CN110696818A - Automatic parking method and system based on optimal path - Google Patents
Automatic parking method and system based on optimal path Download PDFInfo
- Publication number
- CN110696818A CN110696818A CN201910975759.4A CN201910975759A CN110696818A CN 110696818 A CN110696818 A CN 110696818A CN 201910975759 A CN201910975759 A CN 201910975759A CN 110696818 A CN110696818 A CN 110696818A
- Authority
- CN
- China
- Prior art keywords
- parking
- vehicle
- path
- track
- optimal
- 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
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, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D15/00—Steering not otherwise provided for
- B62D15/02—Steering position indicators ; Steering position determination; Steering aids
- B62D15/027—Parking aids, e.g. instruction means
- B62D15/0285—Parking performed automatically
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D15/00—Steering not otherwise provided for
- B62D15/02—Steering position indicators ; Steering position determination; Steering aids
- B62D15/029—Steering assistants using warnings or proposing actions to the driver without influencing the steering system
Abstract
The invention discloses an automatic parking method and system based on an optimal path, which comprises the steps of collecting vehicle parking environment data and judging whether a parking space is suitable for parking by an environment data collection module consisting of a look-around camera and an ultrasonic radar, calculating and analyzing the position relation between a vehicle body and the parking space through a set central processor module to generate the optimal parking path, and finally sending the optimal parking path to an automobile execution mechanism module to control the control quantity of gears, steering, brakes, accelerographs and the like of an automobile so as to achieve the effect of automatic parking; the man-machine interaction module displays the current state information, environmental parameters and operation steps of the automobile through the display screen, and can be operated by a driver to select whether to enter a parking state or terminate an automatic parking process in real time, so that the system has the advantages of being more practical, more convenient, more accurate and safer and the like.
Description
Technical Field
The invention relates to the technical field of automobile electronic control, in particular to an automatic parking method and system based on an optimal path.
Background
With the increasing popularity of automatic parking systems for automobiles, the practicability, convenience and safety of the automatic parking system are concerned by drivers. The automatic parking system can improve the parking efficiency, reduce the fatigue degree of a driver in the parking operation process, reduce the occurrence rate of parking accidents, reduce the parking accidents, and is beneficial to ensuring the integrity and the safety of public facilities such as roads, parking lots and the like.
At present, in a commercialized automatic parking system, most low-end systems are independently used as an environment acquisition module by an ultrasonic sensor, but the parking system can only detect parking spaces with physical obstacles; or an independent camera serves as an environment acquisition module, the parking system has obvious defects and can only identify the parking spaces with the parking space lines. The existing automatic parking scheme requires a driver to manually find a parking space in some scenes, and full-automatic parking is not achieved; the multi-sensor fusion automatic parking scheme mainly based on the radar and the camera can identify parking spaces in complex scenes and realize full-automatic parking, but has the defects of more time consumption, large calculation amount and high cost of the whole system. Most of the existing automatic parking schemes do not model the vehicle kinematics in the parking process and do not optimize the generated parking path, so that the actual parking path is often not very reasonable, time is consumed, and surrounding obstacles are easy to touch.
Disclosure of Invention
The invention aims to provide an automatic parking method and system based on an optimal path, aiming at the defects of the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
an automatic parking method based on an optimal path comprises the following steps:
acquiring environmental data, namely acquiring surrounding image information through a calibrated all-round camera, preprocessing acquired data in the sensor to output potential parking space line information, acquiring surrounding obstacle information through a calibrated ultrasonic radar, preprocessing acquired data in the sensor to output rough potential garage information;
data processing and analysis, namely placing the collected information of surrounding obstacles collected by the ultrasonic radar in an established coordinate system to obtain a feasible region of the vehicle, performing algorithm fusion on potential parking space line information output by the all-round camera and rough potential garage information output by the ultrasonic radar to obtain final parking space information, and performing optimal parking path planning by calculating the position, the rotation angle and the collision point distance of the vehicle relative to the parking spaces and the feasible region of the vehicle;
executing track parking, generating the optimal parking path setting track according to the plan, controlling and changing automobile gears to realize the operation of advancing, retreating and braking of the automobile, and controlling an accelerator, a brake and a steering wheel to work coordinately to realize track tracking angle steering parking according to the calculated target rotation angle;
and automatically parking according to the parking operation instruction, and feeding back the parking state to the driver.
Further, the coordinate system detection calculation divides the vehicle-to-bit line, and the method further comprises:
image preprocessing, namely correcting the panoramic top view, eliminating irrelevant information in the image, recovering useful real information, converting the original color into a gray image, and performing histogram equalization on the gray image;
positioning a search starting point of a position line, dividing a search area of a coordinate system of the panoramic top view, performing statistics on a gridding search area to obtain a position line parameter corresponding to current search, and updating a search base point;
tracking the vehicle position line, and setting a flag bit to detect whether a fitted curve is detected or not when each frame of image is processed finally;
and outputting the structured data, and when the parking space lines in the horizontal and vertical directions are detected, obtaining the intersection points between the lines and outputting the intersection points to the path.
Further, the optimal parking path planning method specifically includes:
analyzing the influence of the wheel rotation angle on parking path parameters, and determining a proper path rotation angle;
calculating a fitting formula of the parking bit length and the slope of the straight line to obtain the slope of the straight line, and then changing the parking radius to determine a complete parking path;
and analyzing the position and the posture of the vehicle, calculating the distance from the collision point to the vehicle, checking the feasibility of path planning, and generating a parking track.
Further, the environmental data collection specifically includes: and acquiring environmental data through 12 paths of ultrasonic radar sensors arranged around the vehicle, capturing the size of the parking space and judging whether the parking space is suitable for parking.
Further, the image stitching includes image registration and image fusion, the image registration can be achieved by adopting automatic image registration or manually selecting a reference point, the image fusion is based on a common reference point in manually selected adjacent images, the image registration is carried out by utilizing the area images, and the stitching is completed when the side view is changed into the top view.
Further, the executing track parking specifically includes the following control steps:
setting a track, and generating an optimal parking path setting track according to the plan, wherein the setting track can be a discrete point or an equation curve;
the method comprises the steps of changing gears, outputting target gears in sequence to control gear change of a vehicle, wherein the changed gears comprise a reverse gear, a neutral gear and a forward gear;
tracking the track, setting global coordinates after finishing setting the track, and calculating the current position of the vehicle movement by using a odometer model;
parking, namely smoothly braking the vehicle;
and restoring the gear to a neutral position, so that the whole track parking execution process is completed.
