CN110154053A - A kind of indoor explanation robot and its explanation method based on OCR - Google Patents
A kind of indoor explanation robot and its explanation method based on OCR Download PDFInfo
- Publication number
- CN110154053A CN110154053A CN201910485389.6A CN201910485389A CN110154053A CN 110154053 A CN110154053 A CN 110154053A CN 201910485389 A CN201910485389 A CN 201910485389A CN 110154053 A CN110154053 A CN 110154053A
- Authority
- CN
- China
- Prior art keywords
- robot
- explanation
- exhibition position
- tourist
- ocr
- 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.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0242—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using non-visible light signals, e.g. IR or UV signals
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Acoustics & Sound (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Manipulator (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The indoor explanation robot and its explanation method that the invention discloses a kind of based on OCR, including ultrasonic sensor, infrared sensor, obliquity sensor, OCR identification module, audio output module, Audio Input Modules, mobile execution module, data memory module and central control unit.The present invention enhances the intelligence of robot using image procossing and text recognition technique, it presents briefly and succinctly two levels by slightly making peace and is explained, the tourist for introducing text and wanting wholwe-hearted ornamental showpiece for being inconvenient to read showpiece is helped to understand showpiece, it is more more accurate than the tour guide APP at this stage based on GPS under environment indoors；It is more relatively sanitary than automatic briefing earphone, convenient and lively；Robot can inquire whether tourist wants a step to understand being discussed in detail for the showpiece after slightly saying showpiece, be presented briefly and succinctly if necessary, and this selectable explanation mode meets the demand of different tourists, more humanized；The human resources for saving tour guide industry to a certain extent, reduce human cost.
Description
Technical field
The invention belongs to intelligent robot technology fields, and in particular to a kind of indoor explanation robot based on OCR and its
Explanation method.
Background technique
The domestic robot having at present for indoor tour guide, but intelligence degree is not also high.With science and technology it is continuous
Progressive and robot technology continuous development, intelligent robot gradually enter into huge numbers of families, also occur many intelligence in the market
Energy robot offers convenience to people's lives and enjoyment, wherein the one kind of interaction robot as intelligent robot, Neng Gouhe
People's interaction adds many enjoyment to people's lives, the especially life to old man or child.With social productive forces
More and more times are used to lie fallow and entertain by development and improvement of living standard, people, to greatly facilitate tourism
The development of industry.In recent years, going sight-seeing the cultural Meccas such as museum, former residences of celebrities becomes a kind of fashion, tourist's increasing number.In order to obtain
Obtain more preferably visit experience, it usually needs guide introduces various articles, traces to tourist and carries out to relevant history story
Explanation.Since tourist is large number of, it need to enter in batches, therefore guide must complete repeated explanation work, waste
Time and manpower, increase job costs.Simultaneously because the memory of human brain is limited, the solution that guide sometimes cannot be clear and complete
Answer the problem of tourist proposes.
A kind of guidance method of intelligent guide robot, but this tour guide are disclosed in CN103699126 in the prior art
Robot mainly realizes navigator fix according to WIFI, is explained by identification article, but this guide robot scene mode
It is very limited, since WIFI layout can be related to a large amount of site, when facing large scene mode, needs to put into a large amount of
Distribution, when cannot achieve and precisely identify and position in face of a network environment is bad or the lesser scene of range, from
And it is unable to complete explanation work.
The indoor explanation robot and its explanation method that therefore, it is necessary to a kind of based on OCR.
Summary of the invention
The indoor explanation robot and its explanation method that it is an object of that present invention to provide a kind of based on OCR, to solve at present
Robot for indoor tour guide in face of a network environment is bad or the lesser scene of range, cannot achieve precisely identification and
Positioning, thus the problem of being unable to complete explanation work.
To achieve the above object, the technical scheme adopted by the invention is that:
A kind of indoor explanation robot based on OCR, including ultrasonic sensor, infrared sensor, obliquity sensor,
OCR identification module, audio output module, Audio Input Modules, mobile execution module, data memory module and center control are single
Member, the central control unit respectively with the ultrasonic sensor, infrared sensor, obliquity sensor, OCR identification module,
Audio output module, Audio Input Modules, mobile execution module are connected with data memory module；It is the ultrasonic sensor, red
Outer sensor and obliquity sensor are used cooperatively, for explaining the distance between robot acquisition and exhibition position and establishing semantically
Figure；The OCR identification module text information on exhibition position for identification；The Audio Input Modules are for explaining robot reception
And identifying audio-frequency information, the audio output module is described for explaining the explanation audio-frequency information that robot output phase answers exhibition position
Mobile execution module completes corresponding movement for explaining robot, and the data memory module is for storing explanation institute, robot
The exhibition position content information and explanation robot information collected for needing to explain；The central control unit is for entirely controlling
Explain the work of robot.
Preferably, the OCR identification module uses Tesseract-OCR engine.
Preferably, the central control unit uses the SCM system of ARM core processor.
It preferably, further include camera, the camera is connect with the central control unit.
It preferably, further include wireless communication module, the wireless communication module is connect with the central control unit.
A kind of explanation method of the indoor explanation robot based on OCR, comprising the following steps:
S1: interpreter is generated by the data that ultrasonic sensor, infrared sensor, camera and obliquity sensor acquire
Device people is responsible for the indoor exhibition position environment semanteme map of explanation, and stores into the data memory module of explanation robot；
S2: explanation robot inquires the visit mode of tourist by audio output module and is received by Audio Input Modules
Tourist's instruction, if tourist's selecting sequence is visited, explanation robot leads tourist's sequence to visit, if tourist specifies exhibition position to visit,
Explanation robot then plans that a paths lead tourist to specified exhibition position；
S3: explanation robot identifies current exhibition position information by OCR identification module, and is tourist by audio output module
Slightly say the summary content of current exhibition position；Position correction is carried out according to exhibition position information simultaneously；S4: explanation robot passes through audio output
Whether module queries tourist is it should be understood that the detailed content of current exhibition position and receive tourist's instruction by Audio Input Modules, if swimming
Visitor is it should be understood that currently the detailed content of exhibition position, explanation robot then call the detailed of the current exhibition position stored in data memory module
Thin content enters step S5 if tourist is not required to the detailed content it is to be understood that current exhibition position；
S5: explanation robot inquires whether tourist terminates to visit and connect by Audio Input Modules by audio output module
Tourist's instruction is received, if tourist terminates to visit, explanation robot terminates this tour guide, if tourist does not terminate to visit, is back to
Step S2.
Preferably, step S1 further includes sub-step:
S101: progress border detection first；Grating map is initialized as 0, starting setting is in explanation robot or so two
Sonar and the start boundary detection of side, read corresponding sonar value；If left sound value and right sound value are respectively less than 0.35 meter, before showing
There is barrier in side, and explanation robot turns left or turns right according to inward turning method algorithm, otherwise explains robot straight trip；Complete border detection
Afterwards, then it is ready for exhibition position detection；
S102: after explaining robot completion border detection, beginning to approach exhibition position, when explanation robot is equal to apart from exhibition position
Or its sonar will be emitted when less than 0.5m and read actual distance value, according to this distance value, explain the center control of robot
Then unit control explanation robot security detects towards exhibition position along the exhibition position clockwise that starts close to exhibition position；
S103: explanation robot completes detection of obstacles during carrying out exhibition position detection, acquires exhibition by camera
Position information picture, calls OCR to identify the semantic information of exhibition position, to generate the indoor exhibition position ring that explanation robot is responsible for explanation
Border semanteme map.
Preferably, in step s3, one exhibition position of the every arrival of robot is explained, carries out positioning school using exhibition position information
Just, it or when robot is artificially moved to some position, needs to relocate, specific step is as follows for positioning:
S301: explanation robot rotates a circle in current location, if discovery exhibition position, explains robot and lean on to the exhibition position
Closely, if not finding exhibition position, robot random movement a distance is explained until discovery exhibition position；
S302: explanation robot identifies the exhibition position information by OCR identification module；
S303: explanation robot is according to exhibition position environment semanteme map in the exhibition position information matches room, so that it is fixed to complete itself
Position.
The method have the benefit that: (1) when a robot enter a new environment, it needs to be familiar with first
Environment, just as servant preferably services.
(2) present invention enhances the intelligence of robot using image procossing and text recognition technique.Robot is pressed first
The visit of tourist requires before taking them to corresponding showpiece, then presents briefly and succinctly two levels by slightly making peace and is explained, helps not
The tourist for introducing text and wanting wholwe-hearted ornamental showpiece of easy-to-read showpiece understands showpiece, diverts one's attention without tourist, reaches a kind of
The good visit effect that audiovisual combines.
(3) more more accurate than the tour guide APP at this stage based on GPS under environment indoors of the invention；Than automatic briefing earphone
It is relatively sanitary, convenient and lively；Robot can inquire whether tourist wants a step to understand the detailed of the showpiece after slightly saying showpiece
It introduces, is presented briefly and succinctly if necessary, this selectable explanation mode meets the demand of different tourists, more humanized；
The human resources for saving tour guide industry to a certain extent, reduce human cost.
(4) when robot is artificially moved, it can identify that exhibition position information is positioned by OCR；Robot is every when explaining
An exhibition position is reached, position correction is carried out using exhibition position information, the accumulated error of robot ambulation process generation can be reduced.
Detailed description of the invention
Fig. 1 is that one embodiment of the present of invention explanation machine manually makees flow diagram.
Fig. 2 is the process signal that one embodiment of the present of invention explanation robot terminates progress self poisoning after this tour guide
Figure.
Fig. 3 is the actual environment figure that one embodiment of the present of invention explains robot.
Fig. 4 be one embodiment of the present of invention explain machine life at semantic map.
Fig. 5 is the structural schematic diagram of one embodiment of the present of invention.
Specific embodiment
Below with reference to attached drawing 1-5 of the invention, technical solution in the embodiment of the present invention is clearly and completely retouched
It states, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based on the present invention
In embodiment, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Embodiment 1:
As shown in figure 5, a kind of indoor explanation robot based on OCR, including ultrasonic sensor, infrared sensor, incline
Angle transducer, OCR identification module, audio output module, Audio Input Modules, mobile execution module, data memory module and in
Control unit is entreated, the central control unit is known with the ultrasonic sensor, infrared sensor, obliquity sensor, OCR respectively
Other module, audio output module, Audio Input Modules, mobile execution module are connected with data memory module；The ultrasonic wave passes
Sensor, infrared sensor and obliquity sensor are used cooperatively, for explaining the distance between robot acquisition and exhibition position and establishing
Semantic map；The OCR identification module text information on exhibition position for identification；The Audio Input Modules are for explaining machine
People receives and identifies audio-frequency information, and the audio output module answers the explanation audio of exhibition position to believe for explaining robot output phase
Breath, the mobile execution module complete corresponding movement for explaining robot, and the data memory module is for storing explanation
The exhibition position content information and explanation robot information collected explained required for robot；The central control unit is used for
The work of entire control explanation robot.
Preferred in this embodiment, the OCR identification module uses Tesseract-OCR engine.Tesseract-OCR
Engine is currently one of higher identification engine of accuracy rate in the industry.Utilize the sample of jTessBoxEditor tool training oneself
Library, so that recognition accuracy is higher on thinking field to be applied.
Preferred in this embodiment, the central control unit uses the SCM system of ARM core processor.And it transports
The insertion scheme of row (SuSE) Linux OS.Its kernel dominant frequency can arrive 1.0GHZ, have 32/64 inside bus structure, 32/
The operational capability of 200,000,000 instructions per second may be implemented in 2 grades of cache of data/commands 1 grade of cache, 512KB of 32KB.Monolithic
Machine core board has 512MDDR2 memory and NandFLASH memory, is powered using 5V DC power supply.Collect on single-chip microcomputer extension plate
At MFC multimedia hardware encoder, support MPEG-1/2/4, H.263, the H.264 encoding and decoding of equal format videos, support simulation and
Digital TV output, to handle video output data, is additionally integrated with JPEG hardware image encoder, maximum can encoding and decoding
The picture of 8192*8192 resolution ratio, the image to capture to camera carry out hardware encoding.In order to connect camera and wireless
Communication module also inherits USB chip and three USB interfaces on single-chip microcomputer extension plate.One of USB interface connection camera shooting
Head, one of USB interface connect wireless communication module, one of USB interface is connected to system debug terminal interface.
The liquid crystal display interface of 45pin is additionally provided on single-chip microcomputer extension plate, connector is inserted using 0.5mmFFC/FPC flat cable
Seat.Single-chip microcomputer extension plate is provided with sound card chip, and sound card chip is connect to complete the sound of image recognition with audio output circuit
Feedback.
It is preferred in this embodiment, it further include camera, the camera is connect with the central control unit.
It is preferred in this embodiment, it further include wireless communication module, the wireless communication module and the center control
Unit connection.
Embodiment 2:
As shown in Figure 1, a kind of explanation method of the indoor explanation robot based on OCR, comprising the following steps:
S1: interpreter is generated by the data that ultrasonic sensor, infrared sensor, camera and obliquity sensor acquire
Device people is responsible for the indoor exhibition position environment semanteme map of explanation, and stores into the data memory module of explanation robot；
S2: explanation robot inquires the visit mode of tourist by audio output module and is received by Audio Input Modules
Tourist's instruction, if tourist's selecting sequence is visited, explanation robot leads tourist's sequence to visit, if tourist specifies exhibition position to visit,
Explanation robot then plans that a paths lead tourist to specified exhibition position；
S3: explanation robot identifies current exhibition position information by OCR identification module, and is tourist by audio output module
Slightly say the summary content of current exhibition position；Position correction is carried out according to exhibition position information simultaneously；S4: explanation robot passes through audio output
Whether module queries tourist is it should be understood that the detailed content of current exhibition position and receive tourist's instruction by Audio Input Modules, if swimming
Visitor is it should be understood that currently the detailed content of exhibition position, explanation robot then call the detailed of the current exhibition position stored in data memory module
Thin content enters step S5 if tourist is not required to the detailed content it is to be understood that current exhibition position；
S5: explanation robot inquires whether tourist terminates to visit and connect by Audio Input Modules by audio output module
Tourist's instruction is received, if tourist terminates to visit, explanation robot terminates this tour guide, if tourist does not terminate to visit, is back to
Step S2.
Preferably, step S1 further includes sub-step:
S101: progress border detection first；Grating map is initialized as 0, starting setting is in explanation robot or so two
Sonar and the start boundary detection of side, read corresponding sonar value；If left sound value and right sound value are respectively less than 0.35 meter, before showing
There is barrier in side, and explanation robot turns left or turns right according to inward turning method algorithm, otherwise explains robot straight trip；Complete border detection
Afterwards, then it is ready for exhibition position detection；
S102: after explaining robot completion border detection, beginning to approach exhibition position, when explanation robot is equal to apart from exhibition position
Or its sonar will be emitted when less than 0.5m and read actual distance value, according to this distance value, explain the center control of robot
Then unit control explanation robot security detects towards exhibition position along the exhibition position clockwise that starts close to exhibition position；
S103: explanation robot completes detection of obstacles during carrying out exhibition position detection, acquires exhibition by camera
Position information picture, calls OCR to identify the semantic information of exhibition position, to generate the indoor exhibition position ring that explanation robot is responsible for explanation
Border semanteme map.
Preferably, in step s3, one exhibition position of the every arrival of robot is explained, carries out positioning school using exhibition position information
Just, it or when robot is artificially moved to some position, needs to relocate, specific step is as follows for positioning:
S301: explanation robot rotates a circle in current location, if discovery exhibition position, explains robot and lean on to the exhibition position
Closely, if discovery exhibition position, then robot random movement a distance is explained until discovery exhibition position；
S302: explanation robot identifies the exhibition position information by OCR identification module；
S303: explanation robot is according to exhibition position environment semanteme map in the exhibition position information matches room, so that it is fixed to complete itself
Position.
Wherein, firstly, explanation robot carries out border detection by two sonars at left and right sides of it.Then, interpreter
Device people is brought in the front of barrier by red ball tracker.When explaining robot and tracking red ball by camera, it can be with
Obtain the distance and angle of ball.The algorithm includes three parts: border detection, detection of obstacles and given semantic information.Side
Boundary's detection and detection of obstacles ambient boundary and all barriers for identification, and semantic information is used to obtain the name of barrier
Claim.
First part: border detection.
When explanation robot enters circumstances not known, border detection will be first carried out in it.Software based on Nao robot is flat
Platform writes program code with Python.Pseudocode is as follows:
Step 1: grid map is initialized as 0.
[[0 indicates in range (row)] indicates b range (column) to map=
Step 2: starting sonar and start boundary detection.
SonarProxy=ALProxy (" ALSonar ", IP, PORT)
MemoryProxy=ALProxy (" ALMemory ", IP, PORT)
Step 3: reading the value of sonar.
Lvalue=memoryProxy.getData (" Device/SubDeviceList/US/Left/Sensor/
Value”)
Rvalue=memoryProxy.getData (" Device/SubDeviceList/US/Right/Sensor/
Value”)
Step 4: if lvalue and r value are both less than 0.35 meter, robot will turn left or turn right according to inward turning method algorithm, turn
It is curved to add 1, otherwise keep straight on.
If (lvalue < 0.35, r value < 0.35):
Self.motionProxy.walkTo (0,0 ,-math.pi/2.0) # turns left
self.motionProxy.walkTo(0.08,0,0)
CountTurn=countTurn+1
Other:
Self.motionProxy.walkTo (0.08,0,0) # straight trip
Step 5: if not completing border detection, going to step 3, otherwise go to step 6 and be ready for barrier
Detection.
If (map [x] [y]==1 and countTurn >=3):
BorderFinish=is true
Step 6: terminating.
Second part and Part III: detection of obstacles and given semantic information.
When explaining robot completion border detection, red club directs it towards the front of barrier.It is connect in explanation robot
Before nearly obstacle, explanation robot continues to follow red ball.When the close enough barrier of explanation robot, (threshold value is arranged for we
For 0.5m), red ball will be rapidly removed.If explanation robot can not detect red ball in 30 seconds, it will emit its sonar
And sonar value is read, according to this value, explaining robot calculating should walk how much walk the close enough barrier of ability.When it is arrived
When up to safe distance (0.25 meter), it towards barrier and will start detection of obstacles clockwise.When explanation robot completes barrier
When hindering the border detection of object, it will identify exhibition position information to the semantic information of acquired disturbance object by OCR.In order to reduce noise
Influence, if the absolute value of arnotto ball angle is less than 30 degree, we allow explanation robot continue to keep straight on.On the other hand, work as angle
When greater than 30 degree, explanation robot will turn left, and otherwise when angle, which is less than -30, to be spent, explanation robot will turn right.Pseudocode
It is as follows:
Step 1: starting red ball and track and follow red ball and the trackerProxy=ALProxy that freely walks
The red ball detection of (" ALRedBallTracker ", IP, PORT) #launch
trackerProxy.startTracker()
If (abs (redBallAngle) < math.radians (30)):
MotionProxy.walkTo (0.08,0,0) # straight trip
Elif (redBallAngle >=math.radians (30)):
MotionProxy.walkTo (0,0, math.pi/2.0) # turns left
Head is switched to 0 radian by motionProxy.angleInterpolation (" HeadYaw ", 0,1.0, True) #
motionProxy.walkTo(0.08,0,0)
Elif (redBallAngle≤- math.radians (30)):
MotionProxy.walkTo (0,0 ,-math.pi/2.0) # turns right
MotionProxy.angleInterpolation (" HeadYaw ", 0,1.0, True)
motionProxy.walkTo(0.08,0,0)
Step 2: if arnotto ball is lost 30 seconds, explanation robot will emit its sonar.
SonarProxy=ALProxy (" ALSonar ", IP, PORT)
MemoryProxy=ALProxy (" ALMemory ", IP, PORT)
sonarProxy.subscribe('Test_sonar')
Step 3: reading the value of sonar
Lvalue=memoryProxy.getData (" Device/SubDeviceList/US/Left/Sensor/
Value”)
Rvalue=memoryProxy.getData (" Device/SubDeviceList/US/Right/Sensor/
Value”)
Step 4: if sonar value less than 0.5 meter, illustrates that there is barrier in front, robot calculates how many step that walk first
It reaches at a distance from barrier less than 0.25 meter, is then transferred to detection of obstacles state；Otherwise, it indicates that map structuring terminates, turns
To step 910.
If (lvalue < 0.5 or r value < 0.5):
The step-length of number of steps=INT (minimum value (lvalue -0.25, r value -0.25)/0.08) # robot is 0.08m
MotionProxy.walkTo (number of steps * 0.08,0.0,0.0)
CountTurn=0
Obstacle=true
ObstacleFinish=is false
Step 5: if lvalue and both less than 0.25 meter of small value, indicating explanation robot just towards barrier, at this time with taking the photograph
As head one frame information of acquisition, then OCR is called to be identified, if there is representing the text information of exhibition position, be then stored into variable
Otherwise result ignores this identification as the semantic information of current barrier, i.e. exhibition position information.If sonar value is not less than
0.25 meter, indicate that explanation robot is located at the corner of barrier, explanation robot will turn right after two steps of walking.
If (lvalue > 0.25):
For the j (2) in range:
self.motionProxy.walkTo(0,0.1,0.0)
Self.motionProxy.walkTo (0,0.0 ,-math.pi/2.0) # turns right
For the k (2) in range:
self.motionProxy.walkTo(0,0.1,0.0)
Other:
Self.motionProxy.walkTo (0,0.1,0) # holding is walked to the left
Step 6: step 5 is repeated, until current detection of obstacles is completed.
Step 7: the word result that explanation robot identifies step 5 inserts concordance list t, and index variables Scount
Add 1.
Scount+=1
T.no=Scount
The exhibition position t.name=result# title
Step 8: going to step 1.
Step 9: terminating.
It explains robot and all detection of obstacles is completed according to above-mentioned algorithm.If explanation robot can not examine in 30 seconds
Red ball is measured, while its sonar can not detect that obstacle, explanation robot can say that " time-out terminates！".
In the description of the present invention, it is to be understood that, term " counterclockwise ", " clockwise " " longitudinal direction ", " transverse direction ",
The orientation of the instructions such as "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" or
Positional relationship is to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of the description present invention, rather than is indicated or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair
Limitation of the invention.
Claims (8)
1. a kind of indoor explanation robot based on OCR, which is characterized in that including ultrasonic sensor, infrared sensor, inclination angle
Sensor, OCR identification module, audio output module, Audio Input Modules, mobile execution module, data memory module and center
Control unit, the central control unit are identified with the ultrasonic sensor, infrared sensor, obliquity sensor, OCR respectively
Module, audio output module, Audio Input Modules, mobile execution module are connected with data memory module；The supersonic sensing
Device, infrared sensor and obliquity sensor are used cooperatively, for explaining the distance between robot acquisition and exhibition position and establishing language
Free burial ground for the destitute figure；The OCR identification module text information on exhibition position for identification；The Audio Input Modules are for explaining robot
Audio-frequency information is received and identified, the audio output module is used to explain the explanation audio-frequency information that robot output phase answers exhibition position,
The mobile execution module completes corresponding movement for explaining robot, and the data memory module is for storing explanation machine
The exhibition position content information and explanation robot information collected explained required for people；The central control unit is for entire
The work of control explanation robot.
2. a kind of indoor explanation robot based on OCR according to claim 1, which is characterized in that the OCR identifies mould
Block uses Tesseract-OCR engine.
3. a kind of indoor explanation robot based on OCR according to claim 1, which is characterized in that the center control
Unit uses the SCM system of ARM core processor.
4. a kind of indoor explanation robot based on OCR according to claim 1, which is characterized in that it further include camera,
The camera is connect with the central control unit.
5. a kind of indoor explanation robot based on OCR according to claim 1, which is characterized in that further include channel radio
Believe module, the wireless communication module is connect with the central control unit.
6. a kind of explanation method of indoor explanation robot based on OCR according to claim 1, which is characterized in that packet
Include following steps:
S1: explanation robot is generated by the data that ultrasonic sensor, infrared sensor, camera and obliquity sensor acquire
It is responsible for the indoor exhibition position environment semanteme map of explanation, and stores into the data memory module of explanation robot；
S2: explanation robot inquires the visit mode of tourist by audio output module and receives tourist by Audio Input Modules
Instruction, if tourist's selecting sequence is visited, explanation robot leads tourist's sequence to visit, if tourist specifies exhibition position to visit, explanation
Robot then plans that a paths lead tourist to specified exhibition position；
S3: explanation robot identifies current exhibition position information by OCR identification module, and is that tourist slightly says by audio output module
The summary content of current exhibition position；Position correction is carried out according to exhibition position information simultaneously；
S4: explanation robot by audio output module inquire tourist whether it should be understood that currently exhibition position detailed content and pass through
Audio Input Modules receive tourist's instruction, if tourist is it should be understood that currently the detailed content of exhibition position, explanation robot call number
According to the detailed content of the current exhibition position stored in memory module, if tourist is not required to the detailed content it is to be understood that current exhibition position, into
Enter step S5；
S5: explanation robot inquires whether tourist terminates to visit and receive by Audio Input Modules to swim by audio output module
Visitor's instruction, if tourist terminates to visit, explanation robot terminates this tour guide, if tourist does not terminate to visit, is back to step
S2。
7. a kind of explanation method of indoor explanation robot based on OCR according to claim 6, which is characterized in that step
Rapid S1 further includes sub-step:
S101: progress border detection first；Grating map is initialized as 0, starting is arranged at left and right sides of explanation robot
Sonar and start boundary detection, read corresponding sonar value；If left sound value and right sound value are respectively less than 0.35 meter, show that front has
Barrier, explanation robot turn left or turn right according to inward turning method algorithm, otherwise explain robot straight trip；After completing border detection,
Then it is ready for exhibition position detection；
S102: after explaining robot and completing border detection, exhibition position is begun to approach, when explanation robot is equal to or small apart from exhibition position
Its sonar will be emitted when 0.5m and read actual distance value, according to this distance value, explain the central control unit of robot
Then control explanation robot security detects towards exhibition position along the exhibition position clockwise that starts close to exhibition position；
S103: explanation robot completes detection of obstacles during carrying out exhibition position detection, acquires exhibition position letter by camera
Picture is ceased, OCR is called to identify the semantic information of exhibition position, to generate the indoor exhibition position environment language that explanation robot is responsible for explanation
Free burial ground for the destitute figure.
8. a kind of explanation method of indoor explanation robot based on OCR according to claim 6, which is characterized in that
In step S3, one exhibition position of the every arrival of robot is explained, carries out positioning correcting using exhibition position information, or when robot is by people
It when being moved to some position for ground, needs to relocate, specific step is as follows for positioning:
S301: explanation robot rotates a circle in current location, if discovery exhibition position, it is close to the exhibition position to explain robot, if
Exhibition position is not found, then explains robot random movement a distance until discovery exhibition position；
S302: explanation robot identifies the exhibition position information by OCR identification module；
S303: explanation robot is according to exhibition position environment semanteme map in the exhibition position information matches room, to complete self poisoning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910485389.6A CN110154053A (en) | 2019-06-05 | 2019-06-05 | A kind of indoor explanation robot and its explanation method based on OCR |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910485389.6A CN110154053A (en) | 2019-06-05 | 2019-06-05 | A kind of indoor explanation robot and its explanation method based on OCR |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110154053A true CN110154053A (en) | 2019-08-23 |
Family
ID=67627774
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910485389.6A Pending CN110154053A (en) | 2019-06-05 | 2019-06-05 | A kind of indoor explanation robot and its explanation method based on OCR |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110154053A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111645089A (en) * | 2020-06-17 | 2020-09-11 | 重庆大学 | Museum tour guide robot and robot system |
| CN111881825A (en) * | 2020-07-28 | 2020-11-03 | 深圳市点通数据有限公司 | Interactive text recognition method and system based on multi-perception data |
| CN112652073A (en) * | 2020-12-31 | 2021-04-13 | 中国电子科技集团公司信息科学研究院 | Autonomous navigation method and system based on cloud network end robot |
| CN113296495A (en) * | 2020-02-19 | 2021-08-24 | 苏州宝时得电动工具有限公司 | Path forming method and device for self-moving equipment and automatic working system |
| CN113370229A (en) * | 2021-06-08 | 2021-09-10 | 山东新一代信息产业技术研究院有限公司 | Exhibition hall intelligent explanation robot and implementation method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106989747A (en) * | 2017-03-29 | 2017-07-28 | 无锡市中安捷联科技有限公司 | A kind of autonomous navigation system based on indoor plane figure |
| CN107553505A (en) * | 2017-10-13 | 2018-01-09 | 刘杜 | Autonomous introduction system platform robot and explanation method |
| KR20180087798A (en) * | 2017-01-25 | 2018-08-02 | 엘지전자 주식회사 | Moving robot and control method therof |
| CN109129507A (en) * | 2018-09-10 | 2019-01-04 | 北京联合大学 | A kind of medium intelligent introduction robot and explanation method and system |
| CN208629445U (en) * | 2017-10-13 | 2019-03-22 | 刘杜 | Autonomous introduction system platform robot |
-
2019
- 2019-06-05 CN CN201910485389.6A patent/CN110154053A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20180087798A (en) * | 2017-01-25 | 2018-08-02 | 엘지전자 주식회사 | Moving robot and control method therof |
| CN106989747A (en) * | 2017-03-29 | 2017-07-28 | 无锡市中安捷联科技有限公司 | A kind of autonomous navigation system based on indoor plane figure |
| CN107553505A (en) * | 2017-10-13 | 2018-01-09 | 刘杜 | Autonomous introduction system platform robot and explanation method |
| CN208629445U (en) * | 2017-10-13 | 2019-03-22 | 刘杜 | Autonomous introduction system platform robot |
| CN109129507A (en) * | 2018-09-10 | 2019-01-04 | 北京联合大学 | A kind of medium intelligent introduction robot and explanation method and system |
Non-Patent Citations (1)
| Title |
|---|
| 邢琦玮: "中国优秀博硕士学位论文全文数据库（硕士）信息科技辑", 《中国优秀博硕士学位论文全文数据库（硕士）信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113296495A (en) * | 2020-02-19 | 2021-08-24 | 苏州宝时得电动工具有限公司 | Path forming method and device for self-moving equipment and automatic working system |
| CN113296495B (en) * | 2020-02-19 | 2023-10-20 | 苏州宝时得电动工具有限公司 | Path forming method and device of self-mobile equipment and automatic working system |
| CN111645089A (en) * | 2020-06-17 | 2020-09-11 | 重庆大学 | Museum tour guide robot and robot system |
| CN111881825A (en) * | 2020-07-28 | 2020-11-03 | 深圳市点通数据有限公司 | Interactive text recognition method and system based on multi-perception data |
| CN111881825B (en) * | 2020-07-28 | 2023-10-17 | 深圳市点通数据有限公司 | Interactive text recognition method and system based on multi-perception data |
| CN112652073A (en) * | 2020-12-31 | 2021-04-13 | 中国电子科技集团公司信息科学研究院 | Autonomous navigation method and system based on cloud network end robot |
| CN113370229A (en) * | 2021-06-08 | 2021-09-10 | 山东新一代信息产业技术研究院有限公司 | Exhibition hall intelligent explanation robot and implementation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110154053A (en) | A kind of indoor explanation robot and its explanation method based on OCR | |
| CN107179086B (en) | Drawing method, device and system based on laser radar | |
| Foxlin et al. | VIS-Tracker: A Wearable Vision-Inertial Self-Tracker. | |
| US6766245B2 (en) | Landmark-based location of users | |
| CN110378965A (en) | Determine the method, apparatus, equipment and storage medium of coordinate system conversion parameter | |
| CN106647745B (en) | Diagnosis guiding robot autonomous navigation system and method based on Bluetooth positioning | |
| WO2016131279A1 (en) | Movement track recording method and user equipment | |
| CN109724603A (en) | A kind of Indoor Robot air navigation aid based on environmental characteristic detection | |
| WO2021077941A1 (en) | Method and device for robot positioning, smart robot, and storage medium | |
| CN106292657A (en) | Mobile robot and patrol path setting method thereof | |
| CN105974456B (en) | A kind of autonomous underwater vehicle combined navigation system | |
| CN105074691A (en) | Context aware localization, mapping, and tracking | |
| CN103892995A (en) | Electronic seeing-eye dog robot | |
| CN108955682A (en) | Mobile phone indoor positioning air navigation aid | |
| CN103312899A (en) | Smart phone with blind guide function | |
| CN109916408A (en) | Robot indoor positioning and air navigation aid, device, equipment and storage medium | |
| Khan et al. | Recent advances in vision-based indoor navigation: A systematic literature review | |
| CN109059929A (en) | Air navigation aid, device, wearable device and storage medium | |
| WO2022161386A1 (en) | Pose determination method and related device | |
| Kamalam et al. | Augmented reality-centered position navigation for wearable devices with machine learning techniques | |
| CN111815844A (en) | Intelligent machine tour guide and control method, control device and storage medium thereof | |
| CN111477131A (en) | Intelligent exhibition hall voice broadcasting device and broadcasting method thereof | |
| WO2022000757A1 (en) | Ar-based robot internet of things interaction method and apparatus, and medium | |
| CN114153310A (en) | Robot guest greeting method, device, equipment and medium | |
| CN112017247A (en) | Method for realizing unmanned vehicle vision by using KINECT |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190823 |