CN110207710A - Robot method for relocating and device - Google Patents
Robot method for relocating and device Download PDFInfo
- Publication number
- CN110207710A CN110207710A CN201910561961.2A CN201910561961A CN110207710A CN 110207710 A CN110207710 A CN 110207710A CN 201910561961 A CN201910561961 A CN 201910561961A CN 110207710 A CN110207710 A CN 110207710A
- Authority
- CN
- China
- Prior art keywords
- local
- robot
- map
- target
- local map
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
Abstract
The present invention relates to robotic technology fields, more particularly to a kind of robot method for relocating and device.This method comprises: environmental information is obtained by camera and radar data, to construct local map and generate local message table.Obtain the corresponding global information table of global map machine, and the local map corresponding target local map in global map is determined with the corresponding relationship of global table information by local message table, further according to the error parameter between local map and target local map, effective error region is selected;By the radar data set for obtaining the multiple pixels chosen in effective error region, the determining and highest target radar data of robot current radar data similarity, are finally determined as the true pose of robot according to the corresponding object pose of target radar data.Using this method, position quickly is presently in robot and is accurately positioned, guarantees that robot is accurately positioned and is judged to ambient enviroment during the work time.
Description
Technical field
The present invention relates to robotic technology fields, more particularly to a kind of robot method for relocating and device.
Background technique
As the fast development of science and technology and people's lives level improve, more and more works in real life
Robot be can use to complete, especially some simple repetitive works, such as lift to move weight, cleaning etc..?
Starting robot carries out work or robot in the process of work, requires to be accurately located itself, to guarantee
The high efficiency of work.
However, in the prior art, using laser radar method or monocular vision to calculate substantially the method for robot reorientation
Method is relocated.Robot reorientation is carried out using laser radar method, is carried out cruelly using laser radar scanning ambient enviroment
Power search, probably determines the pose of robot.And monocular vision algorithm is used to carry out robot reorientation, it needs in environment
Middle deployment two dimensional code, by scanning the two-dimensional code the Position Approximate for carrying out characteristic matching and determining robot;But monocular vision algorithm is only
It can be used in the environment for posting specific two dimensional code, limit the use scope of robot.Therefore, either laser radar method or list
Mesh vision algorithm, it is larger to the reorientation error of robot pose, make robot that can not carry out standard to itself during the work time
True positioning improves the False Rate to ambient enviroment.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of robot method for relocating, in this way, can be right
The robot of initial time is relocated, so that it is determined that the true pose of robot, guarantees robot in the process of work
Ambient enviroment is accurately positioned and is judged.
The present invention also provides a kind of robot relocation device, to guarantee above method realization in practice and answer
With.
A kind of robot method for relocating, comprising:
When robot starting, pre-set camera and laser radar is called to obtain the current institute, robot
The environmental information at place;
According to the environmental information that the robot is presently in, building is presently in position as origin using the robot
Local map, and generate the corresponding local message table of the local map;
Pre-set global map and the corresponding global information table of the global map are obtained, and is based on the part
Corresponding relationship between information table and the global information table is selected corresponding with the local map in the global map
Target local map;
The local map is matched with the target local map, obtains the local map and the target office
Error parameter between portion's map;
Based on the error parameter, the effective error region that the robot is in the target local map is determined;
Multiple pixels are chosen in the effective error region, and determine each pixel in the global map
In corresponding radar data set;
Determine the current radar data in environmental information that the robot is presently in, and by the current radar data
It is matched, is obtained with the current radar data similarity most with each radar data in each radar data set
High target radar data;
The object pose for obtaining target position pixel corresponding with the target radar data, determines the object pose
For the true pose of the robot, the reorientation to the robot is completed.
Above-mentioned method, it is optionally, described that pre-set camera and the laser radar acquisition robot is called to work as
Preceding locating environmental information, comprising:
Pre-set camera is called, each of described robot is obtained and is identified the corresponding object of object
Body information, and by pre-set laser radar, determine each identified object relative to the opposite of the robot
Position;
Based on each identified corresponding object information of object and each identified object relative to the machine
The relative position of device people determines the environmental information that the robot is presently in.
Above-mentioned method, it is optionally, described to generate the corresponding local message table of the local map, comprising:
Relative position based on each identified object relative to the robot determines each identified object
Local coordinate of the body in the local map;
According to the identified corresponding object information of object and each identified object in the local map
Local coordinate, generate corresponding with local map local message table.
Above-mentioned method, it is optionally, described to match the local map with the target local map, obtain institute
State the error parameter between local map and the target part, comprising:
Determine each local objects included in the target local map, each local objects and the part
Each identified object in map corresponds;
Based on the global information table, target local message table corresponding with the target local map, the mesh are generated
Marking includes true coordinate of each local objects in the global map in local message table;
According to true coordinate of each local objects in the global map, calculate in the target local map
Relative distance between each local objects;
According to local coordinate of each identified object in the local map, calculate each in the local map
Relative distance between a identified object;
By the relative distance between each local objects and the relative distance between each identified object into
Row matching primitives obtain the error parameter between the local map and the target part.
Above-mentioned method, it is optionally, described to be based on the error parameter, determine that the robot is in the global map
In effective error region, comprising:
Origin in the local map is mapped in the target local map, it is described to determine that the origin maps to
The mapping point of target local map;
It based on the mapping point and the error parameter, determines using the mapping point as the center of circle, the error parameter is half
The effective error region of diameter, the effective error region are that the robot is in all possible positions in the global map
Region.
Above-mentioned method, optionally, each pixel of determination corresponding radar number in the global map
According to set, comprising:
It determines the pre-set search range of the robot, and according to described search range, each pixel is set
Point needs to carry out the search angle of search lighting;
According to described search range and search angle, determine that each pixel needs to carry out the search time of search lighting
Number, and according to described search number, the environment being presently in each pixel scans for, and obtains each pixel
Point radar data corresponding with each search angle in the global map, with each pixel of determination in the overall situation
Corresponding radar data set in map.
A kind of robot relocation device, comprising:
First acquisition unit, for calling pre-set camera and laser radar to obtain when robot starting
The environmental information for taking the robot to be presently in;
Generation unit, the environmental information for being presently according to the robot are constructed with current institute, the robot
Locate position and be the local map of origin, and generates the corresponding local message table of the local map;
Second acquisition unit, for obtaining pre-set global map and the corresponding global information of the global map
Table, and based on the corresponding relationship between the local message table and the global information table, selected in the global map with
The corresponding target local map of the local map;
First matching unit obtains the office for matching the local map with the target local map
Error parameter between portion's map and the target local map;
First determination unit determines that the robot is in the target local map for being based on the error parameter
In effective error region;
Second determination unit for choosing multiple pixels in the effective error region, and determines each picture
Vegetarian refreshments corresponding radar data set in the global map;
Second matching unit, for determining the current radar data in environmental information that the robot is presently in, and
The current radar data are matched with each radar data in each radar data set, acquisition is worked as with described
The preceding highest target radar data of radar data similarity;
Third determination unit, for obtaining the target position of target position pixel corresponding with the target radar data
Appearance determines that the object pose is the true pose of the robot, completes the reorientation to the robot.
Above-mentioned device, optionally, comprising:
It obtains subelement and obtains each quilt in the robot for calling pre-set camera
Identify the corresponding object information of object, and by pre-set laser radar, determine each identified object relative to
The relative position of the robot;
First determines subelement, for being based on each identified corresponding object information of object and each quilt
It identifies relative position of the object relative to the robot, determines the environmental information that the robot is presently in.
Above-mentioned device, optionally, the generation unit, comprising:
Second determines subelement, for the relative position based on each identified object relative to the robot,
Determine local coordinate of each identified object in the local map;
First generates subelement, for according to the identified corresponding object information of object and each identified object
Local coordinate of the body in the local map generates local message table corresponding with the local map.
Above-mentioned device, optionally, first matching unit, comprising:
Third determines subelement, for determining each local objects included in the target local map, Ge Gesuo
The each identified object stated in local objects and the local map corresponds;
Second generates subelement, for being based on the global information table, generates mesh corresponding with the target local map
Local message table is marked, includes true seat of each local objects in the global map in the target local message table
Mark;
First computation subunit, for the true coordinate according to each local objects in the global map, meter
Calculate the relative distance in the target local map between each local objects;
Second computation subunit, for the local coordinate according to each identified object in the local map,
Calculate the relative distance in the local map between each identified object;
Coupling subelement, for by between each local objects relative distance and each identified object it
Between relative distance carry out matching primitives, obtain the error parameter between the local map and the target part.
A kind of storage medium, the storage medium include the instruction of storage, wherein in described instruction operation described in control
Equipment where storage medium executes above-mentioned robot method for relocating.
A kind of electronic equipment, including memory and one perhaps one of them or one of more than one instruction with
Upper instruction is stored in memory, and is configured to execute above-mentioned robot reorientation by one or more than one processor
Method.
Compared with prior art, the present invention includes the following advantages:
The present invention provides a kind of robot method for relocating, comprising: when robot starting, calling is preset
Camera and laser radar obtain the environmental information that the robot is presently in;The ring being presently according to the robot
Border information, building is presently in local map of the position as origin using the robot, and it is corresponding to generate the local map
Local message table;Pre-set global map and the corresponding global information table of the global map are obtained, and is based on the office
Corresponding relationship between portion's information table and the global information table is selected corresponding with the local map in the global map
Target local map;The local map is matched with the target local map, obtains the local map and institute
State the error parameter between target local map;Based on the error parameter, determine that the robot is in the target part
Effective error region in map;Multiple pixels are chosen in the effective error region, and determine each pixel
The corresponding radar data set in the global map;Determine the current thunder in environmental information that the robot is presently in
It matches, obtains with each radar data in each radar data set up to data, and by the current radar data
It obtains and the highest target radar data of the current radar data similarity;Obtain target corresponding with the target radar data
The object pose of position pixel determines that the object pose is the true pose of the robot, completes to the robot
Reorientation.Using method provided by the invention, environmental information is obtained by camera and radar data, to construct local map
And local message table.Determine that the local map is right in global map by the corresponding relationship of local message table and global table information
The target local map answered selectes effective error area finally according to the error parameter between local map and target local map
Domain finally determines the true pose of robot by effective error region, is quickly presently in position to robot and carries out accurately
Positioning, guarantee robot ambient enviroment is accurately positioned and is judged during the work time.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of method flow diagram of robot method for relocating provided in an embodiment of the present invention;
Fig. 2 is a kind of another method flow diagram of robot method for relocating provided in an embodiment of the present invention;
Fig. 3 is a kind of another method flow diagram of robot method for relocating provided in an embodiment of the present invention;
Fig. 4 is a kind of structural schematic diagram of robot relocation device provided in an embodiment of the present invention;
Fig. 5 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
In this application, relational terms such as first and second and the like be used merely to by an entity or operation with
Another entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this realities
The relationship on border perhaps sequence the terms "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, from
And to include the process, method, article or equipments of a series of elements not only to include those elements, but also including not bright
The other element really listed, or further include for elements inherent to such a process, method, article, or device.Do not having
In the case where more limitations, the element that is limited by sentence "including a ...", it is not excluded that include the element process,
There is also other identical elements in method, article or equipment.
The present invention can be used in numerous general or special purpose computing device environment or configurations.Such as: personal computer, service
Device computer, handheld device or portable device, laptop device, multi-processor device including any of the above devices or devices
Distributed computing environment etc..
The embodiment of the invention provides one kind, this method can be applied in multiple systems platform, and executing subject can be
The processor of the terminal or various mobile devices of the processor of robot interior setting or other connection robots, institute
The method flow diagram of method is stated as shown in Figure 1, specifically including:
S101: when robot starting, pre-set camera and laser radar is called to obtain the robot
The environmental information being presently in;
In embodiments of the present invention, when robot starts, there is global uncertainty due to carving robot at the beginning,
Therefore can not learn that robot is carved at the beginning is properly positioned appearance.Therefore, pre-set camera and laser radar are called, is obtained
The environmental information for taking the robot to be presently in.
