CN116985785A - Automatic parking system based on multiple sensors and visual interaction - Google Patents

Automatic parking system based on multiple sensors and visual interaction Download PDF

Info

Publication number
CN116985785A
CN116985785A CN202311267351.4A CN202311267351A CN116985785A CN 116985785 A CN116985785 A CN 116985785A CN 202311267351 A CN202311267351 A CN 202311267351A CN 116985785 A CN116985785 A CN 116985785A
Authority
CN
China
Prior art keywords
vehicle
parking
automatic parking
obstacle
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202311267351.4A
Other languages
Chinese (zh)
Other versions
CN116985785B (en
Inventor
钱灏
谭海川
马朝华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhangjiagang Jikejia Intelligent Technology Research And Development Co ltd
Original Assignee
Zhangjiagang Jikejia Intelligent Technology Research And Development Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhangjiagang Jikejia Intelligent Technology Research And Development Co ltd filed Critical Zhangjiagang Jikejia Intelligent Technology Research And Development Co ltd
Priority to CN202311267351.4A priority Critical patent/CN116985785B/en
Publication of CN116985785A publication Critical patent/CN116985785A/en
Application granted granted Critical
Publication of CN116985785B publication Critical patent/CN116985785B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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
    • 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
    • B60W40/105—Speed
    • 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
    • B60W40/107—Longitudinal acceleration
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/06—Direction of travel
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • B60W2520/105—Longitudinal acceleration
    • 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
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/50—Barriers
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

The application relates to the technical field of vehicle driving control, in particular to an automatic parking system based on multiple sensors and visual interaction, which comprises: the data acquisition module acquires vehicle motion information according to various sensors and acquires images of surrounding environments of the vehicle; the automatic parking system data analysis module is combined with a Dragon-grid-base tower algorithm to obtain a vehicle motion adjustment model at each parking time point; obtaining a vehicle form vector set and a surrounding obstacle form vector total set according to the outlines of the vehicle and the obstacle, and constructing an anti-collision module; obtaining an anti-collision factor according to the width of the vehicle and the width of the anti-collision frame; an initial automatic parking model is built, and an automatic parking model is obtained according to the initial automatic parking model and the parking time; and the automatic parking navigation instruction transmission module is used for obtaining a parking route according to the automatic parking model and executing automatic parking. The application realizes automatic parking of the vehicle, improves the parking precision and avoids the problem of collision.