And further, the tracking track specifically comprises the steps of calculating the target steering wheel angle by using a Pure Pursui algorithm and controlling an accelerator and a brake by using a PID algorithm.
An automatic parking system based on an optimal path at least comprises the following structures:
the environment data acquisition module consists of a plurality of looking-around cameras and an ultrasonic radar which are arranged around a vehicle body, wherein the looking-around cameras and the ultrasonic radar are internally provided with chips which can carry out data acquisition and data processing operations;
the central processing unit module is used for receiving the environmental data acquired by the acquisition module, performing data processing analysis, detecting, calculating and dividing a parking line through the environmental data and planning an optimal parking path;
the execution mechanism module receives the control command sent by the central processing unit module, can drive the steering, driving and braking operations of the vehicle, and realizes the automatic parking action by controlling the vehicle 1 to track the parking track path;
the human-computer interaction module interacts with a driver through a display screen, realizes information interaction and result feedback between a human and an automatic parking system through image-text display, physical vibration and sound of a central control display screen, an instrument and a square control device, feeds back vehicle parking environment data acquired by the environment data acquisition module, a central processor module vehicle position line detection result, a planned generated parking track and a parking state controlled by the execution mechanism module to the driver in real time, and waits for receiving a parking operation instruction of the driver.
Further, the environmental data collection module includes: the four-way all-round looking camera and the 12-way ultrasonic radar sensor are arranged at the front, the back, the left and the right of the vehicle.
The beneficial effect of adopting above technical scheme is: the invention relates to an automatic parking method and system based on an optimal path, wherein an environment data acquisition module is formed by four looking-around cameras arranged at the front, the rear, the left and the right of a vehicle body and 12 ultrasonic radar sensors arranged around the vehicle, acquires vehicle parking environment data and judges whether a parking space is suitable for parking, the position relation between the vehicle body and the parking space is calculated and analyzed through an arranged central processor module to generate the optimal parking path, and finally the optimal parking path is sent to an execution mechanism module to control the control quantity of gears, steering, brakes, accelerographs and the like of an automobile, so that the automatic parking effect is achieved; the man-machine interaction module displays the current state information, environmental parameters and operation steps of the automobile through the display screen, and can be operated by a driver to select whether to enter a parking state or terminate an automatic parking process in real time, so that the system has the advantages of being more practical, more convenient, more accurate and safer and the like.
Drawings
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
FIG. 1 is a flow chart of an automatic parking method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a parking space line detection result provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of a kinematic model of a vehicle provided by an embodiment of the present invention;
FIG. 4 is a schematic illustration of a parking path provided by an embodiment of the present invention;
FIG. 5 is a geometric diagram of the Pure Pursuit algorithm provided by an embodiment of the present invention;
FIG. 6 is a schematic diagram of a geometric vehicle model provided by an embodiment of the invention;
fig. 7 is a schematic diagram of a camera position and a shooting area thereof according to an embodiment of the present invention;
FIG. 8 is a schematic structural diagram of an automatic parking system according to an embodiment of the present invention;
in the figure: 1. a vehicle; 2. a camera; 3. a vehicle line; 4. and (4) an intersection point.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
The automatic parking method based on the optimal path comprises the following steps:
the method comprises the steps of acquiring environmental data, namely calibrating cameras of four-way panoramic cameras 2 arranged at the front, the rear, the left and the right of a vehicle 1, wherein the image data acquired by the environmental data comprises three parameters of internal reference, external reference and distortion; acquiring surrounding image information through a calibrated all-round camera, performing data acquisition preprocessing in the sensor to output potential parking space line information, acquiring surrounding obstacle information through a calibrated ultrasonic radar, and performing data acquisition preprocessing in the sensor to output rough potential garage information;
the camera calibration aims to acquire internal parameters, external parameters and distortion parameters of the camera and correct pictures. The relationship between the picture coordinates and the world coordinates is shown in formula 1-1:
wherein, a camera coordinate system is formed by taking the focus O as an origin and coordinate axes Xc, Yc and Zc; a pixel plane coordinate system (u, v); world coordinate system (X, Y, Z); the rotation matrix R and the translation matrix t, simplified by L.
Data processing and analysis, namely placing the collected information of surrounding obstacles collected by the ultrasonic radar in an established coordinate system to obtain a feasible region of the vehicle, performing algorithm fusion on potential parking space line information output by the all-round camera and rough potential garage information output by the ultrasonic radar to obtain final parking space information, and performing optimal parking path planning by calculating the position, the rotation angle and the collision point distance of the vehicle relative to the parking spaces and the feasible region of the vehicle; the image registration can be realized by adopting automatic image registration or manually selecting a reference point, and common automatic image registration methods comprise an algorithm based on image brightness information, an algorithm based on characteristics and an algorithm based on a transform domain, but the algorithms have large calculation amount and low accuracy, so the registration is realized by manually selecting the reference point to ensure the real-time property of the registration. The image fusion is based on a common reference point in manually selected adjacent images, image registration is carried out by using regional images, splicing is finished when a side view is changed into a top view, when a plurality of images are spliced, due to the influence of illumination angles and the like, parallax error inevitably exists between the images, therefore, after initial splicing is finished, a splicing seam exists at the joint of the two adjacent images, and under the general condition, the splicing seam is eliminated by carrying out smooth transition processing on an overlapped region, and the common methods include a median filtering method and a weighted average fusion method.
The weighted average fusion algorithm achieves elimination of splicing seams and achieves the best fusion effect by adjusting the splicing seams and the boundary lines (figures 1-3). The weight is obtained from the formula (1-2).
Wherein, P represents the RGB component value after the fusion of the coincidence region, and P1 and P2 represent the RGB value components of the first image and the second image respectively. L represents the distance from a certain pixel point in the overlap region to the boundary line 2, and there are various compensation methods for the illumination unevenness, such as gamma correction for image histogram equalization processing. For the images spliced by the images shot by different cameras 2, a method based on RGB three-channel coefficient correction can be adopted, the minimum sum of color differences of four overlapped areas is taken as a target function, the purpose of illumination homogenization is achieved by solving the color correction coefficient of each view, the panoramic top view splicing is completed through the above operations, a uniform coordinate system is established for the panoramic top view, the parking space line 3 is detected, calculated and divided according to the coordinate system, and the optimal parking path planning is performed by calculating the position, the rotation angle and the collision point distance of the vehicle 1.
And analyzing the influence of the rotation angle on the parking path parameters based on the optimal parking path planning, and determining a proper path rotation angle. And calculating a fitting formula of the parking bit length and the slope of the straight line to obtain the slope of the straight line, and then changing the parking radius to determine a complete parking path. The vehicle kinematics model is used for analyzing the position and the posture of the vehicle 1, the distance between the collision point and the vehicle 1 is calculated, the feasibility of path planning is proved, and the generated parking track is in accordance with the actual parking situation.
In the parking process, the movement of the vehicle 1 around the parking space is restricted by a plurality of conditions, and the vehicle 1 can move normally only if the restrictions are met.
One is the vehicle own parameter constraint, including: (1) the size of the vehicle body of the vehicle to be parked is fixed, and the installation position of the sensor is fixed; (2) the turning radius of the parking process needs to be larger than the minimum turning radius.
Secondly, parking environmental constraint includes: (1) the vehicle to be parked can not collide with the barrier when moving in the parking space, and a certain safe distance needs to be kept: (2) when a vehicle to be parked is put into a garage and turns, collision with the left rear corner of a parked vehicle or an obstacle in front is avoided; (3) when the parking space length is larger than the parking space length, the vehicle can park in a one-time parking mode, and the farthest distance of one-time parking needs to be limited.
Thirdly, parking and parking regulation constraint, including: (1) the course angle is zero when the parking is finished; (2) when the parked vehicle is finished, the outside of the vehicle body is required to be flush with the outside of the vehicle body of the parked vehicle.
Three-stage path planning: in the actual parking process, the parking space is detected through the side ultrasonic sensor, when the detected parking space size meets the requirement of parking in one time, the human-computer interaction interface prompts a driver to find an empty parking space, then the driver continues driving the vehicle to move forward, when the vehicle reaches a proper parking starting position, the human-computer interaction interface prompts the driver to park and hang a reverse gear, then the system can automatically plan a parking path, the electric power steering mechanism controls the vehicle to automatically complete a steering task, and the driver only needs to control an accelerator and a brake well. Based on the daily driver parking experience, the entire parking process can be simplified as shown in fig. 4.
The entire parallel parking path is composed of a straight line (S2) and two arcs (S1, S3). Wherein O1 and O2 are turning centers of two circular arcs; r1 and R2 are two arc radiuses; x is the horizontal distance between the parking starting position and the parking ending position; and Y is the lateral displacement of the parking starting position and the parking ending position. The radius of the circular arcs at the two ends is R.
From the geometrical relationships it can be derived:
the trigonometric function is known as: 1 ═ sin2(θ)+cos2(θ), the above equation can be transformed to:
the three coefficients of the unary quadratic polynomial are respectively:
and wherein the polynomial is present with sufficient conditions that △ ═ b2-4ac>0; wherein the value of the angle theta is required to be between 0 and 90 degrees.
Under the above conditions, the solution of the unary quadratic polynomial can be solved, i.e., the concrete equations of the trajectories S1, S2, and S3 can be obtained.
Planning an optimal parking path: by analyzing the constraints, the characteristics of the path curve can be determined. A smooth curve is planned to connect the start point coordinate and the end point coordinate of the vehicle, namely the curvature of the planned path curve needs to be continuous, and the continuity of the curvature requires the second-order continuity of the planned path. The output of the automatic parking system is the steering angle of the vehicle, the steering angle of the vehicle is controlled by the power-assisted motor, and the steering angle of the wheels cannot be suddenly changed due to the inertia characteristic of the steering system and the steering performance constraint of the steering motor, so that the planned path requires three-order continuity. Thus, when planning a path, the curve is a polynomial of at least a fourth degree.
Optimizing a polynomial: curve fitting is the most common form of curve approximation, and is a method for approximating known discrete data by using analytical expressions in mathematical research. There are various criteria for the curve fitting, such as minimizing the sum of the absolute values of the deviations, minimizing the maximum absolute value of the deviations and minimizing the sum of the squares of the deviations (least squares), since the fitted curve is only required to approximate the basic trend of the data. The coefficients of the polynomial are typically determined using a least squares method.
In order to study some complex functions, the primitive function value can be obtained by performing finite addition, subtraction and multiplication on the function argument, so we usually use a high-order polynomial to approximate the function:
f(x)≈Pn(x)＝a0+a1(x-x0)+a2(x-x0)2+…+an(x-x0)n(2-25)
it can be seen that f (x) is approximated by a linear combination of coefficients of a polynomial of order n.
Specifically, as shown by Taylor expansion, when the derivatives of Pn (x) and f (x) are equal, the errors of f (x) and Pn (x) are infinitesimally small in the high order of (x-x 0). Namely:
the error relationship between f (x) and the polynomial function is expressed by subtracting the square of the result of the polynomial function from the true function value of f (x), i.e.:
let x0 be 0, the error represented by the least squares method is:
now assuming that n sets of data exist, its polynomial of degree k is solved using the least squares method. Wherein the polynomial is assumed to be:
f(x)≈Pn(x)＝a0+a1(x-x0)+a2(x-x0)2+…+an(x-x0)n(2-29)
the error is:
to optimize the objective function, we take the first partial derivative of each coefficient and let it be 0, i.e.:
and directly solving the optimal solution of the partial derivative in one step by using a method for solving the linear equation. The above equation can be converted into:
wherein: AX ═ Y
It can be obtained by solving a linear equation: x is A-1Y, the parameters of the polynomial are obtained.
Executing track parking, generating the optimal parking path setting track according to the plan, controlling and changing automobile gears to realize the operation of advancing, retreating and braking of the automobile, and controlling an accelerator, a brake and a steering wheel to work coordinately to realize track tracking angle steering parking according to the calculated target rotation angle;
and automatically parking according to the parking operation instruction, and feeding back the parking state to the driver.
