CN115123202A - Optimal path planning-based target parking space selection method and system - Google Patents
Optimal path planning-based target parking space selection method and system Download PDFInfo
- Publication number
- CN115123202A CN115123202A CN202210879379.2A CN202210879379A CN115123202A CN 115123202 A CN115123202 A CN 115123202A CN 202210879379 A CN202210879379 A CN 202210879379A CN 115123202 A CN115123202 A CN 115123202A
- Authority
- CN
- China
- Prior art keywords
- parking space
- vehicle
- parking
- target parking
- 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.)
- Pending
Links
- 238000010187 selection method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 18
- 230000033001 locomotion Effects 0.000 claims description 17
- 230000001133 acceleration Effects 0.000 claims description 13
- 230000036461 convulsion Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 8
- 230000003068 static effect Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 abstract description 24
- 230000036544 posture Effects 0.000 description 23
- 230000014509 gene expression Effects 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 3
- 230000000593 degrading effect Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a target parking space selection method and system based on optimal path planning, and relates to the technical field of automatic parking space selection. By adding the track prediction influence of the dynamic barrier, the planning of the parking track and the selection of the optimal track and the optimal target parking space are adjusted, and the safety, the efficiency and the predictability of the parking are further improved. And scene judgment is added, and parking planning of scenes of fixed parking spaces and public parking spaces is comprehensively considered, so that the parking habit and convenience of a driver are better met.
Description
Technical Field
The invention relates to the technical field of automatic parking stall selection, in particular to a target stall selection method and a target stall selection system based on optimal path planning.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
With the rapid growth of the quantity of motor vehicles in China, the problems of urban congestion, short traffic infrastructure resources and the like are aggravated, and particularly, the demand for parking spaces is rapidly increased, so that the existing parking spaces are narrow and compact, and therefore, a plurality of parking problems such as frequent parking safety accidents, high technical difficulty, long time consumption and the like are caused, and the daily trip experience and the driving experience of people are seriously influenced.
Along with the increasingly prominent parking problem, the related automatic parking technology is also rapidly developed, the automatic parking system greatly improves the safety and the high efficiency of parking, reduces the driving difficulty and the driving strength of a driver, improves the driving experience, and realizes safe, efficient and convenient parking.
The inventor finds that the automatic parking system has the following problems: the traditional parking system mainly controls the vehicle to park after planning a parking track by identifying a certain parking space around the vehicle body and sensing the surrounding environment, but has less consideration on identifying the optimal track planning and selecting the optimal target parking space under a plurality of parking spaces around the vehicle body, and does not realize the comprehensive optimal planning under the real parking environment. Meanwhile, the existing automatic parking system only senses and identifies parking spaces, obstacles and the like to acquire environmental information, but does not consider the prediction of the future movement track of the dynamic obstacle, so that the vehicle cannot well adjust the path in real time according to the movement track of the obstacle. Therefore, a method is needed to realize intelligent planning of an optimal path and optimal parking space selection under a real parking scene, so as to reduce safety risks caused by dynamic obstacles and overcome the limitation of parking in a single target parking space.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a target parking space selection method and a target parking space selection system based on optimal path planning. By adding the track prediction influence of the dynamic barrier, the planning of the parking track and the selection of the optimal track and the optimal target parking space are adjusted, and the safety, the efficiency and the predictability of the parking are further improved. And scene judgment is added, and parking planning of scenes of fixed parking spaces and public parking spaces is comprehensively considered, so that the parking habit and convenience of a driver are better met.
In order to achieve the purpose, the invention is realized by the following technical scheme:
the first aspect of the disclosure provides a target parking space selection method based on optimal path planning, which includes the following steps:
vehicle parameters are collected, and the current environment of the vehicle is judged based on the selection of the destination; identifying the parking space and establishing a space coordinate system after the judgment;
sensing obstacles in the environment and predicting short-time trajectories of dynamic obstacles in real time;
determining the initial attitude of the vehicle and the relative position of the vehicle and each recognition parking space by using the sensing data;
judging whether the parking condition is met or not, and determining a first-level target parking space range;
planning longitudinal speed, acceleration and jerk curves of the vehicle in the parking process, and selecting a parking track strategy according to the initial posture of the vehicle and the relative position of the vehicle and each recognition parking space based on a planning result;
considering the influence of obstacles, screening parking spaces capable of successfully planning a safety path in a primary target parking space range to form a secondary target parking space range;
and comprehensively selecting an optimal target parking space and a parking track according to the vehicle parking track efficiency of each target parking space and the distance between the optimal target parking space and the destination in the range of the secondary target parking spaces, and parking the vehicle into the optimal target parking space according to the optimal parking track.
Further, in the parking space identification process, a camera is used for identifying a parking space with a parking space line, and an ultrasonic radar is used for identifying a parking space without the parking space line but with a parked vehicle on one side or two sides of the parking space; and judging the occupation states of all the identified parking spaces, screening all the identified empty parking spaces around the vehicle, and uploading information of all the empty parking spaces.
Furthermore, the spatial coordinate system calculates the position coordinates of each point of the vehicle body through distance and direction angle information by taking the center of the parking space inlet as an origin, the lane direction as an x axis and the vertical lane direction as a y axis.
Furthermore, the sensing process of the obstacles in the environment comprises the steps of sensing the obstacles by utilizing the camera and the ultrasonic radar in a fusion mode, namely identifying the obstacles by utilizing the camera, measuring the size of the obstacles and measuring distance, and simultaneously measuring the distance and the size of the obstacles by utilizing the ultrasonic radar, wherein data of the two sensors are mutually supplemented, and the two sensors are mutually corrected.
Furthermore, after the camera and the ultrasonic radar are fused to sense the dynamic barrier, the motion track of the dynamic barrier is tracked, the motion track of the dynamic barrier in a future period of time is predicted according to the type and the historical motion track, and meanwhile, the motion track of the dynamic barrier is continuously updated and the predicted track is corrected in real time.
Further, the process of obtaining the initial attitude of the vehicle and the relative position of the vehicle to the parking space includes measuring angular distances to the parking space by using cameras and ultrasonic radars at various positions of the vehicle body in the established spatial coordinate system to measure and calculate the position and the attitude of the vehicle body, and obtaining the relative position relationship between the vehicle and the parking space and the initial attitude parameters of the vehicle.
And further, the process of planning out the safe path comprises the steps of judging whether the position and the size of the static barrier conflict with the planned track, degrading the parking track strategy to plan the track again if the position and the size of the static barrier conflict with the planned track, and judging again until a conflict-free track or a safety-free track is planned.
The second aspect of the present disclosure provides a target parking space selecting system based on optimal path planning, including:
the parking space identification module is configured to collect vehicle parameters and judge the current environment of the vehicle based on the selection of the destination; identifying the parking space and establishing a space coordinate system after the judgment;
the obstacle prediction module is configured to sense obstacles in the environment and predict short-time trajectories of the dynamic obstacles in real time;
the primary target parking space module is configured to acquire an initial posture of the vehicle and a relative position of the vehicle and each parking space, and determine the initial posture of the vehicle and the relative position of the vehicle and each recognition parking space by using the sensing data; judging whether the parking condition is met or not, and determining a first-level target parking space range;
planning longitudinal speed, acceleration and jerk curves of the vehicle in the parking process, and selecting a parking track strategy according to the initial posture of the vehicle and the relative position of the vehicle and each recognition parking space based on a planning result;
the secondary target parking space module is configured to consider the influence of obstacles, screen out parking spaces capable of successfully planning a safety path in a primary target parking space range, and form a secondary target parking space range;
the optimal track and parking space selection module is configured to comprehensively select an optimal target parking space and a parking track according to the vehicle parking track efficiency of each target parking space and the distance between the optimal target parking space and a destination in a secondary target parking space range;
and the vehicle driving-in module is configured to park the vehicle into the optimal target parking space according to the optimal parking track.
A third aspect of the present disclosure provides a medium, on which a program is stored, where the program, when executed by a processor, implements the steps in the optimal path planning-based target parking space selection method according to the first aspect of the present disclosure.
A fourth aspect of the present disclosure provides an apparatus, including a memory, a processor, and a program stored in the memory and executable on the processor, where the processor executes the program to implement the steps in the optimal path planning-based target parking space selection method according to the first aspect of the present disclosure.
The beneficial effects of the above-mentioned embodiment of the present invention are as follows:
the invention adjusts the planning of the parking track and the selection of the optimal track and the optimal target parking space by adding the track prediction influence of the dynamic barrier, thereby further improving the safety, the high efficiency and the predictability of the parking. And scene judgment is added, and parking planning of scenes of fixed parking spaces and public parking spaces is comprehensively considered, so that the parking habit and convenience of a driver are better met.
In the parking process, firstly, a plurality of parking spaces are identified around a vehicle body, information of each parking space is obtained, then a parking track is planned for each parking space capable of being parked through different parking track strategies, and the safest and efficient track, namely the optimal track, is selected, so that double optimal selection of the optimal track and the optimal target parking space is realized.
According to the invention, for the selection of the optimal track and the optimal target parking space, the predicted track influence of the dynamic barrier and the distance influence between the parking space and the destination are added, so that the parking track planning with better optimization, safety, high efficiency and predictability and the target parking space selection with higher efficiency and convenience are realized.
The invention adds scene classification to distinguish and plan the public parking space scene and the fixed parking space scene, and can automatically go to the fixed parking space for parking when the fixed parking space is arranged nearby, thereby better conforming to the parking habit of the driver.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a flowchart of a method for selecting a target parking space based on optimal path planning according to an embodiment of the present invention.
The specific implementation mode is as follows:
it should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an", and/or "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof;
the first embodiment is as follows:
the embodiment of the present disclosure provides a target parking space selection method based on optimal path planning, as shown in fig. 1, including the following steps:
s1, collecting vehicle parameters, and judging the current environment of the vehicle based on the selection of the destination; and identifying the parking space and establishing a space coordinate system after the judgment.
