CN110091342A - Vehicle condition detection method, device and detection robot - Google Patents
Vehicle condition detection method, device and detection robot Download PDFInfo
- Publication number
- CN110091342A CN110091342A CN201910417671.0A CN201910417671A CN110091342A CN 110091342 A CN110091342 A CN 110091342A CN 201910417671 A CN201910417671 A CN 201910417671A CN 110091342 A CN110091342 A CN 110091342A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- detected
- detection
- mechanical arm
- path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 247
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000012360 testing method Methods 0.000 claims description 32
- 239000013558 reference substance Substances 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 12
- 238000007689 inspection Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000003993 interaction Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000009434 installation Methods 0.000 description 4
- 239000003973 paint Substances 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 238000011895 specific detection Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000114727 Acetes chinensis Species 0.000 description 1
- 241000675108 Citrus tangerina Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001012 protector Effects 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60S—SERVICING, CLEANING, REPAIRING, SUPPORTING, LIFTING, OR MANOEUVRING OF VEHICLES, NOT OTHERWISE PROVIDED FOR
- B60S5/00—Servicing, maintaining, repairing, or refitting of vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
Abstract
The present invention provides a kind of vehicle condition detection method, device and detection robots；Wherein, this method is applied to the controller of detection robot；Detecting robot further includes movable fixture and mechanical arm；Mechanical arm is mounted on movable fixture；Detection device is installed on mechanical arm；Method includes: to receive vehicle condition detection instruction；Vehicle condition detection instruction includes the location information of vehicle to be detected；Acquire the image data of vehicle to be detected；According to location information and image data, the walking path of movable fixture and the path that walks of mechanical arm are determined；Control movable fixture is moved along walking path, and control mechanical arm is according to the path movement that walks, to acquire the vehicle condition detection data of vehicle to be detected by detection device.Vehicle condition detection in the shops that present invention may apply to environment is complicated and changeable, vehicle is various.
Description
Technical field
The present invention relates to technical field of vehicle detection, more particularly, to a kind of vehicle condition detection method, device and detection machine
People.
Background technique
In the related technology, it generallys use fixed detection workspace and carries out vehicle condition detection, and the safety barrier of profession is set,
Thus it is more suitable the environment such as workshop, workshop, it is higher to detection environmental requirement, and be usually only able to detect fixed a
Or number money vehicle, the vehicle of detection are limited, it is difficult to which vehicle condition detects in shops complicated and changeable suitable for environment, vehicle is various.
Summary of the invention
The purpose of the present invention is to provide a kind of vehicle condition detection method, device and detection robots, with multiple suitable for environment
Vehicle condition detects in miscellaneous shops changeable, vehicle is various.
To achieve the goals above, technical solution used in the embodiment of the present invention is as follows:
In a first aspect, this method is applied to detection robot the embodiment of the invention provides a kind of vehicle condition detection method
Controller；Detecting robot further includes movable fixture and mechanical arm；Mechanical arm is mounted on movable fixture；Pacify on mechanical arm
Equipped with detection device；Method includes: to receive vehicle condition detection instruction；Vehicle condition detection instruction includes the location information of vehicle to be detected；
Acquire the image data of vehicle to be detected；According to location information and image data, the walking path and machine of movable fixture are determined
The path that walks of tool arm；Control movable fixture is moved along walking path, and control mechanical arm is according to the path movement that walks, with logical
Cross the vehicle condition detection data that detection device acquires vehicle to be detected.
In some embodiments, before the step of image data of above-mentioned acquisition vehicle to be detected, the above method is also wrapped
It includes: determining the position reference point of vehicle to be detected according to location information；Control movable fixture is moved to from preset starting point
Position reference point.
In some embodiments, the map datum of current detection environment is previously stored in above controller；Position letter
Breath includes parking stall number or detection zone；The step of above-mentioned position reference point that vehicle to be detected is determined according to location information, comprising:
Determine that location information corresponds to the position reference point of parking stall from map datum；Alternatively, determining location information pair from map datum
Answer the regional scope of parking stall；The position for identifying reserved reference substance from regional scope by photographic device, according to reserved reference substance
Position determine position reference point.
In some embodiments, the step of image data of above-mentioned acquisition vehicle to be detected, comprising: in vehicle to be detected
Position reference point on acquire the preceding face image of vehicle to be detected；Control movable fixture, which is moved to position from position reference point, joins
Examination point corresponds to the side shooting point of parking stall；In side, shooting point acquires the side image of vehicle to be detected.
In some embodiments, above-mentioned according to location information and image data, determine the walking path of movable fixture
With mechanical arm walk path the step of, comprising: by image data be input in advance training complete type identification model, output
The type of vehicle to be detected；Obtain the corresponding vehicle part topology distribution of type of pre-stored vehicle to be detected；According to vehicle
Component topology distribution determines the initial position of the component to be detected of vehicle to be detected；According to location information and portion to be detected
The initial position of part determines the walking path of movable fixture and the path that walks of mechanical arm.
In some embodiments, the step of walking path of above-mentioned determining movable fixture, comprising: according to portion to be detected
The initial position of part and the brachium of mechanical arm determine walking path at a distance from vehicle to be detected；Based on distance, preset walking
The location information of the direction of route and vehicle to be detected determines the walking path of movable fixture.
In some embodiments, above-mentioned determining mechanical arm walk path the step of, comprising: obtained by 3D photographic device
Take the 3D scan image of vehicle to be detected；The initial position of 3D scan image and component to be detected is input to training in advance to complete
Example parted pattern in, export the 3D network model of component to be detected；According to preset sampling rule, from component to be detected
Acquisition testing point in 3D network model, and calculate the normal vector of test point；According to test point, the normal vector of test point and pre-
If mechanical arm control algolithm, determine the path that walks of mechanical arm.
In some embodiments, the above method further include: if vehicle to be detected be it is multiple, according to vehicle to be detected
The map datum of location information and current detection environment determines the position reference point of current detection vehicle；Control movable fixture
It is moved to the position reference point of current detection vehicle；For current detection vehicle, the image of above-mentioned acquisition vehicle to be detected is executed
The step of data；After the completion of the vehicle condition detection data acquisition of current detection vehicle, according to the location information of vehicle to be detected, from
Next current detection vehicle is determined in vehicle to be detected, continues to execute the step of the position reference point of determining target current vehicle
Suddenly, until completing the detection of all vehicles to be detected.
Second aspect, the embodiment of the present invention also provide a kind of vehicle condition detection device, which is set to detection robot
Controller；Detecting robot further includes movable fixture and mechanical arm；Mechanical arm is mounted on movable fixture；Pacify on mechanical arm
Equipped with detection device；Device includes: command reception module, for receiving vehicle condition detection instruction；Vehicle condition detection instruction includes to be checked
The location information of measuring car；Data acquisition module, for acquiring the image data of vehicle to be detected；Path determination module is used for
According to location information and image data, the walking path of movable fixture and the path that walks of mechanical arm are determined；Control module is used
It is moved in control movable fixture along walking path, control mechanical arm is according to the path movement that walks, to be adopted by detection device
Collect the vehicle condition detection data of vehicle to be detected.
The third aspect, the embodiment of the invention provides a kind of detection robot, which includes controller, removable
Dynamic device, mechanical arm and detection device；Above-mentioned vehicle condition detection device setting is in the controller；Mechanical arm is mounted in movable fixture
On；Detection device is installed on mechanical arm.
In aforesaid way, after detection robot receives vehicle condition detection instruction, according to the vehicle to be detected in the instruction
Location information and acquired image data can determine the walking path of movable fixture and the path that walks of mechanical arm；
And then the movable fixture for controlling robot is moved along walking path, control mechanical arm is according to the path movement that walks, to pass through
Detection device acquires the vehicle condition detection data of vehicle to be detected.In which, vehicle condition detection, detection are carried out by detection robot
Robot can position based on vehicle to be detected and image data planning walking path and mechanical arm walk, no setting is required specially
The detection workspace of industry, thus can be adapted for vehicle condition in the shops that environment is complicated and changeable, vehicle is various and detect, it is particularly suitable for
The vehicle condition of shops's used car detects.
Other feature and advantage of the embodiment of the present invention will illustrate in the following description, alternatively, Partial Feature and excellent
Point can deduce from specification or unambiguously determine, or the above-mentioned technology by implementing the embodiment of the present invention can obtain
Know.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of structural schematic diagram for detecting robot provided in an embodiment of the present invention；
Fig. 2 is a kind of flow chart of vehicle condition detection method provided in an embodiment of the present invention；
Fig. 3 is the schematic diagram of current detection environment provided in an embodiment of the present invention；
Fig. 4 is that the movement routine for the image data that detection robot provided in an embodiment of the present invention acquires vehicle to be detected is shown
It is intended to；
Fig. 5 is the flow chart of another vehicle condition detection method provided in an embodiment of the present invention；
Fig. 6 is the structural schematic diagram of another detection robot provided in an embodiment of the present invention；
Fig. 7 is a kind of schematic diagram of walking path provided in an embodiment of the present invention；
Fig. 8 is the schematic diagram of another walking path provided in an embodiment of the present invention；
Fig. 9 is a kind of structural schematic diagram of vehicle condition detection device provided in an embodiment of the present invention；
Figure 10 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
Technical solution of the present invention is clearly and completely described below in conjunction with embodiment, it is clear that described reality
Applying example is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, the common skill in this field
Art personnel every other embodiment obtained without making creative work belongs to the model that the present invention protects
It encloses.
In order to adapt to the business scenario of used car detection, the present embodiment provides one kind to be suitable for reinspection point, Bao Mai shops, vehicle
The vehicle condition detection mode of a variety of environment such as shops afterwards, while various can be adapted to.Based on this, the present embodiment passes through detection machine
Device people carries out vehicle condition detection.In order to make it easy to understand, a kind of detection robot is provided first, as shown in Figure 1, the detection robot 10
Including at least controller 100, movable fixture 101 and mechanical arm 102；Mechanical arm therein is mounted on movable fixture；Machine
Detection device 103 is installed on tool arm；The detection device can be according to specific detection demand setting, such as paint film acetes chinensis
Instrument, tangerine peel instrument etc..The mechanical arm can be six shaft mechanical arms, and movable fixture is specifically as follows AVG (Automated Guided
Vehicle, automatic guide vehicle) or AMR (Automated Mobile Robot, automatically move robot) etc..In addition, the detection
Camera, 3D scanning device etc. are also provided in robot.
Based on above-mentioned detection robot, a kind of flow chart of vehicle condition detection method shown in Figure 2, this method is applied to
The controller of above-mentioned detection robot；This method comprises the following steps:
Step S202 receives vehicle condition detection instruction；The vehicle condition detection instruction includes the location information of vehicle to be detected；
The vehicle condition detection instruction can be issued by staff, specifically, touch can be set in the detection robot
The human-computer interaction devices such as screen, keyboard, display screen, staff issue vehicle condition inspection by the human-computer interaction device in detection robot
Survey instruction；In another way, which can connect with terminal equipment in communication, and staff passes through the terminal device
Go out above-mentioned vehicle condition detection instruction to detection machine human hair；In addition, the detection robot can be communicated to connect with control platform, work
Personnel go out above-mentioned vehicle condition detection instruction to detection machine human hair by the control platform.
The location information of above-mentioned vehicle to be detected also can have diversified forms, for example, multiple parking stalls can be delimited in advance,
And be numbered for each parking stall, the location information of the vehicle to be detected is specifically as follows the number of parking stall；Furthermore it is also possible to base
In the map of current detection environment, staff defined area on this map, the vehicle in the region is required to carry out vehicle condition
Detection, the region, that is, above-mentioned vehicle to be detected location information.
Step S204 acquires the image data of vehicle to be detected；
If being provided with camera in detection robot, the image data of the vehicle to be detected can be acquired by the camera
It obtains；In another way, it can also be acquired by other cameras that current detection environment is arranged in, and be sent to detection machine
People.
Step S206 determines the walking path and mechanical arm of movable fixture according to above-mentioned location information and image data
The path that walks；
Step S208, control movable fixture are moved along walking path, and control mechanical arm is acted according to the path that walks, with
The vehicle condition detection data of vehicle to be detected is acquired by detection device.
The walking path of above-mentioned movable fixture can be understood as detection robot on the ground of current detection environment
Walking path；Controller can determine the position of every vehicle to be detected by above-mentioned location information, pass through above-mentioned image data
Can determine every vehicle to be detected parks direction, specific location of all parts etc., and then determines detection robot from working as
The location of preceding walking path to set out, the walking path usually require covering vehicle to be detected in need portion to be detected
The position of part can also plan shortest walking path for energy saving consideration on this basis.
The mechanical arm that the path that walks of above-mentioned mechanical arm can be understood as in detection robot drives detection device in three-dimensional
The path that walks in space；Controller parks direction, each by what above-mentioned image data can determine every vehicle to be detected
The specific location of component, and then determine based on these information one or more test points of every vehicle to be detected, it is based on these
The position of test point determines the path that walks of above-mentioned mechanical arm；It is in need that the path that walks of the mechanical arm usually requires covering institute
The position of each test point on vehicle to be detected.
It, can be removable according to this after controller determines the walking path of movable fixture and the path that walks of mechanical arm
The walking path control movable fixture walking of device, while the movement of the path clustering mechanical arm that walks according to mechanical arm,
In the action process of mechanical arm, starting detection device acquires related data.
In aforesaid way, after detection robot receives vehicle condition detection instruction, according to the vehicle to be detected in the instruction
Location information and acquired image data can determine the walking path of movable fixture and the path that walks of mechanical arm；
And then the movable fixture for controlling robot is moved along walking path, control mechanical arm is according to the path movement that walks, to pass through
Detection device acquires the vehicle condition detection data of vehicle to be detected.In which, vehicle condition detection, detection are carried out by detection robot
Robot can position based on vehicle to be detected and image data planning walking path and mechanical arm walk, no setting is required specially
The detection workspace of industry, thus can be adapted for vehicle condition in the shops that environment is complicated and changeable, vehicle is various and detect.
The walking path of movable fixture and the path that walks of mechanical arm are determined in order to further increase detection robot
Accuracy, robot need to obtain more accurate clearly image data, are based on this, and the present embodiment also provides another vehicle condition inspection
Survey method.
It is possible, firstly, to plan multiple parking stalls in advance in current detection environment, one end of each parking stall is provided with position ginseng
Examination point, Fig. 3 are an example, and planning has 10 parking stalls in the detection environment domain in the example, and the left end of each parking stall is provided with
Corresponding position reference point.Meanwhile the location information of each parking stall and the coordinate of the position reference point of each parking stall being saved
Into the controller of detection robot.It detects robot and vehicle to be detected is determined according to the location information in vehicle condition detection instruction
Position reference point, then control movable fixture and be moved to position ginseng from preset starting point (from the charging pile such as detection robot)
Examination point；After reaching the position reference point, then start the vehicle to be detected that acquisition is parked in the parking stall.It is each to be detected by being arranged
The corresponding position reference point of vehicle, helps to detect robot and obtains accurate clearly image data, and then after being conducive to raising
The accuracy in the path that walks of the continuous walking path for determining movable fixture and mechanical arm.
The map datum of current detection environment is also previously stored in above controller, which can pass through laser
Radar scanning current detection environment obtains；It is limited by various detection environment, the map datum precision of presumable detection environment
It is higher, such as it can be accurate to 0.01 meter, the map datum precision that some detects environment is lower, such as accuracy is likely difficult to reach
To 0.05 meter；The position reference point of vehicle to be detected can be determined in different ways by being directed to different accuracies, below into
Row specifically describes.
As described in above-described embodiment, location information in vehicle condition detection instruction can be parking stall number, which can be by
Staff's input, or detection zone, the detection zone can be by staff on pre-stored map datum
It delimit.If the map datum stored in detection robot is accurate higher, position can be determined directly from map datum
Information corresponds to the position reference point of parking stall；Detection robot can accurately arrive at the position reference point.Robot is detected from
The path of initial point in-position reference point, can be by the physical constraint of shortest distance cost function and current detection environment (such as
Intrinsic barrier, channel etc. in environment), it is generated by preset path planning algorithm.
When detect robot in store map datum it is accurate lower when, if according only to map datum determine position join
Examination point, then detecting robot may in-position reference point, it is also possible to reach the neighboring area other than the position reference point, such as
Fruit reaches neighboring area, then detects robot and be likely difficult to accurately collect the image data of vehicle to be detected, for example, acquisition
The image-region that image data is imperfect, deflection, vehicle occupy is smaller etc..Based on this, with continued reference to Fig. 3, can relative to
Reserved reference substance is arranged in the designated position of position reference point, the reserved reference substance can be set position reference point front or
Other designated positions, in another way, which can also be arranged in position reference point, for example, the reserved ginseng
Examining object can be certain specific shape or color.
Based on above-mentioned reserved reference substance and map datum, it specifically can first determine that location information is corresponding from map datum
The regional scope of parking stall, then image data or laser SLAM (simultaneous by photographic device acquisition
Localization and mapping, immediately positioning and map structuring) acquisition point cloud data, identified from the regional scope
The position of reserved reference substance, determines position reference point according to the position of reserved reference substance.It detects robot and reaches above-mentioned zone model
After enclosing, the reserved reference substance in the regional scope, and then root again can be positioned using modes such as image recognition, neural network recognizations
According to the positional relationship between preset reserved reference substance and position reference point, position reference point is determined.
It should be noted that detecting robot if including multiple parking stalls in location information in vehicle condition detection instruction
The position reference point that the position reference point of one of parking stall is reached as first can be randomly selected.As an example, simultaneously
In conjunction with Fig. 3, the location information in vehicle condition detection instruction includes parking stall 1 to parking stall 5, detects and has been parked under robot original state
Initial point detects robot from starting point at this time, can first reach the corresponding position in any one parking stall in parking stall 1 to parking stall 5
Reference point is set, after corresponding to the vehicle detection on parking stall to the position reference point, and then it is corresponding to reach next parking stall again
Position reference point, until above-mentioned parking stall 1 all vehicle detections to be detected into parking stall 5 finish.Certainly, for energy conservation consideration,
When determining the track route of detection robot, the position of current detection robot, nearest parking stall, present position can be first reached
Reference point, then successively reach the position reference point of other parking stalls.For example, when detection robot is in the starting point in Fig. 3, it can
First to reach the position reference point of parking stall 1, subsequent parking stall is successively reached according still further to the sequence of parking stall 2, parking stall 3, parking stall 4, parking stall 5
Position reference point, and complete the task of vehicle detection.
Based on foregoing description, the step of robot acquires the image data of vehicle to be detected is detected, following steps can be passed through
Rapid 10- step 14 is realized；
Step 10, the preceding face image of vehicle to be detected is acquired in the position reference point of vehicle to be detected；
After detecting robot in-position reference point, it may also need to further confirm that the corresponding parking stall of the position reference point
On whether parked vehicle to be detected, specifically can by detection robot on photographic device or by being mounted on current inspection
The camera collection image in environment is surveyed, is confirmed in combination with the information of vehicles stored in control platform.
Step 12, control movable fixture is moved to the side shooting that the position reference point corresponds to parking stall from position reference point
Point；
Step 14, in the side, shooting point acquires the side image of vehicle to be detected.
In conjunction with Fig. 4, after detecting the position reference point that robot reaches parking stall n, the camera shooting in detection robot can be passed through
Device acquires the direct picture of parked vehicle on parking stall, and then can reach the side of parking stall n along the dashed path 1 in Fig. 4
Face shooting point acquires the side image of parked vehicle on parking stall by photographic device.If direct picture and side image energy
Enough meet actually detected demand, can stop shooting at this time.In another way, if also requiring the back view of acquisition vehicle
Picture, detection robot can continue on the dashed path 2 in Fig. 4, reach parking stall after acquiring the side image of vehicle
The back side shooting point of n acquires the back side image of parked vehicle on parking stall by photographic device.
Above-mentioned parking stall, position reference point, side shooting point and back side shooting point (if there is) position can set in advance
It sets, thus detects robot to be calculated according to the position coordinates of position reference point, side shooting point and back side shooting point
To the path 1 and path 2 in above-mentioned Fig. 4.
The mode of the image data of above-mentioned acquisition vehicle, can obtain the vehicle image of all angles, and image is accurately clear
It washes, is conducive to the accuracy for improving subsequent vehicle cab recognition, component identification.
The present embodiment also provides another vehicle condition detection method；The position of vehicle to be detected is got in the above-described embodiments
On the basis of information and image data, the present embodiment emphasis describes to determine the walking path of movable fixture and walking for mechanical arm
The specific implementation in path.
After the image data for collecting vehicle to be detected, image data can be input to the class that training is completed in advance first
Type identification model exports the type of vehicle to be detected；Obtain the corresponding vehicle part of type of pre-stored vehicle to be detected
Topology distribution；The initial position of the component to be detected of vehicle to be detected is determined further according to vehicle part topology distribution；Last basis
The initial position of location information and component to be detected determines the walking path of movable fixture and the path that walks of mechanical arm.
Neural network can be used in the above-mentioned type identification model, is obtained by the training of great amount of samples image；Model can be pre-
The type for first dividing vehicle, for example including two-box automobile, three-box car, SUV (sport utilityvehicle, sport utility
Automobile) etc..Typically for same type but the vehicle of different brands, vehicle, vehicle part topology distribution be it is identical, again
Due to the limited types of vehicle, thus the vehicle part topology distribution of various type of vehicle can be acquired in advance, the vehicle part
Topology distribution specifically can be understood as the positional relationship etc. between the shape of each covering of outside vehicle, each covering；It should
Covering generally include front bumper, rear bumper, left front fender, right front fender, left back fender, right rear fender,
Left front door, left back door, right front door, right-rear-door, engine compartment cover, luggage-boot lid, roof, left A column, right A column, left C column, right C column,
Left crossbeam, right crossbeam etc..
In addition, being directed to the type of various vehicles, and actually detected demand is combined, component to be detected can be preassigned, such as
Front bumper, left front door, right-rear-door etc.；After getting the vehicle part topology distribution of the type of vehicle, the vehicle can be based on
Component topology distribution orients the initial position of component to be detected from image data；Since component to be detected has certain face
Product, thus the initial position of component to be detected here can be understood as the location of the component to be detected region.By upper
Mode is stated, the coarse positioning to a plurality of types of vehicles component to be detected may be implemented, the detection suitable for various.
Based on foregoing description, the flow chart of another vehicle condition detection method shown in Figure 5；Before this, this implementation
Example also provides the specific structure of another detection robot, referring to Fig. 6, on the basis of detection robot shown in Fig. 1, and the inspection
Surveying robot further includes 2D (2-Dimension, two dimension) photographic device 104,3D (3-Dimension, three-dimensional) photographic device
105, which is specifically as follows wide-field 2D camera, which is specifically as follows binocular camera, RGBD
Camera etc..It detects and installation version, executing agency or fixture can be set at the 6th axis wrist of the mechanical arm of robot, with fixation
Detection device, if the detection device is contact measurement, the end of detection device can be configured with floating part or Flexible element,
To support end force-feedback control.In addition, the detection robot can also include human-computer interaction device 106, power management module
107, safe early warning module 108 etc..
It should be noted that above-mentioned 2D photographic device 104 and 3D photographic device 105 carry on the robotic arm simultaneously, 2D is taken the photograph
As device and 3D photographic device needs demarcated in advance so that the two acquire image it is corresponding.In another way, detection
3D photographic device can be only carried on the mechanical arm of robot, 2D image is acquired by the 3D photographic device, at this time, it may be necessary to widen
The shooting visual field of 3D photographic device.2D image is marked with 3D point cloud data (i.e. above-mentioned 3D scan image) by camera parameter
It is fixed, so that 2D image and 3D point cloud data have mapping relations.
Detection device therein can be communicated to connect by the communication modes such as bluetooth and controller；Human-computer interaction device can be with
Pass through TCP/IP (Transmission Control Protocol/Internet Protocol, transmission control protocol/Yin Te
Net interconnection protocol) agreement and controller communicate to connect；2D photographic device, 3D photographic device, movable fixture, mechanical arm and outer
The mobile terminal in portion can pass through EtherNet/IP (EtherNet/Internet Protocol, the Yin Te based on Ethernet
Net interconnection protocol) agreement and controller communicate to connect；External control platform can be communicated to connect by WiFi and controller.
Based on above-mentioned detection robot, the step of executing following methods:
Step S502 receives vehicle condition detection instruction；The vehicle condition detection instruction includes the location information of vehicle to be detected；
Step S504 determines the position reference point of the vehicle to be detected according to the positional information；
Step S506 controls the movable fixture from preset starting point and is moved to the position reference point.
Step S506 acquires the preceding face image of vehicle to be detected in the position reference point of vehicle to be detected；
Step S508, control movable fixture are moved to the side bat that the position reference point corresponds to parking stall from position reference point
It takes the photograph a little；
Step S510, in the side, shooting point acquires the side image of vehicle to be detected.
Image data is input to the type identification model that training is completed in advance, exports vehicle to be detected by step S512
Type；
Step S514 obtains the corresponding vehicle part topology distribution of type of pre-stored vehicle to be detected；
Step S516 determines the initial position of the component to be detected of vehicle to be detected according to vehicle part topology distribution；
Above-mentioned steps S502 to S516 is described by the aforementioned embodiment, is continued with description and is determined movable fixture
Walking path and mechanical arm walk path the step of.
Step S518, according to the brachium of the initial position of component to be detected and mechanical arm, determine walking path with it is to be detected
The distance of vehicle；
Step S520 is determined based on the location information of distance, the direction of preset track route and vehicle to be detected
The walking path of movable fixture.
Above-mentioned steps S518 and S520 are used to determine the walking path of movable fixture, it will be understood that in order to acquire vehicle
The coherent detection parameter of upper component to be detected, mechanical arm should will test equipment and be moved to the position for sufficiently closing to component to be detected
It sets, and since the brachium of mechanical arm usually has maximum value, the walking path for detecting robot should be appropriate close to be checked
Measuring car, while also needing to guarantee to detect the safety of robot and vehicle to be detected, it avoids mutually colliding.It to sum up, can be preparatory
Experiment is measured, determines the initial position of component to be detected, the brachium of mechanical arm and walking path and vehicle to be detected
The corresponding relationship of distance, after getting the brachium of the initial position of component to be detected and mechanical arm in current vehicle to be detected,
Walking path can be found from above-mentioned corresponding relationship at a distance from vehicle to be detected.For example, the brachium after mechanical arm expansion
It is 1.2 meters, then the distance can be set to 0.8 meter.
The direction of above-mentioned preset track route can usually be determined according to the side shooting point of parking stall, for example, if side
Face shooting point is located at the left side of parking stall, and the direction of the preset track route can be counterclockwise, if side shooting point is located at
The right side of parking stall, the direction of the preset track route can be it is clockwise, with farthest reduce detection robot row
Walk distance.
As an example, Fig. 7 shows a kind of schematic diagram of walking path；Only in the position reference point of parking stall n in the example
Face image before photographs shoots side image, then detection machine after detection robot is moved to side shooting point along path 1
Device people reaches the upper left position of parking stall along path 2, which can be the initial position of walking path, further according to
The above-mentioned distance determined surrounds vehicle to run to be detected in a counterclockwise direction, until the upper left position of parking stall is arrived again at,
Such as path 3, path 4, path 5 and the path 6 in Fig. 7.That is, the walking path of the movable fixture of detection robot is understood that
Are as follows: since the initial position of walking path, according to the distance determined according to counterclockwise or clockwise about to be detected
The path of vehicle to run.Determining walking path through the above way, it is moderate at a distance from vehicle, be conducive to mechanical arm and walk,
Convenient for acquisition testing data.
In addition, one can be arranged on vehicle to be detected in order to further increase the accurate readability of image data
Local feature label, such as " * " mark in Fig. 7.After detecting robot in-position reference point, marked according to the local feature
The position of fine tuned robot again, so that in acquired image data, the more standard such as position, size of vehicle is conducive to
Improve subsequent walking path and the accurate of path that walk.
Step S522 obtains the 3D scan image of vehicle to be detected by 3D photographic device；
The initial position of 3D scan image and component to be detected is input to the example point that training is completed in advance by step S524
It cuts in model, exports the 3D network model of component to be detected；
Step S526, according to preset sampling rule, the acquisition testing point from the 3D network model of component to be detected, and count
Calculate the normal vector of test point；
Step S528 is determined mechanical according to test point, the normal vector of test point and preset mechanical arm control algolithm
The path that walks of arm.
Step S530, control movable fixture are moved along walking path, and control mechanical arm is acted according to the path that walks, with
The vehicle condition detection data of vehicle to be detected is acquired by detection device.
Above-mentioned steps S522 to S528 is used to determine the path that walks of mechanical arm, due to each to be detected in vehicle to be detected
The height of component and the radian of parts surface will affect the position of detection device, and therefore, it is necessary to pass through vehicle to be detected
3D scan image further determines test point from component to be detected, and then determines the path that walks of mechanical arm.
Specifically, neural network can be used in examples detailed above parted pattern, obtained by the training of great amount of samples image；?
When the image that acquisition is divided for example, it usually needs the visual field of 3D photographic device is greater than maximum component to be detected, and training is real
Sample image used by example parted pattern can be 3D scan image, be also possible to the mixed number of 2D image and 3D scan image
According to.
The initial position of above-mentioned component to be detected can be with distance pole in the image data of vehicle to be detected, by the image data
Be input in the example parted pattern with the 3D scan image of measuring car to be checked, can export be labeled in it is each on 3D scan image
The 3D network model of component to be detected.The type that may include each vehicle in above-mentioned sampling rule is corresponding, each to be detected
The position of the corresponding test point of component.After the 3D network model of the type of vehicle to be detected and each component to be detected determines,
The position of corresponding test point can be found from above-mentioned sampling rule.In addition, due to including to be checked in 3D network model
The normal vector of the test point can be obtained by seeking partial derivative to test point in the location information for surveying each point of parts surface.It should
Normal vector is determined for the posture of detection device, for example, needing the detection on detection device for specific detection project
Sensing device is put along the normal vector direction of test point.
By taking paint film detects as an example, the detection device of the 6th axis installation of mechanical arm is paint film instrument, and the probe of the paint film instrument exists
Data are acquired on test point, collected data can return to the control platform communicated to connect with detection robot in real time.
In aforesaid way, test point is determined for the position that detection device needs to reach, and the normal vector of test point is used
In the posture for determining detection device, and then determine by mechanical arm control algolithm the path that walks of mechanical arm, the path that walks is logical
Often need to cover the position of all test points on the vehicle to be detected, and on each test point, the posture of detection device is full
The normal vector of the foot test point.Which realizes the accurate positioning of component to be detected by 3D scan image, is conducive to improve vehicle
The accuracy of condition detection.
The present embodiment also provides another vehicle condition detection method, and the location information of vehicle to be detected is worked as in the description of this method emphasis
In when including multiple vehicles to be detected, the detection method of vehicle condition.If vehicle to be detected be it is multiple, can be according to measuring car to be checked
Location information and current detection environment map datum, determine the position reference point of current detection vehicle；Control is removable
Device is moved to the position reference point of current detection vehicle；For current detection vehicle, above-mentioned acquisition currently measuring car to be checked is executed
Image data the step of, until current detection vehicle vehicle condition detection data acquire complete.And then further according to measuring car to be checked
Location information, next current detection vehicle is determined from vehicle to be detected, continues to execute determining target current vehicle
The step of position reference point, until completing the detection of all vehicles to be detected.
Fig. 8 shows an example, which is illustrated by taking three vehicles to be detected as an example, respectively parking stall 1, parking stall
2 and parking stall 3 on the vehicle to be detected parked.Detection robot arrives first at the position reference point of parking stall 1, starts to acquire this to be checked
Image data, 3D scan image of measuring car etc., and then determine the walking path of movable fixture and the path that walks of mechanical arm,
Then the walking path of above-mentioned movable fixture and the path that walks of mechanical arm are executed since the upper left corner of parking stall 1, are arrived again
Up to after the upper left corner, illustrates that current vehicle detection to be detected finishes, the position reference point of parking stall 2 is then moved to, according to same
The step of complete the detection of vehicle to be detected on parking stall 2, similarly complete the detection of vehicle to be detected on parking stall 3.When all vehicles
After completing detection, detection robot can return to starting point and charge.
In addition, in order to further increase the safety of detection robot, which usually also needs to configure avoidance
Detection and impact protector function carry out safety instruction after having personnel to enter and detect and go and are set as the function of safe condition, in people
Machine coexisting region is constrained the working condition of detection robot the function of (upper limit that movement speed is such as arranged), Yi Jijian
Survey the function etc. of robot and the mobile terminal progress human-computer interaction of staff.
Corresponding to the embodiment of above-mentioned vehicle condition detection method, a kind of structure of vehicle condition detection device shown in Figure 9 is shown
It is intended to；The device is set to the controller of detection robot；Detecting robot further includes movable fixture and mechanical arm；Mechanical arm
It is mounted on movable fixture；Detection device is installed on mechanical arm；The device includes:
Command reception module 90, for receiving vehicle condition detection instruction；Vehicle condition detection instruction includes the position of vehicle to be detected
Information；
Data acquisition module 91, for acquiring the image data of vehicle to be detected；
Path determination module 92, for according to location information and image data, determine movable fixture walking path and
The path that walks of mechanical arm；
Control module 93 is moved for controlling movable fixture along walking path, controls mechanical arm according to the path that walks
Movement, to acquire the vehicle condition detection data of vehicle to be detected by detection device.
In above-mentioned vehicle condition detection device, after detection robot receives vehicle condition detection instruction, according to be checked in the instruction
The location information and acquired image data of measuring car, can determine the walking path of movable fixture and walking for mechanical arm
Position path；And then the movable fixture for controlling robot is moved along walking path, control mechanical arm is acted according to the path that walks,
To acquire the vehicle condition detection data of vehicle to be detected by detection device.In which, vehicle condition inspection is carried out by detection robot
Survey, detection robot can position based on vehicle to be detected and image data planning walking path and mechanical arm walk, nothing
The detection workspace of profession need to be set, thus can be adapted for vehicle condition in the shops that environment is complicated and changeable, vehicle is various and detect.
Further, above-mentioned apparatus further include: the first reference point determining module, it is to be detected for being determined according to location information
The position reference point of vehicle；First movement control module is moved to position from preset starting point for controlling movable fixture
Reference point.
Further, the map datum of current detection environment is previously stored in above controller；Location information includes vehicle
Position number or detection zone；Above-mentioned reference point determining module, is also used to: determining that location information corresponds to the position of parking stall from map datum
Set reference point；Alternatively, determining that location information corresponds to the regional scope of parking stall from map datum；By photographic device from region model
The middle position for identifying reserved reference substance is enclosed, position reference point is determined according to the position of reserved reference substance.
Further, above-mentioned data acquisition module 91, is also used to: acquiring in the position reference point of vehicle to be detected to be checked
The preceding face image of measuring car；Control movable fixture is moved to the side shooting that position reference point corresponds to parking stall from position reference point
Point；In side, shooting point acquires the side image of vehicle to be detected.
Further, above-mentioned path determination module 92, is also used to: image data is input to the type that training is completed in advance
Identification model exports the type of vehicle to be detected；The corresponding vehicle part of type for obtaining pre-stored vehicle to be detected is opened up
Flutter distribution；The initial position of the component to be detected of vehicle to be detected is determined according to vehicle part topology distribution；According to location information,
And the initial position of component to be detected, determine the walking path of movable fixture and the path that walks of mechanical arm.
Further, above-mentioned path determination module 92, is also used to: according to the initial position of component to be detected and mechanical arm
Brachium determines walking path at a distance from vehicle to be detected；Based on distance, the direction of preset track route and to be detected
The location information of vehicle determines the walking path of movable fixture.
Further, above-mentioned path determination module 92, is also used to: being swept by the 3D that 3D photographic device obtains vehicle to be detected
Trace designs picture；The initial position of 3D scan image and component to be detected is input in the example parted pattern that training is completed in advance,
Export the 3D network model of component to be detected；According to preset sampling rule, acquired from the 3D network model of component to be detected
Test point, and calculate the normal vector of test point；It is controlled and is calculated according to test point, the normal vector of test point and preset mechanical arm
Method determines the path that walks of mechanical arm.
Further, above-mentioned apparatus further include: the second reference point determining module, if for vehicle to be detected be it is multiple,
According to the map datum of the location information of vehicle to be detected and current detection environment, the reference by location of current detection vehicle is determined
Point；Second mobile control module, the position reference point for being moved to current detection vehicle for controlling movable fixture；Execute mould
Block, for the step of being directed to current detection vehicle, executing the image data of above-mentioned acquisition vehicle to be detected；When current detection vehicle
The acquisition of vehicle condition detection data after the completion of, according to the location information of vehicle to be detected, next works as is determined from vehicle to be detected
Preceding detection vehicle, the step of continuing to execute the position reference point of determining target current vehicle, until completing all vehicles to be detected
Detection.
The technical effect of device provided by the present embodiment, realization principle and generation is identical with previous embodiment, for letter
It describes, Installation practice part does not refer to place, can refer to corresponding contents in preceding method embodiment.
The present embodiment also provides a kind of detection robot, which includes controller, movable fixture, mechanical arm
And detection device；Above-mentioned vehicle condition detection device device setting is in the controller；Mechanical arm is mounted on movable fixture；Mechanical arm
On detection device is installed.
The present embodiment also provides a kind of electronic equipment, and the structural schematic diagram of a kind of electronic equipment shown in Figure 10 should
Electronic equipment includes memory 1000 and processor 1001；Wherein, memory 1000 is machine readable storage medium, for depositing
One or more computer instruction is stored up, one or more computer instruction is executed by processor, to realize above-mentioned vehicle condition detection side
The step of method.Above-mentioned detection robot can refer to electronic equipment as shown in Figure 10 and realize, or have compared to shown in Figure 10
The more or fewer components of electronic equipment, be not limited herein.
Further, electronic equipment shown in Fig. 10 further includes bus 1002 and communication interface 1003, processor 1001, communication
Interface 1003 and memory 1000 are connected by bus 1002.
Wherein, memory 1000 may include high-speed random access memory (RAM, Random Access Memory),
It may also further include non-labile memory (non-volatile memory), for example, at least a magnetic disk storage.Pass through
At least one communication interface 1003 (can be wired or wireless) is realized between the system network element and at least one other network element
Communication connection, internet, wide area network, local network, Metropolitan Area Network (MAN) etc. can be used.It is total that bus 1002 can be isa bus, PCI
Line or eisa bus etc..The bus can be divided into address bus, data/address bus, control bus etc..For convenient for expression, Tu10Zhong
It is only indicated with a four-headed arrow, it is not intended that an only bus or a type of bus.
Processor 1001 may be a kind of IC chip, the processing capacity with signal.It is above-mentioned during realization
Each step of method can be completed by the integrated logic circuit of the hardware in processor 1001 or the instruction of software form.On
The processor 1001 stated can be general processor, including central processing unit (Central Processing Unit, abbreviation
CPU), network processing unit (Network Processor, abbreviation NP) etc.；It can also be digital signal processor (Digital
Signal Processing, abbreviation DSP), specific integrated circuit (Application Specific Integrated
Circuit, abbreviation ASIC), field programmable gate array (Field-Programmable Gate Array, abbreviation FPGA) or
Person other programmable logic device, discrete gate or transistor logic, discrete hardware components.It may be implemented or execute sheet
Each method, step and the logic diagram of invention in invention embodiment.General processor can be microprocessor or this at
Reason device is also possible to any conventional processor etc..The step of method invented in conjunction with embodiment of the present invention, can direct body
Now executes completion for hardware decoding processor, or in decoding processor hardware and software module combine and execute completion.It is soft
Part module can be located at random access memory, and flash memory, read-only memory, programmable read only memory or electrically erasable programmable are deposited
In the storage medium of this fields such as reservoir, register maturation.The storage medium is located at memory 1000, and the reading of processor 1001 is deposited
Information in reservoir 1000, in conjunction with its hardware complete aforementioned embodiments method the step of.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
Specific work process, can be with reference to the corresponding process in previous embodiment, and details are not described herein.
The computer program product of vehicle condition detection method, device and system provided by the embodiment of the present invention, including deposit
The computer readable storage medium of program code is stored up, the instruction that said program code includes can be used for executing previous methods implementation
Method described in example, specific implementation can be found in embodiment of the method, and details are not described herein.
In addition, in the description of the embodiment of the present invention unless specifically defined or limited otherwise, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, merely to
Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " first ", " second ",
" third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of vehicle condition detection method, which is characterized in that the method is applied to the controller of detection robot；The detection machine
Device people further includes movable fixture and mechanical arm；The mechanical arm is mounted on the movable fixture；Pacify on the mechanical arm
Equipped with detection device；The described method includes:
Receive vehicle condition detection instruction；The vehicle condition detection instruction includes the location information of vehicle to be detected；
Acquire the image data of the vehicle to be detected；
According to the positional information with described image data, the walking path and the mechanical arm of the movable fixture are determined
Walk path；
It controls the movable fixture to move along the walking path, it is dynamic according to the path that walks to control the mechanical arm
Make, to acquire the vehicle condition detection data of the vehicle to be detected by the detection device.
2. the method according to claim 1, wherein the step of image data of the acquisition vehicle to be detected it
Before, the method also includes:
The position reference point of the vehicle to be detected is determined according to the positional information；
It controls the movable fixture and is moved to the position reference point from preset starting point.
3. according to the method described in claim 2, it is characterized in that, being previously stored with current detection environment in the controller
Map datum；The location information includes parking stall number or detection zone；
The step of determining the position reference point of the vehicle to be detected according to the positional information, comprising:
Determine that the location information corresponds to the position reference point of parking stall from the map datum；
Alternatively, determining that the location information corresponds to the regional scope of parking stall from the map datum；By photographic device from institute
The position for identifying reserved reference substance in regional scope is stated, position reference point is determined according to the position of the reserved reference substance.
4. according to the method described in claim 2, it is characterized in that, the step of the image data of the acquisition vehicle to be detected,
Include:
The preceding face image of the vehicle to be detected is acquired in the position reference point of the vehicle to be detected；
It controls the movable fixture and is moved to the side shooting that the position reference point corresponds to parking stall from the position reference point
Point；
The side image of the vehicle to be detected is acquired in the side shooting point.
5. the method according to claim 1, wherein being determined according to the positional information with described image data
The walking path of the movable fixture and the mechanical arm walk path the step of, comprising:
Described image data are input to the type identification model that training is completed in advance, export the type of the vehicle to be detected；
Obtain the corresponding vehicle part topology distribution of type of the pre-stored vehicle to be detected；
The initial position of the component to be detected of the vehicle to be detected is determined according to the vehicle part topology distribution；
According to the positional information and the initial position of the component to be detected, the walking road of the movable fixture is determined
The path that walks of diameter and the mechanical arm.
6. according to the method described in claim 5, it is characterized in that, the step of determining the walking path of the movable fixture,
Include:
According to the brachium of the initial position of the component to be detected and the mechanical arm, walking path and the measuring car to be checked are determined
Distance；
It, can described in determination based on the location information of the distance, the direction of preset track route and the vehicle to be detected
The walking path of mobile device.
7. according to the method described in claim 5, it is characterized in that, determine the mechanical arm walk path the step of, comprising:
The 3D scan image of the vehicle to be detected is obtained by 3D photographic device；
The initial position of the 3D scan image and the component to be detected is input to the example that training is completed in advance and divides mould
In type, the 3D network model of the component to be detected is exported；
According to preset sampling rule, the acquisition testing point from the 3D network model of the component to be detected, and calculate the inspection
The normal vector of measuring point；
According to the test point, the normal vector of the test point and preset mechanical arm control algolithm, the mechanical arm is determined
The path that walks.
8. according to the method described in claim 2, it is characterized in that, the method also includes:
If the vehicle to be detected be it is multiple, according to the map of the location information of the vehicle to be detected and current detection environment
Data determine the position reference point of current detection vehicle；
Control the position reference point that the movable fixture is moved to the current detection vehicle；
For the current detection vehicle, the step of the image data of the acquisition vehicle to be detected described in perform claim requirement 1
Suddenly；
After the completion of the vehicle condition detection data acquisition of the current detection vehicle, according to the location information of the vehicle to be detected,
Next current detection vehicle is determined from the vehicle to be detected, continues to execute the position reference point of determining target current vehicle
The step of, until completing the detection of all vehicles to be detected.
9. a kind of vehicle condition detection device, which is characterized in that described device is set to the controller of detection robot；The detection machine
Device people further includes movable fixture and mechanical arm；The mechanical arm is mounted on the movable fixture；Pacify on the mechanical arm
Equipped with detection device；Described device includes:
Command reception module, for receiving vehicle condition detection instruction；The vehicle condition detection instruction includes the position letter of vehicle to be detected
Breath；
Data acquisition module, for acquiring the image data of the vehicle to be detected；
Path determination module, for determining the walking of the movable fixture according to the positional information with described image data
The path that walks in path and the mechanical arm；
Control module is moved for controlling the movable fixture along the walking path, controls the mechanical arm according to institute
The path movement that walks is stated, to acquire the vehicle condition detection data of the vehicle to be detected by the detection device.
10. a kind of detection robot, which is characterized in that the detection robot include controller, movable fixture, mechanical arm and
Detection device；Device setting as claimed in claim 9 is in the controller；
The mechanical arm is mounted on the movable fixture；Detection device is installed on the mechanical arm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910417671.0A CN110091342B (en) | 2019-05-20 | Vehicle condition detection method and device and detection robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910417671.0A CN110091342B (en) | 2019-05-20 | Vehicle condition detection method and device and detection robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110091342A true CN110091342A (en) | 2019-08-06 |
| CN110091342B CN110091342B (en) | 2024-04-26 |
Family
ID=
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110780308A (en) * | 2019-10-28 | 2020-02-11 | 西南科技大学 | Three-dimensional point cloud data acquisition system and method under turbid water environment |
| CN111192189A (en) * | 2019-12-27 | 2020-05-22 | 中铭谷智能机器人(广东)有限公司 | Three-dimensional automatic detection method and system for automobile appearance |
| CN112858290A (en) * | 2021-01-08 | 2021-05-28 | 北京中车重工机械有限公司 | Detection system based on digital image processing and detection method and device thereof |
| CN114216496A (en) * | 2021-11-03 | 2022-03-22 | 中科合肥技术创新工程院 | Intelligent detection method for functional indexes of intelligent toilet |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016095490A1 (en) * | 2014-12-17 | 2016-06-23 | 苏州华兴致远电子科技有限公司 | Vehicle operation fault detection system and method |
| CN106468914A (en) * | 2015-08-21 | 2017-03-01 | 苏州华兴致远电子科技有限公司 | Train overhaul method and system |
| CN206029901U (en) * | 2015-08-21 | 2017-03-22 | 苏州华兴致远电子科技有限公司 | Train overhaul machine people |
| WO2018036277A1 (en) * | 2016-08-22 | 2018-03-01 | 平安科技（深圳）有限公司 | Method, device, server, and storage medium for vehicle detection |
| CN208675408U (en) * | 2018-08-30 | 2019-03-29 | 北京酷车易美网络科技有限公司 | Vehicle vehicle condition intelligent detection device and system |
| CN109730590A (en) * | 2019-01-30 | 2019-05-10 | 深圳飞科机器人有限公司 | Clean robot and the method for clean robot auto-returned charging |
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016095490A1 (en) * | 2014-12-17 | 2016-06-23 | 苏州华兴致远电子科技有限公司 | Vehicle operation fault detection system and method |
| CN106468914A (en) * | 2015-08-21 | 2017-03-01 | 苏州华兴致远电子科技有限公司 | Train overhaul method and system |
| CN206029901U (en) * | 2015-08-21 | 2017-03-22 | 苏州华兴致远电子科技有限公司 | Train overhaul machine people |
| WO2018036277A1 (en) * | 2016-08-22 | 2018-03-01 | 平安科技（深圳）有限公司 | Method, device, server, and storage medium for vehicle detection |
| CN208675408U (en) * | 2018-08-30 | 2019-03-29 | 北京酷车易美网络科技有限公司 | Vehicle vehicle condition intelligent detection device and system |
| CN109730590A (en) * | 2019-01-30 | 2019-05-10 | 深圳飞科机器人有限公司 | Clean robot and the method for clean robot auto-returned charging |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110780308A (en) * | 2019-10-28 | 2020-02-11 | 西南科技大学 | Three-dimensional point cloud data acquisition system and method under turbid water environment |
| CN111192189A (en) * | 2019-12-27 | 2020-05-22 | 中铭谷智能机器人(广东)有限公司 | Three-dimensional automatic detection method and system for automobile appearance |
| CN112858290A (en) * | 2021-01-08 | 2021-05-28 | 北京中车重工机械有限公司 | Detection system based on digital image processing and detection method and device thereof |
| CN114216496A (en) * | 2021-11-03 | 2022-03-22 | 中科合肥技术创新工程院 | Intelligent detection method for functional indexes of intelligent toilet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7045816B2 (en) | Methods and systems for measuring the outermost dimensions of vehicles located at inspection stations | |
| CN208255717U (en) | Merchandising machine people | |
| CN109863500A (en) | Event driven area-of-interest management | |
| CN108460791A (en) | Method and apparatus for handling point cloud data | |
| CN108089572A (en) | For the algorithm and infrastructure of steady and effective vehicle location | |
| CN108271408A (en) | Use passive and actively measurement generation scene three-dimensional map | |
| CN109859260A (en) | Determine the method, apparatus and computer readable storage medium of parking stall position | |
| CN106500700A (en) | A kind of multiple mobile robot's cooperation air navigation aid and system | |
| CN112539749B (en) | Robot navigation method, robot, terminal device, and storage medium | |
| CN109814564A (en) | Detection, barrier-avoiding method, electronic equipment and the storage medium of target object | |
| CN106458126B (en) | Drive assistance device | |
| CN110119138A (en) | For the method for self-locating of automatic driving vehicle, system and machine readable media | |
| CN110095769A (en) | A kind of method for detecting parking stalls, device and electronic equipment | |
| CN112146682B (en) | Sensor calibration method and device for intelligent automobile, electronic equipment and medium | |
| CN111947644B (en) | Outdoor mobile robot positioning method and system and electronic equipment thereof | |
| CN104724121B (en) | The device and method in the traveling field of vehicle for identification | |
| CN107782304A (en) | The localization method and device of mobile robot, mobile robot and storage medium | |
| JP2023534795A (en) | Automatic return charging method, device, storage medium, charging base and system | |
| CN114639085A (en) | Traffic signal lamp identification method and device, computer equipment and storage medium | |
| KR102217422B1 (en) | Driving license test processing device | |
| KR20190081334A (en) | Method for tracking moving trajectory based on complex positioning and apparatus thereof | |
| CN113768419B (en) | Method and device for determining sweeping direction of sweeper and sweeper | |
| CN110110678A (en) | Determination method and apparatus, storage medium and the electronic device of road boundary | |
| CN109637148A (en) | Vehicle-mounted whistle monitoring system, method, storage medium and equipment | |
| CN109544983A (en) | Appraisal procedure, device and the electronic equipment of parking space information data |
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 |