CN103901890A - 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
- CN103901890A CN103901890A CN201410140724.6A CN201410140724A CN103901890A CN 103901890 A CN103901890 A CN 103901890A CN 201410140724 A CN201410140724 A CN 201410140724A CN 103901890 A CN103901890 A CN 103901890A
- Authority
- CN
- China
- Prior art keywords
- image
- travelling device
- automatic travelling
- walking
- module
- 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
Images
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Manipulator (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, particularly relate to a kind of outdoor automatic travelling device and control system and method based on family's garden.
Background technology
Along with the continuous progress of computer technology and artificial intelligence technology, the garden outdoor moving robot of family that is similar to intelligent robot has started the life of coming into people slowly.Current many scientific & technical corporation have all developed automatic dust catcher and have put goods on the market.The common volume of this automatic dust catcher is small and exquisite, without manual control, after once arranging, just without dropping into energy management, user from cleaning, free the uninteresting and housework work of wasting time and energy such as lawn maintenance, is therefore subject to very big welcome again.
At present garden outdoor moving robot of family is controlled, there is following methods: the 1) dead reckoning based on scrambler: the basic demand of scheme is that wheel is non-slip, and ground is smooth, so just can calculate according to the number of turns of rotating of wheel, but for automatic mower, skid and all cannot fully ensure with smooth, this will make accumulated error large to accepting; 2) absolute fix based on many base stations: basic scheme be in region four jiaos certain transmitter is set, as ultrasonic, infrared, electromagnetic radio frequency etc., principle by similar GPS is directly located, there is precision advantages of higher, for automatic mower, ultrasonic signal can by plant multiple reflections, infrared cannot through plant and be subject to sunlight disturb, electromagnetism cost superelevation; 3) track formula location: it need to lay the underground track of comparatively dense, substantially inapplicable for automatic mower.
Therefore there are various defects in traditional outdoor moving robot control method, can not effectively control the movement of outdoor moving robot, needs to improve.
Summary of the invention
Based on this, be necessary for the problems referred to above, a kind of outdoor automatic travelling device based on family's garden and control system and the method that can effectively control is provided.
Based on an outdoor automatic travelling device for family's garden, comprising: housing and walking module, described walking module is installed on described housing, also comprises:
Be installed on the image capture module on described housing, in the time that described automatic travelling device is walked on working surface, the image on continuous acquisition working surface;
Be installed on the main control module in described housing, be connected respectively with described walking module and described image capture module, determine characteristic area for the first image of carrying out continuously from gathering, in the second image gathering, identify described characteristic area after described the first image, calculate and record change in location data and the attitude delta data of described automatic travelling device according to the geometry deformation of described characteristic area and displacement meter; The described change in location data that described main control module has also recorded for basis and attitude delta data calculate the run trace of described automatic travelling device.
In one embodiment, when described image capture module is used for the image on continuous acquisition working surface, on working surface, the size of pickup area is for being more than or equal to 100 square centimeters.
In one embodiment, described image capture module is positioned at a side of the close working surface of housing, gather direction towards working surface, and distance between described image capture module and working surface is more than or equal to 3 centimetres.
In one embodiment, described the first image and described the second image are the adjacent image of acquisition time in the image that gathers of described image capture module.
In one embodiment, automatic travelling device also comprises the sensor being installed in described housing, for synchronously obtain location parameter and/or the kinematic parameter of described automatic travelling device in the time gathering image;
Described main control module is also for according to described location parameter and/or kinematic parameter, and the described change in location data that recorded and attitude delta data calculate the run trace of described automatic travelling device.
In one embodiment, whether described main control module also comprises the image on default border in the image for detection of collection, if certainly last time detected according to automatic travelling device described in the image correction of the image that comprises default border that the moment of the image that comprises the image of presetting border was to the run trace of current time.
In one embodiment, described main control module is also for presetting border according to the image detection gathering, control described automatic travelling device along described default border walking one week the record walking run trace of a week, determine boundary profile according to the walking run trace of a week; Or,
Described main control module is also walked one week along default border for control described automatic travelling device under manual control, and the record walking run trace of a week, determines boundary profile according to the walking run trace of a week.
In one embodiment, described main control module is also for determining plan walking path according to described boundary profile, record the actual walking path of described automatic travelling device, determine the relative position of described automatic travelling device with respect to described boundary profile according to actual walking path, walk according to described plan walking path according to automatic travelling device described in described relative position control.
A kind of automatic travelling device control system, comprises the outdoor automatic travelling device based on family's garden of above-mentioned arbitrary embodiment; Also comprise stop device, for stopping for described automatic travelling device and providing energy for described automatic travelling device.
A kind of outdoor automatic travelling device control method based on family's garden, described automatic travelling device comprises: housing and walking module, described walking module is installed on described housing, and described automatic travelling device also comprises: be installed on the image capture module on described housing; Described method comprises:
In the time that described automatic travelling device is walked on working surface, by the image on described image capture module continuous acquisition working surface;
From the first image gathering, determine characteristic area, in the second image gathering, identify described characteristic area after described the first image;
Calculate and record change in location data and the attitude delta data of described automatic travelling device according to the geometry deformation of described characteristic area and displacement meter;
Calculate the run trace of described automatic travelling device according to the change in location data of the described automatic travelling device having recorded and attitude delta data.
In one embodiment, described automatic travelling device also comprises the sensor being installed in described housing; Described method also comprises:
Gathering in image, by synchronously location parameter and/or the kinematic parameter of automatic travelling device described in sensing of described sensor;
The change in location data of the described automatic travelling device that described basis has recorded and attitude delta data calculate the run trace of described automatic travelling device, comprising:
According to described location parameter and/or kinematic parameter, and the described change in location data that recorded and attitude delta data calculate the run trace of described automatic travelling device.
In one embodiment, described method also comprises:
In the image of detection collection, whether comprise the image on default border, if certainly last time detected according to automatic travelling device described in the image correction of the image that comprises default border that the moment of the image that comprises the image of presetting border was to the run trace of current time.
In one embodiment, described method also comprises:
According to the default border of the image detection gathering, control described automatic travelling device along described default border walking one week the record walking run trace of a week, determine boundary profile according to the walking run trace of a week; Or,
Under manual control, control described automatic travelling device and walk one week along default border, and the record walking run trace of a week, determine boundary profile according to the walking run trace of a week.
In one embodiment, described method also comprises:
Determine plan walking path according to described boundary profile;
Record the actual walking path of described automatic travelling device;
Determine the relative position of described automatic travelling device with respect to described boundary profile according to actual walking path;
Walk according to described plan walking path according to automatic travelling device described in described relative position control.
Above-mentioned outdoor automatic travelling device, automatic travelling device control system and method based on family's garden, thereby converse change in location data and the attitude delta data of automatic travelling device by comparing the displacement of characteristic area in multiple images and geometric deformation, and then realize the self-align of automatic travelling device and obtain run trace, scheme is reliable, cost is low, can control accurately and efficiently the walking of automatic travelling device.
Brief description of the drawings
Fig. 1 is the structural representation of automatic travelling device control system in an embodiment;
Fig. 2 is the structural representation of the simplification of automatic travelling device in an embodiment;
Fig. 3 is the part sectioned view of the structural representation of the simplification of automatic travelling device in an embodiment;
Fig. 4 determines characteristic area from the first image gathering in an embodiment, identify the schematic diagram of the process of described characteristic area after described the first image in the second image gathering;
Fig. 5 is the schematic diagram that calculates the change in location data of described automatic travelling device and the process of attitude delta data in an embodiment according to the geometry deformation of described characteristic area and displacement meter;
Fig. 6 is the schematic flow sheet of automatic travelling device control method in an embodiment;
Fig. 7 is the schematic flow sheet of automatic travelling device control method in another embodiment.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
As shown in Figure 1, in one embodiment, provide a kind of outdoor automatic travelling device control system based on family's garden, comprised automatic travelling device 102 and supply automatic travelling device 102 to stop and be the stop device 104 of automatic travelling device 102 makeup energy.The surface that automatic travelling device 102 is walked is its working surface.In the present embodiment, working surface can comprise perform region 106a and inoperative region 106b, the boundary line of perform region 106a and inoperative region 106b forms default border 106, perform region 106a and inoperative region 106b preferably have obvious difference, and default border 106 is for limiting the scope of activities of automatic travelling device 102.Default border 106 has identifiability.Stop device 104 is arranged on default border 106.Automatic travelling device 102 also can be called robot.
The concrete structure of automatic travelling device 102 is described below in conjunction with 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).It is upper that walking module and image capture module 102c are installed on housing 102a, and sensor 102d and main control module are installed in housing 102a.Automatic travelling device 102 when walking, image capture module 102c and sensor 102d keep stationary state with respect to housing 102a, and the walking module of automatic travelling device 102 contact working surface, and housing 102a, image capture module 102c, sensor 102d and main control module do not contact working surface.Housing 102a works to be connected and fixed modules, also can be for the protection of the modules that is installed on automatic travelling device 102.Main control module is connected respectively with walking module, image capture module 102c and sensor 102d.
Be understandable that, automatic travelling device 102 also comprises the energy module (not shown) that is placed in housing 102a, energy module is connected respectively with walking module, image capture module 102c, sensor 102d and main control module, is used to these modules to provide work required energy.Wherein, energy module can provide module for the energy based on fuel, and fuel can be gasoline or diesel oil etc.Energy module can also be power brick.In one embodiment, energy module is rechargeable battery pack; In the time that automatic travelling device 102 is worked, rechargeable battery pack discharges electric energy and works to maintain automatic travelling device 102; In the time that automatic travelling device 102 is not worked, rechargeable battery pack can be connected to external power source with electric energy supplement.In one embodiment, in the time that automatic travelling device 102 detects that rechargeable battery pack electric weight is not enough, automatic travelling device 102 can Automatic-searching stop device 104 electric energy supplement.
In an embodiment, automatic travelling device 102 can also comprise operational module therein, to carry out specific work.Such as operational module can be cutting module, comprise cutting part and the cutting motor that drives cutting part for mowing, in the present embodiment, automatic travelling device 102 becomes mower.In other embodiments, can also the operational module with other function be installed for automatic travelling device 102, make automatic travelling device 102 become trimmer, automatic cleaner etc.
Walking module is walked for the modules that drives housing 102a and install, thereby realizes the walking of automatic travelling device 102.In one embodiment, walking module comprises wheels 102b and for driving the running motor (not shown) of wheels 102b.Wheels 102b can have multiple method to set up, and the quantity of general wheels 102b is multiple, such as at least 3.Multiple wheels 102b, especially can be with different rotational speed with respect to the symmetrically arranged multiple wheels 102b of direction of travel of automatic travelling device 102, thereby automatic travelling device 102 can be turned to.Be understandable that, walking module can also be other module that can realize walking, such as mechanical arm or crawler belt etc., does not repeat them here.
In one embodiment, when image capture module 102c is positioned at a side of the close working surface of housing 102a, and it gathers direction in the time of working surface, distance between image capture module 102c and working surface is more than or equal to 3 centimetres, and/or on working surface the size of pickup area for being more than or equal to 100 square centimeters.Preferably the distance between image capture module 102c and working surface is more than or equal to 5 centimetres, and/or on working surface the size of pickup area for being more than or equal to 200 square centimeters.Arrange is like this because working surface is violent in microcosmic point image change, environment is unpredictable, such as for mower, in microcosmic point (being the image of several sq), landform is relatively uneven, image change is violent on meadow, environment is unpredictable, so pickup area is more suitable for more greatly subsequent treatment, to improve the accuracy that automatic travelling device 102 is controlled.
Main control module is for controlling the normal work of the walking of automatic travelling device 102 and the modules of automatic travelling device 102.Main control module, be connected respectively with walking module and image capture module 102c, determine characteristic area for the first image of carrying out continuously from gathering, recognition feature region in the second image gathering after the first image, calculates and records change in location data and the attitude delta data of automatic travelling device according to the geometry deformation of characteristic area and displacement meter; The change in location data that main control module has also recorded for basis and attitude delta data calculate the run trace of automatic travelling device.
Particularly, automatic travelling device 102 is after startup, and image capture module 102c is for the image according on default sampling time interval continuous acquisition working surface, and by the image transmitting gathering to main control module.Main control module can be received multiple images like this.
With reference to Fig. 4, main control module is used for using one of them image 402 gathering as the first image, and this first image is benchmark image, and an image 404 of the first image 402 rear collections is as the second image, and the second image is contrast images; In the first image 402, this characteristic area 402a, as characteristic area 402a, is identified in selected part region in the second image 404.Next main control module is used for can be used for again using image 404 as the first image, using an image 406 of the first image 404 collection afterwards as the second image; In the first image 404, this characteristic area 404a, as characteristic area 404a, is identified in selected part region in the second image 406.Next when using image 406 as the first image, in the first image 406, selected part region, as characteristic area 406a, continues to carry out so always.Can certainly be using the image gathering as the first image, another image after this image is after the second image, can in the image of collection, be different from previous other image as the first image and the second image as the first image, then using this image image afterwards as the second image.
Wherein characteristic area (402a, 404a or 406a) can be positioned at the first image (402a corresponding 402,404a corresponding 404,406a corresponding 406) middle position, so no matter automatic travelling device 102 whichaways move, and can both ensure as far as possible that the characteristic area in the second image can not lack.In other embodiments, characteristic area also can be positioned at other position of the first image, and such as in the time determining direction of travel roughly of automatic travelling device 102, the chosen position of characteristic area can be slightly along oppositely more mobile distances of direction of travel.
Main control module is for behind selected characteristic region, this characteristic area is processed to extract and record to some characteristics of image of this characteristic area, the mode that extraction feature can adopt includes but not limited to the conversion of SIFT(yardstick invariant features), SURF(speeded up robust features, fast robust feature), DAISY(DAISY is the topography's Feature Descriptor that can calculate fast extracting towards dense characteristic), Haar(rectangular characteristic), WLD(weber local feature), LBP(Local Binary Patterns, local binary patterns), ORB(two-value Feature Descriptor), BRIEF(Feature Descriptor), LDA-hash(Feature Descriptor), MSER(Maximally Stable External Regions, Region Feature Extraction), HOG(Histogram of Oriented Gradient, histograms of oriented gradients), gray-scale value, color histogram, grey level 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, the first image and the second image be image capture module 102c gather image in the adjacent image of acquisition time.In the present embodiment, when automatic travelling device 102 when walking, image capture module 102c is according to default sampling time interval continuous acquisition image, and main control module is using an image after the first image, and the next image that the acquisition time of collection is adjacent after this image is as the second image.The common ground of such the first image and the second image is maximum, the possibility minimum of characteristic area disappearance in the second image, and the registration accuracy of change in location is also the highest.But in other embodiments, between the first image and the second image, can there is the image of other collection, in the image gathering, there is the image of acquisition time between the acquisition time of the first image and the acquisition time of the second image, only need to ensure still to comprise all or part of characteristic area in the second image.
Main control module is used in the second image recognition feature region, particularly, main control module is used for according to the characteristics of image of the characteristic area of precedence record, the part of the Image Feature Matching of finding in the second image and recording, and the part finding is exactly the characteristic area identifying.
Set forth main control module how for calculate change in location data and the attitude delta data of automatic travelling device 102 according to the geometry deformation of characteristic area and displacement meter below in conjunction with Fig. 5.
After main control module is determined for the characteristic area in characteristic area and second image of the first image, according to the feature pairing result of the first image and the second image, calculate in three dimensions image capture module 102c at the acquisition time of the first image and the transformation matrix in these two moment of acquisition time of the second image, thereby extrapolate change in location data and the attitude delta data of image capture module 102c.Because image capture module 102c is static with respect to housing 102a, the change in location data of image capture module 102c and posture changing data just can be converted into change in location data and the attitude delta data of automatic travelling device 102.Wherein change in location data representation automatic travelling device 102 residing position on working surface of automatic travelling device 102.The attitude delta data of automatic travelling device 102 refers to and represents automatic travelling device 102 turning to and/or data that the attitude of the automatic travelling device 102 that topographic relief causes changes because of self.
In one embodiment, be installed on sensor 102d in housing 102a for synchronously obtain location parameter and/or the kinematic parameter of automatic travelling device 102 in the time that image capture module 102c gathers image.Main control module is also for according to location parameter and/or kinematic parameter, and change in location data and attitude delta data calculate the run trace of automatic travelling device 102.
Main control module is for constantly recording change in location data and the attitude delta data of automatic travelling device 102, and calculates the run trace of automatic travelling device 102 according to the change in location data of cumulative record and attitude delta data.From automatic travelling device 102 starts, along with the change in location data of accumulation and increasing of attitude delta data, run trace also increases accordingly.Certainly, main control module also can only record the run trace of restriction length and erase previous run trace data, or the run trace of automatic travelling device 102 in the time period that only recording section needs or spatial dimension, these can need to set or adjust according to real work.
In one embodiment, whether main control module also comprises the image on default border 106 in the image for detection of collection, if certainly last time detected according to the image correction automatic travelling device of the image that comprises default border 106 that the moment of the image that comprises the image of presetting border was to the run trace of current time.
In the present embodiment, by the image on image capture module 102c collecting work surface, synchronously preset the detection on border 106.Particularly, main control module is for realizing the function of following a, b and c:
A, the region to be detected in the image collecting by image capture module 102c is used to moving window cutting is multiple standard-sized images.Region to be detected can be entire image, can be also the subregion of image, is preferably the image-region of removing central characteristic area in image.Adjacent standard-sized image can have overlapping region, also can there is no overlapping region, depending on the performance of main control module, has been preferably overlapping region.
B, each standard-sized image is extracted to feature, send in the sorter training.Sorter can be the sorter that uses the image pattern of the image that comprises default border and do not comprise the image pattern training acquisition of the image on default border.The image that comprises default border can refer to the local image that comprises default border.The feature of wherein extracting can be artificial definition, can be also training automatically, depending on training method.Wherein, the feature of artificial definition can be but be not limited to color histogram, LBP, dynamic texture, symbiosis square, HOG, Haar-like(rectangular characteristic) etc., be preferably color histogram and Haar-like feature, because concerning example mower, working surface is generally meadow, and the bottom surface outside meadow is inoperative region.Automatically the feature of training can be used intelligent characteristic back-and-forth method or feature learning algorithm, and algorithm can be but be not limited to: self-editing ink recorder in Adaboost algorithm, degree of depth study, Boltzmann's learning machine, convolutional neural networks, dark Belief network etc.
C, to sending into the sorter training the classification results of exporting, use evidence theoretical algorithm to merge, finally the testing result on the default border 106 of output.
In the time the collection image of the image that comprises default border 106 being detected, main control module is for revising from moment to the run trace of current time of the image that the image that comprises default border last time detected automatic travelling device 102.Particularly, main control module is used for the error on the position and the default border 106 that calculate automatic travelling device 102, and use error back-propagation algorithm correction automatic travelling device 102 starts the run trace to current time Zi last time touching default border 106.Run trace between the adjacent moment that default border detected for twice may not be optimum trajectory, such as automatic travelling device 102 is from some ridings to another point, efficiency is lower than from any along straight line to another point, thereby now need this section of track correction to be optimized, so that it is more efficient to obtain walking and the work of automatic travelling device 102.
In one embodiment, the default sampling time interval of image capture module 102c collection image can determine according to the speed of travel of automatic travelling device 102.After gathering for the first time image and finishing, in the time that characteristic area is about to leave acquisition range, need to gather for the second time image, this gathers image for the first time and this time interval that gathers for the second time image is the maximal value of default sampling time interval.
In one embodiment, automatic travelling device 102 has boundary profile and delimit function, comprises automatic mode and manual mode.Under automatic mode, main control module, for according to the default border 106 of the image detection gathering, is controlled automatic travelling device and is walked one week along default border 106 and the record walking run trace of a week, determines boundary profile according to the walking run trace of a week.Particularly, image capture module 102c and sensor 102d are for continuous collecting signal and send main control module to, whether main control module is for moving to the edge on default border 106 according to the signal automatic decision automatic travelling device 102 receiving, if controlling automatic travelling device 102 walks along default border 106, until get back to starting point, walk one week along default border 106 and the record walking run trace of a week, the run trace of walking a week is set to boundary profile.In one embodiment, if automatic travelling device 102 is mower, main control module is for carrying out Boundary Detection according to the image gathering by image capture module 102c, judge whether automatic travelling device 102 moves to meadow boundary edge, if control automatic travelling device along border, meadow walking, until the reference position when getting back to automatic travelling device 102 and setting out.In automatic travelling device 102 walking processes, record run trace, then the run trace of record is recorded as to boundary profile simultaneously.
Under manual mode, main control module is walked one week along default border 106 for control automatic travelling device under manual control, and the record walking run trace of a week, determines boundary profile according to the walking run trace of a week.Particularly, automatic travelling device 102 is for from default starting point, walk one week along default border 106, and in the process of walking, continue record run trace, then the run trace of record is recorded as to boundary profile.Default starting point can be stop device 104, the mode that automatic travelling device 102 is walked can be manually to lead, if main control module is for according to the direction of travel of the remote signal control automatic travelling device 102 of telepilot etc., also can for by the artificial road sign arranging as walkings such as electronic edge boundary line or indication road signs.Record the mode of automatic travelling device 102 run trace as the recording mode under automatic mode, repeat no more.
The profile of delimiing a boundary line can bring great advantage for the work of automatic travelling device 102, for example, known location from default border 106 enters after the 106a of perform region, the record being continued due to follow-up run trace, automatic travelling device 102 just can be known the position in any moment it self and the region of having worked like this, and then can ensure that automatic travelling device 102 can not leave perform region 106a, also can select intelligently next step action, as to which region advanced and work etc.In one embodiment, main control module is used for delimiting multiple perform regions according to boundary profile, and controls automatic travelling device 102 and in each perform region, walk and work respectively.
In one embodiment, main control module is also for determining plan walking path according to boundary profile, record the actual walking path of automatic travelling device, determine the relative position of automatic travelling device with respect to boundary profile according to actual walking path, according to the walking path walking according to schedule of this relative position control automatic travelling device.
In the present embodiment, in the time that automatic travelling device 102 is started working, main control module is for setting a plan walking path according to boundary profile, and this path is optimized, thereby can avoid repetition in the work of part position, can save travel time by the walking of rational path.Main control module is walked for control automatic travelling device 102 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 calculate the relative position of automatic travelling device 102 with respect to boundary profile according to actual walking path binding site parameter and/or kinematic parameter, this relative position can represent the particular location of current automatic travelling device 102 in the boundary profile map being formed by boundary profile.Then can be according to the relative position correction direction of travel of automatic travelling device 102, to keep automatic travelling device 102 walking path walking according to schedule.In one embodiment, main control module can be used for actual walking path and plan walking path to contrast, if there is skew with respect to plan walking path in inconsistent explanation now actual walking path, main control module can be used for controlling automatic travelling device 102 oppositely skew when walking, to offset skew, thereby keep automatic travelling device 102 walking path walking according to schedule.
Above-mentioned automatic travelling device 102, thereby converse change in location data and the attitude delta data of automatic travelling device by comparing the displacement of characteristic area in multiple images and geometric deformation, and then realize the self-align of automatic travelling device and obtain run trace, scheme is reliable, cost is low, can control accurately and efficiently the walking of automatic travelling device.
In one embodiment, provide a kind of outdoor automatic travelling device control method based on family's garden, for controlling the as above automatic travelling device of arbitrary embodiment.Wherein, this automatic travelling device comprises: housing, walking module and image capture module; Walking module is installed on housing, and image capture module is installed on housing; As shown in Figure 6, the method comprises the following steps:
Particularly, in the time that automatic travelling device is walked on working surface, by image capture module according to the image on default sampling time interval continuous acquisition working surface.The default sampling time interval here at least will ensure that 2 images that acquisition time is adjacent have overlapping.In one embodiment, image capture module can be positioned at a side of the close working surface of housing, and it gathers direction towards working surface, so that gather automatic travelling device bottom, image capture module below, image under particularly.The pattern distortion that this kind of mode gathers acquisition is little, is convenient to subsequent treatment.In other embodiments, image capture module also can be positioned at optional position on housing, only need to ensure that image capture module can collect the image on working surface, such as image capture module can be positioned on housing opposing in a side of working surface or towards a side of automatic travelling device direction of travel.
In one embodiment, when image capture module is positioned at a side of the close working surface of housing, and it gathers direction in the time of working surface, distance between image capture module and working surface is more than or equal to 3 centimetres, and/or on working surface the size of pickup area for being more than or equal to 100 square centimeters.Preferably the distance between image capture module and working surface is more than or equal to 5 centimetres, and/or on working surface the size of pickup area for being more than or equal to 200 square centimeters.Arrange is like this because working surface is violent in microcosmic point image change, environment is unpredictable, such as for mower, in microcosmic point (being the image of several sq), landform is relatively uneven, image change is violent on meadow, environment is unpredictable, so pickup area is more suitable for more greatly subsequent treatment, to improve the accuracy to automatic travelling device control.
Step 604 is determined characteristic area, recognition feature region in the second image gathering after the first image from the first image gathering.
Particularly, using one of them image in the image gathering as the first image, this first image is benchmark image, and the image gathering after the first image is as the second image, and the second image is contrast images.In the first image, this characteristic area, as characteristic area, is identified in selected part region in the second image.At follow-up circulation time, can be using this second image the first image in follow-up circulation, then using another image in follow-up circulation as the second image.Can certainly be using the image gathering as the first image, another image after this image is after the second image, can in the image of collection, be different from previous other image as the first image and the second image as the first image, then using this image image afterwards as the second image.
Wherein characteristic area can be positioned at the middle position of the first image, and so no matter automatic travelling device whichaway moves, and can both ensure as far as possible that the characteristic area in the second image can not lack.In other embodiments, characteristic area also can be positioned at other position of the first image, and such as in the time determining direction of travel roughly of automatic travelling device, the chosen position of characteristic area can be slightly along oppositely more mobile distances of direction of travel.
After extracting characteristic area, need process to extract and record to this characteristic area some characteristics of image of this characteristic area, the mode that extraction feature can adopt includes but not limited to SIFT, SURF, DAISY, Haar, WLD, LBP, ORB, BRIEF, LDA-hash, MSER, HOG, gray-scale value, color histogram, grey level 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, the first image and the second image be image capture module gather image in the adjacent image of acquisition time.In the present embodiment, when automatic travelling device when walking, image capture module is according to default sampling time interval continuous acquisition image, and main control module is using an image after the first image, and the next image that the acquisition time of collection is adjacent after this image is as the second image.The common ground of such the first image and the second image is maximum, the possibility minimum of characteristic area disappearance in the second image, and the registration accuracy of change in location is also the highest.But in other embodiments, between the first image and the second image, can there is the image of other collection, in the image gathering, there is the image of acquisition time between the acquisition time of the first image and the acquisition time of the second image, only need to ensure still to comprise all or part of characteristic area in the second image.
In the second image when recognition feature region, according to the characteristics of image of the characteristic area of precedence record, in the second image, to find and the part of the Image Feature Matching of record, the part finding is exactly the characteristic area identifying.
After characteristic area in characteristic area in the first image and the second image is determined, according to the feature pairing result of the first image and the second image, calculate in three dimensions at the acquisition time of the first image and the transformation matrix in these two moment of acquisition time of the second image, thereby extrapolate change in location data and the attitude delta data of image capture module.Because image capture module is static with respect to housing, the change in location data of image capture module and posture changing data just can be converted into change in location data and the attitude delta data of automatic travelling device.Wherein change in location data representation automatic travelling device residing position on working surface of automatic travelling device.The attitude delta data of automatic travelling device refers to and represents automatic travelling device turning to and/or data that the attitude of the automatic travelling device that topographic relief causes changes because of self.
Step 608, calculates the run trace of automatic travelling device according to the change in location data of the automatic travelling device having recorded and attitude delta data.
Constantly record change in location data and the attitude delta data of automatic travelling device, and calculate the run trace of automatic travelling device according to the change in location data of cumulative record and attitude delta data.From automatic travelling device starts, along with the change in location data of accumulation and increasing of attitude delta data, run trace also increases accordingly.Certainly, also can only record the run trace of restriction length and erase previous run trace data, or the run trace of automatic travelling device in the time period that only recording section needs or spatial dimension, these can need to set or adjust according to real work.
Above-mentioned automatic travelling device control method, thereby converse change in location data and the attitude delta data of automatic travelling device by comparing the displacement of characteristic area in multiple images and geometric deformation, and then realize the self-align of automatic travelling device and obtain run trace, scheme is reliable, cost is low, can control accurately and efficiently the walking of automatic travelling device.
In one embodiment, automatic travelling device also comprises the sensor being installed in housing.This automatic travelling device control method also comprises: in gathering image, by synchronously location parameter and/or the kinematic parameter of sensing automatic travelling device of sensor.Step 608 comprises: according to location parameter and/or kinematic parameter, and change in location data and attitude delta data calculate the run trace of automatic travelling device.
Sensor includes but not limited to angular-rate sensor, differential GPS sensor or Magnetic Sensor etc.The location parameter that combined sensor gathers and/or kinematic parameter, use displacement and the geometric deformation of filtering algorithm calculated characteristics region in the first image and the second image.Wherein filtering algorithm can be but be not limited to: Kalman filtering algorithm, expanded Kalman filtration algorithm, particle filter algorithm etc.Particularly, can be according to location parameter and/or the kinematic parameter of the feature pairing result in the first image and the second image and sensor collection, in calculating three dimensions, image capture module is at the acquisition time of the first image and the transformation matrix in these two moment of acquisition time of the second image, thereby extrapolate change in location data and the attitude delta data of image capture module, and then obtain change in location data and the attitude delta data of automatic travelling device.
In one embodiment, this automatic travelling device control method also comprises: in the image of detection collection, whether comprise the image on default border, if certainly last time detected according to the image correction automatic travelling device of the image that comprises default border that the moment of the image that comprises the image of presetting border was to the run trace of current time.
In the present embodiment, by the image on image capture module c collecting work surface, synchronously preset the detection on border, particularly, the step that detects default border comprises step 1)～step 3):
Step 1), it is multiple standard-sized images that the region to be detected in the image collecting by image capture module is used to moving window cutting.Region to be detected can be entire image, can be also the subregion of image, is preferably the image-region of removing central characteristic area in image.Adjacent standard-sized image can have overlapping region, also can there is no overlapping region, has been preferably overlapping region.
Step 2), each standard-sized image is extracted to feature, send in the sorter training.Sorter can be the sorter that uses the image pattern of the image that comprises default border and do not comprise the image pattern training acquisition of the image on default border.The image that comprises default border can refer to the local image that comprises default border.The feature of wherein extracting can be artificial definition, can be also training automatically, depending on training method.Wherein, the feature of artificial definition can be but be not limited to color histogram, LBP, dynamic texture, symbiosis square, HOG, Haar-like etc., be preferably color histogram and Haar-like feature, because concerning example mower, working surface is generally meadow, and the bottom surface outside meadow is inoperative region.Automatically the feature of training can be used intelligent characteristic back-and-forth method or feature learning algorithm, and algorithm can be but be not limited to: self-editing ink recorder in Adaboost algorithm, degree of depth study, Boltzmann's learning machine, convolutional neural networks, dark Belief network etc.
Step 3), the classification results of the exporting to sending into the sorter training, is used evidence theoretical algorithm to merge, finally the testing result on the default border of output.
In the time the collection image of the image that comprises default border being detected, automatic travelling device is revised from moment to the run trace of current time of the image that the image that comprises default border last time detected.Particularly, calculate the error on position and the default border of automatic travelling device, use error back-propagation algorithm correction automatic travelling device starts the run trace to current time Zi last time touching default border.Run trace between the adjacent moment that default border detected for twice may not be optimum trajectory, such as automatic travelling device is from some ridings to another point, efficiency is lower than from any along straight line to another point, thereby now need this section of track correction to be optimized, so that it is more efficient to obtain walking and the work of automatic travelling device.
In one embodiment, the default sampling time interval of image capture module collection image can determine according to the speed of travel of automatic travelling device.After gathering for the first time image and finishing, in the time that characteristic area is about to leave acquisition range, need to gather for the second time image, this gathers image for the first time and this time interval that gathers for the second time image is the maximal value of default sampling time interval.
In one embodiment, this automatic travelling device control method also comprises step: according to the default border of the image detection gathering, control automatic travelling device along default border walking one week the record walking run trace of a week, determine boundary profile according to the walking run trace of a week.
Automatic travelling device has boundary profile and delimit function, comprises automatic mode and manual mode.Under automatic mode, by image capture module and sensor continuous collecting signal, and whether move to the edge on default border according to the signal automatic decision automatic travelling device collecting, if control automatic travelling device along the walking of default border, until get back to starting point, along default border walking one week the record walking run trace of a week, the run trace of walking a week is set to boundary profile.In one embodiment, if automatic travelling device is mower, can carry out Boundary Detection according to the image gathering by image capture module, judge whether automatic travelling device moves to meadow boundary edge, if control automatic travelling device along border, meadow walking, until the reference position when getting back to automatic travelling device and setting out.In automatic travelling device walking process, record run trace, then the run trace of record is recorded as to boundary profile simultaneously.
In one embodiment, this automatic travelling device control method also comprises step: under manual control, control automatic travelling device and walk one week along default border, and the record walking run trace of a week, determine boundary profile according to the walking run trace of a week.
Under manual mode, under manual control, to control automatic travelling device and walk one week along default border, the record walking run trace of a week, determines boundary profile according to the walking run trace of a week.Particularly, automatic travelling device, from default starting point, is walked one week along default border, and in the process of walking, continue record run trace, then the run trace of record is recorded as to boundary profile.Default starting point can be stop device, the mode of automatic travelling device walking can be manually to lead, as automatic travelling device can be controlled its direction of travel etc. under the control of remote signal, also can be for the road sign by artificial setting be as walkings such as electronic edge boundary line or indication road signs.Record the mode of automatic travelling device run trace as the recording mode under automatic mode, repeat no more.
The profile of delimiing a boundary line can bring great advantage for the work of automatic travelling device, for example, enter perform region from default borderline known location, the record being continued due to follow-up run trace, automatic travelling device just can be known the position in any moment it self and the region of having worked like this, and then can ensure that automatic travelling device can not leave perform region, also can select intelligently next step action, as to which region advanced and work etc.In one embodiment, can also delimit multiple perform regions according to boundary profile, and control automatic travelling device and in each perform region, walk and work respectively.
In one embodiment, this automatic travelling device control method also comprises: determine plan walking path according to boundary profile; Record the actual walking path of automatic travelling device; Determine the relative position of automatic travelling device with respect to boundary profile according to actual walking path; According to the walking path walking according to schedule of this relative position control automatic travelling device.
In the present embodiment, in the time that automatic travelling device is started working, set a plan walking path according to boundary profile, this path is optimized, thereby can avoid repetition in the work of part position, can save travel time by the walking of rational path.After setting plan walking path, control automatic travelling device walking, and the actual walking path of real time record automatic travelling device, and calculate the relative position of automatic travelling device with respect to boundary profile according to actual walking path, and according to the relative position correction direction of travel of automatic travelling device, to keep automatic travelling device walking path walking according to schedule.
With reference to figure 7, in another embodiment, provide a kind of automatic travelling device control method, comprise the following steps:
Step 702, in the time that automatic travelling device is walked on working surface, by the image on image capture module continuous acquisition working surface.
Perform step 703 at 702 o'clock in execution step, in gathering image, by synchronously location parameter and/or the kinematic parameter of sensing automatic travelling device of sensor.
After step 702, execution step 705, the step of detection boundaries.Specifically comprise: detect the image that whether comprises default border in the image gathering, if perform step 710.
Step 704 is determined characteristic area, recognition feature region in the second image gathering after the first image from the first image gathering.
The circulation of above-mentioned steps 702～step 710 is carried out.
The above embodiment has only expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (14)
1. the outdoor automatic travelling device based on family's garden, comprising: housing and walking module, and described walking module is installed on described housing, it is characterized in that, also comprises:
Be installed on the image capture module on described housing, in the time that described automatic travelling device is walked on working surface, the image on continuous acquisition working surface;
Be installed on the main control module in described housing, be connected respectively with described walking module and described image capture module, determine characteristic area for the first image of carrying out continuously from gathering, in the second image gathering, identify described characteristic area after described the first image, calculate and record change in location data and the attitude delta data of described automatic travelling device according to the geometry deformation of described characteristic area and displacement meter; The described change in location data that described main control module has also recorded for basis and attitude delta data calculate the run trace of described automatic travelling device.
2. automatic travelling device according to claim 1, is characterized in that, when described image capture module is used for the image on continuous acquisition working surface, on working surface, the size of pickup area is for being more than or equal to 100 square centimeters.
3. automatic travelling device according to claim 1, it is characterized in that, described image capture module is positioned at a side of the close working surface of housing, gather direction towards working surface, and distance between described image capture module and working surface is more than or equal to 3 centimetres.
4. automatic travelling device according to claim 1, is characterized in that, described the first image and described the second image are the adjacent image of acquisition time in the image that gathers of described image capture module.
5. automatic travelling device according to claim 1, is characterized in that, also comprises the sensor being installed in described housing, for synchronously obtain location parameter and/or the kinematic parameter of described automatic travelling device in the time gathering image;
Described main control module is also for according to described location parameter and/or kinematic parameter, and the described change in location data that recorded and attitude delta data calculate the run trace of described automatic travelling device.
6. automatic travelling device according to claim 1, it is characterized in that, whether described main control module also comprises the image on default border in the image for detection of collection, if certainly last time detected according to automatic travelling device described in the image correction of the image that comprises default border that the moment of the image that comprises the image of presetting border was to the run trace of current time.
7. automatic travelling device according to claim 1, it is characterized in that, described main control module is also for presetting border according to the image detection gathering, control described automatic travelling device along described default border walking one week the record walking run trace of a week, determine boundary profile according to the walking run trace of a week; Or,
Described main control module is also walked one week along default border for control described automatic travelling device under manual control, and the record walking run trace of a week, determines boundary profile according to the walking run trace of a week.
8. automatic travelling device according to claim 7, it is characterized in that, described main control module is also for determining plan walking path according to described boundary profile, record the actual walking path of described automatic travelling device, determine the relative position of described automatic travelling device with respect to described boundary profile according to actual walking path, walk according to described plan walking path according to automatic travelling device described in described relative position control.
9. the outdoor automatic travelling device control system based on family's garden, is characterized in that, comprises the outdoor automatic travelling device based on family's garden as described in claim 1-8 any one; Also comprise stop device, for stopping for described automatic travelling device and providing energy for described automatic travelling device.
10. the outdoor automatic travelling device control method based on family's garden, described automatic travelling device comprises: housing and walking module, described walking module is installed on described housing, it is characterized in that, described automatic travelling device also comprises: be installed on the image capture module on described housing; Described method comprises:
In the time that described automatic travelling device is walked on working surface, by the image on described image capture module continuous acquisition working surface;
From the first image gathering, determine characteristic area, in the second image gathering, identify described characteristic area after described the first image;
Calculate and record change in location data and the attitude delta data of described automatic travelling device according to the geometry deformation of described characteristic area and displacement meter;
Calculate the run trace of described automatic travelling device according to the change in location data of the described automatic travelling device having recorded and attitude delta data.
11. methods according to claim 10, is characterized in that, described automatic travelling device also comprises the sensor being installed in described housing; Described method also comprises:
Gathering in image, by synchronously location parameter and/or the kinematic parameter of automatic travelling device described in sensing of described sensor;
The change in location data of the described automatic travelling device that described basis has recorded and attitude delta data calculate the run trace of described automatic travelling device, comprising:
According to described location parameter and/or kinematic parameter, and the described change in location data that recorded and attitude delta data calculate the run trace of described automatic travelling device.
12. methods according to claim 10, is characterized in that, described method also comprises:
In the image of detection collection, whether comprise the image on default border, if certainly last time detected according to automatic travelling device described in the image correction of the image that comprises default border that the moment of the image that comprises the image of presetting border was to the run trace of current time.
13. methods according to claim 10, is characterized in that, described method also comprises:
According to the default border of the image detection gathering, control described automatic travelling device along described default border walking one week the record walking run trace of a week, determine boundary profile according to the walking run trace of a week; Or,
Under manual control, control described automatic travelling device and walk one week along default border, and the record walking run trace of a week, determine boundary profile according to the walking run trace of a week.
14. methods according to claim 13, is characterized in that, described method also comprises:
Determine plan walking path according to described boundary profile;
Record the actual walking path of described automatic travelling device;
Determine the relative position of described automatic travelling device with respect to described boundary profile according to actual walking path;
Walk according to described plan walking path according to automatic travelling device described in described relative position control.
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 true CN103901890A (en) | 2014-07-02 |
| CN103901890B 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) |
Cited By (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 |
| CN106489103A (en) * | 2014-10-10 | 2017-03-08 | 美国iRobot公司 | Robot turf-mown border determines |
| 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 |
| 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 |
| 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 |
| TWI673586B (en) * | 2018-02-14 | 2019-10-01 | 國立交通大學 | Online training enabled trail following system and method |
| CN111123905A (en) * | 2018-10-31 | 2020-05-08 | 苏州科瓴精密机械科技有限公司 | Control method and system of walking robot |
| WO2020107687A1 (en) * | 2018-11-27 | 2020-06-04 | 邦鼓思电子科技（上海）有限公司 | Vision-based working area boundary detection system and method, and machine equipment |
| CN111328017A (en) * | 2020-02-18 | 2020-06-23 | 深圳市愚公科技有限公司 | Map transmission method and device |
| WO2021253698A1 (en) * | 2020-06-17 | 2021-12-23 | 苏州科瓴精密机械科技有限公司 | Robot walking control method and system, robot, and storage medium |
| EP3629693B1 (en) | 2017-05-30 | 2022-01-26 | Volta Robots S.r.l. | Method for controlling a soil working means based on image processing and related system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0358628A2 (en) * | 1988-09-06 | 1990-03-14 | Transitions Research Corporation | Visual navigation and obstacle avoidance structured light system |
| US20080219508A1 (en) * | 2007-03-08 | 2008-09-11 | Honeywell International Inc. | Vision based navigation and guidance system |
| 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 |
| 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 |
| 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 |
| 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 |
| CN103586870A (en) * | 2013-11-05 | 2014-02-19 | 中国科学院深圳先进技术研究院 | Steam generator wall-climbing robot |
-
2014
- 2014-04-09 CN CN201410140724.6A patent/CN103901890B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0358628A2 (en) * | 1988-09-06 | 1990-03-14 | Transitions Research Corporation | Visual navigation and obstacle avoidance structured light system |
| US20080219508A1 (en) * | 2007-03-08 | 2008-09-11 | Honeywell International Inc. | Vision based navigation and guidance system |
| 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 |
| 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 |
| 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 |
| CN103586870A (en) * | 2013-11-05 | 2014-02-19 | 中国科学院深圳先进技术研究院 | Steam generator wall-climbing robot |
Cited By (17)
| 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 |
| CN106489103B (en) * | 2014-10-10 | 2021-04-09 | 美国iRobot公司 | Robotic lawn mowing boundary determination |
| CN106489103A (en) * | 2014-10-10 | 2017-03-08 | 美国iRobot公司 | Robot turf-mown border determines |
| US11452257B2 (en) | 2014-10-10 | 2022-09-27 | 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 |
| EP3629693B1 (en) | 2017-05-30 | 2022-01-26 | Volta Robots S.r.l. | Method for controlling a soil working means 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 |
| CN111123905A (en) * | 2018-10-31 | 2020-05-08 | 苏州科瓴精密机械科技有限公司 | Control method and system of walking robot |
| WO2020107687A1 (en) * | 2018-11-27 | 2020-06-04 | 邦鼓思电子科技（上海）有限公司 | Vision-based working area boundary detection system and method, and machine equipment |
| 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 |
| CN111328017A (en) * | 2020-02-18 | 2020-06-23 | 深圳市愚公科技有限公司 | Map transmission method and device |
| WO2021253698A1 (en) * | 2020-06-17 | 2021-12-23 | 苏州科瓴精密机械科技有限公司 | Robot walking control method and system, robot, and storage medium |
| CN113885485A (en) * | 2020-06-17 | 2022-01-04 | 苏州科瓴精密机械科技有限公司 | Robot walking control method, system, robot and storage medium |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103901890B (en) | 2017-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103901890A (en) | Outdoor automatic walking device based on family courtyard and system and method for controlling outdoor automatic walking device based on family courtyard | |
| CN111035327B (en) | Cleaning robot, carpet detection method, and computer-readable storage medium | |
| CN102771246B (en) | Intelligent mower system and intelligent mowing method thereof | |
| CN201573208U (en) | Device for realizing indoor service robot positioning and map creation simultaneously and rotor | |
| CN109797691B (en) | Unmanned sweeper and driving method thereof | |
| US8666554B2 (en) | System and method for area coverage using sector decomposition | |
| CN102368158B (en) | Navigation positioning method of orchard machine | |
| CN104536445B (en) | Mobile navigation method and system | |
| CN107239074A (en) | Automatic working system and its map method for building up of working region | |
| CN108733061B (en) | Path correction method for cleaning operation | |
| CN106428558B (en) | A kind of track synthesis method for inspecting based on the dual-purpose unmanned plane of sky-rail | |
| CN101920498A (en) | Device for realizing simultaneous positioning and map building of indoor service robot and robot | |
| US20110026770A1 (en) | Person Following Using Histograms of Oriented Gradients | |
| CN109483533A (en) | Control method, device and the robot of robot for environmental sanitation operation | |
| CN213424010U (en) | Mowing range recognition device of mowing robot | |
| CN205880664U (en) | Intelligence weeder | |
| CN101509781A (en) | Walking robot positioning system based on monocular cam | |
| CN108364466A (en) | A kind of statistical method of traffic flow based on unmanned plane traffic video | |
| US20210213619A1 (en) | Robot and control method therefor | |
| CN106741890A (en) | A kind of high-speed railway safety detecting system based on the dual-purpose unmanned plane of empty rail | |
| CN106494611B (en) | A kind of dual-purpose patrol unmanned machine of sky rail | |
| US20220114888A1 (en) | System and Method for Intersection Navigation | |
| CN112211145A (en) | Semi-automatic road sweeping method and device for road sweeper | |
| CN114683290A (en) | Method and device for optimizing pose of foot robot and storage medium | |
| CN114005021A (en) | Laser vision fusion based unmanned inspection system and method for aquaculture workshop |
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 |