Description

Automatic parking system based on multiple sensors and visual interaction
Technical Field
The application relates to the technical field of vehicle driving control, in particular to an automatic parking system based on multiple sensors and visual interaction.
Background
The automatic parking refers to automatic parking of the automobile without manual control, and the system can automatically help the automobile to park in a parking space, and can be called as a driver in backing and warehousing. When finding an ideal parking place, people only need to lightly start the button, sit and relax, and all the other things can be automatically completed. The automatic parking technology is also suitable for an active collision avoidance system, and finally automatic driving of the automobile is realized. Different automatic parking systems employ different methods for detecting objects around the vehicle, and some incorporate sensors around the front and rear bumpers of the vehicle that can act as both transmitters and receivers. These sensors send a signal that is reflected back when it hits an obstacle in the periphery of the vehicle body, and the computer on the vehicle then uses the time it takes to receive the signal to determine the position of the obstacle. Most automatic parking systems acquire comprehensive tracks of parking, and the problem of collision with obstacles exists when actual parking is performed.
Disclosure of Invention
To solve the above technical problem, the present application provides an automatic parking system based on multiple sensors and visual interaction, the system comprising:
the data acquisition module is used for acquiring vehicle motion information according to various sensors and acquiring surrounding environment images of vehicles in the parking lot;
the automatic parking system data analysis module is used for obtaining a vehicle motion adjustment model during parking according to the vehicle motion information; according to the vehicle motion adjustment model, a vehicle motion adjustment model at each parking time point is obtained by combining a Dragon lattice tower algorithm; obtaining a vehicle form vector set and a surrounding obstacle form vector total set according to the outlines of the vehicle and the obstacle; obtaining an anti-collision module according to the vehicle form vector set and the surrounding obstacle form vector total set; obtaining an anti-collision factor according to the width of the vehicle and the width of the anti-collision frame; obtaining a vehicle parking limiting module according to the vehicle motion adjusting model, the anti-collision module and the anti-collision factor; constructing an initial automatic parking model according to the parking time and the vehicle parking limiting module, and obtaining an automatic parking model according to the initial automatic parking model and the parking time;
and the automatic parking navigation instruction transmission module is used for obtaining an automatic parking route of the vehicle according to the automatic parking model and executing automatic parking.
Preferably, the collecting vehicle motion information according to various sensors specifically includes: the vehicle is provided with a speed sensor, an acceleration sensor and a vehicle-mounted gyroscope, the speed, the acceleration and the course angle of the vehicle are collected, and the vehicle motion information comprises the barycenter coordinates of the vehicle, the course angle of the vehicle, the speed of the vehicle, the acceleration of the vehicle and the steering angle of the front wheel of the vehicle.
Preferably, the method for obtaining the vehicle motion adjustment model during parking according to the vehicle motion information includes the specific steps of:
,
wherein epsilon is a vehicle motion model, x and y are vehicle centroid coordinates,is course angle, v is vehicle speed, delta represents vehicle acceleration, a is acceleration value, l f 、l r Respectively a front suspension length, a rear suspension length and delta f Is the front wheel steering angle.
Preferably, the vehicle motion adjustment model at each parking time point is obtained by combining the vehicle motion adjustment model with the dragger wall algorithm, specifically: discretizing the parking time, equally dividing the parking time into N sections to obtain N+1 parking time points, wherein the parking time dividing period is as followsT is parking time, and the vehicle motion adjustment model expression of each parking time point is as follows:
,
in the formula ,εk+1 Vehicle movement control for parking time k+1Model epsilon k Adjusting a model for the movement of the vehicle at a parking time point k, wherein T is a parking time dividing period r 1 Is a first-order Dragon lattice tower function, and the expression is r 1 =f(ε k ,u k), wherein ,uk For each set of variables r in the vehicle motion model at parking time k 2 Is a second-order Dragon lattice tower function, and the expression is，r 3 Is a third-order Dragon lattice tower function, and the expression is +.>，r 4 Is a fourth-order Dragon lattice tower function, and the expression is +.>。
Preferably, the vehicle shape vector set and the surrounding obstacle shape vector total set are obtained according to the contours of the vehicle and the obstacle, and the method comprises the following specific steps:
acquiring a vehicle form vector set according to four vertexes of a vehicle, wherein the expression is as follows:
,
wherein A is a vehicle shape vector set,represents a directed line segment pointing from vehicle vertex A1 to vehicle vertex A2,/and>represents a directed line segment pointing from vehicle vertex A2 to vehicle vertex A3,/and>represents a directed line segment pointing from vehicle vertex A3 to vehicle vertex A4,/and>represents a directed line segment pointing from vertex A4 to vertex A1;
obtaining a minimum circumscribed rectangle of an obstacle, and obtaining a morphological vector set of the obstacle Os, wherein the expression is as follows:
,
in the formula ,is the morphological vector set of obstacle Os, < ->Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 1 Minimum circumscribed rectangle vertex Os of directional obstacle Os 2 Directed line segment of (2), is>Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 2 Minimum circumscribed rectangle vertex Os of directional obstacle Os 3 Directed line segment of (2), is>Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 3 Minimum circumscribed rectangle vertex Os of directional obstacle Os 4 Directed line segment of (2), is>Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 4 Minimum circumscribed rectangle vertex Os of directional obstacle Os 1 Is a directed line segment of (2);
the form vector set of all the obstacles is used for obtaining an obstacle form vector total set, and the expression is as follows:
，
wherein s is the total number of obstacles around the vehicle, O is the total set of obstacle form vectors,is the morphological vector set of obstacle O1, < ->Is the morphological vector set of obstacle O2, < ->Is a morphological vector set of the obstacle Os.
Preferably, the anti-collision module is obtained according to a vehicle form vector set and a surrounding obstacle form vector total set, specifically:
，
where n represents the intersection set,and (3) a vehicle form vector set A and an obstacle form vector total set O.
Preferably, the anti-collision factor is obtained according to the width of the vehicle and the width of the anti-collision frame, specifically: an anti-collision frame is built by taking the center of a vehicle as the center, the anti-collision frame is consistent with the center of the vehicle, the length of the anti-collision frame is identical to the length of the vehicle, the width of the anti-collision frame is w+2d, d is respectively added on two sides of the width of the vehicle, the width of the anti-collision frame is obtained, and an expression of an anti-collision factor is as follows:
，
where τ is an anti-collision factor, w is a vehicle width, and d is an increase in the vehicle width.
Preferably, the vehicle parking limiting module is obtained according to the vehicle motion adjustment model, the anti-collision module and the anti-collision factor, and specifically includes:
，
wherein v vehicle speed v min 、v max Respectively minimum and maximum values of vehicle speed when parking, a is vehicle acceleration, a min 、a max Respectively, parkMinimum, maximum, delta of vehicle acceleration f For the steering angle of the front wheels,is the minimum value, the maximum value and epsilon of the steering angle of the front wheel k+1 、ε k The vehicle motion adjustment models respectively refer to a parking time point k+1 and a parking time point k, T is a parking time dividing period, and r is a parking time dividing period 1 As a first-order Dragon-lattice tower function, r 2 As a second-order Dragon's tower function, r 3 As a third-order Dragon-lattice tower function, r 4 As a fourth-order Dragon-Gregory tower function, epsilon start 、ε final Respectively an initial motion adjustment model, an end motion adjustment model, a vehicle form vector set, an O obstacle form vector total set, n represents an intersection, and +.>Is empty, τ is an anti-collision factor, τ D An anti-collision threshold greater than 1.
Preferably, the obtaining the automatic parking model according to the initial automatic parking model and the parking time specifically includes:
，
wherein ,for automatic parking models->Is a weight factor, min { } is operated by taking the minimum value, t is parking time, N is the parking time and is divided into N sections and epsilon k Model epsilon is adapted to the vehicle movement at parking time k initial,k And (3) adjusting a model for the vehicle motion of a parking time point k corresponding to the initial parking track, wherein the I is the Euclidean distance sign.
Preferably, the obtaining the automatic parking route of the vehicle according to the automatic parking model includes:
and selecting an algorithm A to calculate the optimal solution of the automatic parking model, wherein the corresponding route when the automatic parking model is minimum is the automatic parking route of the vehicle.
The application has at least the following beneficial effects:
according to the application, the vehicle motion adjustment model in the vehicle parking state is obtained through the vehicle motion model, so that the obtained vehicle motion state is more in line with the actual parking situation, and the vehicle parking precision is improved. The anti-collision module is obtained by combining the vehicle form vector set and the surrounding obstacle form vector set, so that the problem of collision in the vehicle parking process is solved, meanwhile, in order to improve the anti-collision effect in the vehicle parking process, anti-collision factors are constructed according to the actual condition of the vehicle form, and the sudden problem in the actual vehicle parking process can be effectively solved; the automatic parking model of the vehicle is controlled by constructing the vehicle parking limiting module, and the problem that the parking route is difficult to set in the automatic parking process of the vehicle is solved by combining the vehicle parking limiting module and the automatic parking model; finally, according to the automatic parking navigation instruction transmission module, the navigation of the vehicle in the parking process can be realized, and the automatic parking of the vehicle is ensured. The application has the advantages of high parking precision, good anti-collision effect and the like.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an automatic parking system based on multiple sensors and visual interaction provided by the present application.
Detailed Description
In order to further describe the technical means and effects adopted by the application to achieve the preset aim, the following detailed description is given below of the multi-sensor and visual interaction-based automatic parking system according to the application, and the specific implementation, structure, characteristics and effects thereof, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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.
The following specifically describes a specific scheme of the automatic parking system based on multiple sensors and visual interaction provided by the application with reference to the accompanying drawings.
An embodiment of the present application provides an automatic parking system based on multiple sensors and visual interaction, mainly comprising: the automatic parking system comprises a data acquisition module, an automatic parking system data analysis module and an automatic parking navigation instruction transmission module.
Specifically, the multi-sensor and visual interaction-based automatic parking system of the present embodiment provides a multi-sensor and visual interaction-based automatic parking method as follows, referring to fig. 1, the method includes the steps of:
step S001, a data acquisition module.
The data acquisition module acquires vehicle motion information through multiple sensors and acquires images of surrounding environments of the vehicle. According to the embodiment, the automatic parking process of the vehicle is controlled mainly through the vehicle motion information and the surrounding obstacle information to obtain the optimal automatic parking track, so that in order to accurately obtain the pose of the vehicle, the pose information of the vehicle is acquired through the speed sensor, the ultrasonic sensor, the vehicle-mounted gyroscope and other sensors, the vehicle motion information comprises but is not limited to the vehicle speed, the course angle, the deflection angle, the acceleration and the like, an implementer can load the corresponding sensors in the vehicle according to actual conditions, and the sensor type and the model implementer can select the vehicle. Meanwhile, in order to assist the vehicle to automatically and accurately drive into the parking space, the vehicle-mounted camera and the camera of the parking lot collect the surrounding information of the vehicle to obtain the surrounding image of the vehicle, and the ultrasonic sensor is combined to accurately collect the surrounding obstacle information of the vehicle. The view angle of the vehicle-mounted camera and the camera implementation of the parking lot are set by the user according to actual conditions.
Therefore, the motion information of the vehicle can be acquired through the multiple sensors, and the vehicle-mounted camera and the parking lot camera are combined to acquire the surrounding environment information of the vehicle.
Step S002, an automatic parking system data analysis module.
The data analysis module is mainly used for obtaining a vehicle motion adjustment model when parking according to the vehicle motion information; according to the vehicle motion adjustment model, a vehicle motion adjustment model at each parking time point is obtained by combining a Dragon lattice tower algorithm; obtaining a vehicle form vector set and a surrounding obstacle form vector total set according to the outlines of the vehicle and the obstacle; obtaining an anti-collision module according to the vehicle form vector set and the surrounding obstacle form vector total set; obtaining an anti-collision factor according to the width of the vehicle and the width of the anti-collision frame; obtaining a vehicle parking limiting module according to the vehicle motion adjusting model, the anti-collision module and the anti-collision factor; and constructing an initial automatic parking model according to the parking time and the vehicle parking limiting module, and obtaining the automatic parking model according to the initial automatic parking model and the parking time. The automatic parking system data analysis module specifically comprises:
firstly, according to the prior art, a vehicle model in automatic driving can be simplified into a rigid body structure moving on a two-dimensional plane, a vehicle motion model is obtained, a plurality of existing vehicle motion models are available, an implementer can select the vehicle according to actual conditions, and the vehicle generally adopts a front wheel steering design, so that the steering angle of a rear wheel is set to be 0, and the vehicle motion model in the embodiment is as follows:
wherein epsilon is a vehicle motion model, x and y are vehicle centroid coordinates,is course angle, which means the included angle between the car body and the x-axis, v is the speed of the car, delta represents the acceleration of the car, a is the acceleration value, l f 、l r Respectively a front suspension length and a rear suspension length, wherein beta is a slip angle, which refers to an angle formed between the vehicle running direction and the direction pointed by the rim, delta f The vehicle speed, the front wheel steering angle and the vehicle acceleration are acquired through corresponding vehicle-mounted sensors.
Meanwhile, considering that the running speed of the vehicle is very small in actual parking, the lateral sliding force of the tire in the parking process is very small and can be ignored, so that the sliding angle of the vehicle in the automatic parking process can be ignored, and the vehicle sliding angle is set to be 0 in the embodiment, so that the vehicle motion model is adjusted, and the vehicle motion adjustment model is obtained specifically as follows:
，
wherein epsilon is a vehicle motion model, x and y are vehicle centroid coordinates,is course angle, v is vehicle speed, delta represents vehicle acceleration, a is acceleration value, l f 、l r Respectively a front suspension length, a rear suspension length and delta f Is the front wheel steering angle.
Then, in order to improve the parking efficiency, reduce the time loss in the parking process and simultaneously ensure that the problem of collision during parking is avoided, the embodiment obtains a vehicle motion adjustment model at each parking time point according to a vehicle motion adjustment model and a ringer's tower algorithm, and the conventional automatic parking system obtains the parking route of the vehicle mostly through the vehicle pose, surrounding obstacles and parking space information, but only can deal with the discrete problem when considering the computer system to perform data processing analysis, so the embodiment discretizes the parking time, marks the parking time as t, equally divides the parking time into N sections, can obtain n+1 time points, and divides the parking time into periods of. It should be noted that, during the parking of the vehicle, the variables of the vehicle in each period are kept uniform,that is, parameters representing the motion state of the vehicle are the same, and in this embodiment, the vehicle mainly includes position information, heading angle, speed, acceleration, and the like. In order to update the vehicle motion state in the parking process, the embodiment adopts a Dragon-Gregory tower algorithm to represent the vehicle motion state in a vehicle motion model, and the vehicle motion adjustment model expression at each parking time point is specifically as follows:
，
in the formula ,εk+1 Model epsilon is adjusted for the vehicle movement at parking time k+1 k Model adjustment for the movement of the vehicle at parking time k, u k The method is characterized in that the method comprises the steps of (1) a set of variables in a vehicle motion model of a parking time point k, wherein T is a parking time dividing period, and r 1 Is a first-order Dragon lattice tower function, and the expression is r 1 =f(ε k ,u k )，r 2 Is a second-order Dragon lattice tower function, and the expression is，r 3 Is a third-order Dragon lattice tower function, and the expression is +.>，r 4 Is a fourth-order Dragon lattice tower function, and the expression is +.>. The calculation of the Long Geku tower function is a well-known technique. The motion state of the vehicle during parking can be updated by combining the grid tower algorithm, the vehicle states in adjacent time periods can be linked, and the processing speed of the automatic parking system is improved, so that the optimal parking track can be quickly obtained.
Further, considering that the collision problem with the obstacle needs to be avoided in the automatic parking process of the vehicle, the embodiment limits the collision problem in the automatic parking process of the vehicle according to the obstacle information around the vehicle and the state information of the vehicle, and builds an anti-collision module to prevent the collision problem in the parking process. For vehicle surrounding environment information, the vehicle-mounted ultrasonic sensor, the vehicle-mounted camera and the parking lot camera acquire obstacle information around the vehicle to obtain the positions of various obstacles, the vehicle-mounted camera and the parking lot camera are used for assisting the vehicle-mounted ultrasonic sensor to accurately detect the obstacles around the vehicle, and the vehicle-mounted camera and the parking lot camera are used for detecting and identifying the obstacles mainly through vehicle surrounding images acquired by the camera. For the collected vehicle surrounding image, the object detection network is used for detecting the obstacle in the vehicle surrounding image, and it is to be noted that the object detection network and the process of detecting the obstacle in the image by the object detection network are known technologies, and are not in the protection scope of the embodiment, and are not described in detail.
The anti-collision module construction process in the automatic parking process of the vehicle comprises the following steps: in this embodiment, four vertexes of the vehicle are respectively designated as A1, A2, A3, and A4 clockwise from the left front of the vehicle, and it should be noted that the practitioner can mark the vertexes of the vehicle by himself without completely marking the vertexes clockwise from the left front of the vehicle. Acquiring a vehicle form vector set according to four vertexes of a vehicle, wherein the expression is as follows:
,
wherein A is a vehicle shape vector set,represents a directed line segment pointing from vehicle vertex A1 to vehicle vertex A2,/and>represents a directed line segment pointing from vehicle vertex A2 to vehicle vertex A3,/and>represents a directed line segment pointing from vehicle vertex A3 to vehicle vertex A4,/and>represents a directed line segment pointing from vertex A4 to vertex A1;
then, the obstacles around the vehicle are respectively marked as O1, O2, …, os and s are the total number of the obstacles around the vehicle, and similarly, for each obstacle, the minimum bounding rectangle of each obstacle is obtained, taking the obstacle Os as an example, and four vertexes of the minimum bounding rectangle of the obstacle from the upper left corner of the minimum bounding rectangle of the obstacle Os are respectively marked as Os clockwise 1 ,Os 2 ,Os 3 ,Os 4 It should be noted that, the implementation of the marking mode of the four vertices of the minimum bounding rectangle of the obstacle can also be defined by the user, and each vertex does not need to be marked completely according to the upper left corner of the minimum bounding rectangle of the obstacle and clockwise. Obtaining a morphological vector set of an obstacle Os, wherein the expression is as follows:
;
in the formula ,is the morphological vector set of obstacle Os, < ->Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 1 Minimum circumscribed rectangle vertex Os of directional obstacle Os 2 Directed line segment of (2), is>Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 2 Minimum circumscribed rectangle vertex Os of directional obstacle Os 3 Directed line segment of (2), is>Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 3 Minimum circumscribed rectangle vertex Os of directional obstacle Os 4 Directed line segment of (2), is>Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 4 Minimum circumscribed rectangle vertex Os of directional obstacle Os 1 Is provided withA line segment;
repeating the method to obtain a morphological vector set of each obstacle;
obtaining a total set of obstacle form vectors according to the form vector sets of all the obstacles, wherein the expression is as follows:
,
wherein s is the total number of obstacles around the vehicle, O is the total set of obstacle form vectors,is the morphological vector set of obstacle O1, < ->Is the morphological vector set of obstacle O2, < ->A set of morphology vectors that are obstacle Os;
finally, in this embodiment, considering that, in the running process of the vehicle, as long as there is no intersection between the vehicle form vector set and the obstacle form vector total set, the vehicle will not collide with the obstacle, that is, there is no overlapping area between the area formed by the vehicle form vector and the area formed by the obstacle form vector total set when the vehicle runs, and no collision problem will occur, the embodiment will characterize the collision event between the vehicle and the obstacle according to the form features, and obtain the anti-collision module according to the vehicle form vector set and the surrounding obstacle form vector total set, where the anti-collision module specifically is:wherein ∈ represents the intersection, +.>Is empty set, is->Representing the vehicle form vector set without any intersection with the obstacle form vector set, i.e. the vehicle form vector set is guaranteedThe collision problem can not occur;
thus, the anti-collision module in the automatic parking process of the vehicle can be obtained.
In consideration of the actual situation, the vehicle needs to keep a certain distance from surrounding obstacles in the running process so as to prevent an emergency in the actual running process, so that an anti-collision factor is constructed in the embodiment so as to prevent the emergency problem in the parking process due to the calculation error of the parking route and avoid the occurrence of potential danger. In order to improve the anti-collision effect in the actual parking process, in this embodiment, an anti-collision frame is constructed with the center of the vehicle as the center, the length of the anti-collision frame is identical to the length of the vehicle, the width of the anti-collision frame is w+2d, that is, d is respectively increased on two sides of the width of the vehicle, so as to obtain the width of the anti-collision frame, and the expression of the anti-collision factor is as follows:
;
where τ is an anti-collision factor, w is a vehicle width, and d is an increase in the vehicle width. According to the anti-collision factor, in the automatic parking process of the vehicle, the anti-collision factor needs to be kept to be always larger than 1 so that the anti-collision frame can always cover the running area of the vehicle.
So far, according to the method, each key problem in the automatic parking process of the vehicle can be obtained, and according to the vehicle motion adjustment model, the anti-collision module and the anti-collision factor, the vehicle parking limiting module is obtained, and specifically comprises the following steps:
,
wherein v vehicle speed v min 、v max Respectively minimum and maximum values of vehicle speed when parking, a is vehicle acceleration, a min 、a max Respectively minimum, maximum and delta of vehicle acceleration during parking f For the steering angle of the front wheels,is the minimum value, the maximum value and epsilon of the steering angle of the front wheel k+1 、ε k The vehicle motion adjustment models respectively refer to a parking time point k+1 and a parking time point k, T is a parking time dividing period, and r is a parking time dividing period 1 As a first-order Dragon-lattice tower function, r 2 As a second-order Dragon's tower function, r 3 As a third-order Dragon-lattice tower function, r 4 As a fourth-order Dragon-Gregory tower function, epsilon start 、ε final Respectively an initial motion adjustment model, an end motion adjustment model, a vehicle form vector set, an O obstacle form vector total set, n represents an intersection, and +.>Is empty, τ is an anti-collision factor, τ D To be greater than the collision threshold of 1, the practitioner can set himself, this embodiment is set to 2.
In order to improve the automatic parking efficiency of the vehicle, the parking time is minimized to be used as an initial automatic parking model, and the expression of the initial automatic parking model is as follows:
,
wherein F is an initial automatic parking model, and t is parking time.
And obtaining an initial parking route according to the initial automatic parking model, the initial motion adjustment model and the terminal motion adjustment model of the vehicle. Calculating an initial motion adjustment model for acquiring the state of the vehicle before parking and a final motion adjustment model for acquiring the state of the vehicle after parking through the vehicle motion model, wherein the initial motion adjustment model and the final motion adjustment model of the vehicle are respectively marked as epsilon start 、ε final . According to the initial motion model of the vehicle and the final motion model of the vehicle, combining a limiting module and an initial automatic parking model, acquiring an initial parking route of automatic parking of the vehicle by adopting a path planning algorithm, and further acquiring initial parking states of the vehicle at all time points according to the initial parking route, the motion model epsilon of the vehicle and all divided time points, wherein the initial parking track epsilon is obtained by the collection of the initial parking states at all time points initial It is necessary to explainThe process of obtaining the initial state of the vehicle parking at each time point according to the initial parking route and the vehicle motion model is known in the prior art.
Finally, in order to prevent the problems of local infeasibility, local optimum and the like when the optimal parking route is selected, an initial automatic parking model is adjusted, the parking time is ensured to be minimized, and meanwhile, the problem of local optimum in the process of searching the parking route is prevented, so that the globally optimal parking route is obtained. Obtaining an automatic parking model according to the initial automatic parking model and the parking time, wherein the automatic parking model comprises the following specific steps:
，
wherein ,for an automatic parking model, min is operated by taking the minimum value, t is the parking time, N is the parking time and is divided into N sections, epsilon k Model epsilon is adapted to the vehicle movement at parking time k initial,k The method comprises the steps that a model is adjusted for vehicle motion of a parking time point k corresponding to an initial parking track, wherein the I is Euclidean distance sign, and the I is +.>In order to set the weight factor as small as possible, the operator can set the value of the weight factor to be 0.1 by himself or herself, so as to prevent the search result in the path planning process from being influenced by the excessive weight.
The automatic parking model can be obtained according to analysis of data acquired by each sensor and analysis of obstacle characteristics acquired by combining vision, and can set parking navigation of the vehicle.
Step S003, an automatic parking navigation instruction transmitting module.
The automatic parking navigation instruction transmission module aims at transmitting an automatic parking instruction to a vehicle according to an automatic parking model, and navigating the vehicle to execute automatic parking.
After the automatic parking model in the automatic parking process of the vehicle is acquired, in order to realize automatic parking of the vehicle and acquire an automatic parking route of the vehicle, the embodiment further optimizes the automatic parking route of the vehicle by combining a path planning algorithm to acquire the automatic parking route of the vehicle. It should be noted that the path planning algorithm and the calculation process thereof are known techniques in the prior art, and an operator may select the path planning algorithm by himself, in this embodiment, select an a-th algorithm to calculate an optimal solution of the automatic parking model, and the route corresponding to the minimum automatic parking model is the automatic parking route of the vehicle. The automatic parking navigation instruction transmission module transmits an automatic parking route of the vehicle to the vehicle, and performs automatic parking navigation on the vehicle so as to ensure that the vehicle performs automatic parking.
In summary, the embodiment of the application obtains the vehicle motion adjustment model in the vehicle parking state through the vehicle motion model, so that the obtained vehicle motion state better accords with the actual parking situation, and the vehicle parking precision is improved. The anti-collision module is obtained by combining the vehicle form vector set and the surrounding obstacle form vector set, so that the problem of collision in the vehicle parking process is solved, meanwhile, in order to improve the anti-collision effect in the vehicle parking process, anti-collision factors are constructed according to the actual condition of the vehicle form, and the sudden problem in the actual vehicle parking process can be effectively solved;
according to the embodiment of the application, the automatic parking model of the vehicle is controlled by constructing the vehicle parking limiting module, and the problem that the parking route is difficult to set in the automatic parking process of the vehicle is solved by combining the vehicle parking limiting module and the automatic parking model; finally, according to the automatic parking navigation instruction transmission module, the navigation of the vehicle in the parking process can be realized, and the automatic parking of the vehicle is ensured. The parking device has the beneficial effects of high parking precision, good anti-collision effect and the like.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.

Claims (10)

1. An automatic parking system based on multiple sensors and visual interactions, the system comprising:
the data acquisition module is used for acquiring vehicle motion information according to various sensors and acquiring surrounding environment images of vehicles in the parking lot;
the automatic parking system data analysis module is used for obtaining a vehicle motion adjustment model during parking according to the vehicle motion information; according to the vehicle motion adjustment model, a vehicle motion adjustment model at each parking time point is obtained by combining a Dragon lattice tower algorithm; obtaining a vehicle form vector set and a surrounding obstacle form vector total set according to the outlines of the vehicle and the obstacle; obtaining an anti-collision module according to the vehicle form vector set and the surrounding obstacle form vector total set; obtaining an anti-collision factor according to the width of the vehicle and the width of the anti-collision frame; obtaining a vehicle parking limiting module according to the vehicle motion adjusting model, the anti-collision module and the anti-collision factor; constructing an initial automatic parking model according to the parking time and the vehicle parking limiting module, and obtaining an automatic parking model according to the initial automatic parking model and the parking time;
and the automatic parking navigation instruction transmission module is used for obtaining an automatic parking route of the vehicle according to the automatic parking model and executing automatic parking.
2. The multi-sensor and visual interaction-based automatic parking system according to claim 1, wherein the collecting vehicle motion information according to the plurality of sensors specifically comprises: the vehicle is provided with a speed sensor, an acceleration sensor and a vehicle-mounted gyroscope, the speed, the acceleration and the course angle of the vehicle are collected, and the vehicle motion information comprises the barycenter coordinates of the vehicle, the course angle of the vehicle, the speed of the vehicle, the acceleration of the vehicle and the steering angle of the front wheel of the vehicle.
3. The automatic parking system based on multiple sensors and visual interaction according to claim 1, wherein the vehicle motion adjustment model when parking is obtained according to the vehicle motion information, comprising the specific steps of:
，
wherein epsilon is a vehicle motion model, x and y are vehicle centroid coordinates,is course angle, v is vehicle speed, delta represents vehicle acceleration, a is acceleration value, l f 、l r Respectively a front suspension length, a rear suspension length and delta f Is the front wheel steering angle.
4. The automatic parking system based on multiple sensors and visual interaction according to claim 1, wherein the vehicle motion adjustment model at each parking time point is obtained by combining a lagrangian algorithm according to the vehicle motion adjustment model, specifically: discretizing the parking time, equally dividing the parking time into N sections to obtain N+1 parking time points, wherein the parking time dividing period is as followsT is parking time, and the vehicle motion adjustment model expression of each parking time point is as follows:
，
in the formula ,εk+1 Model epsilon is adjusted for the vehicle movement at parking time k+1 k Adjusting a model for the movement of the vehicle at a parking time point k, wherein T is a parking time dividing period r 1 Is a first-order Dragon lattice tower function, and the expression is r 1 =f(ε k ,u k), wherein ,uk For each set of variables r in the vehicle motion model at parking time k 2 Is a second-order Dragon lattice tower function, and the expression is，r 3 Is a third-order Dragon lattice tower function, and the expression is +.>，r 4 Is a fourth-order Dragon lattice tower function, and the expression is +.>。
5. The multi-sensor and visual interaction-based automatic parking system according to claim 1, wherein the obtaining a vehicle morphology vector set and a surrounding obstacle morphology vector total set from the contours of the vehicle and the obstacle comprises the steps of:
acquiring a vehicle form vector set according to four vertexes of a vehicle, wherein the expression is as follows:
,
wherein A is a vehicle shape vector set,represents a directed line segment pointing from vehicle vertex A1 to vehicle vertex A2,represents a directed line segment pointing from vehicle vertex A2 to vehicle vertex A3,/and>represents a directed line segment pointing from vehicle vertex A3 to vehicle vertex A4,/and>represents a directed line segment pointing from vertex A4 to vertex A1;
obtaining a minimum circumscribed rectangle of an obstacle, and obtaining a morphological vector set of the obstacle Os, wherein the expression is as follows:
,
in the formula ,is the morphological vector set of obstacle Os, < ->Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 1 Minimum circumscribed rectangle vertex Os of directional obstacle Os 2 Directed line segment of (2), is>Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 2 Minimum circumscribed rectangle vertex Os of directional obstacle Os 3 Directed line segment of (2), is>Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 3 Minimum circumscribed rectangle vertex Os of directional obstacle Os 4 Directed line segment of (2), is>Represents the minimum circumscribed rectangle vertex Os from the obstacle Os 4 Minimum circumscribed rectangle vertex Os of directional obstacle Os 1 Is a directed line segment of (2);
the form vector set of all the obstacles is used for obtaining an obstacle form vector total set, and the expression is as follows:
,
wherein s is the total number of obstacles around the vehicle, O is the total set of obstacle form vectors,is the morphological vector set of obstacle O1, < ->Is the morphological vector set of obstacle O2, < ->Is a morphological vector set of the obstacle Os.
6. The multi-sensor and visual interaction-based automatic parking system according to claim 1, wherein the anti-collision module is obtained from a vehicle morphology vector set and a surrounding obstacle morphology vector total set, specifically:
,
where n represents the intersection set,and (3) a vehicle form vector set A and an obstacle form vector total set O.
7. The multi-sensor and visual interaction-based automatic parking system according to claim 1, wherein the anti-collision factor is obtained according to a vehicle width and an anti-collision frame width, specifically: an anti-collision frame is built by taking the center of a vehicle as the center, the anti-collision frame is consistent with the center of the vehicle, the length of the anti-collision frame is identical to the length of the vehicle, the width of the anti-collision frame is w+2d, d is respectively added on two sides of the width of the vehicle, the width of the anti-collision frame is obtained, and an expression of an anti-collision factor is as follows:
，
where τ is an anti-collision factor, w is a vehicle width, and d is an increase in the vehicle width.
8. The multi-sensor and visual interaction based automatic parking system of claim 1, wherein the deriving vehicle parking restriction module based on the vehicle motion adjustment model, the anti-collision module, and the anti-collision factor comprises:
，
wherein V vehicle speed, V min 、V max Respectively minimum and maximum values of vehicle speed when parking, a is vehicle acceleration, a min 、a max Respectively minimum, maximum and delta of vehicle acceleration during parking f For the steering angle of the front wheels,is the minimum value, the maximum value and epsilon of the steering angle of the front wheel k+1 、ε k The vehicle motion adjustment models respectively refer to a parking time point k+1 and a parking time point k, T is a parking time dividing period, and r is a parking time dividing period 1 As a first-order Dragon-lattice tower function, r 2 As a second-order Dragon's tower function, r 3 As a third-order Dragon-lattice tower function, r 4 As a fourth-order Dragon-Gregory tower function, epsilon start 、ε final Respectively an initial motion adjustment model, an end motion adjustment model, a vehicle form vector set, an O obstacle form vector total set, n represents an intersection, and +.>Is empty, τ is an anti-collision factor, τ D An anti-collision threshold greater than 1.
9. The multi-sensor and visual interaction-based automatic parking system according to claim 1, wherein the automatic parking model is obtained according to an initial automatic parking model and a parking time, and the method specifically comprises the following steps:
,
wherein ,for automatic parking models->Is a weight factor, min { } is operated by taking the minimum value, t is parking time, N is the parking time and is divided into N sections and epsilon k Model epsilon is adapted to the vehicle movement at parking time k initial,k And (3) adjusting a model for the vehicle motion of a parking time point k corresponding to the initial parking track, wherein the I is the Euclidean distance sign.
10. The multi-sensor and visual interaction-based automatic parking system of claim 1, wherein the deriving the vehicle automatic parking route from the automatic parking model comprises:
and selecting an algorithm A to calculate the optimal solution of the automatic parking model, wherein the corresponding route when the automatic parking model is minimum is the automatic parking route of the vehicle.
CN202311267351.4A 2023-09-28 2023-09-28 Automatic parking system based on multiple sensors and visual interaction Active CN116985785B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311267351.4A CN116985785B (en) 2023-09-28 2023-09-28 Automatic parking system based on multiple sensors and visual interaction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311267351.4A CN116985785B (en) 2023-09-28 2023-09-28 Automatic parking system based on multiple sensors and visual interaction

Publications (2)

Publication Number Publication Date
CN116985785A true CN116985785A (en) 2023-11-03
CN116985785B CN116985785B (en) 2023-12-12

Family

ID=88527010

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311267351.4A Active CN116985785B (en) 2023-09-28 2023-09-28 Automatic parking system based on multiple sensors and visual interaction

Country Status (1)

Country Link
CN (1) CN116985785B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108121205A (en) * 2017-12-13 2018-06-05 深圳市航盛电子股份有限公司 A kind of paths planning method, system and medium for a variety of scenes of parking
CN113147739A (en) * 2021-03-08 2021-07-23 北京科技大学 Heuristic automatic parking method and device for unmanned vehicle
WO2021184378A1 (en) * 2020-03-20 2021-09-23 Baidu.Com Times Technology (Beijing) Co., Ltd. A method of parking an autonomous driving vehicle for autonomous charging
CN113635891A (en) * 2021-08-02 2021-11-12 北京科技大学 Integrated parallel parking trajectory planning and tracking control method and system
CN113830079A (en) * 2021-10-19 2021-12-24 同济大学 Online planning method and system for continuous curvature parking path with any initial pose
CN114987449A (en) * 2022-05-31 2022-09-02 重庆长安汽车股份有限公司 Automatic parking method, device, electronic equipment and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108121205A (en) * 2017-12-13 2018-06-05 深圳市航盛电子股份有限公司 A kind of paths planning method, system and medium for a variety of scenes of parking
WO2021184378A1 (en) * 2020-03-20 2021-09-23 Baidu.Com Times Technology (Beijing) Co., Ltd. A method of parking an autonomous driving vehicle for autonomous charging
CN113147739A (en) * 2021-03-08 2021-07-23 北京科技大学 Heuristic automatic parking method and device for unmanned vehicle
CN113635891A (en) * 2021-08-02 2021-11-12 北京科技大学 Integrated parallel parking trajectory planning and tracking control method and system
CN113830079A (en) * 2021-10-19 2021-12-24 同济大学 Online planning method and system for continuous curvature parking path with any initial pose
CN114987449A (en) * 2022-05-31 2022-09-02 重庆长安汽车股份有限公司 Automatic parking method, device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN116985785B (en) 2023-12-12

Similar Documents

Publication Publication Date Title
US11126179B2 (en) Motion prediction based on appearance
Wang et al. Automatic parking of vehicles: A review of literatures
US11635764B2 (en) Motion prediction for autonomous devices
US11225247B2 (en) Collision prediction and avoidance for vehicles
US11001256B2 (en) Collision prediction and avoidance for vehicles
JP7411653B2 (en) Systems, methods and computer programs for trajectory generation
US11774975B2 (en) Collision zone detection for vehicles
JP2021524410A (en) Determining the drive envelope
US11163304B2 (en) Trajectory determination device
JP2015506310A (en) Vehicle control based on cognitive uncertainty
Shimchik et al. Golf cart prototype development and navigation simulation using ROS and Gazebo
US11772636B2 (en) Parking assist apparatus and a method of controlling the parking assist apparatus
JP7422747B2 (en) Image scanline timestamp
US20220315037A1 (en) Lane changing based only on local information
WO2021033632A1 (en) Vehicle control method and vehicle control device
CN111679667B (en) Path and vehicle speed collaborative planning method for unmanned racing vehicle
CN111208814A (en) Memory-based optimal motion planning for autonomous vehicles using dynamic models
WO2023076934A1 (en) Estimating vehicle velocity
US11794756B2 (en) Estimating vehicle velocity based on variables associated with wheels
CN116985785B (en) Automatic parking system based on multiple sensors and visual interaction
JP6668915B2 (en) Automatic operation control system for moving objects
WO2023009794A1 (en) Three-dimensional object detection based on image data
JP2023508043A (en) pedestrians with objects
CN115303258A (en) Automatic vertical parking trajectory planning method
JP2024036933A (en) Mobile object control system, its control method, program and recording medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant