CN112492522B - Control method for autonomous parking of vehicle - Google Patents
Control method for autonomous parking of vehicle Download PDFInfo
- Publication number
- CN112492522B CN112492522B CN202011244778.9A CN202011244778A CN112492522B CN 112492522 B CN112492522 B CN 112492522B CN 202011244778 A CN202011244778 A CN 202011244778A CN 112492522 B CN112492522 B CN 112492522B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parking
- mobile terminal
- terminal app
- cloud server
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004364 calculation method Methods 0.000 claims abstract description 41
- 230000000007 visual effect Effects 0.000 claims abstract description 14
- 239000000284 extract Substances 0.000 claims abstract description 4
- 230000003068 static effect Effects 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012800 visualization Methods 0.000 description 4
- 241001465754 Metazoa Species 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007794 visualization technique Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/024—Guidance services
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/06—Automatic manoeuvring for parking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Mechanical Engineering (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Transportation (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a control method for autonomous parking of a vehicle, which comprises the following steps: the mobile terminal APP sends a command for reading the vehicle position and the vehicle surrounding environment information to the cloud server; the vehicle computing unit forwards the acquired vehicle position and the vehicle surrounding environment information to a mobile terminal APP through a cloud server, and meanwhile, the cloud server sends the current parking lot three-dimensional scene; the data acquisition unit acquires images around the vehicle and transmits the images to the vehicle calculation unit, and the vehicle calculation unit classifies and identifies objects in the images to obtain object classification results and identifies and acquires the positions of the objects relative to the vehicle; the data acquisition unit acquires the current position and the orientation information of the vehicle body and then sends the information; the mobile terminal APP receives the object classification result, extracts a corresponding object model from the visual system model library, and displays the corresponding object model in the current parking lot three-dimensional scene; the invention displays the vehicle and the surrounding environment on the mobile terminal APP in real time, realizes autonomous parking, and does not limit the getting-off position of a user.
Description
Technical Field
The invention relates to a control method for autonomous parking of a vehicle, and belongs to the technical field of automobile control.
Background
At present, parking is divided into automatic parking and autonomous parking, wherein the automatic parking is realized by parking a vehicle into a parking space beside the parking space, a certain distance range is increased on the basis of the automatic parking, and automatic driving in the last kilometer is realized. The autonomous parking mainly utilizes sensors distributed around the vehicle to acquire information such as surrounding environment, obstacles and the like, and the whole process of autonomous parking is completed. The method comprises the following steps that by means of sensing and presenting of the surrounding environment of the vehicle and commands output by a mobile phone APP, the vehicle automatically controls to drive to a vehicle owner, and information of the vehicle and the surrounding environment are presented in the APP in real time.
However, because the indoor and basement GPS signals are weak and cannot be located by the GPS, most of the existing parking functions on the market can only complete free parking, rather than autonomous parking, that is, the vehicle owner must drive the vehicle to the vicinity of the parking space, and when the vehicle identifies the parking space, the vehicle is allowed to park in the garage by itself. That is to say, vehicles with parking function in the current market are all automatically parked, but not autonomously parked, the vehicle owner still needs to drive the vehicle to the side of the parking space, and after the vehicle sensor identifies the parking space, the vehicle finishes the process of entering the garage, for example, tesla requires that the vehicle owner is within 12 meters of the vehicle, and the vehicle can automatically finish entering and exiting the garage. If the autonomous parking is really realized in a place with weak GPS signals, a local map needs to be established, and the positioning problem when the GPS signals do not exist is solved.
In addition, only the button on two-dimensional UI layer triggers when the APP interface of the same type in market, and call the in-process, can't look over the situation of going of vehicle, all ring edge border information, vehicle self situation, when the accident happens, can't in time handle, so the function of parking on the current market, all recommend the user to use in the position that can see the vehicle, the position of getting off to the car owner has so both limited, the user still need be looking at the vehicle all the time, in order to ensure that the vehicle travels safely, so do not really bring the user convenience, the experience of reassurance.
Therefore, the prior art suggests that the vehicle owner uses the function in the sight line range when the vehicle is in the sight line range, so as to give the vehicle owner a sense of safety and prevent accidents from happening, if the vehicle owner leaves the sight line, the periphery and the running state of the vehicle cannot be observed, so that a user has no sense of safety, and if accidents happen in the running process of the vehicle, the vehicle owner cannot be timely treated, so that unnecessary loss is caused.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a control method for autonomous parking of a vehicle, solves the problem of positioning the vehicle in a scene without GPS signals in a laser radar and uwb mode, establishes a three-dimensional scene map of a parking lot in advance, and simultaneously acquires information of surrounding environment through a data acquisition unit in the automatic parking process of the vehicle so as to avoid collision and ensure that the vehicle safely and reliably parks in a parking space, thereby truly realizing time-saving, worry-saving and labor-saving autonomous parking of a vehicle owner, and simultaneously enabling the vehicle owner to observe the surrounding environment and the self state of the vehicle by using a three-dimensional visualization technology in a mobile terminal APP at any time so as to realize that the vehicle automatically finishes the parking process.
The invention specifically adopts the following technical scheme to solve the technical problems:
a control method for autonomous parking of a vehicle is based on a mobile terminal APP, a cloud server, a vehicle calculation unit and a data acquisition unit, and comprises the following steps:
step 1, a mobile terminal APP sends a command for reading a vehicle position and vehicle surrounding environment information to a cloud server, and the cloud server receives the command and forwards the command to a vehicle computing unit; the vehicle computing unit forwards the acquired vehicle position and the vehicle surrounding environment information to the mobile terminal APP through the cloud server, and meanwhile, the cloud server sends the current parking lot three-dimensional scene to the mobile terminal APP;
step 2, the data acquisition unit acquires images around the vehicle and transmits the images to the vehicle calculation unit, and the vehicle calculation unit performs classification and identification on objects in the images around the vehicle to obtain object classification results and identifies and obtains the position of the object relative to the vehicle; the vehicle calculation unit forwards the object classification result and the position of the object relative to the vehicle to the mobile terminal APP through the cloud server; meanwhile, the data acquisition unit acquires the current position and the orientation information of the vehicle body and then sends the information to the vehicle calculation unit, and the vehicle calculation unit forwards the information to the mobile terminal APP through the cloud server;
step 4, the mobile terminal APP selects a parking place in the current parking lot three-dimensional scene, and the selected parking place position information is transmitted to the vehicle computing unit through the cloud server in a corresponding command mode; after receiving the command, the vehicle calculation unit plans a path of the parking space position according to the parking space position information, the current position of the vehicle and the orientation information of the vehicle body, and forwards the planned path to the mobile terminal APP through the cloud server for three-dimensional display;
step 5, the vehicle calculation unit carries out tracking control according to the planned path, starts to move the vehicle to the selected position with the parking space available, and simultaneously sends real-time data in the movement of the vehicle to the mobile terminal APP through the cloud server; and the mobile terminal APP updates and determines the real-time position of the vehicle in the current parking lot three-dimensional scene according to the vehicle real-time data and carries out three-dimensional display.
Further, as a preferred technical solution of the present invention: and in the step 2, the data acquisition unit acquires images around the vehicle by adopting a camera or a laser radar, a millimeter wave radar and an ultrasonic radar.
Further, as a preferred technical solution of the present invention: the vehicle computing unit in the step 2 further comprises the step of carrying out deep learning on the object classification in advance by using the wavelet neural network model.
Further, as a preferable technical solution of the present invention: and 3, when the mobile terminal APP does not have the model corresponding to the object from the visual system model library, creating a new object model record according to the current object information and storing the new object model record into the visual system model library.
Further, as a preferred technical solution of the present invention, the method further includes:
and 6, when the vehicle is moved to the selected position capable of parking, the data acquisition unit identifies the position of the parking space in real time, whether an error exists between the position of the real-time parking space and the selected position capable of parking is judged, and when the error exists, the vehicle calculation unit corrects the selected position capable of parking according to a distance measurement algorithm and carries out secondary path planning.
Further, as a preferred technical solution of the present invention, the method further includes:
and 6, when the vehicle is moved to the selected position of the parking place, the data acquisition unit identifies the position of the parking place in real time, judges whether other vehicles exist in the position of the parking place, and sends feedback of reselecting the parking place to the mobile terminal APP through the vehicle calculation unit via the cloud server when judging that other vehicles exist.
Further, as a preferred technical solution of the present invention, the method further comprises:
and 7, when the vehicle is moved to the selected position capable of parking, the data acquisition unit acquires an image of the surrounding environment of the vehicle in real time, judges whether an object appears on the planned path according to the image, and controls the vehicle to automatically avoid when the object appears on the planned path.
Further, as a preferred technical solution of the present invention, in the step 7, the data acquisition unit judges whether the object in the image is a static object or a dynamic object according to the image, and when the object is judged to be the dynamic object, the vehicle calculation unit controls the vehicle to take a braking avoidance measure, otherwise, when the object is judged to be the static object, the vehicle calculation unit controls the vehicle to take a detour measure.
By adopting the technical scheme, the invention can produce the following technical effects:
according to the method, the problem of positioning of the vehicle in a scene without GPS signals can be solved through the laser radar and the uwb, a three-dimensional scene map of a parking lot is built in advance, meanwhile, in the automatic parking process of the vehicle, the surrounding environment information is collected through the data collection unit, collision is avoided, the vehicle is guaranteed to safely and reliably park in the parking space, time-saving, worry-saving and labor-saving autonomous parking of a vehicle owner is really achieved, meanwhile, the vehicle owner can observe the surrounding environment and the self state of the vehicle through 3D imaging in the mobile terminal APP at any time, the safety feeling is brought to the vehicle owner, the use of the vehicle owner is facilitated, and unnecessary accidents and property loss are avoided.
In addition, the vehicle does not limit the getting-off position of the user in the autonomous parking process, so that the user can still be ensured to check the self and the surrounding conditions of the vehicle in real time through the mobile terminal APP even if the vehicle is not in the sight range of the user, the vehicle does not need to be driven to the side of the parking space by self, and the safety and the convenience are brought to the user.
Drawings
Fig. 1 is a schematic diagram of a control method for autonomous parking of a vehicle according to the present invention.
Fig. 2 is a schematic diagram showing a three-dimensional scene of a parking lot for selecting autonomous parking for a vehicle by a mobile terminal APP.
Fig. 3 is a schematic diagram showing a three-dimensional scene of a parking lot where a mobile terminal APP selects a parking space for a vehicle according to the present invention.
Fig. 4 is a schematic diagram illustrating path planning by the mobile terminal APP according to the present invention.
FIG. 5 is a logic diagram of determining a real-time parking space position according to the present invention.
Fig. 6 is a logic diagram of avoidance in the planned path of vehicle travel according to the present invention.
Detailed Description
The following describes embodiments of the present invention with reference to the drawings.
As shown in fig. 1, the present invention relates to a control method for autonomous parking of a vehicle, the method is based on a mobile terminal APP, a cloud server, a vehicle computing unit, and a data acquisition unit, wherein the mobile terminal APP and the vehicle computing unit are respectively connected to the cloud server, and the data acquisition unit is connected to the vehicle computing unit in a data communication manner, and the method specifically includes the following steps:
step 1, firstly, establishing connection between a mobile terminal APP and a cloud server and a vehicle computing unit, so that the mobile terminal APP can acquire relevant information of a vehicle and the surrounding environment. Then, the mobile terminal APP sends a command for reading the vehicle position and the vehicle surrounding environment information to the cloud server, and the cloud server receives the command and forwards the command to the vehicle computing unit; the vehicle computing unit forwards the acquired vehicle position and the vehicle surrounding environment information to the mobile terminal APP through the cloud server, and meanwhile, the cloud server sends the current parking lot three-dimensional scene to the mobile terminal APP; the method comprises the following specific steps:
step 1.1: and (3) establishing socket connection between the vehicle computing unit and the cloud server by using but not limited to a socket communication mode.
Step 1.2: when the user starts the mobile terminal APP, the mobile terminal APP is a three-dimensional visual APP, the mobile terminal APP is connected with the socket of the cloud server, and a command for reading the vehicle and the surrounding environment of the vehicle is sent to the cloud server.
Step 1.3: and after receiving the command from the mobile terminal APP, the cloud server forwards the command to the vehicle computing unit.
Step 1.4: and after receiving the command, the vehicle computing unit sends the acquired vehicle position and the vehicle surrounding environment information to the mobile terminal APP through the cloud server.
Step 1.5: meanwhile, the cloud server sends the current parking lot three-dimensional scene I to the mobile terminal APP, and the three-dimensional scene manufacturing mode comprises the following modes without limitation: 1) a three-dimensional scene provided by a map manufacturer; 2) scanning a point cloud model by using a laser radar; 3) and (3) utilizing modeling software such as 3dmax, maya and the like to make a model, obtaining a scene model of the current place, and making a corresponding three-dimensional display in a three-dimensional visual APP.
Step 2, the data acquisition unit acquires images around the vehicle and transmits the images to the vehicle calculation unit, and the vehicle calculation unit performs classification and identification on objects in the images around the vehicle to obtain object classification results and identifies and obtains the position of the object relative to the vehicle; the vehicle calculation unit forwards the object classification result and the position of the object relative to the vehicle to the mobile terminal APP through the cloud server; meanwhile, the data acquisition unit acquires the current position and the orientation information of the vehicle body and then sends the information to the vehicle calculation unit, and the vehicle calculation unit forwards the information to the mobile terminal APP through the cloud server; the method comprises the following steps:
step 2.1: the data acquisition unit is deployed around the vehicle, including but not limited to a camera, a laser radar, a millimeter wave radar and an ultrasonic radar.
Step 2.2: the camera through the vehicle whole body carries out image acquisition, and millimeter wave radar, ultrasonic radar carry out the point cloud data acquisition.
Step 2.3: the vehicle calculation unit carries out deep learning on object classification in advance by utilizing the wavelet neural network model, carries out image recognition on the image collected by the camera through the deep learning in advance, identifies motor vehicles, non-motor vehicles, pedestrians, animals and the like in the image, and calculates the information of orientation, length, width, height and the like of the object.
Step 2.4: the vehicle calculating unit can also measure and recognize the distance to the object through binocular ranging, correct through data collected by the radar to obtain a distance value with a small error, and obtain the relative position of the recognized object through the distance and the angle between the recognized object and the vehicle by taking the vehicle as an origin.
Step 2.5: the vehicle computing unit acquires information such as the current position and the vehicle body orientation of the vehicle through a UWB terminal, a laser radar and an IMU in the data acquisition unit.
Step 2.6: the vehicle computing unit sends the obtained various information to the mobile terminal APP through the cloud server.
Step 2.7: and the mobile terminal APP loads the entering scene after receiving the object classification result, the position of the object relative to the vehicle, the current position of the vehicle and the current parking lot three-dimensional scene returned by the vehicle calculation unit.
step 3.1: and (4) according to the object classification result obtained in the step (2.3), providing a corresponding object model from the visual system model library. When no object corresponding model exists in the visual system model base, the mobile terminal APP establishes a new object model record according to the current object information and stores the new object model record in the visual system model base, namely if the mobile terminal APP does not exist in the object model, the mobile terminal APP is replaced by a square box, the size of the square box is correspondingly adjusted according to the obtained length, width and height of the object, and meanwhile, the new object model is established and uploaded to a cloud server for recording and storing the object which cannot correspond to the model base, so that the visual system model base is supplemented and updated; placing the object model at a corresponding position in the three-dimensional scene of the parking lot of the three-dimensional visual APP according to the relative position of the object obtained in the step 2.4;
step 3.2: and (5) obtaining information such as the current position, the body orientation and the like of the vehicle according to the step 2.5, and correspondingly presenting the information in real time in a three-dimensional visual parking lot three-dimensional scene.
Step 4, the mobile terminal APP selects a parking place in the current parking lot three-dimensional scene, and transmits the selected parking place position information to the vehicle computing unit through the cloud server; after receiving the command, the vehicle computing unit plans a path of the parking space position according to the parking space position information, the current position of the vehicle and the orientation information of the vehicle body, and forwards the planned path to the mobile terminal APP through the cloud server for three-dimensional display; the method comprises the following steps:
step 4.1: a user initiates a free parking command to a vehicle by using voice service or a button clicking mode, and the mobile terminal APP obtains the intention of the user.
And 4.2: the mobile terminal APP obtains a position of a parking space according to the selection of the parking space of the user as shown in FIG. 3, and sets the position as a terminal point.
Step 4.3: and the mobile terminal APP sends the autonomous parking command and the parking position information of the terminal point to the vehicle calculation unit by using the connection established with the cloud server and the vehicle calculation unit in the step 1.
Step 4.4: and the vehicle calculation unit takes the current position of the vehicle as a starting point, takes the position of the parking space obtained in the step 4.3 as an end point, performs path planning through an algorithm, and sends a path planning result to the mobile terminal APP through the cloud service terminal.
Step 4.5: the mobile terminal APP obtains the planned path, displays the path in the three-dimensional scene of the parking lot, and displays the whole path, the starting point and the end point in the small map.
Step 5, the vehicle calculation unit carries out tracking control according to the planned path, starts to move the vehicle to the selected position with the parking space available, and simultaneously sends real-time data in the movement of the vehicle to the mobile terminal APP through the cloud server; the method comprises the following steps that a mobile terminal APP updates and determines the real-time position of a vehicle in a current parking lot three-dimensional scene according to vehicle real-time data and carries out three-dimensional display, and as shown in figure 4, the method comprises the following steps:
step 5.1: and the vehicle calculation unit carries out path tracking control according to the path planned in the step 4.4, so that the vehicle runs according to the planned path.
And step 5.2: and (2) connecting the vehicle computing unit, the cloud server and the mobile terminal APP established in the step (1), and packaging and sending real-time data of the vehicle such as position, gear, speed, remaining mileage and other information to the mobile terminal APP by the vehicle computing unit.
Step 5.3: the mobile terminal APP displays the vehicle in real time in the current parking lot three-dimensional scene according to the acquired vehicle real-time data information; meanwhile, information such as gears, speeds, remaining mileage and the like of the vehicle is presented on a UI layer;
step 5.4: and in the running process of the vehicle, when the elements such as pedestrians, vehicles and the like in the surrounding environment of the vehicle are identified by using the camera in the data acquisition unit, three-dimensional presentation is carried out on the corresponding elements according to the step 3.1 and the step 3.2.
And 6, when the vehicle is moved to the selected position capable of parking, the data acquisition unit identifies the position of the parking space in real time. Can judge real-time parking stall position and the parking stall position of selection whether have the error, when judging for there being the error, but vehicle computing unit corrects the parking stall position of selection and carries out the secondary path planning according to range finding algorithm, or when removing the vehicle to the parking stall position of selection, data acquisition unit discerns the parking stall position in real time, judge whether there are other vehicles in the parking stall position, when judging for having other vehicles, send the feedback of reelecting the parking stall to removing end APP through vehicle computing unit through high in the clouds server. As shown in fig. 5, the method comprises the following steps:
step 6.1: and identifying the parking space line and other vehicles according to a camera in the data acquisition unit, if no other vehicle exists in the parking space or the position error of the parking space is centimeter level, stopping the vehicle into the parking space according to the path planned in the step 4.4, and ending the parking process.
Step 6.2: according to the camera in the data acquisition unit, the parking space line and other vehicles are identified, if no other vehicle exists in the parking space but the position of the parking space has a large error, the vehicle calculation unit corrects the position of the parking space according to the distance measurement algorithm, secondarily plans a path according to the corrected position of the parking space, and controls the vehicle to park in the parking space according to the secondarily planned path.
Step 6.3: according to a camera in the data acquisition unit, identifying a parking space line and other vehicles, and if other vehicles exist in the parking space, sending feedback of reselecting the parking space to a mobile terminal APP by a vehicle calculation unit through a cloud server; mobile terminal APP
And changing the terminal point into an empty parking space closest to the current position according to the latest information of the parking spaces, and feeding back the empty parking space to the vehicle calculation unit by taking the new parking space as the terminal point to perform the previous steps again so that the vehicle can be safely parked in the parking space.
Step 6.4: and (2) connecting the vehicle computing unit, the cloud server and the mobile terminal APP established in the step (1), sending a call ending flow instruction to the mobile terminal APP by the vehicle computing unit, and correspondingly displaying the finish of autonomous parking by the mobile terminal APP.
And 7, when the vehicle is moved to the selected position capable of parking, the data acquisition unit acquires an image of the surrounding environment of the vehicle in real time, judges whether an object appears on the planned path according to the image, and controls the vehicle to automatically avoid when the object appears on the planned path. As shown in fig. 6, the method comprises the following steps:
step 7.1: in the vehicle calling process, the objects such as motor vehicles, non-motor vehicles, pedestrians and animals are identified according to the step 2.3, and the distance between the object and the vehicle is obtained according to the step 2.4.
Step 7.2: the vehicle computing unit judges whether the object is a static object or a dynamic object according to the vehicle surrounding environment image acquired by the camera in the data acquisition unit.
Step 7.3: when the dynamic object is or is about to be in the vehicle driving planned path and the distance between the dynamic object and the vehicle is less than or equal to 2m, the vehicle calculation unit actively takes a braking avoidance measure; when the static object is in the vehicle driving planned path, the vehicle actively takes a bypassing measure, and meanwhile risk prompt is conducted on the risk object in the mobile terminal APP.
Step 7.4: when the object leaves the planned driving path of the vehicle, the vehicle continues the parking process, and the APP risk at the mobile terminal is eliminated.
Therefore, the method combines three-dimensional visualization, and presents the vehicle and the surrounding environment in the autonomous parking process of the vehicle on the mobile terminal APP in real time by using a perception technology, an algorithm technology and a three-dimensional visualization technology. The car owner gets off the back and lets the vehicle independently park through APP, can utilize three-dimensional visualization technique to observe the vehicle situation at any time in APP, does not do the restriction to the user position of getting off, even the vehicle is not in user's sight range, still can guarantee that the user looks over vehicle self and peripheral circumstances in real time through three-dimensional visualization APP, also need not to drive the vehicle by oneself to the parking stall by, brings user's sense of safety and convenience.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (8)
1. A control method for autonomous parking of vehicles is characterized by being based on a mobile terminal APP, a cloud server, a vehicle calculation unit and a data acquisition unit and comprising the following steps:
step 1, a mobile terminal APP sends a command for reading a vehicle position and vehicle surrounding environment information to a cloud server, and the cloud server receives the command and forwards the command to a vehicle computing unit; the vehicle computing unit forwards the acquired vehicle position and the vehicle surrounding environment information to the mobile terminal APP through the cloud server, and meanwhile, the cloud server sends the current parking lot three-dimensional scene to the mobile terminal APP;
step 2, the data acquisition unit acquires images around the vehicle and transmits the images to the vehicle calculation unit, and the vehicle calculation unit performs classification and identification on objects in the images around the vehicle to obtain object classification results and identifies and obtains the position of the object relative to the vehicle; the vehicle calculation unit forwards the object classification result and the position of the object relative to the vehicle to the mobile terminal APP through the cloud server; meanwhile, the data acquisition unit acquires the current position and the orientation information of the vehicle body and then sends the information to the vehicle calculation unit, and the vehicle calculation unit forwards the information to the mobile terminal APP through the cloud server;
step 3, the mobile terminal APP receives the object classification result, extracts an object corresponding model from the visual system model library, and displays the object and the vehicle in the current parking lot three-dimensional scene according to the extracted object corresponding model, the position of the object relative to the vehicle, the current position of the vehicle and the orientation information of the vehicle body;
step 4, the mobile terminal APP selects a parking place in the current parking lot three-dimensional scene, and transmits the selected parking place position information to the vehicle computing unit through the cloud server; after receiving the command, the vehicle computing unit plans a path of the parking space position according to the parking space position information, the current position of the vehicle and the orientation information of the vehicle body, and forwards the planned path to the mobile terminal APP through the cloud server for three-dimensional display;
step 5, the vehicle calculation unit carries out tracking control according to the planned path, starts to move the vehicle to the selected position with the parking space available, and simultaneously sends real-time data in the movement of the vehicle to the mobile terminal APP through the cloud server; and the mobile terminal APP updates and determines the real-time position of the vehicle in the current parking lot three-dimensional scene according to the vehicle real-time data and carries out three-dimensional display.
2. The control method for autonomous parking of a vehicle according to claim 1, characterized in that: and in the step 2, the data acquisition unit acquires images around the vehicle by adopting a camera or a laser radar, a millimeter wave radar and an ultrasonic radar.
3. The control method for autonomous parking of a vehicle according to claim 1, characterized in that: the vehicle computing unit in the step 2 further comprises the step of carrying out deep learning on the object classification in advance by using the wavelet neural network model.
4. The control method for autonomous parking of a vehicle according to claim 1, characterized in that: and 3, when the mobile terminal APP does not have the model corresponding to the object from the vision system model library, creating a new object model record according to the current object information and storing the new object model record into the vision system model library.
5. The control method for autonomous parking of a vehicle according to claim 1, characterized in that the method further comprises:
and 6, when the vehicle is moved to the selected position capable of parking, the data acquisition unit identifies the position of the parking space in real time, whether an error exists between the position of the real-time parking space and the selected position capable of parking is judged, and when the error exists, the vehicle calculation unit corrects the selected position capable of parking according to a distance measurement algorithm and carries out secondary path planning.
6. The control method for autonomous parking of a vehicle according to claim 1, characterized by further comprising:
and 6, when the vehicle is moved to the selected parking position, the data acquisition unit identifies the parking position in real time, judges whether other vehicles exist in the parking position, and sends the feedback of reselecting the parking position to the mobile terminal APP through the vehicle calculation unit via the cloud server when judging that other vehicles exist.
7. The control method for autonomous parking of a vehicle according to claim 1, characterized in that the method further comprises:
and 7, when the vehicle is moved to the selected position capable of parking, the data acquisition unit acquires an image of the surrounding environment of the vehicle in real time, judges whether an object appears on the planned path according to the image, and controls the vehicle to automatically avoid when the object appears on the planned path.
8. The control method for autonomous parking of a vehicle according to claim 7, characterized in that: and in the step 7, the data acquisition unit judges whether the object in the image is a static object or a dynamic object according to the image, when the object is judged to be the dynamic object, the vehicle calculation unit controls the vehicle to take a braking avoidance measure, otherwise, when the object is judged to be the static object, the vehicle calculation unit controls the vehicle to take a detour measure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011244778.9A CN112492522B (en) | 2020-11-10 | 2020-11-10 | Control method for autonomous parking of vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011244778.9A CN112492522B (en) | 2020-11-10 | 2020-11-10 | Control method for autonomous parking of vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112492522A CN112492522A (en) | 2021-03-12 |
| CN112492522B true CN112492522B (en) | 2022-09-23 |
Family
ID=74929340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011244778.9A Active CN112492522B (en) | 2020-11-10 | 2020-11-10 | Control method for autonomous parking of vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112492522B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113085900B (en) * | 2021-04-29 | 2022-11-04 | 的卢技术有限公司 | Method for calling vehicle to travel to user position |
| CN113747119A (en) * | 2021-07-30 | 2021-12-03 | 的卢技术有限公司 | Method and system for remotely checking vehicle surrounding environment |
| CN113823113A (en) * | 2021-09-09 | 2021-12-21 | 东风汽车集团股份有限公司 | Parking space data acquisition and remote upgrading method for full-automatic parking system |
| CN115376360A (en) * | 2022-08-10 | 2022-11-22 | 小米汽车科技有限公司 | Parking and information processing method, apparatus, device, medium, and program product |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517533A (en) * | 2019-09-29 | 2019-11-29 | 武汉中海庭数据技术有限公司 | A kind of autonomous parking method and system |
| CN110758243A (en) * | 2019-10-31 | 2020-02-07 | 的卢技术有限公司 | Method and system for displaying surrounding environment in vehicle driving process |
| CN111415523A (en) * | 2020-03-06 | 2020-07-14 | 北京智行者科技有限公司 | Autonomous passenger-riding-substituting parking method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20200057819A (en) * | 2018-11-13 | 2020-05-27 | 현대자동차주식회사 | Parking control system for autonomous vehicle |
-
2020
- 2020-11-10 CN CN202011244778.9A patent/CN112492522B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517533A (en) * | 2019-09-29 | 2019-11-29 | 武汉中海庭数据技术有限公司 | A kind of autonomous parking method and system |
| CN110758243A (en) * | 2019-10-31 | 2020-02-07 | 的卢技术有限公司 | Method and system for displaying surrounding environment in vehicle driving process |
| CN111415523A (en) * | 2020-03-06 | 2020-07-14 | 北京智行者科技有限公司 | Autonomous passenger-riding-substituting parking method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112492522A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112492522B (en) | Control method for autonomous parking of vehicle | |
| CN107757616B (en) | Using environmental information to assist image processing for autonomous vehicles | |
| CN104837705B (en) | Enable and disable automatic Pilot | |
| CN110576852B (en) | Automatic parking method and device and vehicle | |
| DE112018007091T5 (en) | VEHICLE CONTROL SYSTEM AND CONTROL PROCEDURE | |
| CN113085900B (en) | Method for calling vehicle to travel to user position | |
| US11104328B2 (en) | Parking control method and parking control device | |
| CN111183428A (en) | Identifying assigned passengers of an autonomous vehicle | |
| EP3407257A1 (en) | Method for generating a wide-area perception scene graph | |
| WO2020116195A1 (en) | Information processing device, information processing method, program, mobile body control device, and mobile body | |
| CN110293965A (en) | Method of parking and control device, mobile unit and computer-readable medium | |
| CN110789533A (en) | Data presentation method and terminal equipment | |
| CN113228135A (en) | Blind area image acquisition method and related terminal device | |
| CN111361549A (en) | Parking and recalling method and system adopting self-built map | |
| EP4134867A1 (en) | Identification method and identification device for object of interest of user | |
| CN114228491A (en) | Head-up display system and method with night vision enhanced virtual reality | |
| CN114842075B (en) | Data labeling method and device, storage medium and vehicle | |
| CN114585540A (en) | Display of a vehicle environment for moving a vehicle to a target position | |
| CN115100377B (en) | Map construction method, device, vehicle, readable storage medium and chip | |
| CN114954438A (en) | Vehicle running control method and device, vehicle, readable storage medium and chip | |
| CN116420096A (en) | Method and system for marking LIDAR point cloud data | |
| CN115042821A (en) | Vehicle control method, vehicle control device, vehicle and storage medium | |
| DE102022112349A1 (en) | SYSTEMS AND PROCEDURES FOR COMMUNICATION WITH VEHICLE OCCUPANTS WITH VISUAL AND HEARING IMPAIRMENTS | |
| CN116674557A (en) | Vehicle autonomous lane change dynamic programming method and device and domain controller | |
| CN113724525B (en) | Automatic passenger-replacing patrol type parking method and system based on big data platform and storage device |
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 |