CN 115727864 A CN115727864 A CN 115727864A
- Authority
- CN
- China
- Prior art keywords
- tracking path
- coordinate system
- vehicle
- equation
- track
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000000007 visual effect Effects 0.000 title claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 6
- 238000013519 translation Methods 0.000 claims description 23
- 238000013507 mapping Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000008447 perception Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 230000016776 visual perception Effects 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 abstract description 3
- 230000003287 optical effect Effects 0.000 abstract description 3
- 238000012546 transfer Methods 0.000 abstract description 3
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 230000002411 adverse Effects 0.000 abstract description 2
- 238000005452 bending Methods 0.000 abstract description 2
- 238000012937 correction Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003137 locomotive effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Navigation (AREA)
Abstract
The method can accurately predict and plan a smooth driving path for the vehicle in real time by a vehicle automatic driving system path prediction method combining driving reference track recognition and driving local path terminal point prediction based on camera visual perception, improves the anti-interference performance of the vehicle on road conditions, has good riding comfort, avoids adverse consequences caused by abnormal reference track detection, and realizes stable and reliable over-bending and track transfer. In addition, the path prediction planning algorithm can also plan a path of the optical scooter from the current position of the vehicle to the reference track when the vehicle deviates from the reference track greatly, so that the automatic driving system has automatic deviation correction capability.
Description
Technical Field
The application relates to the technical field of automatic driving, in particular to a path prediction method based on a visual navigation vehicle and related equipment.
Background
When the automatic driving vehicle tracks and tracks on the transition section of a reference track from a straight road to a curved road or from a curved road to a straight road and the transition section of a reference track turnout, the phenomenon of sudden change of steering often exists, and even the automatic driving vehicle cannot smoothly pass a curve or change a track. The main factors causing this phenomenon include a certain deviation of the reference track construction, partial wear during use, and large curvature of the curve, resulting in poor quality of track curvature data collected by the front camera of the vehicle or sudden drop of the detection range of the camera, and these sensing errors may cause the automatic driving system to be subjected to undesirable steering control, and even cause the vehicle to run out of the lane boundary. Current safety precautions are that when the above events occur, the autopilot system may require the driver to hold the steering wheel and prepare to take over steering control in a short time. However, this increases the workload on the driver and reduces the driver's confidence in the autopilot system.
Disclosure of Invention
In view of the above, an object of the present application is to provide a method and related apparatus for predicting a path of a vehicle based on visual navigation.
In view of the above, the present application provides a path prediction method based on a visual navigation vehicle, including:
constructing a track equation coordinate system by taking the vehicle-mounted camera as an original point, wherein the positive direction of an x axis of the coordinate system is vertical to the vehicle head and points to the driving direction of the vehicle, and the positive direction of a y axis of the coordinate system is parallel to the vehicle head and points to the left side of the driving direction of the vehicle;
the method comprises the following steps that a vehicle runs along a global reference track, a camera acquires local reference track information for multiple times within the range of the maximum perception longitudinal distance of the camera, and multiple track line equations are constructed on the basis of the local reference track information acquired for multiple times;
determining a starting point of a tracking path based on the track equation coordinate system where the track line equation corresponding to the local reference track information obtained last time is located, and performing translation and rotation mapping on a plurality of track line equations to obtain a plurality of groups of state constant values;
estimating the end point of the tracking path by calculation based on the track line equation corresponding to the local reference track information obtained last time and a plurality of track line equations subjected to translation and rotation mapping to obtain a plurality of estimated end points;
calculating to obtain a tracking path end point based on the estimated end points;
determining a tracking path curve based on the tracking path start point and the tracking path end point;
iteratively updating the plurality of sets of state constant values based on the tracking path profile to generate the tracking path profile for a next cycle.
Further, the vehicle runs along the global reference track, the camera acquires local reference track information for multiple times within a range where a running distance is a maximum perceived longitudinal distance of the camera, and a plurality of track line equations are constructed based on the local reference track information acquired for multiple times, including:
the vehicle obtains the local reference track information once through the camera within the maximum perception longitudinal distance range of the camera after driving a pre-aiming distance, and the vehicle at least obtains N pieces of local reference track information within the range to construct N track line equations, wherein N is expressed as
N is a positive integer, floor denotes a floor operation, L m The maximum perceived longitudinal distance of the camera is represented, and Ls represents the preview distance.
Further, the determining a tracking path starting point based on the track equation coordinate system where the track line equation corresponding to the local reference track information that is obtained last time is located includes obtaining multiple sets of state constant values by performing translation and rotation mapping on multiple track line equations, and includes:
according to the sequence of the local reference orbit information, the local reference orbit information acquired last time corresponds to the Nth orbit line equation, the origin of the coordinate system of the Nth orbit line equation is determined as the starting point of the tracking path, and the first N-1 orbit line equations are mapped into the coordinate system of the Nth orbit line equation through translation and rotation respectively to obtain N-1 groups of state constant values.
Further, the state constant value is expressed as (x) 0 ,y 0 ,θ)，x 0 And y 0 Represents the coordinates of the origin of the coordinate system of the r-th orbit equation in the coordinate system of the r-1-th orbit equation, and theta represents the included angle between the x axis of the coordinate system of the r-th orbit equation and the x axis of the coordinate system of the r-1-th orbit equation, 1<r≤N。
Further, the calculating a tracking path end point based on a plurality of the estimated end points includes:
and calculating to obtain a plurality of tracking path predicted end points based on the plurality of predicted end points, and obtaining the tracking path end point based on the plurality of tracking path predicted end points through an exponential weighting fusion algorithm.
Further, the determining a tracking path curve based on the tracking path starting point and the tracking path ending point includes:
determining the tracking path curve by constructing a first-order cubic equation in a coordinate system of the Nth track line equation based on the tracking path start point and the tracking path end point.
Further, the iteratively updating the plurality of sets of state constant values based on the tracking path curve to generate the tracking path curve for a next cycle includes:
and extracting parameters from the tracking path curve to replace the N-1 th group of the state constant values as an updated N-1 th group of the state constant values, then sequentially using the s-1 th group of the state constant values as a new s-2 th group of the state constant values, wherein s is more than or equal to 3 and less than or equal to N, and generating the tracking path curve of the next segment based on the updated N-1 groups of the state constant values.
Based on the same inventive concept, the application also provides a path prediction method and device based on the visual navigation vehicle, which comprises the following steps:
the coordinate system construction module is configured to construct a track equation coordinate system by taking the vehicle-mounted camera as an original point, the positive direction of an x axis of the coordinate system is perpendicular to the vehicle head and points to the vehicle running direction, and the positive direction of a y axis of the coordinate system is parallel to the vehicle head and points to the global reference track direction;
the equation building module is configured to enable a vehicle to run along the global reference track, enable the camera to acquire local reference track information for multiple times within a range of the maximum perception longitudinal distance of the camera, and build a plurality of track line equations based on the local reference track information acquired for multiple times;
the mapping module is configured to determine a starting point of a tracking path based on the track equation coordinate system where the track line equation corresponding to the local reference track information acquired last time is located, and obtain multiple sets of state constant values by performing translation and rotation mapping on multiple track line equations;
the terminal point pre-estimation module is configured to pre-estimate the terminal point of the tracking path through calculation based on the track line equation corresponding to the local reference track information obtained last time and a plurality of track line equations subjected to translation and rotation mapping to obtain a plurality of pre-estimated terminal points;
an end point determination module configured to calculate a tracking path end point based on a plurality of the predicted end points;
a path generation module configured to determine a tracking path curve based on the tracking path starting point and the tracking path ending point;
an iterative update module configured to iteratively update sets of the state constant values based on the tracking path profile to generate the tracking path profile for a next cycle.
From the above, according to the path prediction method based on the visual navigation vehicle and the related device, the smooth driving path can be accurately predicted and planned in real time for the vehicle through the vehicle automatic driving system path prediction method combining the driving reference track recognition based on the camera visual perception and the driving local path end point prediction, the anti-interference performance of the vehicle on road conditions is improved, and therefore the method has good riding comfort, adverse consequences caused by abnormal reference track detection are avoided, and stable and reliable over-bending and track transfer are achieved. In addition, the path prediction planning algorithm can also plan a path of the optical scooter from the current position of the vehicle to the reference track when the vehicle deviates from the reference track greatly, so that the automatic driving system has automatic deviation correction capability.
Based on the same inventive concept, the present application further provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable by the processor, wherein the processor implements the method as described above when executing the computer program.
Based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method as described above.
Drawings
In order to more clearly illustrate the technical solutions in the present application or the related art, the drawings needed to be used in the description of the embodiments or the related art will be briefly introduced below, and it is obvious that the drawings in the following description are only embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart illustrating a method for predicting a path of a vehicle based on visual navigation according to an embodiment of the present disclosure;
FIG. 2 is a schematic view of a visual perception of a reference track according to an embodiment of the present application;
FIG. 3 is a schematic diagram of N partial reference track lines according to an embodiment of the present application;
FIG. 4 is a diagram illustrating tracking path end point prediction according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a tracking path profile according to an embodiment of the present application;
FIG. 6 is a schematic structural diagram of a visual navigation vehicle-based route prediction device according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described in detail below with reference to the accompanying drawings in combination with specific embodiments.
It should be noted that technical terms or scientific terms used in the embodiments of the present application should have a general meaning as understood by those having ordinary skill in the art to which the present application belongs, unless otherwise defined. The use of "first," "second," and similar terms in the embodiments of the present application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
Embodiments of the present application are described in detail below with reference to the accompanying drawings.
The application provides a path prediction method based on a visual navigation vehicle, and with reference to fig. 1, the method comprises the following steps:
and S101, constructing a track equation coordinate system by taking the vehicle-mounted camera as an original point, wherein the positive direction of the x axis of the coordinate system is perpendicular to the vehicle head and points to the driving direction of the vehicle, and the positive direction of the y axis of the coordinate system is parallel to the vehicle head and points to the left side of the driving direction of the vehicle.
Specifically, the visual perception of the front camera of the autonomous vehicle for the global reference trajectory is shown in fig. 2. The local reference orbit line identified by the camera is a real line segment part in the global reference orbit, and the equation of the local reference orbit line is as follows:
y(x)＝C 3 x 3 +C 2 x 2 +C 1 x+C 0 ,0≤x≤L m
wherein, x is the longitudinal distance of track line for the camera, and coordinate system x axle perpendicular to locomotive, y is the horizontal distance of track line for the camera, and coordinate system y axle is on a parallel with the locomotive. C 3 、C 2 、C 1 、C 0 Respectively, the cubic coefficient, quadratic coefficient, first-order coefficient and zero-order coefficient of the equation, L m The maximum effective longitudinal distance recognizable by the camera.
And S102, the vehicle runs along the global reference track, the camera acquires local reference track information for multiple times within the range of the maximum perception longitudinal distance of the camera, and multiple track line equations are constructed on the basis of the local reference track information acquired for multiple times.
Specifically, in the process that the vehicle runs along the global reference track, the local reference track information is acquired by the camera at intervals, and the distance that the vehicle runs does not exceed the maximum perceived longitudinal distance L of the camera m . In the driving process, local reference orbit information is acquired for multiple times, an orbit line equation is constructed according to the local reference orbit information acquired each time, and a plurality of orbit line equations are constructed on the basis of the local reference orbit information.
Step S103, determining a tracking path starting point based on the track equation coordinate system where the track line equation corresponding to the local reference track information obtained last time is located, and obtaining multiple sets of state constant values by performing translation and rotation mapping on multiple track line equations.
Specifically, the vehicle runs L m The method comprises the steps of obtaining multiple times of local reference orbit information within a distance range, determining a starting point of a tracking path based on an orbit equation coordinate system to which an orbit line equation constructed by the finally and sequentially obtained local reference orbit information belongs, executing translation and rotation mapping on a plurality of orbit line equations at the same time, and obtaining a group of state constant values by performing translation and rotation mapping once.
And S104, estimating the end point of the tracking path through calculation based on the track line equation corresponding to the local reference track information obtained last time and the plurality of track line equations subjected to translation and rotation mapping to obtain a plurality of estimated end points.
Specifically, the obtained multiple orbital line equations are translated and rotationally mapped to a coordinate system to which the finally obtained orbital line equation belongs, an estimated end point is obtained by calculating each of the translated and rotationally mapped orbital line equations, and meanwhile, an estimated end point is also obtained by calculating the finally obtained orbital line equation and is used for calculating the tracking path end point.
And S105, calculating to obtain a tracking path end point based on the estimated end points. And performing fusion calculation on the plurality of predicted end points to obtain a final tracking path end point, namely the predicted end point of the vehicle running in a section of range.
Step S106, determining a tracking path curve based on the tracking path starting point and the tracking path end point. The starting point and the end point of the tracking path are obtained through calculation, and the tracking path curve is obtained through calculation based on the starting point and the end point by constructing a curve equation.
Step S107, iteratively updating the plurality of groups of state constant values based on the tracking path curve to generate the tracking path curve of the next cycle. After the first section of tracking path curve is obtained, the plurality of groups of state constant values are subjected to iterative updating to obtain a plurality of groups of new state constant values, a second section of tracking path curve is obtained by calculation based on the plurality of groups of new state constant values, and the rest of tracking path curves are calculated by analogy.
In some embodiments, the vehicle travels along the global reference track, the camera acquires local reference track information a plurality of times within a range of a travel distance that is a maximum perceived longitudinal distance of the camera, and constructs a plurality of track line equations based on the local reference track information acquired a plurality of times, including:
the vehicle obtains the local reference track information once through the camera within the maximum perception longitudinal distance range of the camera after driving a pre-aiming distance, and the vehicle at least obtains N pieces of local reference track information within the range to construct N track line equations, wherein N is expressed as
N is a positive integer, floor denotes a floor operation, L m The maximum perceived longitudinal distance of the camera is represented, and Ls represents the preview distance.
Specifically, referring to fig. 3, the vehicle travels L m After the distance is reached, N times of local reference orbit information is obtained through the camera, and N orbit line equations are constructed. Are respectively as
Each orbit linear equation corresponds to different orbit equation coordinate systems respectively, and is x 0 -y 0 Coordinate system, x 1 -y 1 Coordinate system, x n -y n Coordinate system and x n-1 -y n-1 A coordinate system.
In some embodiments, the determining a starting point of a tracking path based on the trajectory equation coordinate system where the trajectory line equation corresponding to the local reference trajectory information obtained last time is located, and obtaining multiple sets of state constant values by performing translation and rotation mapping on multiple trajectory line equations includes:
according to the sequence of obtaining the local reference track information, the local reference track information obtained last time corresponds to the Nth track line equation, the origin of the coordinate system of the Nth track line equation is determined as the starting point of the tracking path, and the first N-1 track line equations are mapped into the coordinate system of the Nth track line equation through translation and rotation respectively to obtain N-1 groups of state constant values.
In some embodiments, the stateThe constant value is expressed as (x) k ,y k θ), where x k And y k Represents the coordinates of the origin of the coordinate system of the r-th orbit equation in the coordinate system of the r-1-th orbit equation, and theta represents the included angle between the x axis of the coordinate system of the r-th orbit equation and the x axis of the coordinate system of the r-1-th orbit equation, 1<r≤N。
Specifically, as shown in FIG. 3, at x 0 -y 0 The local reference orbit line equation in the coordinate system satisfies:
x is to be 1 -y 1 The orbital line equations in the coordinate system are mapped to x through translation and rotation 0 -y 0 In the coordinate system, we can get:
wherein (x) o1 ,y o1 ) Is x 0 -y 0 The origin of the coordinate system is at x 1 -y 1 Coordinates in a coordinate system, θ 1 Is x 0 -y 0 X in the coordinate system 0 Axis in x 1 -y 1 In the coordinate system with x 1 Angle of axes (x) o1 ,y o1 ,θ 1 ) For autonomous driving the vehicle corresponds to x 1 -y 1 A set of state constant values for a coordinate system.
In the same way, x n -y n The orbital line equation in the coordinate system is mapped to x through translation and rotation 0 -y 0 In the coordinate system, we can get:
wherein n is a positive integer, and n is an element of [1, N-1 ]]，(x on ,y on ) Is x n-1 -y n-1 The origin of the coordinate system is at x n -y n Coordinates in a coordinate system, θ n Is x n-1 -y n-1 X in the coordinate system n-1 Axis in x n -y n In the coordinate system with x n Angle of axis, (x) on ,y on ,θ n ) For autonomous driving of the vehicle corresponding to x n -y n A set of state constant values for a coordinate system.
Finally, x is N-1 -y N-1 The orbital line equation in the coordinate system is mapped to x through translation and rotation 0 -y 0 In the coordinate system, we can get:
wherein (x) o(N-1) ,y o(N-1) ) Is x N-2 -y N-2 The origin of the coordinate system is at x N-1 -y N-1 Coordinates in a coordinate system, θ N-1 Is x N-2 -y N-2 X in the coordinate system N-2 Axis in x N-1 -y N-1 In the coordinate system with x N-1 Angle of axes (x) o(N-1) ,y o(N-1) ,θ N-1 ) For autonomous driving of the vehicle corresponding to x N-1 -y N-1 A set of state constant values for a coordinate system.
In some embodiments, the calculating a tracking path end point based on a plurality of the predicted end points comprises:
and calculating to obtain a plurality of tracking path predicted end points based on the plurality of predicted end points, and obtaining the tracking path end point based on the plurality of tracking path predicted end points through an exponential weighting fusion algorithm.
In order to further ensure the accuracy and smoothness of the tracking path, the equation of the N track lines is adopted for the X track line 0 -y 0 Vehicle edge x in coordinate system 0 The tracking path end point corresponding to the distance Ls traveled in the axial direction is estimated, and a tracking path curve is planned as shown in fig. 4.
Starting point (x) of tracking path s ,y s ) Is x 0 -y 0 The origin of the coordinate system, satisfying the following formula:
the end point of the tracking path can be estimated by the N track lines corresponding to the formulas (1.1) - (1.4), so that the end point can be obtained according to the formula (1.1)
Wherein (x) e0 ,y e0 ) Is an equation curve y 0 (x 0 ) At x 0 -y 0 And (4) estimating the tracking path end point under the coordinate system. Similarly, the formula (1.2) can be used to obtain
Wherein (x) e1 ,y e1 ) Is an equation curve y 1 (x 1 ) At x 0 -y 0 And (5) estimating the tracking path terminal point under the coordinate system. According to the formula (1.3)
Wherein (x) en ,y en ) Is an equation curve y n (x n ) At x 0 -y 0 And (4) estimating the tracking path end point under the coordinate system. Obtained according to equation (1.4)
Wherein (x) e(N-1) ,y e(N-1) ) Is an equation curve y N-1 (x N-1 ) At x 0 -y 0 And (5) estimating the tracking path terminal point under the coordinate system. From the above equation (1.6) to equation (1.9), N estimated end points can be obtained, which are (x) respectively e0 ,y e0 )、(x e1 ,y e1 )…(x en ,y en )…(x e(N-1) ,y e(N-1) )。
In some embodiments, the calculating a tracking path end point based on a plurality of the predicted end points includes:
and calculating to obtain a plurality of tracking path predicted end points based on the plurality of predicted end points, and obtaining the tracking path end point based on the plurality of tracking path predicted end points through an exponential weighting fusion algorithm.
By substituting the first two equations in equation (1.8) into the corresponding orbital line equations, i.e., into the third equation, one can obtain information about x n First order cubic equation of
Wherein
Solving the formula (1.10) can obtain x n Real number solution of
Further obtained according to the formula (1.8)
Using the latter three equations in equation (1.8) results
Thereby obtaining N tracking path predicted end points
Performing exponential weighted fusion on the N predicted end points of the tracking paths in the formula (1.15) to obtain a final end point (x) of the tracking path e ,y e )
Wherein alpha belongs to (0, 1), and the value is specifically taken according to an actual vehicle experiment.
In some embodiments, said determining a tracking path curve based on a starting point of said tracking path and an ending point of said tracking path comprises:
determining the tracking path curve by constructing a cubic equation in a coordinate system of the Nth track line equation based on the starting point of the tracking path and the end point of the tracking path.
Specifically, a first-order cubic polynomial equation is selected at x 0 -y 0 Planning a tracking path curve in a coordinate system, in particular
Wherein A is 3 、A 2 、A 1 、A 0 The coefficient of the third order, the coefficient of the second order, the coefficient of the first order and the coefficient of the zero order of the equation are respectively. According to equations (1.5) and (1.16), the starting point (x) of the tracking path curve is considered s ,y s ) And end point (x) e ,y e ) Is in a state of
Wherein, y p Represents the solution of the equation in equation (1.17) in the y-axis direction. Substituting the formula (1.18) into the formula (1.17) to obtain
Solving equation (1.19) can obtain
Thus, the formula (1.17) can be expressed as
From equation (1.21), we can see that 0 -y 0 The planned tracking path curve in the coordinate system is shown in fig. 5, in which the solid line part represents the tracking path curve.
In some embodiments, the iteratively updating the plurality of sets of the state constant values based on the tracking path curve to generate the tracking path curve for a next cycle comprises:
extracting parameters from the tracking path curve replacing the N-1 th group of the state constant values as an updated N-1 th group of the state constant values, then sequentially using the s-1 th group of the state constant values as a new s-2 th group of the state constant values, s is more than or equal to 3 and less than or equal to N, and generating the tracking path curve of the next cycle based on updating all the state constant values.
Specifically, the values of the state constants obtained in the above embodiments are (x), respectively o1 ,y o1 ,θ 1 )、(x o2 ,y o2 ,θ 2 )…(x on ,y on ,θ n )…(x o(N-1) ,y o(N-1) ,θ N-1 ) Iteratively updating all state constant values based on the tracking path curve, specifically iteratively updating the state constant values from left to right according to the following formula for generation of the tracking path curve of the next cycle
Wherein the state constant value (x) o1 ,y o1 ,θ 1 ) Is replaced by (L) s ,y e ,arctan(y e ')) and then the state constant value (x) o2 ,y o2 ,θ 2 ) Replacement by (x) o1 ,y o1 ,θ 1 ) And performing replacement updating in the same way, calculating and generating the tracking path curve of the next period based on all the updated state constant values, then performing iterative updating on all the state constant values, and calculating and generating the subsequent tracking path curve.
It should be noted that the method of the embodiment of the present application may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and is completed by the mutual cooperation of a plurality of devices. In this distributed scenario, one device of the multiple devices may only perform one or more steps of the method of the embodiment of the present application, and the multiple devices interact with each other to complete the method.
It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Based on the same inventive concept, corresponding to the method of any embodiment, the application also provides a path prediction method and device based on the visual navigation vehicle.
Referring to fig. 6, the method for predicting a path based on a visual navigation vehicle includes:
the coordinate system building module 601 is configured to build a track equation coordinate system by taking the vehicle-mounted camera as an origin, wherein the positive direction of an x axis of the coordinate system is perpendicular to the vehicle head and points to the driving direction of the vehicle, and the positive direction of a y axis of the coordinate system is parallel to the vehicle head and points to the left side of the driving direction of the vehicle;
an equation construction module 602 configured to allow the vehicle to travel along the global reference track, acquire local reference track information a plurality of times by the camera within a range where a travel distance is a maximum perceived longitudinal distance of the camera, and construct a plurality of track line equations based on the local reference track information acquired a plurality of times;
a mapping module 603 configured to determine a starting point of a tracking path based on the trajectory equation coordinate system where the trajectory line equation corresponding to the latest acquired local reference trajectory information is located, and obtain multiple sets of state constant values by performing translation and rotation mapping on multiple trajectory line equations;
an end point pre-estimating module 604, configured to pre-estimate an end point of a tracking path by calculation based on the trajectory line equation corresponding to the latest acquired local reference trajectory information and a plurality of trajectory line equations subjected to translation and rotation mapping, so as to obtain a plurality of pre-estimated end points;
an endpoint determination module 605 configured to calculate a tracking path endpoint based on a plurality of the predicted endpoints;
a path generation module 606 configured to determine a tracking path curve based on the tracking path starting point and the tracking path ending point;
an iterative update module 607 configured to iteratively update sets of the state constant values based on the tracking path profile to generate the tracking path profile for a next cycle.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the various modules may be implemented in the same one or more software and/or hardware implementations as the present application.
The device of the above embodiment is used to implement the corresponding path prediction method based on the visual navigation vehicle in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the method for predicting a path based on a visual navigation vehicle according to any of the above embodiments.
Fig. 7 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and the output devices may include a display, speaker, vibrator, indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present device and other devices. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only the components necessary to implement the embodiments of the present disclosure, and need not include all of the components shown in the figures.
The electronic device of the above embodiment is used to implement the corresponding path prediction method based on the visual navigation vehicle in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to any of the above embodiments methods, the present application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method for path prediction based on visual navigation vehicle according to any of the above embodiments.
Computer-readable media of the present embodiments, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
The storage medium of the above embodiment stores computer instructions for causing the computer to execute the method for predicting a path based on a visual navigation vehicle according to any of the above embodiments, and has the advantages of the corresponding method embodiments, which are not repeated herein.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the context of the present application, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of brevity.
In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown in the provided figures for simplicity of illustration and discussion, and so as not to obscure the embodiments of the application. Furthermore, devices may be shown in block diagram form in order to avoid obscuring embodiments of the application, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the embodiments of the application are to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the application, it should be apparent to one skilled in the art that the embodiments of the application can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present application has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures, such as Dynamic RAM (DRAM), may use the discussed embodiments.
The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present application are intended to be included within the scope of the present application.
Claims (10)
1. A method for path prediction based on a visual navigation vehicle, comprising:
constructing a track equation coordinate system by taking the vehicle-mounted camera as an original point, wherein the positive direction of an x axis of the coordinate system is vertical to the vehicle head and points to the vehicle running direction, and the positive direction of a y axis of the coordinate system is parallel to the vehicle head and points to the left side of the vehicle running direction;
the method comprises the following steps that a vehicle runs along a global reference track, a camera acquires local reference track information for multiple times within the range of the maximum perception longitudinal distance of the camera, and multiple track line equations are constructed on the basis of the local reference track information acquired for multiple times;
determining a starting point of a tracking path based on the track equation coordinate system where the track line equation corresponding to the local reference track information obtained last time is located, and performing translation and rotation mapping on a plurality of track line equations to obtain a plurality of groups of state constant values;
estimating the end point of the tracking path by calculation based on the track line equation corresponding to the local reference track information obtained last time and a plurality of track line equations subjected to translation and rotation mapping to obtain a plurality of estimated end points;
calculating to obtain a tracking path end point based on the estimated end points;
determining a tracking path curve based on the tracking path start point and the tracking path end point;
iteratively updating sets of the state constant values based on the tracking path profile to generate the tracking path profile for a next cycle.
2. The path prediction method according to claim 1, wherein the vehicle travels along the global reference track, the camera acquires local reference track information a plurality of times within a range of a travel distance that is a maximum perceived longitudinal distance of the camera, and constructs a plurality of track line equations based on the local reference track information acquired a plurality of times, including:
the vehicle obtains the local reference track information once through the camera within the maximum perception longitudinal distance range of the camera after driving a pre-aiming distance, and the vehicle at least obtains N pieces of local reference track information within the range to construct N track line equations, wherein N is expressed as
N is a positive integer, floor denotes a floor operation, L m The maximum perceived longitudinal distance of the camera is represented, and Ls represents the pre-aiming distance.
3. The method according to claim 2, wherein the determining a tracking path starting point based on the track equation coordinate system where the track line equation corresponding to the local reference track information obtained last time is located, and obtaining a plurality of sets of state constant values by performing translation and rotation mapping on a plurality of track line equations comprises:
according to the sequence of obtaining the local reference track information, the local reference track information obtained last time corresponds to the Nth track line equation, the origin of the coordinate system of the Nth track line equation is determined as the starting point of the tracking path, and the first N-1 track line equations are mapped into the coordinate system of the Nth track line equation through translation and rotation respectively to obtain N-1 groups of state constant values.
4. Method for path prediction according to claim 2, characterized in that said state constant value is represented by (x) k ,y k θ), where x k And y k Represents the coordinate of the origin of the coordinate system of the r-th orbit equation in the coordinate system of the r-1-th orbit equation, theta represents the included angle between the x axis of the coordinate system of the r-th orbit equation and the x axis of the coordinate system of the r-1-th orbit equation, 1<r≤N。
5. The method of claim 1, wherein the calculating a tracking path end point based on a plurality of the predicted end points comprises:
and calculating to obtain a plurality of tracking path predicted end points based on the plurality of predicted end points, and obtaining the tracking path end point based on the plurality of tracking path predicted end points through an exponential weighting fusion algorithm.
6. The method of claim 2, wherein the determining a tracking path curve based on the tracking path start point and the tracking path end point comprises:
determining the tracking path curve by constructing a cubic equation in a coordinate system of the Nth track line equation based on the tracking path starting point and the tracking path ending point.
7. The path prediction method of claim 3, wherein the iteratively updating the plurality of sets of state constant values based on the tracking path curve to generate the tracking path curve for a next cycle comprises:
extracting parameters from the tracking path curve replacing the N-1 th group of the state constant values as an updated N-1 th group of the state constant values, then sequentially using the s-1 th group of the state constant values as a new s-2 th group of the state constant values, s is more than or equal to 3 and less than or equal to N, and generating the tracking path curve of the next cycle based on updating all the state constant values.
8. A path prediction method device based on a visual navigation vehicle is characterized by comprising the following steps:
the coordinate system construction module is configured to construct a track equation coordinate system by taking the vehicle-mounted camera as an original point, the positive direction of an x axis of the coordinate system is perpendicular to the vehicle head and points to the vehicle running direction, and the positive direction of a y axis of the coordinate system is parallel to the vehicle head and points to the global reference track direction;
the system comprises an equation construction module, a global reference track control module and a camera, wherein the equation construction module is configured to run a vehicle along the global reference track, the camera acquires local reference track information for multiple times within a range of a running distance which is the maximum perceived longitudinal distance of the camera, and constructs a plurality of track line equations based on the local reference track information acquired for multiple times;
the mapping module is configured to determine a starting point of a tracking path based on the track equation coordinate system where the track line equation corresponding to the local reference track information acquired last time is located, and obtain multiple sets of state constant values by performing translation and rotation mapping on multiple track line equations;
the end point estimation module is configured to estimate an end point of a tracking path by calculation based on the track line equation corresponding to the local reference track information acquired last time and the plurality of track line equations subjected to translation and rotation mapping to obtain a plurality of estimated end points;
an end point determination module configured to calculate a tracking path end point based on a plurality of the predicted end points;
a path generation module configured to determine a tracking path curve based on the tracking path starting point and the tracking path ending point;
an iterative update module configured to iteratively update sets of the state constant values based on the tracking path profile to generate the tracking path profile for a next cycle.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable by the processor, the processor implementing the method of any one of claims 1 to 7 when executing the computer program.
10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111021722.1A CN115727864B (en) | 2021-09-01 | 2021-09-01 | Path prediction method based on visual navigation vehicle and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111021722.1A CN115727864B (en) | 2021-09-01 | 2021-09-01 | Path prediction method based on visual navigation vehicle and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115727864A true CN115727864A (en) | 2023-03-03 |
| CN115727864B CN115727864B (en) | 2024-06-21 |
Family
ID=85292152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111021722.1A Active CN115727864B (en) | 2021-09-01 | 2021-09-01 | Path prediction method based on visual navigation vehicle and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115727864B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060030987A1 (en) * | 2004-07-20 | 2006-02-09 | Aisin Seiki Kabushiki Kaisha | Lane keeping assist device for vehicle |
| WO2019052567A1 (en) * | 2017-09-18 | 2019-03-21 | 中车株洲电力机车研究所有限公司 | Virtual turnout system and method for virtual rail vehicle |
| CN112020014A (en) * | 2020-08-24 | 2020-12-01 | 中国第一汽车股份有限公司 | Lane change track planning method, device, server and storage medium |
| CN112486156A (en) * | 2019-09-10 | 2021-03-12 | 中车株洲电力机车研究所有限公司 | Automatic tracking control system and control method for vehicle |
-
2021
- 2021-09-01 CN CN202111021722.1A patent/CN115727864B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060030987A1 (en) * | 2004-07-20 | 2006-02-09 | Aisin Seiki Kabushiki Kaisha | Lane keeping assist device for vehicle |
| WO2019052567A1 (en) * | 2017-09-18 | 2019-03-21 | 中车株洲电力机车研究所有限公司 | Virtual turnout system and method for virtual rail vehicle |
| CN112486156A (en) * | 2019-09-10 | 2021-03-12 | 中车株洲电力机车研究所有限公司 | Automatic tracking control system and control method for vehicle |
| CN112020014A (en) * | 2020-08-24 | 2020-12-01 | 中国第一汽车股份有限公司 | Lane change track planning method, device, server and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 肖宏宇;付志强;陈慧勇;: "面向低速自动驾驶车辆的避障规划研究", 同济大学学报(自然科学版), no. 1, 15 December 2019 (2019-12-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115727864B (en) | 2024-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111771141B (en) | LIDAR positioning for solution inference using 3D CNN network in autonomous vehicles | |
| CN111415387B (en) | Camera pose determining method and device, electronic equipment and storage medium | |
| US10816977B2 (en) | Path and speed optimization fallback mechanism for autonomous vehicles | |
| CN106855415B (en) | Map matching method and system | |
| CN110647151B (en) | Coordinate conversion method and device, computer readable storage medium and electronic equipment | |
| JP2018084573A (en) | Robust and efficient algorithm for vehicle positioning and infrastructure | |
| CN108061555B (en) | Vehicle positioning error correction method and device | |
| JP7356528B2 (en) | Map data processing method and device | |
| CN113183975B (en) | Control method, device, equipment and storage medium for automatic driving vehicle | |
| JP7235060B2 (en) | Route planning device, route planning method, and program | |
| CN111882494B (en) | Pose graph processing method and device, computer equipment and storage medium | |
| CN115617051B (en) | Vehicle control method, device, equipment and computer readable medium | |
| CN114578401B (en) | Method and device for generating lane track points, electronic equipment and storage medium | |
| CN112009460A (en) | Vehicle control method, device, equipment and storage medium | |
| CN115727864B (en) | Path prediction method based on visual navigation vehicle and related equipment | |
| CN114055459B (en) | Track planning method, device, electronic equipment and storage medium | |
| CN113753024B (en) | Method, device, equipment and storage medium for eliminating steady-state deviation of vehicle | |
| CN112729349B (en) | Method and device for on-line calibration of odometer, electronic equipment and storage medium | |
| CN114194201A (en) | Vehicle control method and device, electronic equipment and storage medium | |
| CN115447584A (en) | Method, device and equipment for determining lane center line and storage medium | |
| CN115858706A (en) | Automatic cruise map building information storage method and device and vehicle | |
| CN115727871A (en) | Track quality detection method and device, electronic equipment and storage medium | |
| CN114488237A (en) | Positioning method and device, electronic equipment and intelligent driving method | |
| CN115655302B (en) | Laser odometer implementation method, computer equipment, storage medium and vehicle | |
| CN115009266B (en) | Vehicle control method, device and storage medium |
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 |