CN103901890B - Outdoor automatic walking device based on family courtyard and system and method for controlling outdoor automatic walking device based on family courtyard - Google Patents
Outdoor automatic walking device based on family courtyard and system and method for controlling outdoor automatic walking device based on family courtyard Download PDFInfo
- Publication number
- CN103901890B CN103901890B CN201410140724.6A CN201410140724A CN103901890B CN 103901890 B CN103901890 B CN 103901890B CN 201410140724 A CN201410140724 A CN 201410140724A CN 103901890 B CN103901890 B CN 103901890B
- Authority
- CN
- China
- Prior art keywords
- image
- travelling device
- automatic travelling
- walking
- automatic
- 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
Landscapes
- Manipulator (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides an outdoor automatic walking device based on a family courtyard. The outdoor automatic walking device comprises a shell and a walking module, and the walking module is installed on the shell. The outdoor automatic walking device further comprises an image collecting module and a main control module, the image collecting module is installed on the shell and used for continuously collecting images on the working surface when the automatic walking device walks on the working surface, and the main control module is installed in the shell, respectively connected with the walking module and the image collecting module, and used for continuously determining feature regions from the collected first images, recognizing the feature regions in the second images collected after the first images, and calculating and recording position change data and posture change data of the automatic walking device according to geometric deformation and displacement of the feature regions. The main control module is further used for calculating to obtain a walking track of the automatic walking device according to the recorded position change data and the recorded posture change data. The outdoor automatic walking device can be effectively controlled. The invention further provides a system and method for controlling the outdoor automatic walking device.
Description
Technical field
The present invention relates to automatic control technology field, more particularly to a kind of outdoor automatically walk dress based on family's garden
Put and its control system and method.
Background technology
With the continuous progress of computer technology and artificial intelligence technology, the family's garden similar to intelligent robot is outdoor
Mobile robot has begun to the life for coming into people slowly.Current many scientific & technical corporation develop automatic dust catcher simultaneously
Market has been put into.This usual compact of automatic dust catcher, without manual control, just without throwing again after once setting
Enter energy management, housework that is user is uninteresting from cleaning, lawn maintenance etc. and wasting time and energy is freed in working, therefore suffered from
Greatly welcome.
Garden outdoor moving robot of family is controlled at present, there are following methods:1)Flight path based on encoder
Predication method:The basic demand of scheme is non-slip wheel, and ground even, the number of turns that so can be just rotated according to wheel come
Calculated, but for automatic mower, skidding cannot fully ensure that with flat, and this will cause that accumulated error arrives greatly nothing
Method receives;2)Absolute fix based on many base stations:Basic scheme is to set certain transmitter in region corner, such as ultrasonic, infrared,
Electromagnetic radio frequency etc., is directly positioned by the principle for being similar to GPS, has the advantages that high precision, for automatic mower,
Ultrasonic signal can by plant multiple reflections, it is infrared cannot be through plant and by sunlight interference, electromagnetism cost superelevation;3)Track formula is determined
Position:It needs to lay the underground track of comparatively dense, is not applied to substantially for automatic mower.
Therefore there are various defects in traditional outdoor moving robot control method, can not effectively control outdoor moving machine
The movement of device people is, it is necessary to improve.
The content of the invention
Based on this, it is necessary to regarding to the issue above, there is provided a kind of open air based on family's garden that can effectively control is automatic
Running gear and its control system and method.
A kind of outdoor automatic travelling device based on family's garden, including:Housing and walking module, the walking module peace
Loaded on the housing, also include:
The image capture module on the housing is installed on, for being walked on the work surface when the automatic travelling device
When, the image on continuous acquisition working surface;
The main control module in the housing is installed on, is connected respectively with the walking module and described image acquisition module
Connect, determine characteristic area from the first image of collection for continuously performing, the second figure gathered after described first image
The characteristic area is recognized as in, the geometry deformation and displacement according to the characteristic area are calculated and record the automatically walk
The change in location data and attitudes vibration data of device;The main control module is additionally operable to according to the change in location for having recorded
Data and attitudes vibration data are calculated the run trace of the automatic travelling device.
In one embodiment, during the image that described image acquisition module is used on continuous acquisition working surface, worksheet
The size of pickup area is more than or equal to 100 square centimeters on face.
In one embodiment, described image acquisition module is located at the side near working surface of housing, gathers direction
Towards working surface, and the distance between described image acquisition module and working surface are more than or equal to 3 centimetres.
In one embodiment, described first image and the image that second image is the collection of described image acquisition module
The adjacent image of middle acquisition time.
In one embodiment, automatic travelling device also includes the sensor being installed in the housing, in collection
The location parameter and/or kinematic parameter of the automatic travelling device are synchronously obtained during image;
The main control module is additionally operable to according to the location parameter and/or kinematic parameter, and the institute's rheme for having recorded
Put delta data and attitudes vibration data are calculated the run trace of the automatic travelling device.
In one embodiment, the main control module be additionally operable to detection collection image in whether comprising preset boundary
Image, if then automatic travelling device described in the image correction according to the image comprising preset boundary is detected comprising pre- from previous
If the run trace at the moment of the image of the image on border to current time.
In one embodiment, the main control module is additionally operable to the image detection preset boundary according to collection, controls institute
The run trace that automatic travelling device is walked one week along the preset boundary and records walking one week is stated, according to the walking row of a week
Walk track and determine boundary profile;Or,
The main control module is additionally operable to control under manual control the automatic travelling device along preset boundary walking one
Week, the run trace of record walking one week determines boundary profile according to the walking run trace of a week.
In one embodiment, the main control module is additionally operable to according to the boundary profile determination plan walking path,
Record the actual walking path of the automatic travelling device, according to actual walking path determine the automatic travelling device relative to
The relative position of the boundary profile, the automatic travelling device is controlled according to the plan walking road according to the relative position
Walk in footpath.
A kind of automatic travelling device control system, including any of the above-described embodiment the automatic row in open air based on family's garden
Walking apparatus;Also include stop device, for being stopped and for the automatic travelling device provides energy for the automatic travelling device.
A kind of outdoor automatic travelling device control method based on family's garden, the automatic travelling device includes:Housing
And walking module, the walking module is installed on the housing, and the automatic travelling device also includes:It is installed on the housing
On image capture module;Methods described includes:
When the automatic travelling device is walked on the work surface, worked by described image acquisition module continuous acquisition
Image on surface;
Determine characteristic area from the first image of collection, recognized in the second image gathered after described first image
The characteristic area;
Geometry deformation and displacement according to the characteristic area are calculated and record the position change of the automatic travelling device
Change data and attitudes vibration data;
Described in change in location data and attitudes vibration data according to the automatic travelling device for having recorded are calculated
The run trace of automatic travelling device.
In one embodiment, the automatic travelling device also includes the sensor being installed in the housing;The side
Method also includes:
While image is gathered, the location parameter of the automatic travelling device is synchronously sensed by the sensor
And/or kinematic parameter;
The change in location data and attitudes vibration data of the automatic travelling device that the basis has been recorded are calculated
The run trace of the automatic travelling device, including:
According to the location parameter and/or kinematic parameter, and the change in location data that have recorded and attitudes vibration
Data are calculated the run trace of the automatic travelling device.
In one embodiment, methods described also includes:
Whether the image of preset boundary is included in the image of detection collection, if then according to the image comprising preset boundary
Moment to current time of the automatic travelling device described in image correction from the previous image for detecting the image comprising preset boundary
Run trace.
In one embodiment, methods described also includes:
According to the image detection preset boundary of collection, the automatic travelling device is controlled to be walked one week along the preset boundary
And the run trace walked a week is recorded, boundary profile is determined according to the walking run trace of a week;Or,
Control the automatic travelling device to be walked one week along preset boundary under manual control, and record the row of walking one week
Track is walked, boundary profile is determined according to the walking run trace of a week.
In one embodiment, methods described also includes:
Plan walking path is determined according to the boundary profile;
Record the actual walking path of the automatic travelling device;
Relative position of the automatic travelling device relative to the boundary profile is determined according to actual walking path;
The automatic travelling device is controlled to be walked according to the plan walking path according to the relative position.
The above-mentioned outdoor automatic travelling device based on family's garden, automatic travelling device control system and method, by than
Displacement and geometric deformation to characteristic area in multiple images are so as to converse the change in location data and appearance of automatic travelling device
State delta data, and then realize the self-positioning of automatic travelling device and obtain run trace, scheme is reliable, low cost, Neng Gouzhun
Really, the walking of automatic travelling device is efficiently controlled.
Brief description of the drawings
Fig. 1 is the structural representation of automatic travelling device control system in one embodiment;
Fig. 2 is the structural representation of the simplification of automatic travelling device in one embodiment;
Fig. 3 is the part sectioned view of the structural representation of the simplification of automatic travelling device in one embodiment;
Fig. 4 is adopted to determine characteristic area from the first image of collection in one embodiment after described first image
The schematic diagram of the process of the characteristic area is recognized in second image of collection;
Fig. 5 is filled to calculate the automatically walk according to the geometry deformation of the characteristic area and displacement in one embodiment
The change in location data and the schematic diagram of the process of attitudes vibration data put;
Fig. 6 is the schematic flow sheet of automatic travelling device control method in one embodiment;
Fig. 7 is the schematic flow sheet of automatic travelling device control method in another embodiment.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
As shown in figure 1, in one embodiment, there is provided a kind of outdoor automatic travelling device control based on family's garden
System, including automatic travelling device 102 and stop for automatic travelling device 102 and be the supplement energy of automatic travelling device 102
Stop device 104.The surface of the walking of automatic travelling device 102 is its working surface.In the present embodiment, working surface can be wrapped
Working region 106a and non-active area 106b is included, the boundary line of working region 106a and non-active area 106b forms default side
Boundary 106, working region 106a and non-active area 106b are preferably formed with significant difference, and preset boundary 106 is used to limit automatically walk
The scope of activities of device 102.Preset boundary 106 has identifiability.Stop device 104 is arranged on preset boundary 106.Automatically
Running gear 102 is referred to as robot.
The concrete structure of automatic travelling device 102 is illustrated with reference to Fig. 2 and Fig. 3.Automatic travelling device 102 has housing
102a, walking module, image capture module 102c, sensor 102d and main control module(Not shown in figure).Walking module and
Image capture module 102c is installed on housing 102a, and sensor 102d and main control module are installed in housing 102a.Automatically
Running gear 102 when walking, image capture module 102c and sensor 102d relative to housing 102a remains stationary states, and
The walking module contact working surface of automatic travelling device 102, and housing 102a, image capture module 102c, sensor 102d
Working surface is not contacted with main control module.Housing 102a acts the modules that are connected, it is also possible to pacify for protecting
Modules loaded on automatic travelling device 102.Main control module and walking module, image capture module 102c and sensor
102d is connected respectively.
It is understood that automatic travelling device 102 also includes the energy module being placed in housing 102a(Do not show in figure
Go out), energy module is connected respectively with walking module, image capture module 102c, sensor 102d and main control module, for for
Energy needed for these module offer work.Wherein, energy module can provide module for the energy based on fuel, and fuel can be with
It is gasoline or diesel oil etc..Energy module can also be battery bag.In one embodiment, energy module is rechargeable battery pack;
When automatic travelling device 102 works, rechargeable battery pack discharges electric energy to maintain automatic travelling device 102 to work;When automatic
When running gear 102 does not work, rechargeable battery pack may be coupled to external power source with electric energy supplement.In one embodiment,
When automatic travelling device 102 detects rechargeable battery pack not enough power supply, automatic travelling device 102 can Automatic-searching stop dress
Put 104 electric energy supplements.
Automatic travelling device 102 can also include operational module in one embodiment wherein, to perform specific work.
Such as operational module can be cutting module, including cutting part and the cutting motor of driving cutting part for mowing, this
Automatic travelling device 102 turns into hay mover in embodiment.In other embodiments, can also be installed for automatic travelling device 102
Operational module with other functions, makes automatic travelling device 102 turn into trimmer, automatic cleaner etc..
Walking module is used for the modules walking for driving housing 102a and its being installed, so as to realize automatic travelling device
102 walking.In one embodiment, walking module includes wheel group 102b and the running motor for drive wheel group 102b(Figure
Not shown in).Wheel group 102b can have various methods to set up, and the quantity of general wheel group 102b is multiple, such as at least 3.It is many
Individual wheel group 102b, the symmetrically arranged multiple wheel group 102b of direction of travel especially relative to automatic travelling device 102 can be with
Different rotational speed, so that automatic travelling device 102 can be turned to.It is understood that walking module can also be
Other can realize the module of walking, such as mechanical arm or crawler belt etc., will not be repeated here.
Image capture module 102c is installed on automatic travelling device 102, for when automatic travelling device 102 is in worksheet
When being walked on face, according to the image on default sampling time interval continuous acquisition working surface.Between the default sampling time here
Every at least ensureing that 2 adjacent images of acquisition time have overlap.The scope of image capture module 102c collection images is image
The pickup area of acquisition module 102c.In one embodiment, as shown in figure 3, image capture module 102c is located at housing 102a
The side near working surface, and its collection direction is towards working surface, in order to gather the bottom of automatic travelling device 102,
The image of image capture module 102c lower sections, particularly underface.The pattern distortion that this kind of mode gathers acquisition is small, is easy to follow-up
Treatment.In Fig. 3 300 represent this kind in the case of image capture module 102c pickup area side view.In other embodiments,
Image capture module 102c can also be located at optional position on housing 102a, only need to ensure that image capture module 102c can be gathered
Image on to working surface, such as image capture module 102c can be located at opposite in the one of working surface on housing 102a
Side or the side towards the direction of travel of automatic travelling device 102.
In one embodiment, when image capture module 102c is located at the side near working surface of housing 102a, and
When its collection direction is towards working surface, the distance between image capture module 102c and working surface are more than or equal to 3 centimetres,
And/or the size of pickup area is more than or equal to 100 square centimeters on working surface.Preferably image capture module 102c and work
Make the distance between surface more than or equal to 5 centimetres, and/or the size of pickup area is flat more than or equal to 200 on working surface
Square centimetre.So set because working surface microcosmic point image change acutely, environment is unpredictable, such as mow
For machine, meadow is in microcosmic point(The image of i.e. several sqs)Landform is relatively uneven, image change violent,
Environment is unpredictable, so pickup area is more larger to be more suitable for subsequent treatment, to improve the standard controlled automatic travelling device 102
True property.
Main control module is used to control walking and the modules of automatic travelling device 102 of automatic travelling device 102
Normal work.Main control module, is connected respectively with walking module and image capture module 102c, for continuously performing from collection
Determine characteristic area in first image, identification feature region in the second image gathered after the first image, according to characteristic area
The geometry deformation in domain and displacement are calculated and record the change in location data and attitudes vibration data of automatic travelling device;Main control
Module is additionally operable to be calculated according to the change in location data and attitudes vibration data for having recorded the walking rail of automatic travelling device
Mark.
Specifically, upon actuation, image capture module 102c is used for according between the default sampling time automatic travelling device 102
Image on continuous acquisition working surface, and the image transmitting that will be gathered is to main control module.So main control module can be received
To multiple images.
Reference picture 4, main control module is used for the one of image 402 that will be gathered as the first image, first image
On the basis of image, used as the second image, the second image is contrast images to the image 404 gathered after the first image 402;
This feature region 402a is identified in selected part region as characteristic area 402a in the second image 404 in one image 402.
Following main control module is used to can be used for again using image 404 as the first image, by one of collection after the first image 404
Image 406 is used as the second image;Selected part region is used as characteristic area 404a in the first image 404, in the second image 406
In identify this feature region 404a.Next when using image 406 as the first image, the selection portion in the first image 406
Subregion is so continued for performing as characteristic area 406a.The image that can certainly be gathered is used as the first figure
Picture, using another image after the image as after the second image, be different from the image that can be gathered previously as
Other images of first image and the second image as the first image, then using an image after the image as the second figure
Picture.
Wherein characteristic area(402a, 404a or 406a)May be located at the first image(402a is corresponding 402,404a correspondences
404,406a corresponding 406)Middle position, so no matter the whichaway of automatic travelling device 102 movement, can use up
Can guarantee that the characteristic area in the second image will not be lacked.In other embodiments, characteristic area can also be located at the first figure
The other positions of picture, such as, it is determined that during the direction of travel substantially of automatic travelling device 102, the chosen position of characteristic area can be with
Slightly some distances are moved backward along direction of travel.
Main control module is used for behind selected characteristic region, is processed this feature region to extract and recorded this feature
Some characteristics of image in region, extracting feature can include but is not limited to SIFT by the way of(Scale invariant feature is changed)、
SURF(Speeded up robust features, fast robust feature)、DAISY(DAISY is extracted towards dense characteristic
Can quickly calculate local image characteristics description son)、Haar(Rectangular characteristic)、WLD(Weber local feature)、LBP(Local
Binary Patterns, local binary patterns)、ORB(A kind of binary feature description)、BRIEF(A kind of Feature Descriptor)、
LDA-hash(A kind of Feature Descriptor)、MSER(Maximally Stable External Regions, provincial characteristics is carried
Take)、HOG(Histogram of Oriented Gradient, histograms of oriented gradients), gray value, color histogram, gray scale
Histogram, Gray Moment etc..Characteristic area can be registered as one group of position coordinates scope in the coordinate system of pickup area.
In one embodiment, when being gathered in the first image and the image that the second image is image capture module 102c collections
Between adjacent image.In the present embodiment, when automatic travelling device 102 when walking, image capture module 102c is adopted according to default
Sample time interval continuous acquisition image, main control module using an image as after the first image, by what is gathered after the image
The adjacent next image of acquisition time is used as the second image.The common ground of such first image and the second image is most, then
The possibility of characteristic area missing is minimum in second image, the registration accuracy of change in location also highest.But in other embodiments
In, there may be the image of other collections between the first image and the second image, that is, there is acquisition time Jie in the image for gathering
Image between the acquisition time of the first image and the acquisition time of the second image, only need to ensure still to be included in the second image
All or part of characteristic area.
Main control module is used for the identification feature region in the second image, and specifically, main control module is used for according to previously
The characteristics of image of the characteristic area of record, finds the part with the Image Feature Matching of record, the portion for finding in the second image
It is exactly the characteristic area for identifying to divide.
Illustrate main control module how for being calculated according to the geometry deformation of characteristic area and displacement below in conjunction with Fig. 5
The change in location data and attitudes vibration data of automatic travelling device 102.
After characteristic area in characteristic area and the second image that main control module is used in the first image determines, root
Result is matched according to the feature of the first image and the second image, image capture module 102c is in the first image in calculating three dimensions
Acquisition time and the transformation matrix at the two moment of the acquisition time of the second image, so as to extrapolate image capture module 102c's
Change in location data and attitudes vibration data.Relative to housing 102a it is static due to image capture module 102c, image is adopted
The change in location data and posture changing data of collection module 102c can just be converted into the change in location number of automatic travelling device 102
According to attitudes vibration data.The change in location data of wherein automatic travelling device 102 represent automatic travelling device 102 in worksheet
The location of on face.The attitudes vibration data of automatic travelling device 102 refer to represent the turning because of itself of automatic travelling device 102
To and/or hypsography caused by automatic travelling device 102 attitudes vibration data.
In one embodiment, the sensor 102d being installed in housing 102a is used in image capture module 102c collections
The location parameter and/or kinematic parameter of automatic travelling device 102 are synchronously obtained during image.Main control module is additionally operable to according to position
Parameter and/or kinematic parameter, and change in location data and attitudes vibration data are calculated the walking of automatic travelling device 102
Track.
Sensor 102d includes but is not limited to angular-rate sensor, differential GPS(Global positioning system)Sensor or magnetic are passed
Sensor etc..Location parameter refers to the information for representing the present position of automatic travelling device 102, such as longitude and latitude;Kinematic parameter refers to
Represent the information of the motion state of automatic travelling device 102, such as angular speed, acceleration, linear velocity etc..Main control module is additionally operable to
With reference to location parameter and/or kinematic parameter that sensor 102d is gathered, characteristic area is calculated in the first figure using filtering algorithm
Displacement and geometric deformation in picture and the second image.Wherein filtering algorithm can be but not limited to:Kalman filtering algorithm, extension
Kalman filtering algorithm, particle filter algorithm etc..Specifically, main control module is used for according in the first image and the second image
Feature matches the location parameter and/or kinematic parameter of result and sensor collection, calculates image capture module in three dimensions
102c the first image acquisition time and the transformation matrix at the two moment of the acquisition time of the second image, so as to extrapolate figure
As the change in location data and attitudes vibration data of acquisition module 102c, and then obtain the change in location of automatic travelling device 102
Data and attitudes vibration data.
Main control module is used for the change in location data and attitudes vibration data of constantly record automatic travelling device 102, and
Change in location data and attitudes vibration data according to cumulative record are calculated the run trace of automatic travelling device 102.From
Automatic travelling device 102 starts and starts, with the change in location data of accumulation and increasing for attitudes vibration data, run trace
It is corresponding to increase.Certainly, main control module can also only record the run trace of limit length and the run trace before erasing
The run trace of automatic travelling device 102 in data, or time period that only record part needs or spatial dimension, these can be with
Needed according to real work and set or adjustment.
In one embodiment, main control module be additionally operable to detection collection image in whether comprising preset boundary 106
Image, if then the image correction automatic travelling device according to the image comprising preset boundary 106 is detected comprising pre- from previous
If the run trace at the moment of the image of the image on border to current time.
In the present embodiment, while the image by image capture module 102c collecting works surface, synchronously carry out pre-
If the detection on border 106.Specifically, main control module is used to realize the function of following a, b and c:
Region to be detected in a, the image that will be collected by image capture module 102c is using sliding window cutting
Multiple standard-sized images.Region to be detected can be the subregion of entire image, or image, preferably image
The image-region of the middle characteristic area for removing center.The image of adjacent modular size can have overlapping region, it is also possible to without weight
, depending on the performance of main control module, preferably there is overlapping region in folded region.
In b, the grader trained to each standard-sized image zooming-out feature, feeding.Grader can be used
The grader that the image pattern training of the image pattern of the image comprising preset boundary and the image not comprising preset boundary is obtained.
Image comprising preset boundary can refer to the local image comprising preset boundary.The feature wherein extracted can be Manual definition
, or automatic training, depending on training method.Wherein, can be but not limited to color straight for the feature of Manual definition
Fang Tu, LBP, dynamic texture, symbiosis square, HOG, Haar-like(Rectangular characteristic)Deng preferably color histogram and Haar-
Like features, because for example hay mover, working surface is generally meadow, the bottom surface outside meadow is non-active area.From
Feature usable intelligent characteristic back-and-forth method or the feature learning algorithm of dynamic training, algorithm can be but not limited to:Adaboost is calculated
Self-editing ink recorder, Boltzmann's learning machine, convolutional neural networks, deep Belief network in method, deep learning etc..
C, the classification results exported to sending into the grader for training, are merged, finally using evidence theoretical algorithm
Export the testing result of preset boundary 106.
When the collection image of the image comprising preset boundary 106 is detected, main control module is used to fill automatically walk
102 run trace from moment to the current time of the previous image for detecting the image comprising preset boundary are put to be modified.
Specifically, main control module is used to be calculated the error of the position with preset boundary 106 of automatic travelling device 102, using by mistake
Difference back-propagation algorithm amendment automatic travelling device 102 is since the previous walking touched preset boundary 106 to current time
Track.Run trace between the adjacent moment for detecting preset boundary twice may not be optimum trajectory, such as automatically walk
From some ridings to another point, efficiency is less than from any along straight line to another point device 102, now needs to this section of rail
Mark is modified so as to optimize, so as to obtain the walking of automatic travelling device 102 and work more efficient.
In one embodiment, the default sampling time interval of image capture module 102c collections image can be according to automatic row
The speed of travel of walking apparatus 102 is determined.After first time collection image terminates, when characteristic area will leave acquisition range,
Second collection image is needed, the first time collection image and the time interval that should gather image for second are the default sampling time
The maximum at interval.
In one embodiment, automatic travelling device 102 have boundary profile delimit function, including automatic mode and manually
Pattern.In automatic mode, main control module is used for the image detection preset boundary 106 according to collection, control automatically walk dress
The run trace that walking one week is walked one week and recorded along preset boundary 106 is put, side is determined according to the walking run trace of a week
Boundary's profile.Specifically, image capture module 102c and sensor 102d is used for continuous collecting signal and sends main control module to,
Whether main control module is used for moving to preset boundary 106 according to the signal automatic decision automatic travelling device 102 for receiving
Edge, if then control automatic travelling device 102 is walked along preset boundary 106, until starting point is returned to, along the row of preset boundary 106
The run trace of walking one week is walked one week and recorded, the run trace walked a week is set to boundary profile.In an implementation
In example, if automatic travelling device 102 is hay mover, main control module is used for what basis was gathered by image capture module 102c
Image carries out border detection, judges whether automatic travelling device 102 moves to meadow boundary edge, if then controlling automatically walk
Device is walked along meadow border, until returning to original position when automatic travelling device 102 sets out.Simultaneously in automatically walk dress
Put and record run trace in 102 walking processes, the run trace of record is then recorded as boundary profile.
In a manual mode, main control module is used to control under manual control automatic travelling device along preset boundary 106
Walking one week, the run trace of record walking one week determines boundary profile according to the walking run trace of a week.Specifically, certainly
Dynamic running gear 102 is used to since default starting point, be walked one week along preset boundary 106, and continues during walking
Record run trace, the run trace of record is then recorded as boundary profile.Default starting point can be stop device
104, the mode of the walking of automatic travelling device 102 can manually be led, and such as main control module is used for the remote control according to remote control
Direction of travel etc. of signal control automatic travelling device 102, or by the artificial road sign such as electronic edge boundary line for setting or
Person's indication road sign etc. is walked.The recording mode under the mode such as automatic mode of the run trace of automatic travelling device 102 is recorded, no
Repeat again.
Profile of delimiing a boundary line can be that the work of automatic travelling device 102 bring great advantage, for example, from preset boundary
After known location on 106 enters working region 106a, due to follow-up run trace be by lasting record, it is so automatic
Running gear 102 just understand that the position and worked region of any moment its own, and then ensure that certainly
Dynamic running gear 102 will not leave working region 106a, it is also possible to next step action intelligently be selected, such as to which area row
Enter and work.In one embodiment, main control module is used to delimit multiple working regions according to boundary profile, and controls certainly
Dynamic running gear 102 is walked and is worked in each working region respectively.
In one embodiment, main control module is additionally operable to according to boundary profile determination plan walking path, and record is automatic
The actual walking path of running gear, relative position of the automatic travelling device relative to boundary profile is determined according to actual walking path
Put, automatic travelling device walking path walking according to schedule is controlled according to the relative position.
In the present embodiment, when automatic travelling device 102 is started working, main control module is used to be set according to boundary profile
One plan walking path, the path is optimization, such that it is able to avoid repeating to be worked in portion, by rational path row
Walking can save travel time.Main control module is used to control automatic travelling device 102 to walk after setting plan walking path, and
The actual walking path of real time record automatic travelling device 102, and according to actual walking path, or according to actual walking path
Binding site parameter and/or kinematic parameter calculate relative position of the automatic travelling device 102 relative to boundary profile, and this is relative
Position can represent particular location of the current automatic travelling device 102 in the boundary profile map formed by boundary profile.
Then can be according to the relative position amendment direction of travel of automatic travelling device 102, to keep automatic travelling device 102 according to schedule
Walking path is walked.In one embodiment, main control module can be used to carry out actual walking path with plan walking path
Contrast, illustrates that now actual walking path there occurs skew relative to plan walking path if inconsistent, and main control module can
For controlling the reserve migration when walking of automatic travelling device 102, to offset skew, so as to keep automatic travelling device 102 to press
According to plan walking path walking.
Above-mentioned automatic travelling device 102, by compare characteristic area in multiple images displacement and geometric deformation so as to change
The change in location data and attitudes vibration data of automatic travelling device are calculated, and then is realized the self-positioning of automatic travelling device and is obtained
To run trace, scheme is reliable, low cost, can accurately and efficiently control the walking of automatic travelling device.
In one embodiment, there is provided a kind of outdoor automatic travelling device control method based on family's garden, it is used for
Control the automatic travelling device of as above any embodiment.Wherein, the automatic travelling device includes:Housing, walking module and image
Acquisition module;Walking module is installed on housing, and image capture module is installed on housing;As shown in fig. 6, the method include with
Lower step:
Step 602, when automatic travelling device is walked on the work surface, is worked by image capture module continuous acquisition
Image on surface.
Specifically, when automatic travelling device is walked on the work surface, by image capture module according to default sampling
Image on time interval continuous acquisition working surface.Here default sampling time interval will at least ensure that acquisition time is adjacent
2 images have overlap.In one embodiment, image capture module can be located at the side near working surface of housing, and
It gathers direction towards working surface, under gathering automatic travelling device bottom, image capture module lower section, being particularly just
The image of side.The pattern distortion that this kind of mode gathers acquisition is small, is easy to subsequent treatment.In other embodiments, IMAQ mould
Block can also be located at optional position on housing, only need to ensure that image capture module can collect the image on working surface i.e.
Can, such as image capture module can be located on housing opposite in the side of working surface or towards automatic travelling device direction of travel
Side.
In one embodiment, when image capture module is located at the side near working surface of housing, and its collection side
During to towards working surface, the distance between image capture module and working surface are more than or equal to 3 centimetres, and/or worksheet
The size of pickup area is more than or equal to 100 square centimeters on face.Preferably between image capture module and working surface away from
From more than or equal to 5 centimetres, and/or on working surface, the size of pickup area is more than or equal to 200 square centimeters.So set
Because working surface is violent in microcosmic point image change, environment is unpredictable, such as hay mover, meadow is micro-
Sight aspect(The image of i.e. several sqs)Landform is relatively uneven, image change violent, and environment is unpredictable, institute
It is more suitable for subsequent treatment so that pickup area is more larger, to improve the accuracy controlled automatic travelling device.
Step 604, determines characteristic area, in the second image gathered after the first image from the first image of collection
Identification feature region.
Specifically, will gather image in one of image as the first image, image on the basis of first image,
Used as the second image, the second image is contrast images to the image gathered after first image.Selected part area in first image
This feature region is identified in the second image as characteristic area in domain.In following cycle, can be using second image as rear
The first image in continuous circulation, then using another image in following cycle as the second image.Can certainly be by collection
One image as the first image, using another image after the image as after the second image, the figure that can be gathered
It is different from previously as other images of the first image and the second image as the first image as in, then by after the image
Individual image is used as the second image.
Wherein characteristic area may be located at the middle position of the first image, so no matter automatic travelling device whichaway
It is mobile, can as far as possible ensure that the characteristic area in the second image will not be lacked.In other embodiments, characteristic area also may be used
With positioned at the other positions of the first image, such as it is determined that during automatic travelling device direction of travel substantially, the choosing of characteristic area
Fetch bit is put slightly can move backward some distances along direction of travel.
After characteristic area is extracted, some of this feature region need to be processed this feature region to extract and recorded
Characteristics of image, extract feature can be included but is not limited to by the way of SIFT, SURF, DAISY, Haar, WLD, LBP, ORB,
BRIEF, LDA-hash, MSER, HOG, gray value, color histogram, grey level histogram, Gray Moment etc..Characteristic area can be remembered
Record one group of position coordinates scope in the coordinate system for pickup area.
In one embodiment, the first image and the second image are acquisition time phase in the image that image capture module is gathered
Adjacent image.In the present embodiment, when automatic travelling device when walking, image capture module connects according to default sampling time interval
Continuous collection image, main control module is using an image as after the first image, and the acquisition time that will be gathered after the image is adjacent
Next image as the second image.The common ground of such first image and the second image is at most, then special in the second image
The possibility for levying region missing is minimum, the registration accuracy of change in location also highest.But in other embodiments, the first image and
There may be the image of other collections between second image, that is, there is acquisition time adopting between the first image in the image for gathering
Image between the acquisition time of collection time and the second image, need to only ensure in the second image still comprising all or part of spy
Levy region.
In the second image during identification feature region, the characteristics of image of the characteristic area according to precedence record, in the second figure
The part with the Image Feature Matching of record is found as in, the part found is exactly the characteristic area for identifying.
Step 606, geometry deformation and displacement according to characteristic area are calculated and record the position change of automatic travelling device
Change data and attitudes vibration data.
After characteristic area in characteristic area and the second image in the first image determines, according to the first image and the
Two images feature pairing result, calculate three dimensions in the first image acquisition time and the second image acquisition time this
Two transformation matrixs at moment, so as to extrapolate the change in location data and attitudes vibration data of image capture module.Due to figure
Relative to housing it is static as acquisition module, the change in location data and posture changing data of image capture module can just turn
Turn to the change in location data and attitudes vibration data of automatic travelling device.The wherein change in location tables of data of automatic travelling device
Show automatic travelling device location on the work surface.The attitudes vibration data of automatic travelling device refer to represent automatic row
The data of the attitudes vibration of automatic travelling device of the walking apparatus caused by the steering of itself and/or hypsography.
Step 608, change in location data and attitudes vibration data according to the automatic travelling device for having recorded are calculated
The run trace of automatic travelling device.
The change in location data and attitudes vibration data of automatic travelling device are constantly recorded, and according to the position of cumulative record
Delta data and attitudes vibration data are calculated the run trace of automatic travelling device.Since automatic travelling device starts,
With the change in location data of accumulation and increasing for attitudes vibration data, run trace also increases accordingly.It is of course also possible to only
Record limit length run trace and the run trace data before erasing, or time period that only record part needs or sky
Between in the range of automatic travelling device run trace, these can according to real work need and set or adjust.
Above-mentioned automatic travelling device control method, by compare characteristic area in multiple images displacement and geometric deformation from
And the change in location data and attitudes vibration data of automatic travelling device are conversed, and then realize the self-positioning of automatic travelling device
With obtain run trace, scheme is reliable, low cost, can accurately and efficiently control the walking of automatic travelling device.
In one embodiment, automatic travelling device also includes the sensor being installed in housing.The automatic travelling device
Control method also includes:Gather image while, synchronously sensed by sensor automatic travelling device location parameter and/
Or kinematic parameter.Then step 608 includes:According to location parameter and/or kinematic parameter, and change in location data and attitudes vibration
Data are calculated the run trace of automatic travelling device.
Sensor includes but is not limited to angular-rate sensor, differential GPS sensor or Magnetic Sensor etc..With reference to sensor institute
The location parameter and/or kinematic parameter of collection, using filtering algorithm calculating characteristic area in the first image and the second image
Displacement and geometric deformation.Wherein filtering algorithm can be but not limited to:Kalman filtering algorithm, expanded Kalman filtration algorithm,
Particle filter algorithm etc..Specifically, can be gathered according to the pairing result of the feature in the first image and the second image and sensor
Location parameter and/or kinematic parameter, acquisition time and second figure of the image capture module in the first image in calculating three dimensions
The transformation matrix at the two moment of the acquisition time of picture, so as to the change in location data and attitude of extrapolating image capture module become
Change data, and then obtain the change in location data and attitudes vibration data of automatic travelling device.
In one embodiment, the automatic travelling device control method also includes:Whether included in the image for detecting collection
The image of preset boundary, if then the image correction automatic travelling device according to the image comprising preset boundary is detected from previous
The run trace at the moment of the image of the image comprising preset boundary to current time.
In the present embodiment, while the image by image capture module c collecting works surface, default side is synchronously carried out
The detection on boundary, specifically, detection preset boundary the step of include step 1)~step 3):
Step 1), the region to be detected in the image that will be collected by image capture module is using sliding window cutting
Multiple standard-sized images.Region to be detected can be the subregion of entire image, or image, preferably image
The image-region of the middle characteristic area for removing center.The image of adjacent modular size can have overlapping region, it is also possible to without weight
, preferably there is overlapping region in folded region.
Step 2), in the grader trained to each standard-sized image zooming-out feature, feeding.Grader can be
What the image pattern training of the image pattern using the image comprising preset boundary and the image not comprising preset boundary was obtained divides
Class device.Image comprising preset boundary can refer to the local image comprising preset boundary.The feature wherein extracted can be people
It is work definition, or automatic training, depending on training method.Wherein, the feature of Manual definition can be but not limited to
Color histogram, LBP, dynamic texture, symbiosis square, HOG, Haar-like etc., preferably color histogram and Haar-like are special
Levy, because for example hay mover, working surface is generally meadow, the bottom surface outside meadow is non-active area.Automatic training
Feature intelligent characteristic back-and-forth method or feature learning algorithm can be used, algorithm can be but not limited to:Adaboost algorithm, depth
Self-editing ink recorder, Boltzmann's learning machine, convolutional neural networks, deep Belief network in study etc..
Step 3), the classification results exported to the grader that trains of feeding are merged using evidence theoretical algorithm,
Finally export the testing result of preset boundary.
When the collection image of the image comprising preset boundary is detected, automatic travelling device is included from previous detecting
The run trace at the moment of the image of the image of preset boundary to current time is modified.Specifically, it is calculated automatic row
The position of walking apparatus and the error of preset boundary, are touched using error backpropagation algorithm amendment automatic travelling device from previous
Preset boundary starts the run trace to current time.Run trace between the adjacent moment for detecting preset boundary twice can
Can not be optimum trajectory, such as from some ridings to another point, efficiency is less than from any along straight line automatic travelling device
To another point, now need to be modified so as to optimize this section of track so that automatic travelling device walking and
Work is more efficient.
In one embodiment, the default sampling time interval of image capture module collection image can be filled according to automatically walk
The speed of travel put is determined.After first time collection image terminates, when characteristic area will leave acquisition range, it is necessary to second
Secondary collection image, the first time gathers image and should the time interval of collection image be for the second time to preset sampling time interval most
Big value.
In one embodiment, the automatic travelling device control method also includes step:Image detection according to collection is pre-
If border, control automatic travelling device is walked one week along preset boundary and records the run trace of walking one week, according to walking one
The run trace in week determines boundary profile.
There is automatic travelling device boundary profile to delimit function, including automatic mode and manual mode.In automatic mode,
By image capture module and sensor continuous collecting signal, and according to the signal automatic decision automatic travelling device for collecting it is
The no edge for moving to preset boundary, if then control automatic travelling device is walked along preset boundary, until starting point is returned to, along pre-
If border is walked one week and records the run trace of walking one week, the run trace walked a week is set to boundary profile.
In one embodiment, if automatic travelling device is hay mover, side can be carried out according to the image gathered by image capture module
Boundary's detection, judges whether automatic travelling device moves to meadow boundary edge, if then control automatic travelling device is along meadow
Border is walked, until returning to original position when automatic travelling device sets out.Remember in automatic travelling device walking process simultaneously
Record run trace, is then recorded as boundary profile by the run trace of record.
In one embodiment, the automatic travelling device control method also includes step:Control under manual control automatic
Running gear is walked one week along preset boundary, and records the run trace of walking one week, true according to the walking run trace of a week
Determine boundary profile.
In a manual mode, control automatic travelling device is walked one week along preset boundary under manual control, record walking
The run trace of one week, boundary profile is determined according to the walking run trace of a week.Specifically, automatic travelling device is from default
Starting point starts, and is walked one week along preset boundary, and lasting record run trace during walking, the row that then will be recorded
Track record is walked for boundary profile.Default starting point can be stop device, and the mode of automatic travelling device walking can be people
Work is led, and such as automatic travelling device can control its direction of travel under the control of remote signal, or by manually setting
The road sign the put such as walking such as electronic edge boundary line or indication road sign.Record the mode such as automatic mold of automatic travelling device run trace
Recording mode under formula, repeats no more.
Profile of delimiing a boundary line can be that the work of automatic travelling device brings great advantage, for example, from preset boundary
Known location enter working region after, because follow-up run trace is by lasting record, such automatic travelling device
The position and worked region of any moment its own are just understand that, and then ensure that automatic travelling device not
Working region can be left, it is also possible to intelligently select next step action, such as be advanced to which region and worked.In a reality
Apply in example, multiple working regions can also be delimited according to boundary profile, and control automatic travelling device respectively in each workspace
Walked in domain and worked.
In one embodiment, the automatic travelling device control method also includes:Plan walking is determined according to boundary profile
Path;Record the actual walking path of automatic travelling device;Determine automatic travelling device relative to side according to actual walking path
The relative position of boundary's profile;Automatic travelling device walking path walking according to schedule is controlled according to the relative position.
In the present embodiment, when automatic travelling device is started working, a plan walking path is set according to boundary profile,
The path is optimization, such that it is able to avoid repeating to be worked in portion, travel time can be saved by the walking of rational path.
Setting plan walking path after control automatic travelling device walking, and real time record automatic travelling device actual walking road
Footpath, and relative position of the automatic travelling device relative to boundary profile is calculated according to actual walking path, and according to automatically walk
The relative position amendment direction of travel of device, to keep automatic travelling device, walking path is walked according to schedule.
With reference to Fig. 7, in another embodiment, there is provided a kind of automatic travelling device control method, comprise the following steps:
Step 702, when automatic travelling device is walked on the work surface, is worked by image capture module continuous acquisition
Image on surface.
Step 703 is performed when step 702 is performed, while image is gathered, is synchronously sensed by sensor automatic
The location parameter and/or kinematic parameter of running gear.
After step 702, the step of performing step 705, detection border.Specifically include:It is in the image for detecting collection
The no image comprising preset boundary, if then performing step 710.
Step 704, determines characteristic area, in the second image gathered after the first image from the first image of collection
Identification feature region.
Step 706, geometry deformation and displacement according to characteristic area are calculated and record the position change of automatic travelling device
Change data and attitudes vibration data.
Step 708, according to location parameter and/or kinematic parameter, and the change in location data that have recorded and attitudes vibration
Data are calculated the run trace of automatic travelling device.
Step 710, when the collection image of the image comprising preset boundary is detected, to automatic travelling device from previous inspection
The run trace for measuring moment to the current time of the image of the image comprising preset boundary is modified.
The circulation of 702~step 710 of above-mentioned steps is performed.
Embodiment described above only expresses several embodiments of the invention, and its description is more specific and detailed, but simultaneously
Therefore the limitation to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for one of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Shield scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (12)
1. a kind of outdoor automatic travelling device based on family's garden, including:Housing and walking module, the walking module are installed
In on the housing, it is characterised in that also include:
The image capture module on the housing is installed on, for when the automatic travelling device is walked on the work surface,
Image on continuous acquisition working surface;
The main control module in the housing is installed on, is connected respectively with the walking module and described image acquisition module, used
Determine characteristic area from the first image of collection in continuously performing, know in the second image gathered after described first image
Not described characteristic area, second image includes the characteristic area in all or part of described first image, according to institute
The geometry deformation and displacement for stating characteristic area are calculated and record change in location data and the attitude change of the automatic travelling device
Change data;The change in location data represent automatic travelling device location on the work surface;The attitude becomes
Change data and represent the automatic travelling device of the automatic travelling device caused by the steering of itself and/or hypsography
The data of attitudes vibration;
The main control module is additionally operable to be calculated institute according to the change in location data and attitudes vibration data that have recorded
State the run trace of automatic travelling device;
The region to be detected that the main control module is additionally operable in the image that will be collected by image capture module uses slip
Window cutting is multiple standard-sized images;The grader trained to each standard-sized image zooming-out feature, feeding
In;The classification results exported to sending into the grader for training, are merged using evidence theoretical algorithm, finally export default
The testing result on border;If detecting the image comprising preset boundary in the image of collection, according to the shadow comprising preset boundary
As image correction described in automatic travelling device from moment of the previous image for detecting the image comprising preset boundary to current
The run trace at moment, the preset boundary is used to limit the scope of activities of the automatic travelling device.
2. automatic travelling device according to claim 1, it is characterised in that described image acquisition module is used for continuous acquisition
During image on working surface, the size of pickup area is more than or equal to 100 square centimeters on working surface.
3. automatic travelling device according to claim 1, it is characterised in that described image acquisition module is located at leaning on for housing
The side of nearly working surface, collection direction is towards working surface, and the distance between described image acquisition module and working surface
More than or equal to 3 centimetres.
4. automatic travelling device according to claim 1, it is characterised in that described first image and second image are
The adjacent image of acquisition time in the image of described image acquisition module collection.
5. automatic travelling device according to claim 1, it is characterised in that the also sensing including being installed in the housing
Device, location parameter and/or kinematic parameter for synchronously obtaining the automatic travelling device when image is gathered;
The main control module is additionally operable to according to the location parameter and/or kinematic parameter, and the position for having recorded becomes
Change data and attitudes vibration data are calculated the run trace of the automatic travelling device.
6. automatic travelling device according to claim 1, it is characterised in that the main control module is additionally operable to according to collection
Image detection preset boundary, control the automatic travelling device to be walked one week along the preset boundary and recorded and walk one week
Run trace, boundary profile is determined according to the walking run trace of a week;Or,
The main control module is additionally operable to control the automatic travelling device to be walked one week along preset boundary under manual control, note
The run trace of record walking one week, boundary profile is determined according to the walking run trace of a week.
7. automatic travelling device according to claim 6, it is characterised in that the main control module is additionally operable to according to described
Boundary profile determines plan walking path, the actual walking path of the automatic travelling device is recorded, according to actual walking path
Determine relative position of the automatic travelling device relative to the boundary profile, it is described automatic according to relative position control
Running gear is walked according to the plan walking path.
8. a kind of outdoor automatic travelling device control system based on family's garden, it is characterised in that including such as claim 1-7
The outdoor automatic travelling device based on family's garden described in any one;Also include stop device, for supplying the automatic row
Walking apparatus are stopped and for the automatic travelling device provides energy.
9. a kind of outdoor automatic travelling device control method based on family's garden, the automatic travelling device includes:Housing and
Walking module, the walking module is installed on the housing, it is characterised in that the automatic travelling device also includes:Install
Image capture module on the housing;Methods described includes:
When the automatic travelling device is walked on the work surface, by described image acquisition module continuous acquisition working surface
On image;
Determine characteristic area from the first image of collection, recognized in the second image gathered after described first image described
Characteristic area;Comprising the characteristic area in all or part of described first image in second image;
Geometry deformation and displacement according to the characteristic area are calculated and record the change in location number of the automatic travelling device
According to attitudes vibration data;The change in location data represent automatic travelling device location on the work surface;
The attitudes vibration data represent that the automatic travelling device is described automatic caused by the steering of itself and/or hypsography
The data of the attitudes vibration of running gear;
Change in location data and attitudes vibration data according to the automatic travelling device for having recorded are calculated described automatic
The run trace of running gear;
Region to be detected in the image that will be collected by image capture module is multiple gauges using sliding window cutting
Very little image;In the grader trained to each standard-sized image zooming-out feature, feeding;The classification trained to feeding
Device and the classification results that export, are merged using evidence theoretical algorithm, finally export the testing result of preset boundary;If detection
The image of preset boundary is included in the image of collection, then the automatic row according to the image correction of the image comprising preset boundary
Walking apparatus are described default from the run trace at moment to the current time of the previous image for detecting the image comprising preset boundary
Border is used to limit the scope of activities of the automatic travelling device.
10. method according to claim 9, it is characterised in that the automatic travelling device also includes being installed on the shell
Sensor in body;Methods described also includes:
Gather image while, by the sensor synchronously sense the automatic travelling device location parameter and/or
Kinematic parameter;
The change in location data and attitudes vibration data of the automatic travelling device that the basis has been recorded are calculated described
The run trace of automatic travelling device, including:
According to the location parameter and/or kinematic parameter, and the change in location data and attitudes vibration data for having recorded
It is calculated the run trace of the automatic travelling device.
11. methods according to claim 9, it is characterised in that methods described also includes:
According to the image detection preset boundary of collection, the automatic travelling device is controlled along one Zhou Bingji of preset boundary walking
The run trace of record walking one week, boundary profile is determined according to the walking run trace of a week;Or,
Control the automatic travelling device to be walked one week along preset boundary under manual control, and record the walking rail of walking one week
Mark, boundary profile is determined according to the walking run trace of a week.
12. methods according to claim 11, it is characterised in that methods described also includes:
Plan walking path is determined according to the boundary profile;
Record the actual walking path of the automatic travelling device;
Relative position of the automatic travelling device relative to the boundary profile is determined according to actual walking path;
The automatic travelling device is controlled to be walked according to the plan walking path according to the relative position.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410140724.6A CN103901890B (en) | 2014-04-09 | 2014-04-09 | Outdoor automatic walking device based on family courtyard and system and method for controlling outdoor automatic walking device based on family courtyard |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410140724.6A CN103901890B (en) | 2014-04-09 | 2014-04-09 | Outdoor automatic walking device based on family courtyard and system and method for controlling outdoor automatic walking device based on family courtyard |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103901890A CN103901890A (en) | 2014-07-02 |
CN103901890B true CN103901890B (en) | 2017-05-24 |
Family
ID=50993278
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410140724.6A Active CN103901890B (en) | 2014-04-09 | 2014-04-09 | Outdoor automatic walking device based on family courtyard and system and method for controlling outdoor automatic walking device based on family courtyard |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103901890B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105512689A (en) * | 2014-09-23 | 2016-04-20 | 苏州宝时得电动工具有限公司 | Lawn identification method based on images, and lawn maintenance robot |
US9516806B2 (en) * | 2014-10-10 | 2016-12-13 | Irobot Corporation | Robotic lawn mowing boundary determination |
WO2017206950A1 (en) * | 2016-06-03 | 2017-12-07 | 苏州宝时得电动工具有限公司 | Automatic walking device and method for controlling the walking thereof |
CN107463168A (en) * | 2016-06-06 | 2017-12-12 | 苏州宝时得电动工具有限公司 | Localization method and system, map constructing method and system, automatic running device |
IT201700058505A1 (en) | 2017-05-30 | 2018-11-30 | Volta Robots S R L | Method of control of a soil processing vehicle based on image processing and related system |
CN107306923A (en) * | 2017-06-05 | 2017-11-03 | 广西英伟科技有限公司 | It is a kind of can automatically walk pesticide spraying device |
TWI673586B (en) * | 2018-02-14 | 2019-10-01 | 國立交通大學 | Online training enabled trail following system and method |
CN111198557B (en) * | 2018-10-31 | 2022-03-18 | 苏州科瓴精密机械科技有限公司 | Control method and control system for walking robot |
CN109859158A (en) * | 2018-11-27 | 2019-06-07 | 邦鼓思电子科技(上海)有限公司 | A kind of detection system, method and the machinery equipment on the working region boundary of view-based access control model |
CN110109454A (en) * | 2019-04-18 | 2019-08-09 | 福建信息职业技术学院 | A kind of intelligent carriage motion profile clone method |
CN111328017B (en) * | 2020-02-18 | 2021-05-14 | 深圳市愚公科技有限公司 | Map transmission method and device |
CN113885485B (en) * | 2020-06-17 | 2023-12-22 | 苏州科瓴精密机械科技有限公司 | Robot walking control method, system, robot and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101727756A (en) * | 2008-10-16 | 2010-06-09 | 财团法人工业技术研究院 | Mobile image-aided guidance method and mobile image-aided guidance system for vehicles |
CN102662400A (en) * | 2012-05-10 | 2012-09-12 | 慈溪思达电子科技有限公司 | Path planning algorithm of mowing robot |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4954962A (en) * | 1988-09-06 | 1990-09-04 | Transitions Research Corporation | Visual navigation and obstacle avoidance structured light system |
US7881497B2 (en) * | 2007-03-08 | 2011-02-01 | Honeywell International Inc. | Vision based navigation and guidance system |
CN102545275A (en) * | 2010-12-07 | 2012-07-04 | 上海新世纪机器人有限公司 | Robot automatic charging device and robot automatic charging method |
CN102681541A (en) * | 2011-03-10 | 2012-09-19 | 上海方伴自动化设备有限公司 | Method for image recognition and vision positioning with robot |
CN103324192A (en) * | 2012-03-23 | 2013-09-25 | 苏州宝时得电动工具有限公司 | Boundary setting method and boundary setting system |
CN103324191A (en) * | 2012-03-23 | 2013-09-25 | 苏州宝时得电动工具有限公司 | Control method and control system executing same |
CN103586870B (en) * | 2013-11-05 | 2016-06-29 | 中国科学院深圳先进技术研究院 | Steam generator climbing robot |
-
2014
- 2014-04-09 CN CN201410140724.6A patent/CN103901890B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101727756A (en) * | 2008-10-16 | 2010-06-09 | 财团法人工业技术研究院 | Mobile image-aided guidance method and mobile image-aided guidance system for vehicles |
CN102662400A (en) * | 2012-05-10 | 2012-09-12 | 慈溪思达电子科技有限公司 | Path planning algorithm of mowing robot |
Also Published As
Publication number | Publication date |
---|---|
CN103901890A (en) | 2014-07-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103901890B (en) | Outdoor automatic walking device based on family courtyard and system and method for controlling outdoor automatic walking device based on family courtyard | |
CN107239074A (en) | Automatic working system and its map method for building up of working region | |
CN104714547B (en) | Autonomous gardens vehicle with camera | |
CN110928301B (en) | Method, device and medium for detecting tiny obstacle | |
CN110477825B (en) | Cleaning robot, autonomous charging method, system, and readable storage medium | |
CN106428558B (en) | A kind of track synthesis method for inspecting based on the dual-purpose unmanned plane of sky-rail | |
CN111035327A (en) | Cleaning robot, carpet detection method, and computer-readable storage medium | |
CN102368158B (en) | Navigation positioning method of orchard machine | |
CN107003675A (en) | The method that processing surface is surveyed and drawn for autonomous robot vehicle | |
CN106127113A (en) | A kind of road track line detecting method based on three-dimensional laser radar | |
CN104134209A (en) | Feature extraction and matching method and feature extraction and matching system in visual navigation | |
CN106289285A (en) | Map and construction method are scouted by a kind of robot associating scene | |
CN108364466A (en) | A kind of statistical method of traffic flow based on unmanned plane traffic video | |
CN112243698A (en) | Automatic walnut picking and collecting method based on multi-sensor fusion technology | |
CN103680291A (en) | Method for realizing simultaneous locating and mapping based on ceiling vision | |
CN109483533A (en) | Control method, device and the robot of robot for environmental sanitation operation | |
CN102034355A (en) | Feature point matching-based vehicle detecting and tracking method | |
CN213424010U (en) | Mowing range recognition device of mowing robot | |
CN106741890A (en) | A kind of high-speed railway safety detecting system based on the dual-purpose unmanned plane of empty rail | |
CN110081873A (en) | Recognition methods is got in region ready and agricultural machinery gets identifying system ready | |
CN110388926A (en) | A kind of indoor orientation method based on mobile phone earth magnetism and scene image | |
CN107315410A (en) | A kind of automatic troubleshooting method of robot | |
CN111077890A (en) | Implementation method of agricultural robot based on GPS positioning and automatic obstacle avoidance | |
CN106592499A (en) | Snow-shoveling robot and snow-shoveling method thereof | |
CN112211145A (en) | Semi-automatic road sweeping method and device for road sweeper |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |