CN105717928A - Vision-based robot navigation door-passing method - Google Patents

Abstract

The invention discloses a vision-based robot navigation door-passing method. The vision-based robot navigation door-passing method comprises the following steps that position and attitude parameters of a robot in a global coordinate system are obtained according to a sensor; a door to be passed by the robot is determined; the area for starting cameras of the robot is determined; a navigation destination is calculated; the robot moves to the navigation destination; the robot starts double cameras to recognize the door; a Cartesian coordinate is established by adopting the center of the door as an origin; the robot is controlled to reach 3 correction points respectively; and after the door is passed, the door-passing operation is finished. According to the technical scheme, the relative position relation between the door and the robot is calculated according to information returned from the vision, the global position information of the robot is calculated according to information from a milemeter, and the position and attitude parameters of the robot are effectively acquired, so that the robot is controlled to realize door-passing movement accurately.

Description

The robot navigation of a kind of view-based access control model moves into one's husband's household upon marriage method

Technical field

The present invention relates to technical field of automation, move into one's husband's household upon marriage method particularly to the robot navigation of a kind of view-based access control model.

Background technology

Along with the development of robotics, indoor autonomous robot will be widely used in the every field in life, such as office, hospital and factory etc..Realize the robot independent navigation in these fields, one important problem Shi Shi robot is through door, accordingly, it would be desirable to robot can obtain environmental information, door in environment-identification, makes robot autonomous shuttling back and forth between each room thereby through path planning and navigation.

For being relevant to of moving into one's husband's household upon marriage of robot, research is existing it has been proposed that multiple method, but every kind of method has its limitation and shortcoming.Such as traditional method is to use ultrasound wave or the infrared sensor distance of measuring robots car body and door two frame near door such that it is able to makes robot avoid door two frame in the process moved into one's husband's household upon marriage preferably, passes through door.But this kind of method is it is to be appreciated that the initial position of more accurate environmental map and robot, otherwise owing to ultrasound wave and infrared detection performance very likely guided robot are moved into one's husband's household upon marriage unsuccessfully.Additionally, utilize ultrasound wave or infrared recognitiion gate to need to utilize more priori, this certainly will require that robot obtains information as much as possible near door, accurately determines a position for both sides phase opposite house thereby through blending algorithm.

In recent years, along with the lifting of the universal correlation technique of vision sensor, use the object in vision sensor environment-identification to be possibly realized and to have cost low, the advantages such as arithmetic speed is very fast.For other objects in vision sensor recognitiion gate or environment, it is thus proposed that the method strengthening study obtains the relative pose of door and robot thus robot is navigated, and completes the task of moving into one's husband's household upon marriage of robot.But this method is based on the algorithm of study, it is necessary to great amount of samples is also trained the long period, and discrimination is heavily dependent on the rich of institute's training sample, if samples selection is abundant not will not adapt to various door identification.Someone uses Hough transformation to carry out image extracting line processing, so that estimate the relative pose of door and robot by the method based on model, although this algorithm does not rely on sample, but error is relatively big, and algorithm is more complicated.Also having some algorithms to use the algorithm of image procossing related fields, inefficient, success rate is limited.This patent proposes a kind of door recognition methods based on binocular, use setting height(from bottom) this characteristic identical of two photographic head cleverly, thus being conducive to the upper Feature Points Matching of two width image level axis about binocular, reach the purpose of the pose better determining door under robot coordinate system.

Summary of the invention

The present invention proposes the navigation of a kind of indoor moving robot view-based access control model and moves into one's husband's household upon marriage method, the sensor that the method uses has speedometer, vision sensor, the information calculating door returned according to vision and the relative position relation of robot, global position information according to the information computer device people that speedometer returns, thus controlling the motion that robot realizes moving into one's husband's household upon marriage accurately.

Technical scheme provides the robot navigation of a kind of view-based access control model and moves into one's husband's household upon marriage method, comprises the following steps:

S101, obtain robot current time Position and orientation parameters (x in global coordinate system according to speedometer or Global localization sensor, y, θ), x is the robot abscissa relative to initial point, y is the robot vertical coordinate relative to initial point, θ be robot towards the angle relative to x-axis, rotate to be counterclockwise on the occasion of angle angle, clockwise turn to negative value angle angle；

S102, determine the door that robot to pass through according to user instruction；

S103, determining that robot moves into one's husband's household upon marriage and open the region of photographic head before, each unlatching photographic head region is: Area_i=(x_j,y_k) (1≤j≤N, 1≤k≤M), wherein i represents the numbering of door, and N and M represents the scope in certain region in front of the door；

S104, calculate and this time navigate terminal；

After S105, beginning and end are determined, by A* algorithm calculating robot's walking path, control robot motion to the terminal that navigates；

S106, the dead reckoning information (x returned according to speedometer_r,y_r,θ_r), the position of calculating robot's phase opposite house and attitude, obtain robot towards the angle Δ θ with robot Yu door midpoint line, control revolute Δ θ and make robot towards door；

S107, robot are static, and slave computer sends request to host computer and opens photographic head order simultaneously, and host computer opens the binocular camera being positioned at robot front, and starts to gather image, carry out an identification；

S108, the coordinate x of door the right and left frame returned according to image procossing_l,y_l,x_r,y_rx_l,y_l,x_r,y_r(x_l< x_r,y_l< y_r) calculate door centre coordinate (x₀,y₀), wherein

$x_0=\frac{x_l+x_r}{2},$

$y_0=\frac{y_l+y_r}{2};$

S109, with xo, yo for initial point, robot is currently oriented benchmark, with from door left frame point to left frame set up cartesian coordinate system XOY for x-axis forward；

S110, obtain robot coordinate (x ' under XOY coordinate system_r1,y′_r1,θ′_r1), and obtain robot and relatively move into one's husband's household upon marriage in process first and correct point (x_l1,y_l1) distance, delta d₁With angle delta θ₁, wherein,

-200mm < x_l1< 200mm,

-1400mm < y_l1<-1000mm；

S111, control robot craspedodrome Δ d₁, then turning Δ θ₁, according to dead reckoning information obtain robot currently towards with door perpendicular bisector angle Δ θ '₁, control robot and turn over Δ θ '₁Angle aligns target door；

S112, obtain robot coordinate (x ' under XOY coordinate system_r2,y′_r2,θ′_r2), obtain robot and relatively move into one's husband's household upon marriage in process second and correct point (x_l2,y_l2) distance, delta d₂With angle delta θ₂, wherein,

-200mm < x_l2< 200mm,

-1000mm < y_l2<-600mm；

S113, control robot craspedodrome Δ d₂, then turning Δ θ₂, according to dead reckoning information calculate robot currently towards with door perpendicular bisector angle Δ θ '₂, make robot turn over Δ θ '₂To main entrance；

S114, obtain robot coordinate (x ' under XOY coordinate system_r3,y′_r3,θ′_r3), obtain robot and relatively move into one's husband's household upon marriage in process the 3rd and correct point (x_l3,y_l3) distance, delta d₃With angle delta θ₃, wherein,

-200mm < x_l3< 200mm,

-600mm < y_l3<-300mm；

S115, control robot craspedodrome Δ d₃, then turning Δ θ₃, according to dead reckoning information obtain robot currently towards with door perpendicular bisector angle Δ θ '₃, make robot turn over Δ θ '₃To main entrance；

S116, control robot advance Δ d, wherein 800mm < Δ d < 1200mm, make the complete 6 one-tenth operations of entering of robot.

Further, in step S104, described calculating is this time navigated terminal, farther includes:

Reference zone is scanned for, obtain each reference point in reference zone to robot current location Euclidean distance namelyWherein x, y represent certain grid coordinate in grating map；

To all d tried to achieve_iD is tried to achieve in sequence_iMinima；

d_iMinima corresponding grid positions be terminal of robot this time navigation.

Further, in step s 107, described in carry out identifying, farther include:

The left and right two width RBG image I that binocular camera is collected by S201, host computer_l、I_rCarry out gray processing process respectively, obtain gray level image Gray_l、Gray_r；

S202, employing image overall Binarization methods (such as threshold method, the big law of OSTU, Shanbhag method etc.) are to the gray level image Gray obtained_l、Gray_rCarry out binary conversion treatment respectively and obtain bianry image Binary_l、Binary_r；

S203, use are shaped as rectangle (a < b, and a value is 1 or 2, b span be b < h&b > h.2, wherein h is the height collecting image) structural element, carry out morphological image burn into expansion process obtain bianry image Binary '_l、Binary′_lIn vertical stripe regionNamely this region is likely doorframe or the region of door leaf existence；

S204, the vertical stripe region obtained in step S203 are Matching unit, to R_lAnd R_rIn vertical stripe region mate；

S205, left and right sides corresponding point application binocular range measurement principle is drawn this positional information (x and y) under robot coordinate system by the vertical stripe region obtained in step S204, obtain the developed width information in each vertical stripe region in image simultaneously

$wide=\sqrt{{(x_l-x_r)}^2+{(y_l-y_r)}^2}$

S206, developed width in conjunction with domestic environment Xiamen are 850mm-1200mm, can obtain meeting the vertical stripe region (vertical stripe region (door leaf+left and right sides doorframe), two vertical stripe regions (doorframe and doorframe, doorframe and door leaf)) of actual door width, further door is thought in the vertical stripe region obtained, and by door the right and left frame coordinate x under robot coordinate system_l,y_l,x_r,y_rReturn slave computer and (when for vertical stripe region (door leaf), return the coordinate of both sides, vertical stripe region；When for two vertical stripe regions (doorframe and doorframe), return the coordinate of two vertical stripe areas outside；When for two vertical stripe regions (doorframe and door leaf), return the coordinate of two vertical stripe area inside).

Further, in step S204, described to R_lAnd R_rIn vertical stripe region mate, farther include:

S301, there is parallax according to the object same in binocular solid matching principle imaging in the photographic head of two, left and right, and for the parallel binocular range finding model of optical axis, it is the x of imaging point under left camera image coordinate system_lValue is more than its x of imaging point under right camera image coordinate system_r, i.e. R_lIn elementCorresponding R_rIn occurrenceMeetWhereinForThe x value of regional center point,ForThe x value of regional center point, selectsImaging point.

S302, retrain according to geometric similarity in binocular solid matching principle, i.e. R_lIn elementCorresponding R_rIn occurrenceMeet its geometric properties to be more or less the same, include but not limited to peak width w, color (rgb color space, HSV color space, YUV color space etc.), texture (LBP etc.) feature, by features described above similarity is measured:

For width characteristics: RespectivelyWidth, n is R_rMeet the region total quantity of constraint；

To other features: adopt statistics with histogram, and adopt the mode of similarity measurement (such as Euclidean distance, mahalanobis distance, Pasteur's distance etc.) to carry out Similarity measures and can obtain feature correspondence similarity S_feature；

May finally obtain its similarity is

Select similarity maximumForOccurrence.

S303, return S301, repeat S301, S302 and obtain all of matching area in left images.

Technical solution of the present invention adopts speedometer, the position of visual response device robot measurement and surrounding enviroment, the information calculating door returned according to vision and the relative position relation of robot, global position information according to the information computer device people that speedometer returns, the effective position obtaining robot and pose parameter, thus controlling the motion that robot realizes moving into one's husband's household upon marriage accurately.

Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from description, or understand by implementing the present invention.The purpose of the present invention and other advantages can be realized by structure specifically noted in the description write, claims and accompanying drawing and be obtained.

Below by drawings and Examples, technical scheme is described in further detail.

Accompanying drawing explanation

Accompanying drawing is for providing a further understanding of the present invention, and constitutes a part for description, is used for together with embodiments of the present invention explaining the present invention, is not intended that limitation of the present invention.In the accompanying drawings:

Fig. 1 is that in the embodiment of the present invention one, the robot navigation of view-based access control model moves into one's husband's household upon marriage the flow chart of method；

Fig. 2 is that in the embodiment of the present invention one, the robot navigation of view-based access control model moves into one's husband's household upon marriage the method flow diagram of the door identification in method；

Fig. 3 is that in the embodiment of the present invention one, the robot navigation of view-based access control model moves into one's husband's household upon marriage the method flow diagram of the vertical stripe Region Matching in method.

Detailed description of the invention

Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are illustrated, it will be appreciated that preferred embodiment described herein is merely to illustrate and explains the present invention, is not intended to limit the present invention.

Fig. 1 is that in the embodiment of the present invention one, the robot navigation of view-based access control model moves into one's husband's household upon marriage method flow diagram.As it is shown in figure 1, this flow process comprises the following steps:

S101, obtain robot current time Position and orientation parameters (x in global coordinate system according to speedometer or Global localization sensor, y, θ), x is the robot abscissa relative to initial point, y is the robot vertical coordinate relative to initial point, θ be robot towards the angle relative to x-axis, rotate to be counterclockwise on the occasion of angle angle, clockwise turn to negative value angle angle；

S102, determine the door that robot to pass through according to user instruction；

S103, determining that robot moves into one's husband's household upon marriage and open the region of photographic head before, each unlatching photographic head region is: Area_i=(x_j,y_k) (1≤j≤N, 1≤k≤M), wherein i represents the numbering of door, and N and M represents the scope in certain region in front of the door；

S104, calculate and this time navigate terminal；

After S105, beginning and end are determined, by A* algorithm calculating robot's walking path, control robot motion to the terminal that navigates；

S106, the dead reckoning information (x returned according to speedometer_r,y_r,θ_r), the position of calculating robot's phase opposite house and attitude, obtain robot towards the angle Δ θ with robot Yu door midpoint line, control revolute Δ θ and make robot towards door；

S107, robot are static, and slave computer sends request to host computer and opens photographic head order simultaneously, and host computer opens the binocular camera being positioned at robot front, and starts to gather image, carry out an identification；

S108, the coordinate x of door the right and left frame returned according to image procossing_l,y_l,x_r,y_r(x_l< x_r,y_l< y_r) calculate door centre coordinate (x₀,y₀), wherein,

$x_0=\frac{x_l+x_r}{2},$

$y_0=\frac{y_l+y_r}{2};$

S109, with x_o,y_oFor initial point, robot is currently oriented benchmark, to set up cartesian coordinate system XOY from door left frame sensing left frame for x-axis forward；

S110, obtain robot coordinate (x ' under XOY coordinate system_r1,y′_r1,θ′_r1), and obtain robot and relatively move into one's husband's household upon marriage first distance, delta d correcting point (0 ,-1200) in process₁With angle delta θ₁；

S111, control robot craspedodrome Δ d₁, then turning Δ θ₁, according to dead reckoning information obtain robot currently towards with door perpendicular bisector angle Δ θ '₁, control robot and turn over Δ θ '₁Angle aligns target door；

S112, obtain robot coordinate (x ' under XOY coordinate system_r2,y′_r2,θ′_r2), obtain robot and relatively move into one's husband's household upon marriage second distance, delta d correcting point (0 ,-800) in process₂With angle delta θ₂；

S113, control robot craspedodrome Δ d₂, then turning Δ θ₂, according to dead reckoning information calculate robot currently towards with door perpendicular bisector angle Δ θ '₂, make robot turn over Δ θ '₂To main entrance；

S114, obtain robot coordinate (x ' under XOY coordinate system_r3,y′_r3,θ′_r3), obtain robot and relatively move into one's husband's household upon marriage the 3rd the distance, delta d correcting point (0 ,-400) in process₃With angle delta θ₃；

S115, control robot craspedodrome Δ d₃, then turning Δ θ₃, according to dead reckoning information obtain robot currently towards with door perpendicular bisector angle Δ θ '₃, make robot turn over Δ θ '₃To main entrance；

S116, control robot advance 1000mm, make robot complete operation of entering.

Further, in step S104, described calculating is this time navigated terminal, farther includes following steps:

Reference zone is scanned for, obtain each reference point in reference zone to robot current location Euclidean distance namelyWherein x, y represent certain grid coordinate in grating map；

To all d tried to achieve_iD is tried to achieve in sequence_iMinima；

d_iMinima corresponding grid positions be terminal of robot this time navigation.

Fig. 2 is that in the embodiment of the present invention one, the robot navigation of view-based access control model moves into one's husband's household upon marriage the method flow diagram of the door identification in method, namely carries out a step identified in step S107.As in figure 2 it is shown, this flow process comprises the following steps:

The left and right two width RBG image I that binocular camera is collected by S201, host computer_l、I_rCarry out gray processing process respectively, obtain gray level image Gray_l、Gray_r；

S202, employing image overall Binarization methods (such as threshold method, the big law of OSTU, Shanbhag method etc.) are to the gray level image Gray obtained_l、Gray_rCarry out binary conversion treatment respectively and obtain bianry image Binary_l、Binary_r；

S203, use are shaped as rectangle (a < b, and a value is 1 or 2, b span be b < h&b > h.2, wherein h is the height collecting image) structural element, carry out morphological image burn into expansion process obtain bianry image Binary '_l、Binary′_rIn vertical stripe regionNamely this region is likely doorframe or the region of door leaf existence；

S204, the vertical stripe region obtained in step S203 are Matching unit, to R_lAnd R_rIn vertical stripe region mate；

S205, left and right sides corresponding point application binocular range measurement principle is drawn this positional information (x and y) under robot coordinate system by the vertical stripe region obtained in step S204, obtain the developed width information in each vertical stripe region in image simultaneously

$wide=\sqrt{{(x_l-x_r)}^2+{(y_l-y_r)}^2}$

S206, developed width in conjunction with domestic environment Xiamen are 850mm-1200mm, can obtain meeting the vertical stripe region (vertical stripe region (door leaf+left and right sides doorframe), two vertical stripe regions (doorframe and doorframe, doorframe and door leaf)) of actual door width, further door is thought in the vertical stripe region obtained, and by door the right and left frame coordinate x under robot coordinate system_l,y_l,x_r,y_rReturn slave computer and (when for vertical stripe region (door leaf), return the coordinate of both sides, vertical stripe region；When for two vertical stripe regions (doorframe and doorframe), return the coordinate of two vertical stripe areas outside；When for two vertical stripe regions (doorframe and door leaf), return the coordinate of two vertical stripe area inside).

Fig. 3 is that in the embodiment of the present invention one, the robot navigation of view-based access control model moves into one's husband's household upon marriage the method flow diagram of the vertical stripe Region Matching in method, namely to R in step S204_lAnd R_rIn vertical stripe region carry out the step mated.As it is shown on figure 3, this flow process comprises the following steps:

S301, there is parallax according to the object same in binocular solid matching principle imaging in the photographic head of two, left and right, and for the parallel binocular range finding model of optical axis, it is the x of imaging point under left camera image coordinate system_lValue is more than its x of imaging point under right camera image coordinate system_r, i.e. R_lIn elementCorresponding R_rIn occurrenceMeetWhereinForThe x value of regional center point,ForThe x value of regional center point, selectsImaging point.

S302, retrain according to geometric similarity in binocular solid matching principle, i.e. R_lIn elementCorresponding R_rIn occurrenceMeet its geometric properties to be more or less the same, include but not limited to peak width w, color (rgb color space, HSV color space, YUV color space etc.), texture (LBP etc.) feature, by features described above similarity is measured:

For width characteristics: RespectivelyWidth, n is R_rMeet the region total quantity of constraint；

To other features: adopt statistics with histogram, and adopt the mode of similarity measurement (such as Euclidean distance, mahalanobis distance, Pasteur's distance etc.) to carry out Similarity measures and can obtain feature correspondence similarity S_feature；

May finally obtain its similarity is

Select similarity maximumForOccurrence.

S303, return S301, repeat S301, S302 and obtain all of matching area in left images.

Technical scheme in above-described embodiment is owing to employing speedometer, vision sensor etc., global position information according to the information computer device people that speedometer returns, the information calculating door returned according to vision and the relative position relation of robot, position and posture to robot effectively obtain, thus controlling the motion that robot realizes moving into one's husband's household upon marriage accurately.

Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt the form of complete hardware embodiment, complete software implementation or the embodiment in conjunction with software and hardware aspect.And, the present invention can adopt the form at one or more upper computer programs implemented of computer-usable storage medium (including but not limited to disk memory and optical memory etc.) wherein including computer usable program code.

The present invention is that flow chart and/or block diagram with reference to method according to embodiments of the present invention, equipment (system) and computer program describe.It should be understood that can by the combination of the flow process in each flow process in computer program instructions flowchart and/or block diagram and/or square frame and flow chart and/or block diagram and/or square frame.These computer program instructions can be provided to produce a machine to the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device so that the instruction performed by the processor of computer or other programmable data processing device is produced for realizing the device of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.

These computer program instructions may be alternatively stored in and can guide in the computer-readable memory that computer or other programmable data processing device work in a specific way, the instruction making to be stored in this computer-readable memory produces to include the manufacture of command device, and this command device realizes the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.

These computer program instructions also can be loaded in computer or other programmable data processing device, make on computer or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computer or other programmable devices provides for realizing the step of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.

Obviously, the present invention can be carried out various change and modification without deviating from the spirit and scope of the present invention by those skilled in the art.So, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.

Claims (4)

1. the robot navigation of a view-based access control model moves into one's husband's household upon marriage method, it is characterised in that comprise the following steps:

S101, obtain robot current time Position and orientation parameters (x in global coordinate system according to speedometer or Global localization sensor, y, θ), x is the robot abscissa relative to initial point, y is the robot vertical coordinate relative to initial point, θ be robot towards the angle relative to x-axis, rotate to be counterclockwise on the occasion of angle angle, clockwise turn to negative value angle angle；

S102, determine the door that robot to pass through according to user instruction；

S103, determining that robot moves into one's husband's household upon marriage and open the region of photographic head before, each unlatching photographic head region is: Area_i=(x_j,y_k) (1≤j≤N, 1≤k≤M), wherein i represents the numbering of door, and N and M represents the scope in certain region in front of the door；

S104, calculate and this time navigate terminal；

After S105, beginning and end are determined, by A* algorithm calculating robot's walking path, control robot motion to the terminal that navigates；

S106, the dead reckoning information (x returned according to speedometer_r,y_r,θ_r), the position of calculating robot's phase opposite house and attitude, obtain robot towards the angle Δ θ with robot Yu door midpoint line, control revolute Δ θ and make robot towards door；

S107, robot are static, and slave computer sends request to host computer and opens photographic head order simultaneously, and host computer opens the binocular camera being positioned at robot front, and starts to gather image, carry out an identification；

S108, the coordinate x of door the right and left frame returned according to image procossing_l,y_l,x_r,y_r(x_l<x_r,y_l<y_r) calculate door centre coordinate (x₀,y₀), wherein,

$x_0=\frac{x_l+x_r}{2},$

$y_0=\frac{y_l+y_r}{2};$

S109, with x_o,y_oFor initial point, robot is currently oriented benchmark, to set up cartesian coordinate system XOY from door left frame sensing left frame for x-axis forward；

S110, obtain robot coordinate (x ' under XOY coordinate system_r1,y′_r1,θ′_r1), and obtain robot and relatively move into one's husband's household upon marriage in process first and correct point (x_l1,y_l1) distance, delta d₁With angle delta θ₁, wherein,

-200mm<x_l1< 200mm,

-1400mm<y_l1<-1000mm；

S111, control robot craspedodrome Δ d₁, then turning Δ θ₁, according to dead reckoning information obtain robot currently towards with door perpendicular bisector angle Δ θ '₁, control robot and turn over Δ θ '₁Angle is to main entrance；

S112, obtain robot coordinate (x ' under XOY coordinate system_r2,y′_r2,θ′_r2), obtain robot and relatively move into one's husband's household upon marriage in process second and correct point (x_l2,y_l2) distance, delta d₂With angle delta θ₂, wherein,

-200mm<x_l2< 200mm,

-1000mm<y_l2<-600mm；

S113, control robot craspedodrome Δ d₂, then turning Δ θ₂, according to dead reckoning information calculate robot currently towards with door perpendicular bisector angle Δ θ '₂, make robot turn over Δ θ '₂To main entrance；

S114, obtain robot coordinate (x ' under XOY coordinate system_r3,y′_r3,θ′_r3), obtain robot and relatively move into one's husband's household upon marriage in process the 3rd and correct point (x_l3,y_l3) distance, delta d₃With angle delta θ₃, wherein,

-200mm<x_l3< 200mm,

-600mm<y_l3<-300mm；

S115, control robot craspedodrome Δ d₃, then turning Δ θ₃, according to dead reckoning information obtain robot currently towards with door perpendicular bisector angle Δ θ '₃, make robot turn over Δ θ '₃To main entrance；

S116, control robot advance Δ d, wherein 800mm < Δ d < 1200mm, make robot complete operation of entering.

2. method according to claim 1, it is characterised in that in step S104, described calculating is this time navigated terminal, farther includes:

Reference zone is scanned for, obtain each reference point in reference zone to robot current location Euclidean distance namelyWherein x, y represent certain grid coordinate in grating map；

To all d tried to achieve_iD is tried to achieve in sequence_iMinima；

d_iMinima corresponding grid positions be terminal of robot this time navigation.

3. method according to claim 1, it is characterised in that in step s 107, described in carry out identifying, farther include:

The left and right two width RBG image I that binocular camera is collected by S201, host computer_l、I_rCarry out gray processing process respectively, obtain gray level image Gray_l、Gray_r；

S202, employing image overall Binarization methods (such as threshold method, the big law of OSTU, Shanbhag method etc.) are to the gray level image Gray obtained_l、Gray_rCarry out binary conversion treatment respectively and obtain bianry image Binary_l、Binary_r；

S203, use are shaped as rectangle (a<b, and a value be 1 or 2, b spans is b<h&b>h.2, wherein h is the height collecting image) structural element, carry out morphological image burn into expansion process obtain bianry image Binary '_l、Binary′_rIn vertical stripe regionNamely this region is likely doorframe or the region of door leaf existence；

S204, the vertical stripe region obtained in step S203 are Matching unit, to R_lAnd R_rIn vertical stripe region mate；

S205, left and right sides corresponding point application binocular range measurement principle is drawn this positional information (x and y) under robot coordinate system by the vertical stripe region obtained in step S204, obtain the developed width information in each vertical stripe region in image simultaneously

$wide=\sqrt{{(x_l-x_r)}^2+{(y_l-y_r)}^2}$

S206, developed width in conjunction with domestic environment Xiamen are 850mm-1200mm, can obtain meeting the vertical stripe region (vertical stripe region (door leaf+left and right sides doorframe), two vertical stripe regions (doorframe and doorframe, doorframe and door leaf)) of actual door width, further door is thought in the vertical stripe region obtained, and by door the right and left frame coordinate x under robot coordinate system_l,y_l,x_r,y_rReturn slave computer and (when for vertical stripe region (door leaf), return the coordinate of both sides, vertical stripe region；When for two vertical stripe regions (doorframe and doorframe), return the coordinate of two vertical stripe areas outside；When for two vertical stripe regions (doorframe and door leaf), return the coordinate of two vertical stripe area inside).

4. method according to claim 3, it is characterised in that in step S204, described to R_lAnd R_rIn vertical stripe region mate, farther include:

S301, there is parallax according to the object same in binocular solid matching principle imaging in the photographic head of two, left and right, and for the parallel binocular range finding model of optical axis, it is the x of imaging point under left camera image coordinate system_lValue is more than its x of imaging point under right camera image coordinate system_r, i.e. R_lIn elementCorresponding R_rIn occurrenceMeetWhereinForThe x value of regional center point,ForThe x value of regional center point, selectsImaging point.

S302, retrain according to geometric similarity in binocular solid matching principle, i.e. R_lIn elementCorresponding R_rIn occurrenceMeet its geometric properties to be more or less the same, include but not limited to peak width w, color (rgb color space, HSV color space, YUV color space etc.), texture (LBP etc.) feature, by features described above similarity is measured:

For width characteristics: RespectivelyWidth, n is R_rMeet the region total quantity of constraint；

To other features: adopt statistics with histogram, and adopt the mode of similarity measurement (such as Euclidean distance, mahalanobis distance, Pasteur's distance etc.) to carry out Similarity measures and can obtain feature correspondence similarity S_feature；

May finally obtain its similarity is

Select similarity maximumForOccurrence.

S303, return S301, repeat S301, S302, obtain all of matching area in left images.