Preferably, the vehicle parameters include vehicle size, driver's fixed parking position, and the like.
S1.1: and judging the current environment of the vehicle, and acquiring environment information such as the position of an entrance and an exit.
Preferably, the current environment of the vehicle includes a roadside parking environment, a public parking lot, and a parking lot with a fixed parking space, such as a community, a company, and the like.
S1.1.1: the vehicle position information acquired by the vehicle-mounted GPS is firstly used for judging the distance from the fixed parking space position input by the vehicle owner, and when the distance is short, the vehicle goes to the fixed parking space directly for parking. When the distance is farther: and judging the environment of the vehicle in the map according to the position information of the vehicle, and further confirming the environment of the vehicle according to different environment characteristics through a camera and an ultrasonic radar. When the vehicle position is in a road and the environment has a plurality of lane lines, the environment is a roadside parking environment; a parking lot environment is when the vehicle location is in a parking lot and there are no multiple lane lines in the environment.
S1.2: when the vehicle is located in a parking lot with a fixed parking space, such as a residential area, a company and the like, the parking space does not need to be selected, and the vehicle only needs to be controlled to go to the fixed parking space and an optimal parking track is planned for parking.
S1.3: the method comprises the steps of utilizing a camera and an ultrasonic radar to identify parking spaces in a certain range around a vehicle, determining specific information such as occupation states, positions and sizes of the parking spaces, and establishing a space coordinate system.
S1.3.1: the parking spaces with the parking space lines are identified by the aid of the cameras, and the parking spaces without the parking space lines but with parking vehicles on one side or two sides are identified by the aid of the ultrasonic radar. And judging the occupation states of all the identified parking spaces, screening all the identified empty parking spaces around the vehicle, and uploading information of all the empty parking spaces.
Preferably, the parking space information such as the parking space position and the size is determined by the position of a parking space angle, and the parking space angle position information is obtained by sensing of a camera and an ultrasonic radar.
S1.3.2: the space coordinate system is established by taking the center of the parking space inlet as an original point, taking the lane direction as an x axis and taking the vertical lane direction as a y axis, and the position coordinates of each point of the vehicle body can be calculated through information such as distance, direction angle and the like.
S1.4: if no empty parking space is identified around the vehicle, the driver is reminded that no parking space can be parked around the vehicle, the vehicle is controlled to keep running at a low speed in the current lane, and if the driver reaches a turning opening, the vehicle automatically turns to one side to continuously search for the parking space.
And S2, sensing the obstacles in the environment and predicting the short-time track of the dynamic obstacles in real time.
S2.1: the camera and the ultrasonic radar are fused to sense the obstacles in a certain range around the vehicle in real time, and the information such as the type, the position, the size, the motion trail of the dynamic obstacles and the like is obtained.
S2.1.1: the camera and the ultrasonic radar are used for sensing the obstacle in a fusion mode, namely the camera is used for identifying the obstacle, measuring the size of the obstacle and measuring distance, the ultrasonic radar is used for measuring the distance and the size of the obstacle, data of the two sensors are mutually supplemented, and mutual rectification is realized. The obstacle is represented by a polygon:
in the formula, Z i Denotes the ith obstacle, Z ij A jth vertex angle representing an ith polygonal obstacle, i representing the ith obstacle, j representing the jth vertex angle of the obstacle, for a total of j vertex angles,
z representing the ith obstacle i1 、Z i2 A connecting line segment of the vertex angle.
S2.2: and predicting the short-time track of the dynamic obstacle in real time.
S2.2.1: after the camera and the ultrasonic radar are fused to sense the dynamic barrier, the motion trail of the dynamic barrier is tracked, the motion trail of the dynamic barrier in the future 5S is predicted according to the type and the historical motion trail of the dynamic barrier, and meanwhile, the motion trail of the dynamic barrier is continuously updated and the predicted trail is corrected in real time.
Preferably, the parking lot scene dynamic obstacle categories mainly include: vehicles, pedestrians, children, pets, motorcycles, and non-motorized vehicles.
The specific prediction curve expression is as follows:
y＝k 1 x 5 +k 2 x 4 +k 3 x 3 +k 4 x 2 +k 5 x
wherein y represents the ordinate of a point on the curve, x represents the abscissa of a point on the curve, and k 1 、k 2 、k 3 、k 4 、k 5 Predicting the influence coefficient of a track curve for the obstacle, and substituting the influence coefficient into historical track points to obtain a specific value; v represents the predicted instantaneous speed of the obstacle at time t, t represents the predicted duration of the obstacle trajectory, v e An instantaneous speed representing the predicted starting point of the obstacle trajectory, i.e., an instantaneous speed of the last point of the obstacle motion trajectory, and a represents the historical average acceleration of the obstacle.
And S3, acquiring the initial posture of the vehicle and the relative position of the vehicle and the parking space, and determining the initial posture of the vehicle and the relative position of the vehicle and each identified parking space by using the sensing data.
S3.1: in the established space coordinate system, the cameras and the ultrasonic radar at each part of the vehicle body are used for respectively measuring the angular distance to the parking space so as to measure and calculate the position and the posture of the vehicle body, and the relative position relation between the vehicle and the parking space and the initial posture parameter of the vehicle are obtained, wherein the specific calculation formula is as follows:
wherein alpha is the included angle between the vehicle body and the horizontal line, the positive and negative of the included angle indicate that the included angle is above or below the horizontal line, and y A 、y C Ordinate values, x, respectively representing A, C points A 、x C Respectively, an abscissa value of point A, C, point a representing the front left corner of the vehicle, and point C representing the rear right corner of the vehicle.
S3.2, the calculation formula of the central position coordinates of the rear axle of the vehicle is as follows:
in the formula, x E 、y E Respectively representing the x value and the y value of the rear axle center of the vehicle, D is the rear overhang length of the vehicle, point C represents the right rear corner of the vehicle, point D is the left rear corner of the vehicle, and theta is the attitude angle of the vehicle.
And S4, judging whether the parking condition is met, and determining the first-level target parking space range.
And S4.1, judging the sizes of all the surrounding recognized empty parking spaces and the space constraint parking conditions, and taking the parking spaces meeting the parking conditions as a first-level target parking space range.
The specific parking conditions are mainly judged as follows:
wherein the condition (1) is to ensure that the size of the parking space meets the requirement of parking a vehicle(2) In order to ensure that the lane width meets the requirement of turning and parking of the vehicle, the condition (3) is to ensure that no static barrier is sheltered in the parking space and at the parking space opening. Q Obstacle Denotes a static obstacle region, Q Parking space Showing the areas of the interior and the mouth of the parking space, a and b respectively showing the length and width distances of the vehicle and the parking space, and S R Indicates the width of the lane beside the parking space, S a Is a lane width threshold.
And S5, planning longitudinal speed, acceleration and jerk curves of the vehicle in the parking process, and selecting a parking track strategy according to the initial posture of the vehicle and the relative position of the vehicle and each identified parking space based on the planning result.
S5.1, setting the highest values of the speed v, the acceleration a and the jerk j, and planning a change curve of the highest values to ensure that the automobile stably runs according to acceleration, uniform speed and deceleration, wherein the expressions of the speed and the acceleration are as follows:
in the formula, t x Time node representing different changes in velocity caused by changes in acceleration, x ∈ [1, 7 ]]And t represents a certain instant in time during which the vehicle is parked.
S5.2: and calculating parking track strategies in different relative position areas of the vehicle and the parking space according to parameters such as basic parameters of the vehicle, the type and the size of the parking space, the position of the parking space, kinematic constraints, space constraints and the like.
Preferably, the vehicle kinematic constraints, spatial constraints and dimensional constraints are mainly:
wherein, the formula (1) is the kinematic constraint of the vehicle, the formula (2) is the space constraint, the formula (3) is the size constraint of the parking space, in the formula,delta is the maximum turning angle of the front wheels of the vehicle,
for the maximum angular rate of the front wheels, S, of the vehicle R Is the lane width, S a The threshold value of the minimum width of the lane is represented, and a and b represent the length and the width distances of the vehicle and the parking space respectively.
S5.3: and selecting a corresponding optimal parking strategy according to the relative positions of the vehicle and the parking spaces and the difference of the initial postures of the vehicle body aiming at different parking space types.
Preferably, the parking track strategy comprises one-time reverse parking, forward adjustment, backward parking and direct reverse multiple parking adjustment. The priority is that one-time reverse parking is the optimal level, the reverse parking is the suboptimal level after forward adjustment, and the direct reverse parking is the worst level.
Under the constraint condition, selecting a corresponding optimal parking strategy according to the relationship between the initial position of the vehicle and the position of the parking space and the initial posture of the vehicle, wherein the main selection conditions are as follows:
in the formula, w x 、w y Respectively expressed as the distances in the directions of the x axis and the y axis between the initial position of the vehicle and the center position of the parking space opening, w xa 、w ya Respectively expressed as the distance threshold values in the directions of the x axis and the y axis of the initial position of the vehicle and the center position of the parking space opening, R min Represents the minimum turning radius of the vehicle, theta is the initial attitude angle of the vehicle body, S R Is the lane width, S a Representing a lane width second threshold.
Preferably, when the initial position and the lane width of the vehicle meet the conditions, namely the expressions (1), (2) and (3) are met, a primary backing parking strategy is preferred, when the expression (3) is met, the expressions (1) and (2) meet one item or both the expressions are not met, a backing parking strategy after forward adjustment is preferred, and when the expression (3) is not met, a direct backing adjustment parking strategy is selected.
S5.4: and substituting the obtained initial position and initial attitude parameters of the vehicle to determine a parking strategy, and respectively and independently planning the parking track of the vehicle for the parking space in each primary target parking space under the vehicle kinematic constraint and the space constraint by using a straight line-arc-convolution curve combination method.
Preferably, the parking trajectory is a curve from an initial position point to a successful parking space of the vehicle with a certain initial posture based on a straight line, an arc curve and a clothoid curve. The expressions of the straight line, the circular arc curve and the clothoid curve are respectively as follows:
the formula (1) is a straight line expression, the formula (2) is an arc curve expression, the formula (3) is a clothoid expression, the formula (4) is a transverse and longitudinal running distance expression when the automobile runs on an arc curve, and the formula (5) is a transverse and longitudinal running distance expression when the automobile runs on a clothoid; x is the number of a 、y a 、θ a The horizontal and vertical coordinates and the body posture x of the central point of the rear axle of the vehicle when the vehicle is running in a straight line b 、y b 、θ b The horizontal and vertical coordinates of the central point of the rear axle of the vehicle and the posture x of the vehicle body when the vehicle runs on the arc curve c 、y c 、θ c Indicating the center of the rear axle of the vehicle when the vehicle is travelling in a clothoid curveThe horizontal and vertical coordinates of the points and the posture of the vehicle body; x is the number of 1 、y 1 、θ 1 The abscissa and ordinate of the center point of the rear axle of the vehicle at the beginning of straight running and the body attitude, x 2 、y 2 、θ 2 The abscissa and ordinate of the center point of the rear axle of the vehicle at the beginning of the circular arc curve running and the body attitude, x 3 、y 3 、θ 3 The horizontal and vertical coordinates and the vehicle body posture of the central point of the rear axle of the vehicle, which represent the vehicle just starts to run in a clothoid curve; d 1 Indicating the length of the distance, dx, over which the vehicle is travelling in a straight line 2 、dy 2 、dθ 2 Respectively represents the length of the transverse and longitudinal running distance and the variation of the body attitude angle, dx of the vehicle running on the circular arc curve 3 、dy 3 、dθ 3 The length of the transverse and longitudinal running distance and the variation of the vehicle body attitude angle of the vehicle rotating curve running are represented; l. the 2 、l 3 、l 4 Respectively representing the driving distance of the circular arc curve and the clothoid curve of the vehicle and the total length of the clothoid curve, R 2 、R 3 Respectively representing the radius of curvature of the vehicle circular arc curve and the radius of curvature at the end point of the clothoid curve.
And S6, considering the influence of the obstacles, screening the parking spaces which can successfully plan the safety path in the primary target parking space range, and forming a secondary target parking space range.
S6.1: and judging whether the position and the size of the static barrier conflict with the planned track, if so, degrading the parking track strategy to re-plan the track, and judging again until a conflict-free track or a safety-free track is planned.
S6.2: the influence of the dynamic barrier is considered, the short-time predicted track of the dynamic barrier is mainly considered, and the collision risk value is mainly determined by the area size and the time overlap ratio of the predicted track of the dynamic barrier and the planned track of the vehicle parking and the conflict point in the safety distance around the track.
S6.3: and (4) considering the influence of dynamic obstacles, and adding additional adjustment strategies for trajectory planning such as secondary parking, parking waiting and the like. And calculating a dynamic barrier collision risk value according to the position, the size, the motion track and the short-time predicted track of the dynamic barrier, setting a safety threshold, degrading the parking track strategy to re-plan the track if the safety threshold is exceeded, and judging again until a collision-free track or a safety-free track is planned.
S6.3.1: the parking waiting is a parking dynamic strategy adopted when the predicted track collision risk value of the dynamic barrier exceeds the safety threshold after the vehicle starts to park, and is a two-stage parking track planning strategy, namely an adjusting strategy possibly adopted according to the dynamic environment on the basis of the original track planning strategy. When the predicted track of the obstacle does not conflict with the current position of the vehicle and has a certain safety distance, adopting a parking waiting strategy; and when the predicted track of the obstacle conflicts with the current position of the vehicle or the distance is very close, adopting a quadratic planning strategy.
S6.3.2: the secondary planning strategy is mainly vehicle avoidance, namely the vehicle also plans to drive to the road side by using a straight line-arc-convolution curve combination method, other obstacles are avoided, and after the vehicle is avoided, the parking track is re-planned according to the current position.
And S7, comprehensively selecting the optimal target parking space and the optimal parking track according to the vehicle parking track efficiency of each target parking space and the distance between the optimal target parking space and the destination in the range of the secondary target parking spaces, and parking the vehicle into the optimal target parking space according to the optimal parking track.
Preferably, efficiency mainly takes into account track length, vehicle turn times and vehicle waiting time.
S7.1: calculating the distance between each target parking space and the destination: when in a public parking environment: calculating the distance between each target parking space and the pedestrian entrance and exit of the parking lot by utilizing the position relation between the vehicle and the pedestrian entrance and exit of the parking lot and the position relation between the vehicle and each target parking space; and when the vehicle is in a roadside parking environment, calculating the distance between each target parking space and the destination by using the position relation between the vehicle and the destination and the position relation between the vehicle and each target parking space.
S7.2: selecting an optimal track according to the comprehensive values under different weight coefficients, and selecting an optimal target parking space according to the optimal track, wherein the selection formula is as follows:
M＝k 1 (k 11 L+k 12 N+k 13 T)+k 2 S
wherein M is a quantitative evaluation index, k 1 、k 2 Weighting factors, k, for trajectory efficiency and parking space-to-destination distance 1 +k 2 ＝1，k 11 、k 12 、k 13 To influence the weighting factor of the efficiency, k 11 +k 12 +k 13 When the vehicle is parked, the distance between the parking space and the destination is 1, L is the distance of the whole route, N is the steering times, T is the parking waiting time when the vehicle is parked, and S is the distance between the parking space and the destination.
S7.3: after the optimal target parking space is selected and the optimal parking track is planned, the time for passengers to get off is judged, namely, corresponding threshold values are set according to the sizes of doors and the like of the vehicle, and when the distance between the left side and the right side of the vehicle and the barrier is smaller than the threshold value through calculation after the vehicle is parked in the parking space, the passengers are advised to get off in advance. And calculating the distance between the left side and the right side of the vehicle and the obstacle in the whole parking process, giving out a prompt when the distance between the left side and the right side of the vehicle is larger, parking the vehicle at a recommended position after the driver agrees, and continuously parking the vehicle after all the vehicle doors are closed again.
Example two:
the second embodiment of the present disclosure provides a system for selecting a target parking space based on optimal path planning, including:
the parking space identification module is configured to collect vehicle parameters and judge the current environment of the vehicle based on the selection of the destination; identifying the parking space and establishing a space coordinate system after the judgment;
the obstacle prediction module is configured to sense obstacles in the environment and predict short-time trajectories of the dynamic obstacles in real time;
the primary target parking space module is configured to acquire an initial posture of the vehicle and a relative position of the vehicle and each parking space, and determine the initial posture of the vehicle and the relative position of the vehicle and each recognition parking space by using the sensing data; judging whether the parking condition is met or not, and determining a first-level target parking space range;
planning longitudinal speed, acceleration and jerk curves of the vehicle in the parking process, and selecting a parking track strategy according to the initial posture of the vehicle and the relative position of the vehicle and each recognition parking space based on a planning result;
the secondary target parking space module is configured to consider the influence of obstacles, screen out parking spaces capable of successfully planning a safety path in a primary target parking space range, and form a secondary target parking space range;
the optimal track and parking space selection module is configured to comprehensively select an optimal target parking space and a parking track according to the vehicle parking track efficiency of each target parking space and the distance between the optimal target parking space and a destination in a secondary target parking space range;
and the vehicle driving-in module is configured to park the vehicle into the optimal target parking space according to the optimal parking track.
Example three:
a third embodiment of the present disclosure provides a medium, where a program is stored, and when the program is executed by a processor, the third embodiment of the present disclosure provides a method for selecting a target parking space based on optimal path planning, where the method includes:
s1, collecting vehicle parameters, and judging the current environment of the vehicle based on the selection of the destination; identifying the parking space and establishing a space coordinate system after the judgment;
s2, sensing the obstacles in the environment and predicting the short-time track of the dynamic obstacles in real time;
s3, acquiring the initial posture of the vehicle and the relative position of the vehicle and the parking space, and determining the initial posture of the vehicle and the relative position of the vehicle and each identified parking space by using the sensing data;
s4, judging whether the parking condition is met, and determining the first-level target parking space range;
s5, planning longitudinal speed, acceleration and jerk curves of the vehicle in the parking process, and selecting a parking track strategy according to the initial posture of the vehicle and the relative position of the vehicle and each identified parking space based on the planning result;
s6, considering the influence of the obstacles, screening the parking spaces capable of successfully planning the safety path in the primary target parking space range to form a secondary target parking space range;
and S7, comprehensively selecting the optimal target parking space and the optimal parking track according to the vehicle parking track efficiency of each target parking space and the distance between the optimal target parking space and the destination in the range of the secondary target parking spaces, and parking the vehicle into the optimal target parking space according to the optimal parking track.
The detailed steps are the same as those of the optimal path planning-based target parking space selection method provided in the first embodiment, and are not repeated here.
Example four:
a fourth embodiment of the present disclosure provides an apparatus, including a memory, a processor, and a program stored in the memory and capable of running on the processor, where the processor executes the program to implement the steps in the optimal path planning-based target parking space selection method according to the first embodiment of the present disclosure, where the steps are:
s1, collecting vehicle parameters, and judging the current environment of the vehicle based on the selection of the destination; identifying the parking space and establishing a space coordinate system after the judgment;
s2, sensing the obstacles in the environment and predicting the short-time track of the dynamic obstacles in real time;
s3, acquiring the initial attitude of the vehicle and the relative position of the vehicle and the parking space, and determining the initial attitude of the vehicle and the relative position of the vehicle and each identified parking space by using the sensing data;
s4, judging whether the parking condition is met, and determining the first-level target parking space range;
s5, planning longitudinal speed, acceleration and jerk curves of the vehicle in the parking process, and selecting a parking track strategy according to the initial posture of the vehicle and the relative position of the vehicle and each identified parking space based on the planning result;
s6, considering the influence of obstacles, screening parking spaces capable of successfully planning a safety path in the primary target parking space range to form a secondary target parking space range;
and S7, comprehensively selecting the optimal target parking space and the optimal parking track according to the vehicle parking track efficiency of each target parking space and the distance between the optimal target parking space and the destination in the range of the secondary target parking spaces, and parking the vehicle into the optimal target parking space according to the optimal parking track.
The detailed steps are the same as those of the optimal path planning-based target parking space selection method provided in the first embodiment, and are not repeated here.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A target parking space selection method based on optimal path planning is characterized by comprising the following steps:
vehicle parameters are collected, and the current environment of the vehicle is judged based on the selection of the destination; identifying the parking space and establishing a space coordinate system after the judgment;
sensing obstacles in the environment and predicting short-time trajectories of dynamic obstacles in real time;
determining the initial attitude of the vehicle and the relative position of the vehicle and each recognition parking space by using the sensing data;
judging whether the parking condition is met or not, and determining a first-level target parking space range;
planning longitudinal speed, acceleration and jerk curves of the vehicle in the parking process, and selecting a parking track strategy according to the initial posture of the vehicle and the relative position of the vehicle and each recognition parking space based on a planning result;
considering the influence of obstacles, screening parking spaces capable of successfully planning a safety path in the primary target parking space range to form a secondary target parking space range;
and comprehensively selecting an optimal target parking space and a parking track according to the vehicle parking track efficiency of each target parking space and the distance between the optimal target parking space and the destination in the range of the secondary target parking spaces, and parking the vehicle into the optimal target parking space according to the optimal parking track.
2. The optimal path planning-based target parking space selection method according to claim 1, wherein the parking space identification process is to identify a parking space with a parking space line by using a camera, and identify a parking space without a parking space line but with a parked vehicle on one side or two sides of the parking space by using an ultrasonic radar; and judging the occupation states of all the identified parking spaces, screening all the identified empty parking spaces around the vehicle, and uploading information of all the empty parking spaces.
3. The optimal path planning-based target parking space selection method according to claim 1, wherein the spatial coordinate system calculates position coordinates of each point of the vehicle body through distance and direction angle information by using a parking space entrance center as an origin, a lane direction as an x-axis and a vertical lane direction as a y-axis.
4. The optimal path planning-based target parking space selection method according to claim 1, wherein the obstacle sensing process in the environment is implemented by sensing the obstacle through a camera and an ultrasonic radar in a fusion manner, namely, the camera is used for identifying the obstacle, measuring the size of the obstacle and measuring distance, the ultrasonic radar is used for measuring the distance and the size of the obstacle, and the data of the two sensors are mutually supplemented and mutually corrected.
5. The optimal path planning-based target parking space selection method according to claim 4, wherein the camera and the ultrasonic radar are fused to sense a dynamic obstacle, the motion track of the dynamic obstacle is tracked, the motion track of the dynamic obstacle in a future period of time is predicted according to the type and the historical motion track of the dynamic obstacle, and meanwhile, the motion track of the dynamic obstacle is continuously updated and the predicted track is corrected in real time.
6. The optimal path planning-based target parking space selection method according to claim 1, wherein the process of obtaining the initial attitude of the vehicle and the relative position of the vehicle to the parking space comprises measuring the angular distance to the parking space by using cameras and ultrasonic radar at various positions of the vehicle body in the established spatial coordinate system, so as to measure the position and attitude of the vehicle body, and obtain the relative position relationship between the vehicle and the parking space and the initial attitude parameters of the vehicle.
7. The optimal path planning-based target parking space selection method according to claim 1, wherein the process of planning out the safe path is to judge whether the position and size of the static obstacle conflict with the planned trajectory, if so, the parking trajectory strategy is degraded to re-plan the trajectory, and the judgment is performed again until a conflict-free trajectory or a safety-free trajectory is planned.
8. The utility model provides a system is selected to target parking stall based on optimal path planning which characterized in that includes:
the parking space identification module is configured to collect vehicle parameters and judge the current environment of the vehicle based on the selection of the destination; identifying the parking space and establishing a space coordinate system after the judgment;
the obstacle prediction module is configured to sense obstacles in the environment and predict short-time trajectories of the dynamic obstacles in real time;
the primary target parking space module is configured to determine the initial posture of the vehicle and the relative position of the vehicle and each recognition parking space by using the sensing data; judging whether the parking condition is met or not, and determining a first-level target parking space range;
planning longitudinal speed, acceleration and jerk curves of the vehicle in the parking process, and selecting a parking track strategy according to the initial posture of the vehicle and the relative position of the vehicle and each recognition parking space based on a planning result;
the secondary target parking space module is configured to consider the influence of obstacles, screen out parking spaces capable of successfully planning a safety path in a primary target parking space range, and form a secondary target parking space range;
the optimal track and parking space selection module is configured to comprehensively select an optimal target parking space and a parking track according to the vehicle parking track efficiency of each target parking space and the distance between the optimal target parking space and a destination in a secondary target parking space range;
and the vehicle driving-in module is configured to park the vehicle into the optimal target parking space according to the optimal parking track.
9. A computer-readable storage medium characterized by: a plurality of instructions are stored, wherein the instructions are suitable for being loaded by a processor of a terminal device and executing the optimal path planning-based target parking space selection method according to any one of claims 1 to 7.
10. A terminal device characterized by: the system comprises a processor and a computer readable storage medium, wherein the processor is used for realizing instructions; the computer readable storage medium is used for storing a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the optimal path planning-based target parking space selection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210879379.2A CN115123202A (en) | 2022-07-25 | 2022-07-25 | Optimal path planning-based target parking space selection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210879379.2A CN115123202A (en) | 2022-07-25 | 2022-07-25 | Optimal path planning-based target parking space selection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115123202A true CN115123202A (en) | 2022-09-30 |
Family
ID=83385195
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210879379.2A Pending CN115123202A (en) | 2022-07-25 | 2022-07-25 | Optimal path planning-based target parking space selection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115123202A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116118719A (en) * | 2023-04-14 | 2023-05-16 | 禾多科技（北京）有限公司 | Automatic driving parking speed measuring system based on obstacle judgment vehicle speed |
| CN117601848A (en) * | 2023-12-20 | 2024-02-27 | 广州车全影电子科技有限公司 | Parking control method, system, medium and equipment based on automobile panorama |
| WO2024087642A1 (en) * | 2022-10-24 | 2024-05-02 | 比亚迪股份有限公司 | Parking space determination method, storage medium, controller, and vehicle |
| WO2024109019A1 (en) * | 2022-11-23 | 2024-05-30 | 浙大城市学院 | Visual identification-based driving assistance system and method |
-
2022
- 2022-07-25 CN CN202210879379.2A patent/CN115123202A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024087642A1 (en) * | 2022-10-24 | 2024-05-02 | 比亚迪股份有限公司 | Parking space determination method, storage medium, controller, and vehicle |
| WO2024109019A1 (en) * | 2022-11-23 | 2024-05-30 | 浙大城市学院 | Visual identification-based driving assistance system and method |
| CN116118719A (en) * | 2023-04-14 | 2023-05-16 | 禾多科技（北京）有限公司 | Automatic driving parking speed measuring system based on obstacle judgment vehicle speed |
| CN117601848A (en) * | 2023-12-20 | 2024-02-27 | 广州车全影电子科技有限公司 | Parking control method, system, medium and equipment based on automobile panorama |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115123202A (en) | Optimal path planning-based target parking space selection method and system | |
| US11532167B2 (en) | State machine for obstacle avoidance | |
| CN108459588B (en) | Automatic driving method and device and vehicle | |
| US11427191B2 (en) | Obstacle avoidance action | |
| CN110304074B (en) | Hybrid driving method based on layered state machine | |
| EP4230964A1 (en) | Navigation based on vehicle activity | |
| CN113916246A (en) | Unmanned obstacle avoidance path planning method and system | |
| CN113932823A (en) | Unmanned multi-target-point track parallel planning method based on semantic road map | |
| US8352112B2 (en) | Autonomous vehicle management | |
| CN112204350A (en) | Trajectory planning | |
| WO2021147748A1 (en) | Self-driving method and related device | |
| JP7331939B2 (en) | In-vehicle device and driving support method | |
| US11615702B2 (en) | Determining vehicle path | |
| CN116249643A (en) | Method and system for predicting actions of an object by an autonomous vehicle to determine a viable path through a conflict area | |
| EP3822945A1 (en) | Driving environment information generation method, driving control method, driving environment information generation device | |
| US11718290B2 (en) | Methods and systems for safe out-of-lane driving | |
| JP7225262B2 (en) | Trajectory planning for obstacle avoidance of self-driving cars | |
| CN115489548B (en) | Intelligent automobile park road path planning method | |
| CN113785252A (en) | Method of parking an autonomously driven vehicle for autonomous charging | |
| CN115520218A (en) | Four-point turning track planning method for automatic driving vehicle | |
| EP4052174A1 (en) | Obstacle avoidance action | |
| CN114644016A (en) | Vehicle automatic driving decision-making method and device, vehicle-mounted terminal and storage medium | |
| CN115140096A (en) | Spline curve and polynomial curve-based automatic driving track planning method | |
| CN115620536A (en) | Method for improving crossing traffic efficiency based on danger degree in automatic driving environment | |
| JP7260792B2 (en) | Control device and control system |
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 |