The coordinate system detection calculation divides the vehicle-line 3, and the method further comprises the following steps:
the image preprocessing is used for correcting the panoramic top view, the original image is inevitably influenced by illumination, noise and the like, and the quality of the preprocessing directly influences the effect of the later-stage identification, so that irrelevant information in the image is eliminated, useful real information is recovered, the detectability of the relevant information is enhanced, and the simplification is realized to the maximum extent; the original color is first converted into a gray image, and the gray image needs to be subjected to histogram equalization in consideration of uneven gray distribution caused by illumination. The basic idea of histogram equalization is to perform some mapping transformation on the pixels in the original image, so that the transformed image has uniformly distributed gray level probability density, i.e. the transformed image is an image with uniformly distributed gray levels, which means that the dynamic range of the image gray level is increased, and thus the contrast of the image can be improved. However, the gray level transformation function operation in the traditional histogram equalization is irrelevant to the position of the pixel, and the algorithm of the global processing has the advantages of simple algorithm, high calculation speed and the like, but because the same processing is performed on all the pixel points, the local characteristics of the image are ignored, so that the useful information of the image subjected to the histogram equalization is lost, and the loss is brought to the denoising processing and the edge detection of the image. Therefore, contrast-limited adaptive histogram equalization (CLAHE) is adopted herein to limit the enhancement amplitude of the local contrast by limiting the height of the local histogram, thereby limiting the amplification of noise and the over-enhancement of the local contrast.
Positioning a search starting point of the parking space line 3, obtaining a parking space line 3 parameter corresponding to the current search by dividing a search area and carrying out statistics on a gridding search area of a coordinate system of the panoramic top view, and updating a search base point; 1) firstly, dividing a search area, dividing an image into an interested area according to the x-axis direction, performing histogram statistics on two parts of the image in the x direction and the y direction, and positioning a peak value as a search starting point of two horizontal and vertical parking lines 3.
2) The searching process comprises the following steps: firstly, setting the size (width and height) of a search window; then, taking the searching initial point as the base point of the current searching, taking the current base point as the center, performing a gridding searching, and calculating by dividing the initial position x, width as the manual setting, height as the picture size by the number of the set searching windows, wherein the number of the windows is 10;
secondly, performing horizontal and vertical direction histogram statistics on each search window respectively, counting the number of non-zero pixels in a search frame area, and filtering frames with the number of the non-zero pixels smaller than 50;
and finally, calculating the mean value of the non-zero pixel coordinates as the center of the current search frame, and performing second-order least square fitting on the center points to obtain the lane line parameters corresponding to the current search.
3) Updating the search base point:
in step 2), after the polynomial is approximated, a linear equation is obtained, so that a new search base point can be obtained.
The method of tracking the car position line 3 and sliding the window is usually used for detecting the restart of the first frame or the detection failure, because the waste of computing resources is excessive and the detection time is long, in the project, because the difference between the images of the continuous frames is not large during automatic parking, the images of the later frames can only be detected around the curve fitted to the first frame, the surrounding frame is set, and then the pixel point of the curve of the next frame is searched in the range so as to fit the curve. And setting a flag bit when each frame of image is finally processed to detect whether a fitted curve is detected, wherein if the fitted curve is detected, a search _ from _ previous method is used, otherwise, a sliding window method is used for searching the lane line again.
As shown in fig. 2, when the vehicle lane 3 in the horizontal and vertical directions is detected, the structured data is output, and then the intersection 4 between the lines is obtained and output to the route.
In unmanned systems, reasonable vehicle model selection has a large impact on the complexity and performance of planning and control modules. Kinematics is the study of the law of motion of an object from the perspective of geometry, and includes the change of the position, speed and the like of the object in space with time. In the path planning and control module, a vehicle kinematic model is used, so that the planned path is feasible, and the geometric constraint in the vehicle motion process is met.
Consider a two-wheel model of an automobile, as shown in FIG. 3. In the two-wheel model, the two right and left front wheels are replaced by the wheel at point a. Likewise, the rear wheels are replaced by wheels located at point B. The steering angles of the front and rear wheels are represented by δ f and δ r, respectively. For front wheel only steering, the rear wheels are limited to 0. The distances from the center of mass of the vehicle to the points A and B are lf and lr respectively, and the wheelbase of the vehicle is L ═ lf + lr.
Assuming that the car makes a planar motion, three coordinate values are required to describe the motion of the car. X, Y and ψ. (X, Y) represents the center of mass of the car and ψ represents the bearing of the car. The speed of the mass center of the automobile is V, and the included angle between the speed of the mass center of the automobile and the automobile body is beta. At low speeds, the lateral forces generated by the tire are small, ignoring lateral slip. For movement on an endless track of arbitrary radius R, the sum of the lateral forces of the two wheels is such that it varies as the square of the velocity V. The point O is the instantaneous center of rotation of the vehicle and is determined by the intersection of the lines AO and BO perpendicular to the two rollers. The radius R of the vehicle path is defined as the length of the line segment OC connecting the center of mass C and the instantaneous center of rotation.
Using sine theorem on triangles OCA and OCB
Decomposing to obtain:
multiplication on both sides of formula (3-3) simultaneously
Simultaneous multiplication of both sides of formula (3-4)
Adding the following equations (3-5) (3-6):
angular velocity of the vehicle is
Thus is provided withFinishing to obtain:
thus, the general equation for the instantaneous state of motion is:
there are three quantities in this model: δ f, δ r, and V, where V is the external input quantity.
The two sides of the formula (6-5) are multiplied by lr, and the two sides of the formula (6-6) are multiplied by lr to obtain:
obtaining an included angle beta between the vehicle speed and the vehicle body:
kinematic model summary:
x-axis coordinate rate of change:
rate of change of Y-axis coordinate:
rate of change of included angle with X-axis coordinate:
the included angle between the vehicle speed and the vehicle body is as follows:
finally, obtaining a discrete state updating equation of the model taking the center of mass of the vehicle as the center:
the limiting conditions are as follows: as described above, since most of the rear wheels of the vehicle cannot be steered, the steering angle control input δ r of the rear wheel of the bicycle model is 0. The control input on the steering wheel is all reflected on the turning angle of the front wheels. Wherein the included angle beta between the vehicle speed and the vehicle body and the included angle between the vehicle body and the X axis
The rate of change was:
the scheme takes the center of the rear axle of the automobile as the center of the automobile kinematic model, and the state variable quantity of the model obtained through conversion is as follows:
the discrete state update formula is:
the optimal parking path planning method specifically comprises the following steps:
analyzing the influence of the wheel rotation angle on parking path parameters, and determining a proper path rotation angle;
calculating a fitting formula of the parking bit length and the slope of the straight line to obtain the slope of the straight line, and then changing the parking radius to determine a complete parking path;
and analyzing the position and the posture of the vehicle, calculating the distance from the collision point to the vehicle, checking the feasibility of path planning, and generating a parking track.
The environmental data acquisition specifically further comprises: and acquiring environmental data through 12 paths of ultrasonic radar sensors arranged around the vehicle, capturing the size of the parking space and judging whether the parking space is suitable for parking.
The executing track parking specifically comprises the following control steps:
setting a track, and generating an optimal parking path setting track according to the plan, wherein the setting track can be a discrete point or an equation curve, and the center of the front and rear axes is taken as the origin of coordinates;
shifting gears, sequentially outputting target gears to control vehicle gear shifting, wherein the shifting gears comprise a reverse gear, a neutral gear and a forward gear, for example, the forward gear is shifted to the reverse gear, the neutral gear is required to be shifted, and then the reverse gear is shifted;
and tracking the track, setting global coordinates after finishing setting the track, and calculating the current position of the vehicle motion by using the odometer model. And calculating the target steering wheel angle by using the Pure Pursuit algorithm. Controlling an accelerator and a brake by using a PID algorithm, controlling the longitudinal speed within 2km/h, outputting a proper numerical value by the rotating speed of a steering wheel, and circularly performing the whole process until the track tracking is finished;
parking, namely controlling the brake by using a PID algorithm and stably braking the vehicle;
and restoring the gear to a neutral position, so that the whole track parking execution process is completed.
The tracking track specifically comprises the steps of calculating the angle of a target steering wheel by using a Pure Pursui algorithm, and controlling an accelerator and a brake by using a PID algorithm.
The Pure Pursuit algorithm is an algorithm applied to robot path tracking, and is proposed in the last 80 th century, and the algorithm is widely applied to intelligent vehicle path tracking.
As shown in fig. 5, the Pure Pursuit algorithm connects the target point with the rear axle of the vehicle in a straight line, and calculates the circular arc curvature from the geometry, as shown in the above figure. Wherein, (Gx, Gy) is a target point on the planned path; ld is a pre-aiming distance which is the distance between a target point on the planned path and the rear axle of the vehicle; alpha is the included angle between the preview vector and the vehicle advance vector. The following formula can be obtained according to sine theorem:
equation (4-1) can also be expressed as equation (4-2), where κ is the curvature of the arc:
as shown in FIG. 6, from the simplified two-wheel bicycle model, a relationship (4-3) between the front wheel slip angle of the vehicle and the curvature of the running track of the vehicle can be obtained, where δ is the front wheel slip angle of the vehicle, L is the wheelbase length of the front and rear wheels of the vehicle, and R is the turning radius of the vehicle.
By substituting the formula (4-2) into the formula (4-3), the front wheel slip angle can be expressed by the following formula:
δ＝tan-1(κL) (4-4)
according to the formulas (4-2) and (4-4), the control quantity expression of the Pure Pursuit algorithm can be obtained:
by introducing a new variable eldThe Pure Pursuit algorithm can be better understood, where eldThe distance of the desired point in the direction of the longitudinal axis of the vehicle thus results in:
the formula (4-6) can be collated to obtain:
as can be seen from the equations (4-7), the Pure Pursuit algorithm essentially has a gain of
The proportional controller of (1). The Purpursuit algorithm calculates a steering angle according to the deviation between the vehicle advance distance and the planned path, and then realizes path tracking.
An optimal path-based automatic parking system comprising:
the environmental data acquisition module comprises a plurality of look around camera and the ultrasonic radar of installing around the automobile body, look around the camera with the ultrasonic radar embeds there is the chip can carry out data acquisition and data processing operation, environmental data acquisition module is used for gathering 1 environmental data of parking of vehicle, environmental data acquisition module includes: the four-way all-round looking camera 2 and the 12-way ultrasonic radar sensors around the vehicle 1 are arranged at the front, the back, the left and the right of the vehicle 1;
the central processing unit module is used for receiving the environmental data acquired by the acquisition module, processing and analyzing the environmental data, detecting, calculating and dividing the parking line 3 through the environmental data and planning the optimal parking path;
the execution mechanism module receives the control command sent by the central processing unit module, can drive the steering, driving and braking operations of the vehicle, and realizes the automatic parking action by controlling the vehicle 1 to track the parking track path;
the human-computer interaction module interacts with a driver through a display screen, realizes information interaction and result feedback between a human and an automatic parking system through image-text display, physical vibration and sound of a central control display screen, an instrument and a square control device, feeds back parking environment data of the vehicle 1, detection results of a vehicle position line 3 of the central processor module, a planned parking track and a parking state controlled by the execution mechanism module, which are acquired by the environment data acquisition module, to the driver in real time, and waits for receiving a parking operation instruction of the driver.
The environment data acquisition module transmits the sensed information around the vehicle 1 to the central processor module, the central processor module analyzes and calculates the acquired environment information, deduces the specific position, environment parameters and distance change relative to a target parking space of the vehicle in the parking environment in real time, judges whether a proper parking space exists or not through a parking space line 3 detection algorithm, and makes a parking strategy based on vehicle motion model analysis and shortest parking path planning if the proper parking space exists. The execution mechanism module receives the control command sent by the central processing unit module, and tracks the generated path of the vehicle 1 by controlling a steering wheel, a gear, an accelerator pedal and the like, so that the automatic parking action is realized. The man-machine interaction module displays the current state information, environment parameters and operation steps of the automobile through the display screen, and can be operated by a driver to select whether to enter a parking state or not in real time or terminate an automatic parking process.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. An automatic parking method based on an optimal path is characterized by comprising the following steps:
acquiring environmental data, namely acquiring surrounding image information through a calibrated all-round camera, preprocessing acquired data in the sensor to output potential parking space line information, acquiring surrounding obstacle information through a calibrated ultrasonic radar, preprocessing acquired data in the sensor to output rough potential garage information;
data processing and analysis, namely placing the collected information of surrounding obstacles collected by the ultrasonic radar in an established coordinate system to obtain a feasible region of the vehicle, performing algorithm fusion on potential parking space line information output by the all-round camera and rough potential garage information output by the ultrasonic radar to obtain final parking space information, and performing optimal parking path planning by calculating the position, the rotation angle and the collision point distance of the vehicle relative to the parking spaces and the feasible region of the vehicle;
executing track parking, generating the optimal parking path setting track according to the plan, controlling and changing automobile gears to realize the operation of advancing, retreating and braking of the automobile, and controlling an accelerator, a brake and a steering wheel to work coordinately to realize track tracking angle steering parking according to the calculated target rotation angle;
and automatically parking according to the parking operation instruction, and feeding back the parking state to the driver.
2. The optimal path-based automatic parking method according to claim 1, wherein the coordinate system detection calculation divides a parking line, the method further comprising:
image preprocessing, namely correcting the panoramic top view, eliminating irrelevant information in the image, recovering useful real information, converting the original color into a gray image, and performing histogram equalization on the gray image;
positioning a search starting point of a position line, dividing a search area of a coordinate system of the panoramic top view, performing statistics on a gridding search area to obtain a position line parameter corresponding to current search, and updating a search base point;
tracking the vehicle position line, and setting a flag bit to detect whether a fitted curve is detected or not when each frame of image is processed finally;
and outputting the structured data, and when the parking space lines in the horizontal and vertical directions are detected, obtaining the intersection points between the lines and outputting the intersection points to the path.
3. The optimal path-based automatic parking method according to claim 1, wherein the optimal parking path is planned, and the method specifically comprises:
analyzing the influence of the wheel rotation angle on parking path parameters, and determining a proper path rotation angle;
calculating a fitting formula of the parking bit length and the slope of the straight line to obtain the slope of the straight line, and then changing the parking radius to determine a complete parking path;
and analyzing the position and the posture of the vehicle, calculating the distance from the collision point to the vehicle, checking the feasibility of path planning, and generating a parking track.
4. The optimal path-based automatic parking method according to claim 1, wherein the environmental data collection specifically further comprises: and acquiring environmental data through 12 paths of ultrasonic radar sensors arranged around the vehicle, capturing the size of the parking space and judging whether the parking space is suitable for parking.
5. The optimal path-based automatic parking method according to claim 1, wherein: the image registration comprises image registration and image fusion, wherein the image registration can be realized by adopting automatic image registration or manually selecting a reference point, the image fusion is based on a common reference point in manually selected adjacent images, the image registration is carried out by utilizing the regional images, and the registration is completed when the side view is changed into the top view.
6. The optimal path-based automatic parking method according to claim 1, wherein the trajectory parking is performed, and the method further comprises the following control steps:
setting a track, and generating an optimal parking path setting track according to the plan, wherein the setting track can be a discrete point or an equation curve;
the method comprises the steps of changing gears, outputting target gears in sequence to control gear change of a vehicle, wherein the changed gears comprise a reverse gear, a neutral gear and a forward gear;
tracking the track, setting global coordinates after finishing setting the track, and calculating the current position of the vehicle movement by using a odometer model;
parking, namely smoothly braking the vehicle 1;
and restoring the gear to a neutral position, so that the whole track parking execution process is completed.
7. The automatic parking method based on the optimal path is characterized in that the tracking track specifically comprises the steps of calculating a target steering wheel angle by using a Pure Pursui algorithm and controlling an accelerator and a brake by using a PID algorithm.
8. An automatic parking system based on an optimal path is characterized by at least comprising the following structures:
the environment data acquisition module consists of a plurality of looking-around cameras and an ultrasonic radar which are arranged around a vehicle body, wherein the looking-around cameras and the ultrasonic radar are internally provided with chips which can carry out data acquisition and data processing operations;
the central processing unit module is used for receiving the environmental data acquired by the acquisition module, performing data processing analysis, detecting, calculating and dividing a parking line through the environmental data and planning an optimal parking path;
the execution mechanism module receives the control command sent by the central processing unit module, can drive the steering, driving and braking operations of the vehicle, and realizes the automatic parking action by controlling the vehicle 1 to track the parking track path;
the human-computer interaction module interacts with a driver through a display screen, realizes information interaction and result feedback between a human and an automatic parking system through image-text display, physical vibration and sound of a central control display screen, an instrument and a square control device, feeds back vehicle parking environment data acquired by the environment data acquisition module, a central processor module vehicle position line detection result, a planned generated parking track and a parking state controlled by the execution mechanism module to the driver in real time, and waits for receiving a parking operation instruction of the driver.
9. The optimal path-based automatic parking system according to claim 8, wherein the environment data collection module comprises: the four-way all-round looking camera and the 12-way ultrasonic radar sensor are arranged at the front, the back, the left and the right of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910975759.4A CN110696818A (en) | 2019-10-12 | 2019-10-12 | Automatic parking method and system based on optimal path |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910975759.4A CN110696818A (en) | 2019-10-12 | 2019-10-12 | Automatic parking method and system based on optimal path |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110696818A true CN110696818A (en) | 2020-01-17 |
Family
ID=69198362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910975759.4A Pending CN110696818A (en) | 2019-10-12 | 2019-10-12 | Automatic parking method and system based on optimal path |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110696818A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111609866A (en) * | 2020-06-04 | 2020-09-01 | 山东交通学院 | Park vehicle intelligent driving path fitting tracking control method based on differential GPS |
| CN111811517A (en) * | 2020-07-15 | 2020-10-23 | 中国科学院上海微系统与信息技术研究所 | Dynamic local path planning method and system |
| CN111845723A (en) * | 2020-08-05 | 2020-10-30 | 北京四维智联科技有限公司 | Full-automatic parking method and system |
| CN111942375A (en) * | 2020-08-24 | 2020-11-17 | 米传科技（上海）有限公司 | Automatic parking system based on millimeter wave radar and 5G |
| CN111959498A (en) * | 2020-07-14 | 2020-11-20 | 重庆智行者信息科技有限公司 | Vertical parking method and device for automatically driving vehicle and vehicle |
| CN111976718A (en) * | 2020-07-13 | 2020-11-24 | 浙江大华汽车技术有限公司 | Automatic parking control method and system |
| CN112061114A (en) * | 2020-08-17 | 2020-12-11 | 广东工业大学 | Optimal path control method of autonomous parking system based on self-adaptive pseudo-spectral method |
| CN112158195A (en) * | 2020-09-16 | 2021-01-01 | 重庆长安汽车股份有限公司 | Parking path planning method, system, vehicle and storage medium |
| CN112232275A (en) * | 2020-11-03 | 2021-01-15 | 上海西井信息科技有限公司 | Obstacle detection method, system, equipment and storage medium based on binocular recognition |
| CN112319464A (en) * | 2020-11-09 | 2021-02-05 | 恒大新能源汽车投资控股集团有限公司 | Automatic parking method, device, equipment and storage medium |
| CN112373462A (en) * | 2020-11-05 | 2021-02-19 | 广州汽车集团股份有限公司 | Automatic parking method, device, controller and system |
| CN112389465A (en) * | 2020-11-17 | 2021-02-23 | 湖南三一智能控制设备有限公司 | Control method and control system of engineering vehicle and engineering vehicle |
| CN112572417A (en) * | 2020-12-11 | 2021-03-30 | 武汉乐庭软件技术有限公司 | Gear pre-judging method and device in automatic parking control system and storage device |
| CN112793562A (en) * | 2021-02-03 | 2021-05-14 | 武汉理工大学 | Automatic parking path planning and tracking control method, planning device, storage medium and computer equipment |
| CN113033349A (en) * | 2021-03-11 | 2021-06-25 | 北京文安智能技术股份有限公司 | Overlook image selection method for pedestrian re-identification, storage medium and electronic device |
| CN113095393A (en) * | 2021-04-06 | 2021-07-09 | 兰州交通大学 | High-income taxi driver and extraction method, equipment and storage medium of experience track of taxi driver |
| CN113449648A (en) * | 2021-06-30 | 2021-09-28 | 北京纵目安驰智能科技有限公司 | Method, system, equipment and computer readable storage medium for detecting indicator line |
| CN113472833A (en) * | 2020-03-31 | 2021-10-01 | 广州汽车集团股份有限公司 | Parking control method and system and cloud service platform |
| CN114274948A (en) * | 2021-12-15 | 2022-04-05 | 武汉光庭信息技术股份有限公司 | Automatic parking method and device based on 360-degree panorama |
| CN114454873A (en) * | 2020-11-10 | 2022-05-10 | 陕西重型汽车有限公司 | Automatic parking control system and automatic parking method for commercial vehicle |
| CN114454872A (en) * | 2020-11-10 | 2022-05-10 | 上汽通用汽车有限公司 | Parking system and parking method |
| CN114593726A (en) * | 2022-02-22 | 2022-06-07 | 深圳鹏行智能研究有限公司 | Path smoothing method and device |
| CN115243960A (en) * | 2020-03-02 | 2022-10-25 | 法雷奥开关和传感器有限责任公司 | Method for operating a vehicle, parking assistance system and vehicle |
| CN115402324A (en) * | 2022-11-01 | 2022-11-29 | 北京千种幻影科技有限公司 | Intelligent guiding control method and system for virtual driving for side-entering |
| CN116778457A (en) * | 2023-08-16 | 2023-09-19 | 钧捷科技（北京）有限公司 | Automatic parking auxiliary control system and device for vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104691544A (en) * | 2015-04-03 | 2015-06-10 | 重庆瓦力仪器有限公司 | Full-automatic parking system and parking method thereof |
| US20160061618A1 (en) * | 2014-08-27 | 2016-03-03 | Parklife Ltd. | Technique for navigating a vehicle to a parking place |
| CN108928343A (en) * | 2018-08-13 | 2018-12-04 | 吉利汽车研究院（宁波）有限公司 | A kind of panorama fusion automated parking system and method |
| CN109131317A (en) * | 2018-07-23 | 2019-01-04 | 同济大学 | Automatic vertical parking system and method based on multisection type planning and machine learning |
| CN109649384A (en) * | 2019-02-15 | 2019-04-19 | 华域汽车系统股份有限公司 | A kind of parking assistance method |
-
2019
- 2019-10-12 CN CN201910975759.4A patent/CN110696818A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160061618A1 (en) * | 2014-08-27 | 2016-03-03 | Parklife Ltd. | Technique for navigating a vehicle to a parking place |
| CN104691544A (en) * | 2015-04-03 | 2015-06-10 | 重庆瓦力仪器有限公司 | Full-automatic parking system and parking method thereof |
| CN109131317A (en) * | 2018-07-23 | 2019-01-04 | 同济大学 | Automatic vertical parking system and method based on multisection type planning and machine learning |
| CN108928343A (en) * | 2018-08-13 | 2018-12-04 | 吉利汽车研究院（宁波）有限公司 | A kind of panorama fusion automated parking system and method |
| CN109649384A (en) * | 2019-02-15 | 2019-04-19 | 华域汽车系统股份有限公司 | A kind of parking assistance method |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115243960A (en) * | 2020-03-02 | 2022-10-25 | 法雷奥开关和传感器有限责任公司 | Method for operating a vehicle, parking assistance system and vehicle |
| CN115243960B (en) * | 2020-03-02 | 2024-03-08 | 法雷奥开关和传感器有限责任公司 | Method for operating a vehicle, parking assistance system and vehicle |
| CN113472833A (en) * | 2020-03-31 | 2021-10-01 | 广州汽车集团股份有限公司 | Parking control method and system and cloud service platform |
| CN113472833B (en) * | 2020-03-31 | 2024-02-20 | 广州汽车集团股份有限公司 | Parking control method, system and cloud service platform |
| CN111609866A (en) * | 2020-06-04 | 2020-09-01 | 山东交通学院 | Park vehicle intelligent driving path fitting tracking control method based on differential GPS |
| CN111609866B (en) * | 2020-06-04 | 2023-09-12 | 山东交通学院 | Intelligent driving path fitting tracking control method for park vehicles based on differential GPS |
| CN111976718A (en) * | 2020-07-13 | 2020-11-24 | 浙江大华汽车技术有限公司 | Automatic parking control method and system |
| CN111959498A (en) * | 2020-07-14 | 2020-11-20 | 重庆智行者信息科技有限公司 | Vertical parking method and device for automatically driving vehicle and vehicle |
| CN111811517A (en) * | 2020-07-15 | 2020-10-23 | 中国科学院上海微系统与信息技术研究所 | Dynamic local path planning method and system |
| CN111845723A (en) * | 2020-08-05 | 2020-10-30 | 北京四维智联科技有限公司 | Full-automatic parking method and system |
| CN112061114A (en) * | 2020-08-17 | 2020-12-11 | 广东工业大学 | Optimal path control method of autonomous parking system based on self-adaptive pseudo-spectral method |
| CN112061114B (en) * | 2020-08-17 | 2022-02-25 | 广东工业大学 | Optimal path control method of autonomous parking system based on self-adaptive pseudo-spectral method |
| CN111942375A (en) * | 2020-08-24 | 2020-11-17 | 米传科技（上海）有限公司 | Automatic parking system based on millimeter wave radar and 5G |
| CN111942375B (en) * | 2020-08-24 | 2021-02-19 | 米传科技（上海）有限公司 | Automatic parking system based on millimeter wave radar and 5G |
| CN112158195A (en) * | 2020-09-16 | 2021-01-01 | 重庆长安汽车股份有限公司 | Parking path planning method, system, vehicle and storage medium |
| CN112232275A (en) * | 2020-11-03 | 2021-01-15 | 上海西井信息科技有限公司 | Obstacle detection method, system, equipment and storage medium based on binocular recognition |
| CN112373462A (en) * | 2020-11-05 | 2021-02-19 | 广州汽车集团股份有限公司 | Automatic parking method, device, controller and system |
| CN112319464B (en) * | 2020-11-09 | 2021-10-15 | 恒大新能源汽车投资控股集团有限公司 | Automatic parking method, device, equipment and storage medium |
| CN112319464A (en) * | 2020-11-09 | 2021-02-05 | 恒大新能源汽车投资控股集团有限公司 | Automatic parking method, device, equipment and storage medium |
| CN114454872A (en) * | 2020-11-10 | 2022-05-10 | 上汽通用汽车有限公司 | Parking system and parking method |
| CN114454873A (en) * | 2020-11-10 | 2022-05-10 | 陕西重型汽车有限公司 | Automatic parking control system and automatic parking method for commercial vehicle |
| CN114454873B (en) * | 2020-11-10 | 2023-07-25 | 陕西重型汽车有限公司 | Automatic parking control system and automatic parking method for commercial vehicle |
| CN112389465B (en) * | 2020-11-17 | 2022-03-18 | 湖南三一智能控制设备有限公司 | Control method and control system of engineering vehicle and engineering vehicle |
| CN112389465A (en) * | 2020-11-17 | 2021-02-23 | 湖南三一智能控制设备有限公司 | Control method and control system of engineering vehicle and engineering vehicle |
| CN112572417A (en) * | 2020-12-11 | 2021-03-30 | 武汉乐庭软件技术有限公司 | Gear pre-judging method and device in automatic parking control system and storage device |
| CN112572417B (en) * | 2020-12-11 | 2022-01-18 | 武汉乐庭软件技术有限公司 | Gear pre-judging method and device in automatic parking control system and storage device |
| CN112793562A (en) * | 2021-02-03 | 2021-05-14 | 武汉理工大学 | Automatic parking path planning and tracking control method, planning device, storage medium and computer equipment |
| CN112793562B (en) * | 2021-02-03 | 2023-02-28 | 武汉理工大学 | Automatic parking path planning and tracking control method, planning device, storage medium and computer equipment |
| CN113033349A (en) * | 2021-03-11 | 2021-06-25 | 北京文安智能技术股份有限公司 | Overlook image selection method for pedestrian re-identification, storage medium and electronic device |
| CN113033349B (en) * | 2021-03-11 | 2023-12-26 | 北京文安智能技术股份有限公司 | Overhead image selection method for pedestrian re-recognition, storage medium and electronic equipment |
| CN113095393A (en) * | 2021-04-06 | 2021-07-09 | 兰州交通大学 | High-income taxi driver and extraction method, equipment and storage medium of experience track of taxi driver |
| CN113449648A (en) * | 2021-06-30 | 2021-09-28 | 北京纵目安驰智能科技有限公司 | Method, system, equipment and computer readable storage medium for detecting indicator line |
| CN114274948A (en) * | 2021-12-15 | 2022-04-05 | 武汉光庭信息技术股份有限公司 | Automatic parking method and device based on 360-degree panorama |
| CN114593726A (en) * | 2022-02-22 | 2022-06-07 | 深圳鹏行智能研究有限公司 | Path smoothing method and device |
| CN115402324A (en) * | 2022-11-01 | 2022-11-29 | 北京千种幻影科技有限公司 | Intelligent guiding control method and system for virtual driving for side-entering |
| CN116778457A (en) * | 2023-08-16 | 2023-09-19 | 钧捷科技（北京）有限公司 | Automatic parking auxiliary control system and device for vehicle |
| CN116778457B (en) * | 2023-08-16 | 2023-11-03 | 钧捷科技（北京）有限公司 | Automatic parking auxiliary control system and device for vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110696818A (en) | Automatic parking method and system based on optimal path | |
| CN110775052B (en) | Automatic parking method based on fusion of vision and ultrasonic perception | |
| CN110969655B (en) | Method, device, equipment, storage medium and vehicle for detecting parking space | |
| CN106054174B (en) | It is used to cross the fusion method of traffic application using radar and video camera | |
| US10046803B2 (en) | Vehicle control system | |
| US10867409B2 (en) | Methods and systems to compensate for vehicle calibration errors | |
| US9902425B2 (en) | System for guiding trailer along target route during reversing maneuver | |
| CN106295560B (en) | Lane keeping method based on vehicle-mounted binocular camera and segmented PID control | |
| JP6910973B2 (en) | Vehicle control device, its control method, and vehicle control system | |
| CN110979305A (en) | Vehicle abnormal lane change control method, device and system | |
| CN111627054A (en) | Method and device for predicting depth completion error map of high-confidence dense point cloud | |
| CN112419776B (en) | Autonomous parking method and device, automobile and computing equipment | |
| CN112068574A (en) | Control method and system for unmanned vehicle in dynamic complex environment | |
| CN113267199A (en) | Driving track planning method and device | |
| CN112537294B (en) | Automatic parking control method and electronic equipment | |
| CN111967360A (en) | Target vehicle attitude detection method based on wheels | |
| CN111123950A (en) | Driving control method and device and vehicle | |
| CN112731925A (en) | Conical barrel identification and path planning and control method for unmanned formula racing car | |
| CN111402328A (en) | Pose calculation method and device based on laser odometer | |
| CN112819711A (en) | Monocular vision-based vehicle reverse positioning method utilizing road lane line | |
| Schanz et al. | Autonomous parking in subterranean garages-a look at the position estimation | |
| CN115144849A (en) | Sensor fusion for object avoidance detection | |
| GB2580400A (en) | A control system, system and method for providing assistance to an occupant of a vehicle | |
| Wu et al. | Design and Simulation of an Autonomous Racecar: Perception, SLAM, Planning and Control | |
| Mancuso | Study and implementation of lane detection and lane keeping for autonomous driving vehicles |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |