CN111089594A - Autonomous parking trajectory planning method suitable for multiple scenes - Google Patents
Autonomous parking trajectory planning method suitable for multiple scenes Download PDFInfo
- Publication number
- CN111089594A CN111089594A CN201911391911.0A CN201911391911A CN111089594A CN 111089594 A CN111089594 A CN 111089594A CN 201911391911 A CN201911391911 A CN 201911391911A CN 111089594 A CN111089594 A CN 111089594A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- virtual
- vertex
- expansion coefficient
- time
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0002—Automatic control, details of type of controller or control system architecture
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0021—Differentiating means
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
- B60W2050/0031—Mathematical model of the vehicle
- B60W2050/0034—Multiple-track, 2D vehicle model, e.g. four-wheel model
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
Abstract
The invention discloses an autonomous parking trajectory planning method suitable for multiple scenes, which comprises the following steps: (1) constructing a parking map; (2) determining the current position of the vehicle and the position of a target parking space; (3) determining physical parameters of the vehicle, and initializing the expansion coefficient of a virtual protection frame of the vehicle; (4) expressing a vehicle kinematic differential equation as a vehicle kinematic state constraint; (5) establishing collision avoidance restraint between the vehicle and the barrier by using the virtual protective frame and the expansion coefficient of the virtual protective frame; (6) establishing state variable and input variable constraints; (7) determining an optimization target and establishing an optimization problem; (8) solving an optimization problem by a solver to obtain an alternative autonomous parking track; (9) and (4) recalculating the expansion coefficient of the virtual guard frame, obtaining the final autonomous parking track if the stop condition is met, otherwise, updating the expansion coefficient of the virtual guard frame, and repeating the steps (4) to (8). By using the invention, the collision-free parking track can be planned in various scenes.
Description
Technical Field
The invention belongs to the field of automatic driving track planning, and particularly relates to an autonomous parking track planning method suitable for multiple scenes.
Background
The automatic parking is an important function in automatic driving, partial commercial vehicles with automatic parking are already available on the market at present, the traditional automatic parking trajectory planning method mainly comprises two links, a parking map is divided into grids, a parking path is calculated in the grids by using search algorithms such as A, state lattices and the like, the path speed is calculated by using an optimization method according to the parking path, and the parking trajectory is finally formed.
The other method for calculating the parking track is an optimization method based on a vehicle kinematic model, the method combines two steps of path planning and speed matching by using optimal control to directly calculate the parking track, but the method generally needs to manually select an optimization point number, and after a continuous optimization problem is dispersed, a constraint violation problem often exists, and finally the path and an obstacle collide to cause the parking safety hidden trouble.
At present, there are some methods for calculating the shortest distance between an obstacle and a vehicle by using a dual method, and some trajectory planning methods regard the vehicle and the obstacle as polygons, and use an area method to represent collision avoidance constraints of the vehicle and the obstacle, and these methods still have constraint violation phenomena in optimization problems in the implementation process.
Aiming at the problems and the defects of the autonomous parking trajectory planning technology, the trajectory planning method which can ensure that the autonomous parking trajectory does not collide with the obstacle, and the generated trajectory is safe and feasible and is easy to implement by a lower-layer controller is found, and the method has very high practical value.
Disclosure of Invention
The invention provides the autonomous parking trajectory planning method suitable for multiple scenes, which has the characteristics of safety, feasibility, easiness in implementation and the like and has high practical application value.
An autonomous parking trajectory planning method suitable for multiple scenes is characterized by comprising the following steps:
(1) detecting a parking environment and constructing a parking map;
(2) determining the current position of the vehicle and the position of a target parking space;
(3) determining physical parameters of the vehicle, and initializing the expansion coefficient of a virtual protection frame of the vehicle;
(4) according to a vehicle kinematic differential equation, establishing vehicle motion state constraint;
(5) establishing collision avoidance restraint between the vehicle and the barrier by using the virtual protective frame and the expansion coefficient of the virtual protective frame;
(6) establishing state variable and input variable constraints according to vehicle mechanical principle limitations and comfort requirements;
(7) determining an optimization target and establishing an optimization problem;
(8) solving an optimization problem by using a nonlinear programming solver to obtain an alternative autonomous parking track;
(9) and (4) recalculating the expansion coefficient of the virtual protection frame, obtaining the final autonomous parking track if the expansion coefficient of the virtual protection frame meets the stop condition, otherwise, updating the expansion coefficient of the virtual protection frame, and repeating the steps (4) to (8).
The invention can plan a safe and feasible parking track in multiple scenes, and provides a track planning solution for automatic driving and autonomous parking.
In the step (1), when the parking map is constructed, a closed or semi-closed polygon is used for representing the obstacle.
In the step (2), the current position and the target parking space position of the vehicle are respectively expressed asAndthe vehicle center of gravity detection method specifically comprises an x-axis coordinate and a y-axis coordinate of the vehicle center of gravity under a global coordinate system, and an included angle between the vehicle advancing direction and the positive direction of the x axis of the global coordinate system.
In the step (3), the physical parameters of the vehicle to be determined comprise the width w and the wheel base L of the vehicle, and the initial value of the expansion coefficient of the virtual protection frame is α0=1。
The specific process of the step (4) is as follows:
(4-1) describing a motion state of the vehicle using a differential equation as follows:
wherein X represents the X-axis coordinate of the center of gravity of the vehicle in the global coordinate system, Y represents the Y-axis coordinate of the center of gravity of the vehicle in the global coordinate system,representing the included angle between the right front direction of the vehicle and the x axis;andrespectively X, Y anddifferentiation of (1); v represents the vehicle forward speed, δfRepresenting a front wheel steering angle; taking the differential equation as a kinematic model of the vehicle, and recording as:
wherein the content of the first and second substances,denotes the state variable, u ═ v δf]TRepresenting an input variable;
(4-2) hypothesis ξ0,ξ1,...,ξNIs N +1 state variables to be planned, the state variable ξ at the known current time k according to the kinematic model of the vehiclekState variables of time, next timeExpressed as:
r1=f(ξk,uk)
wherein r is1,r2,r3,r4Is an intermediate state value, ukAn input variable representing time k, and T represents a sampling period;
(4-3) establishing vehicle motion state constraint:
the specific process of the step (5) is as follows:
(5-1) obstacle composed of polygon OjIs represented by, defined as
Wherein the subscript J indicates the jth obstacle, for a total of J obstacles,represents a polygon OjThe ith vertex in the clockwise direction,v representing jth obstaclej1,Vj2The line segment of the vertex is analogized in the same way;
(5-2) the vehicle is represented by a rectangle E, defined as
Wherein E is1Indicates the left front vertex of the rectangle in which the vehicle is located, E2Indicating the right front vertex of the rectangle in which the vehicle is located, E3Indicating the right rear vertex of the rectangle in which the vehicle is located, E4The left rear vertex of the rectangle in which the vehicle is located is shown,indicating the vehicle E1,E2The line segment of the vertex is analogized in the same way;
(5-3) defining a virtual protective frame E around the vehiclef
E and EfThe relationship of (A) is EfThe length in the direction parallel to the vehicle is equal to the corresponding length of E, EfA corresponding length in the direction perpendicular to the vehicle equal to E multiplied by the virtual bezel expansion coefficient α;
(5-4) representing the vehicle trajectory between adjacent time instants using a set of line segments
Wherein the content of the first and second substances,on the virtual protective frameThe position of the point at the moment k, and so on;
(5-5) establishing a vehicle and obstacle avoidance collision restraint:
wherein the content of the first and second substances, it is shown that the intersection is by-passed,indicating vehicle trajectoryAnd obstaclesNon-intersecting.
In the step (6), the established state variable and input variable constraint concrete formula is as follows:
wherein v isminIndicating the minimum speed, v, at which the vehicle is moving forwardmaxRepresenting the maximum speed, δ, at which the vehicle is travellingfminIndicating the minimum angle, δ, of steering of the front wheelsfmaxIndicating the maximum angle of steering of the front wheels.
In the step (7), the optimization objective and the optimization problem are specifically as follows:
minT·N
s.t.
wherein minT.N is an optimization target and represents the minimum total time, T is a sampling period, N is the number of samples, s.t. represents obedience to the following constraints, ξ0State variable representing time 0, ξNRepresenting the state variable at time N.
In step (8), the information track included in the autonomous parking track is trackAnd corresponding operationsWherein traj (k) represents an x-axis coordinate, a y-axis coordinate, and an included angle between a vehicle advancing direction and an x-axis of the vehicle in the global coordinate system at the time k, and u (k) represents a vehicle advancing speed and a front wheel steering angle at the time k.
In the step (9), the step of recalculating the expansion coefficient of the virtual protection frame is as follows:
(9-1) calculating a difference between the virtual fender frame and the curvature radius of the vehicle contour at each time:
wherein, δ R1|kIndicating the difference of the radius of curvature of the front left of the vehicle, δ R2|kIndicating the difference, δ R, in the radius of curvature of the front right of the vehicle3|kIndicating vehicleDifference between rear right-hand radius of curvature, δ R4|kIndicating the difference in the left rear radius of curvature of the vehicle,represents the turning radius of the vertex of the left front of the rectangle where the vehicle is positioned at the moment k,represents the turning radius of the right front vertex of the rectangle where the vehicle is located at the moment k,indicating the turning radius of the right rear vertex of the rectangle in which the vehicle is located at the time point k,represents the turning radius of the left rear vertex of the rectangle where the vehicle is located at the moment k,represents the turning radius of the left front vertex of the virtual protective frame at the time point k,represents the turning radius of the left front vertex of the virtual protective frame at the time point k,represents the turning radius of the left front vertex of the virtual protective frame at the time point k,the turning radius at the time k of the left front vertex of the virtual fender frame is shown as follows
Wherein the content of the first and second substances,is the vehicle turning curvature; w is expressed as vehicle width, lfIndicating the distance between the center of gravity of the vehicle and the head, lrExpressed as the distance between the center of gravity of the vehicle and the rear of the vehicle, α1|kThe virtual mask expansion coefficient represented as the vertex at the front left of the virtual mask at time k, α2|kThe virtual reticle expansion coefficient represented as the right front vertex of the virtual reticle at time k, α3|kThe virtual mask expansion coefficient represented as the right rear vertex of the virtual mask at time k, α4|kThe virtual protection frame expansion coefficient is expressed as the vertex at the left back of the virtual protection frame at the moment k;
(9-2) calculating the maximum error of the turning arc and the turning line segment:
wherein the content of the first and second substances,represents the maximum error of the vertex at the front left of the virtual protective frame at the moment k,represents the maximum error of the right front vertex of the virtual protective frame at the moment k,expressed as the maximum error of the rear right vertex of the virtual protection frame at the time k,the maximum error of the left rear vertex of the virtual protection frame at the moment k is represented;
(9-3) defining a distance function
Calculating the optimal virtual protection frame expansion coefficient
Wherein the content of the first and second substances,representing distance function distancei|kMax represents the maximum value of the set;
if α*Absolute value of- α being less than 0.001, stopStopping iteration, and finally stopping the autonomous parking trajectory, otherwise, leading α0=α*And (5) repeating the steps (4) to (8).
Compared with the prior art, the invention has the following beneficial effects:
1. the invention generates the parking track with time information, thereby facilitating the subsequent controller design.
2. The invention uses the concept of the virtual protection frame and the concept of the expansion coefficient of the virtual protection frame to ensure that the generated track does not collide with the barrier.
3. The method has no specific requirements on parking scenes, and can be widely applied to parking scenes such as backing up and warehousing, parking at a side position, parking at an oblique direction and the like.
Drawings
FIG. 1 is a parking scenario in an embodiment of the present invention;
FIG. 2 is a flow chart of an autonomous parking trajectory planning method suitable for multiple scenes according to the present invention;
fig. 3 is a final planned parking trajectory in the embodiment of the present invention.
Detailed Description
The invention will be described in further detail below with reference to the drawings and examples, which are intended to facilitate the understanding of the invention without limiting it in any way.
In the embodiment, a vehicle backing and warehousing is taken as an example, and the autonomous parking trajectory planning method suitable for multiple scenes is described in detail.
The vehicle needs to complete backing and parking in the parking scene shown in fig. 1, wherein the parking space is 5 meters long, the width is 2.5 meters, and the width of the operation road surface is 6 m.
As shown in fig. 2, an autonomous parking trajectory planning method suitable for multiple scenes includes:
step 1, detecting a parking environment and constructing a parking map, wherein obstacles are represented by closed or semi-closed polygons;
And 3, determining vehicle physical parameters and initializing an expansion coefficient of the virtual protection frame, wherein the vehicle physical parameters to be determined are that the vehicle width w is 1.9m, the wheel base L is 2.7m, and the initialized value of the expansion coefficient of the virtual protection frame is α0=1。
And 4, expressing a vehicle kinematic differential equation as vehicle motion state constraint, wherein the specific implementation mode is as follows:
step 4-1, the motion state of the vehicle is described using the following differential equation:
wherein X represents the X-axis coordinate of the center of gravity of the vehicle in the global coordinate system, Y represents the Y-axis coordinate of the center of gravity of the vehicle in the global coordinate system,representing the included angle between the right front direction of the vehicle and the x axis; v represents the vehicle forward speed, δfIndicating the front wheel steering angle. The above differential equation is written as:
wherein the content of the first and second substances,denotes the state variable, u ═ v δf]TRepresenting the input variables.
Step 4-2, assume ξ0,ξ1,...,ξNIs N +1 state variables to be planned, according to the kinematic model of the vehicle, at the known current state ξkThen, next oneState of the momentCan be expressed as:
r1=f(ξk,uk)
wherein r is1,r2,r3,r4Is the intermediate state value and T represents the sampling period, in this embodiment, N is taken to be 50.
Step 4-3, establishing vehicle motion state constraint:
step 5-1, the obstacle is composed of a polygon OjIs represented by, defined as
Wherein the subscript J indicates the jth obstacle, for a total of J obstacles,represents a polygon OjIn the clockwise directionThe (i) th vertex is (is) the vertex,representing the jth obstacleAnd the line segment of the vertex is connected, and the like.
Step 5-2, the vehicle is represented by rectangle E, defined as
Wherein E is1Indicates the left front vertex of the rectangle in which the vehicle is located, E2Indicating the right front vertex of the rectangle in which the vehicle is located, E3Indicating the right rear vertex of the rectangle in which the vehicle is located, E4The left rear vertex of the rectangle in which the vehicle is located is shown,indicating the vehicle E1,E2And the line segment of the vertex is connected, and the like.
Step 5-3, defining a virtual protective frame E around the vehiclef
E and EfThe relationship of (A) is EfThe length in the direction parallel to the vehicle is equal to the corresponding length of E, EfThe length in the direction perpendicular to the vehicle is equal to the corresponding length of E multiplied by the virtual bezel expansion coefficient α.
Step 5-4, representing the vehicle track between adjacent moments by using a line segment set
Step 5-5, establishing collision avoidance restraint of the vehicle and the barrier:
and 7, determining an optimization target, and establishing an optimization problem, wherein the specific form of the optimization problem is as follows:
minT·N
s.t.
and 8, solving the optimization problem by using a nonlinear programming solver to obtain an alternative autonomous parking track containing information with tracksAnd corresponding operations
Step 9, recalculating the expansion coefficient of the virtual protection frame, wherein the specific implementation method comprises the following steps:
step 9-1, calculating the difference between the curvature radii of the virtual protective frame and the vehicle outline at each moment:
wherein the content of the first and second substances,
Step 9-2, calculating the maximum error of the turning arc and the turning line segment:
step 9-3, defining a distance function
distancei|k=ErrorEi|k-δRi|k
Calculating the optimal expansion coefficient of the virtual protective frame,
wherein the content of the first and second substances,representing distance function distancei|kLower limit of (1), max tableThe maximum value of the set is shown.
If α*- α absolute value less than 0.001, stop iteration, final autonomous parking trajectory, otherwise order α0=α*And repeating the steps 4 to 8.
The finally planned parking trajectory is shown in fig. 3, the vehicle from global coordinatesStarting from a target berth ofBy using the method, the planned track can be ensured not to collide with the barrier, and the method has the advantages of safety and feasibility.
The embodiments described above are intended to illustrate the technical solutions and advantages of the present invention, and it should be understood that the above-mentioned embodiments are only specific embodiments of the present invention, and are not intended to limit the present invention, and any modifications, additions and equivalents made within the scope of the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. An autonomous parking trajectory planning method suitable for multiple scenes is characterized by comprising the following steps:
(1) detecting a parking environment and constructing a parking map;
(2) determining the current position of the vehicle and the position of a target parking space;
(3) determining physical parameters of the vehicle, and initializing the expansion coefficient of a virtual protection frame of the vehicle;
(4) according to a vehicle kinematic differential equation, establishing vehicle motion state constraint;
(5) establishing collision avoidance restraint between the vehicle and the barrier by using the virtual protective frame and the expansion coefficient of the virtual protective frame;
(6) establishing state variable and input variable constraints according to vehicle mechanical principle limitations and comfort requirements;
(7) determining an optimization target and establishing an optimization problem;
(8) solving an optimization problem by using a nonlinear programming solver to obtain an alternative autonomous parking track;
(9) and (4) recalculating the expansion coefficient of the virtual protection frame, obtaining the final autonomous parking track if the expansion coefficient of the virtual protection frame meets the stop condition, otherwise, updating the expansion coefficient of the virtual protection frame, and repeating the steps (4) to (8).
2. The method for planning the autonomous parking trajectory for multiple scenes according to claim 1, wherein in the step (1), the parking map is constructed by using closed or semi-closed polygons to represent the obstacles.
3. The method for planning the autonomous parking trajectory for multiple scenes according to claim 1, wherein in step (2), the current position and the target parking space position of the vehicle are respectively represented asAndthe vehicle center of gravity detection method specifically comprises an x-axis coordinate and a y-axis coordinate of the vehicle center of gravity under a global coordinate system, and an included angle between the vehicle advancing direction and the positive direction of the x axis of the global coordinate system.
4. The method for planning the autonomous parking trajectory in multiple scenes according to claim 3, wherein in the step (3), the physical parameters of the vehicle to be determined include a vehicle width w and a wheel base L, and the initial value of the expansion coefficient of the virtual fender box is α0=1。
5. The method for planning the autonomous parking trajectory in multiple scenes according to claim 4, wherein the specific process of the step (4) is as follows:
(4-1) describing a motion state of the vehicle using a differential equation as follows:
wherein X represents the X-axis coordinate of the center of gravity of the vehicle in the global coordinate system, Y represents the Y-axis coordinate of the center of gravity of the vehicle in the global coordinate system,representing the included angle between the right front direction of the vehicle and the x axis;andrespectively X, Y anddifferentiation of (1); v represents the vehicle forward speed, δfRepresenting a front wheel steering angle; taking the differential equation as a kinematic model of the vehicle, and recording as:
wherein the content of the first and second substances,denotes the state variable, u ═ v δf]TRepresenting an input variable;
(4-2) hypothesis ξ0,ξ1,...,ξNIs N +1 state variables to be planned, the state variable ξ at the known current time k according to the kinematic model of the vehiclekState variables of time, next timeExpressed as:
r1=f(ξk,uk)
wherein r is1,r2,r3,r4Is an intermediate state value, ukAn input variable representing time k, and T represents a sampling period;
(4-3) establishing vehicle motion state constraint:
6. the method for planning the autonomous parking trajectory for multiple scenes according to claim 5, wherein the specific process of the step (5) is as follows:
(5-1) obstacle composed of polygon OjIs represented by, defined as
Wherein the subscript J indicates the jth obstacle, for a total of J obstacles,represents a polygon OjThe ith vertex in the clockwise direction,representing the jth obstacleThe line segment of the vertex is analogized in the same way;
(5-2) the vehicle is represented by a rectangle E, defined as
Wherein E is1Indicates the left front vertex of the rectangle in which the vehicle is located, E2Indicating the right front vertex of the rectangle in which the vehicle is located, E3Indicating the right rear vertex of the rectangle in which the vehicle is located, E4The left rear vertex of the rectangle in which the vehicle is located is shown,indicating the vehicle E1,E2The line segment of the vertex is analogized in the same way;
(5-3) defining a virtual protective frame E around the vehiclef
E and EfThe relationship of (A) is EfThe length in the direction parallel to the vehicle is equal to the corresponding length of E, EfA corresponding length in the direction perpendicular to the vehicle equal to E multiplied by the virtual bezel expansion coefficient α;
(5-4) representing the vehicle trajectory between adjacent time instants using a set of line segments
Wherein the content of the first and second substances,on the virtual protective frameThe position of the point at the moment k, and so on;
(5-5) establishing a vehicle and obstacle avoidance collision restraint:
7. The method for planning the autonomous parking trajectory in multiple scenes according to claim 6, wherein in the step (6), the specific formula of the established state variable and input variable constraints is as follows:
wherein v isminIndicating the minimum speed, v, at which the vehicle is moving forwardmaxRepresenting the maximum speed, δ, at which the vehicle is travellingfminIndicating the minimum angle, δ, of steering of the front wheelsfmaxIndicating the maximum angle of steering of the front wheels.
8. The method for planning the autonomous parking trajectory in multiple scenes according to claim 6, wherein in the step (7), the optimization objective and the optimization problem are specifically as follows:
minT·N
s.t.
wherein minT.N is an optimization target and represents the minimum total time, T is a sampling period, N is the number of samples, s.t. represents obedience to the following constraints, ξ0State variable representing time 0, ξNRepresenting the state variable at time N.
9. The method for planning an autonomous parking trajectory for multiple scenes according to claim 8, wherein in step (8), the autonomous parking trajectory includes information including a trajectoryAnd corresponding operationsWherein traj (k) represents an x-axis coordinate, a y-axis coordinate, and an included angle between a vehicle advancing direction and an x-axis of the vehicle in the global coordinate system at the time k, and u (k) represents a vehicle advancing speed and a front wheel steering angle at the time k.
10. The method for planning the autonomous parking trajectory for multiple scenes according to claim 9, wherein in step (9), the step of recalculating the expansion coefficient of the virtual guard frame is as follows:
(9-1) calculating a difference between the virtual fender frame and the curvature radius of the vehicle contour at each time:
wherein, δ R1|kIndicating the difference of the radius of curvature of the front left of the vehicle, δ R2|kIndicating the difference, δ R, in the radius of curvature of the front right of the vehicle3|kIndicating the difference between the right rear radii of curvature of the vehicle, δ R4|kIndicating the difference in the left rear radius of curvature of the vehicle,represents the turning radius of the vertex of the left front of the rectangle where the vehicle is positioned at the moment k,represents the turning radius of the right front vertex of the rectangle where the vehicle is located at the moment k,indicating the turning radius of the right rear vertex of the rectangle in which the vehicle is located at the time point k,represents the turning radius of the left rear vertex of the rectangle where the vehicle is located at the moment k,represents the turning radius of the left front vertex of the virtual protective frame at the time point k,represents the turning radius of the left front vertex of the virtual protective frame at the time point k,represents the turning radius of the left front vertex of the virtual protective frame at the time point k,the turning radius at the time k of the left front vertex of the virtual fender frame is shown as follows
Wherein the content of the first and second substances,is the vehicle turning curvature; w is expressed as vehicle width, lfIndicating the distance between the center of gravity of the vehicle and the head, lrExpressed as the distance between the center of gravity of the vehicle and the rear of the vehicle, α1|kThe virtual mask expansion coefficient represented as the vertex at the front left of the virtual mask at time k, α2|kThe virtual reticle expansion coefficient represented as the right front vertex of the virtual reticle at time k, α3|kThe virtual mask expansion coefficient represented as the right rear vertex of the virtual mask at time k, α4|kThe virtual protection frame expansion coefficient is expressed as the vertex at the left back of the virtual protection frame at the moment k;
(9-2) calculating the maximum error of the turning arc and the turning line segment:
wherein the content of the first and second substances,represents the maximum error of the vertex at the front left of the virtual protective frame at the moment k,represents the maximum error of the right front vertex of the virtual protective frame at the moment k,expressed as the maximum error of the rear right vertex of the virtual protection frame at the time k,the maximum error of the left rear vertex of the virtual protection frame at the moment k is represented;
(9-3) defining a distance function
Calculating the optimal virtual protection frame expansion coefficient
Wherein the content of the first and second substances,representing distance function distancei|kMax represents the maximum value of the set;
if α*- α absolute value less than 0.001, stop iteration, final autonomous parking trajectory, otherwise order α0=α*And (5) repeating the steps (4) to (8).
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911391911.0A CN111089594B (en) | 2019-12-30 | 2019-12-30 | Autonomous parking trajectory planning method suitable for multiple scenes |
PCT/CN2020/125930 WO2021135617A1 (en) | 2019-12-30 | 2020-11-02 | Autonomous parking trajectory planning method suitable for multiple scenes |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911391911.0A CN111089594B (en) | 2019-12-30 | 2019-12-30 | Autonomous parking trajectory planning method suitable for multiple scenes |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111089594A true CN111089594A (en) | 2020-05-01 |
CN111089594B CN111089594B (en) | 2021-09-07 |
Family
ID=70397573
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911391911.0A Active CN111089594B (en) | 2019-12-30 | 2019-12-30 | Autonomous parking trajectory planning method suitable for multiple scenes |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111089594B (en) |
WO (1) | WO2021135617A1 (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111783595A (en) * | 2020-06-24 | 2020-10-16 | 中国第一汽车股份有限公司 | Vehicle parking method and device, vehicle-mounted equipment and storage medium |
CN112799393A (en) * | 2020-12-04 | 2021-05-14 | 湖南大学 | Parking scene oriented map simplifying system |
CN112937555A (en) * | 2021-03-08 | 2021-06-11 | 华南理工大学 | Parallel parking trajectory planning method based on vehicle kinematics model |
WO2021135617A1 (en) * | 2019-12-30 | 2021-07-08 | 浙江大学 | Autonomous parking trajectory planning method suitable for multiple scenes |
CN113096209A (en) * | 2021-03-29 | 2021-07-09 | 惠州华阳通用电子有限公司 | Display method of vehicle-mounted image trajectory line |
WO2021227304A1 (en) * | 2020-05-09 | 2021-11-18 | 惠州市德赛西威汽车电子股份有限公司 | Obstacle avoidance method in automatic parking path planning and parking path planning system |
CN114347982A (en) * | 2021-12-24 | 2022-04-15 | 北京经纬恒润科技股份有限公司 | Path planning method and system for automatic parking |
CN114435345A (en) * | 2022-01-25 | 2022-05-06 | 岚图汽车科技有限公司 | Automatic parking square column anti-collision method and system |
CN114475780A (en) * | 2021-12-21 | 2022-05-13 | 大连中科创达软件有限公司 | Automatic parking method, device, equipment and storage medium |
WO2023123704A1 (en) * | 2021-12-28 | 2023-07-06 | 魔门塔(苏州)科技有限公司 | Automatic parking path planning method and apparatus, medium, and device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100076640A1 (en) * | 2008-09-22 | 2010-03-25 | Komatsu Ltd. | Travel route generating method for unmanned vehicle |
CN102963355A (en) * | 2012-11-01 | 2013-03-13 | 同济大学 | Intelligent auxiliary parking method and implementation system thereof |
CN105335797A (en) * | 2015-11-03 | 2016-02-17 | 浙江大学 | Automatic parking locus optimization method based on full-simultaneous dynamic optimization framework |
CN105857306A (en) * | 2016-04-14 | 2016-08-17 | 中国科学院合肥物质科学研究院 | Vehicle autonomous parking path programming method used for multiple parking scenes |
CN108121205A (en) * | 2017-12-13 | 2018-06-05 | 深圳市航盛电子股份有限公司 | A kind of paths planning method, system and medium for a variety of scenes of parking |
CN109910878A (en) * | 2019-03-21 | 2019-06-21 | 山东交通学院 | Automatic driving vehicle avoidance obstacle method and system based on trajectory planning |
CN110352391A (en) * | 2017-01-20 | 2019-10-18 | 株式会社久保田 | Operation Van |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB201100840D0 (en) * | 2011-01-18 | 2011-08-17 | Bae Systems Plc | Trajectory planning |
KR101525897B1 (en) * | 2014-02-04 | 2015-06-04 | 계명대학교 산학협력단 | auto-docking control method of bus, and thereof control system |
KR102463453B1 (en) * | 2016-12-14 | 2022-11-04 | 현대자동차주식회사 | Method of Auto Parking Control and Shift By Wire System thereof |
CN107672585B (en) * | 2017-08-29 | 2019-09-17 | 广州小鹏汽车科技有限公司 | A kind of automatic parking paths planning method and system |
CN111089594B (en) * | 2019-12-30 | 2021-09-07 | 浙江大学 | Autonomous parking trajectory planning method suitable for multiple scenes |
-
2019
- 2019-12-30 CN CN201911391911.0A patent/CN111089594B/en active Active
-
2020
- 2020-11-02 WO PCT/CN2020/125930 patent/WO2021135617A1/en active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100076640A1 (en) * | 2008-09-22 | 2010-03-25 | Komatsu Ltd. | Travel route generating method for unmanned vehicle |
CN102963355A (en) * | 2012-11-01 | 2013-03-13 | 同济大学 | Intelligent auxiliary parking method and implementation system thereof |
CN105335797A (en) * | 2015-11-03 | 2016-02-17 | 浙江大学 | Automatic parking locus optimization method based on full-simultaneous dynamic optimization framework |
CN105857306A (en) * | 2016-04-14 | 2016-08-17 | 中国科学院合肥物质科学研究院 | Vehicle autonomous parking path programming method used for multiple parking scenes |
CN110352391A (en) * | 2017-01-20 | 2019-10-18 | 株式会社久保田 | Operation Van |
CN108121205A (en) * | 2017-12-13 | 2018-06-05 | 深圳市航盛电子股份有限公司 | A kind of paths planning method, system and medium for a variety of scenes of parking |
CN109910878A (en) * | 2019-03-21 | 2019-06-21 | 山东交通学院 | Automatic driving vehicle avoidance obstacle method and system based on trajectory planning |
Non-Patent Citations (2)
Title |
---|
XIAOJING ZHANG 等: "Autonomous Parking using Optimization-Based Collision Avoidance", 《2018 IEEE CONFERENCE ON DECISION AND CONTROL (CDC)》 * |
张仁永: "平行泊车轨迹规划及控制算法研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021135617A1 (en) * | 2019-12-30 | 2021-07-08 | 浙江大学 | Autonomous parking trajectory planning method suitable for multiple scenes |
WO2021227304A1 (en) * | 2020-05-09 | 2021-11-18 | 惠州市德赛西威汽车电子股份有限公司 | Obstacle avoidance method in automatic parking path planning and parking path planning system |
CN111783595A (en) * | 2020-06-24 | 2020-10-16 | 中国第一汽车股份有限公司 | Vehicle parking method and device, vehicle-mounted equipment and storage medium |
CN112799393B (en) * | 2020-12-04 | 2022-04-19 | 湖南大学 | Parking scene oriented map simplifying system |
CN112799393A (en) * | 2020-12-04 | 2021-05-14 | 湖南大学 | Parking scene oriented map simplifying system |
CN112937555A (en) * | 2021-03-08 | 2021-06-11 | 华南理工大学 | Parallel parking trajectory planning method based on vehicle kinematics model |
CN113096209A (en) * | 2021-03-29 | 2021-07-09 | 惠州华阳通用电子有限公司 | Display method of vehicle-mounted image trajectory line |
CN114475780A (en) * | 2021-12-21 | 2022-05-13 | 大连中科创达软件有限公司 | Automatic parking method, device, equipment and storage medium |
CN114475780B (en) * | 2021-12-21 | 2023-09-15 | 大连中科创达软件有限公司 | Automatic parking method, device, equipment and storage medium |
CN114347982A (en) * | 2021-12-24 | 2022-04-15 | 北京经纬恒润科技股份有限公司 | Path planning method and system for automatic parking |
WO2023123704A1 (en) * | 2021-12-28 | 2023-07-06 | 魔门塔(苏州)科技有限公司 | Automatic parking path planning method and apparatus, medium, and device |
CN114435345A (en) * | 2022-01-25 | 2022-05-06 | 岚图汽车科技有限公司 | Automatic parking square column anti-collision method and system |
CN114435345B (en) * | 2022-01-25 | 2023-10-24 | 岚图汽车科技有限公司 | Automatic parking square column anti-collision method and system |
Also Published As
Publication number | Publication date |
---|---|
WO2021135617A1 (en) | 2021-07-08 |
CN111089594B (en) | 2021-09-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111089594B (en) | Autonomous parking trajectory planning method suitable for multiple scenes | |
CN110298122B (en) | Unmanned vehicle urban intersection left-turn decision-making method based on conflict resolution | |
CN107264531B (en) | The autonomous lane-change of intelligent vehicle is overtaken other vehicles motion planning method in a kind of semi-structure environment | |
CN110018689B (en) | Dynamic window-based multi-virtual target point global dynamic path planning algorithm | |
US20200406969A1 (en) | Lane Change Maneuvers With Minimized Tire Slip | |
CN110361013B (en) | Path planning system and method for vehicle model | |
CN105857306A (en) | Vehicle autonomous parking path programming method used for multiple parking scenes | |
CN111806467A (en) | Variable speed dynamic track changing planning method based on vehicle driving rule | |
CN109941275A (en) | Lane changing method, apparatus, electronic equipment and storage medium | |
CN112810630A (en) | Method and system for planning track of automatic driving vehicle | |
JP7315039B2 (en) | How to find an avoidance route for a car | |
CN114610016B (en) | Intelligent vehicle collision avoidance path planning method based on obstacle dynamic virtual expansion | |
CN111896004A (en) | Narrow passage vehicle track planning method and system | |
CN113895463B (en) | Path planning method suitable for turning around of automatic driving vehicle | |
CN116499486B (en) | Complex off-road environment path planning method and system and electronic equipment | |
CN114637292A (en) | Vehicle track tracking robust control method and system considering obstacle avoidance | |
CN113635898A (en) | Method, apparatus, storage medium, and program product for vehicle speed limit control | |
Li et al. | Adaptive sampling-based motion planning with a non-conservatively defensive strategy for autonomous driving | |
Osman et al. | Vision based lane reference detection and tracking control of an automated guided vehicle | |
CN112238856B (en) | Intelligent vehicle overtaking track optimization method based on hybrid particle swarm optimization | |
Wurts et al. | Minimum slip collision imminent steering in curved roads using nonlinear model predictive control | |
Hu et al. | Decision-making System based on Finite State Machine for Low-speed Autonomous Vehicles in the Park | |
CN114537435A (en) | Real-time whole vehicle track planning method in automatic driving | |
CN114889589A (en) | Intelligent automobile steering and braking cooperative collision avoidance control system and method | |
CN111857112B (en) | Automobile local path planning method and electronic equipment |
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 |