It should be noted that the camera can be monocular cam;The laser radar can be single line laser radar.
S102: the environmental information being presently according to the robot, building are presently in position with the robot and are
The local map of origin, and generate the corresponding local message table of the local map;
In embodiments of the present invention, the specific location as locating for uncertain robot manipulators can be presently according to robot
Environmental information construct a Ge Yi robot and be presently in the local map that position is origin, and according to the environmental information, generate
Local message table corresponding with the local map.Wherein, local map can be the semantic map in part;Local message table can be
Local semantic information table.
S103: pre-set global map and the corresponding global information table of the global map are obtained, and based on described
Corresponding relationship between local message table and the global information table is selected and the local map pair in the global map
The target local map answered;
In embodiments of the present invention, which has been stored in advance global map, when building local map and generates
After local message table, preset global map and global information table are obtained.Wherein, it is had recorded in global map in global information table
The object information of each object and the specific location in global map.According to pair between local message table and global information table
It should be related to, target local map corresponding with local map is determined in global map.
It should be noted that the local map is to belong to a part of region in global map, since robot is initial
The uncertainty at moment can not learn specific location of the local map in global map.Pass through local message table and global letter
The corresponding relationship between table is ceased, to select target local map corresponding with local map in global map.
It further illustrates, local message table has corresponding relationship, the object for including in local message table with global information table
Body information can search to obtain corresponding object information in global information table.
S104: the local map is matched with the target local map, obtain the local map with it is described
Error parameter between target local map;
In embodiments of the present invention, after selecting target local map corresponding with local map in global map, by office
Portion's map is matched with target local map, the error parameter after being matched.
It should be noted that since there are certain equipment errors with laser radar for camera, when obtaining environmental information,
There is also certain errors, and therefore, there is also errors during constructing local map, locally with target by local map
Error parameter after figure is matched, after determining matching.
S105: it is based on the error parameter, determines the effective error that the robot is in the target local map
Region;
In embodiments of the present invention, since, there are error, robot is former between local map and target local map
The first position in local map is mapped to the position in target local map, and there is also errors.According to error parameter, determining should
Effective error region of the robot in target local map.
It should be noted that in the effective error region, any one position is likely to be machine since there are errors
The authentic and valid position of device people.
S106: choosing multiple pixels in the effective error region, and determines each pixel described complete
Corresponding radar data set in local figure;
In embodiments of the present invention, multiple pixels are chosen in effective error region, wherein each pixel has
It may be the actual position of the robot.Accordingly, it can be determined that each pixel corresponding radar data set in global map.
It should be noted that each pixel can have multiple radar datas, multiple radar numbers of each pixel
According to composition radar data set.The radar data number of each pixel is identical.
S107: determining the current radar data in environmental information that the robot is presently in, and by the current thunder
It is matched, is obtained and the current radar data phase with each radar data in each radar data set up to data
Like the highest target radar data of degree;
In embodiments of the present invention, according to the environmental information originally obtained, the current radar number of the robot is determined
According to.The current radar data of the robot multiple radar datas corresponding with each pixel are matched one by one, from each
In a radar data, the highest target radar data of matching similarity are obtained.
It should be noted that the robot current radar data are the corresponding unique radar numbers of the current pose of robot
According to.
S108: the object pose of target position pixel corresponding with the target radar data is obtained, determines the mesh
Mark appearance is the true pose of the robot, completes the reorientation to the robot.
In embodiments of the present invention, the radar number is obtained after the highest target radar data of similarity after being matched
According to object pose corresponding with the target radar data in corresponding target pixel points and the target pixel points.It is final to determine
The object pose is the true pose of the robot, completes the reorientation to the robot.
In robot method for relocating provided in an embodiment of the present invention, when robot starting, pass through camera and laser
Radar obtains the environmental information of the robot, and is constructed by the environmental information and be presently in office of the position as origin using robot
Portion's map, and generate local message table.Determine the corresponding relationship between the local message table and pre-set global information table,
In pre-set global map, target local map corresponding with local map is determined.By local map and target part
Map is matched, and determines the error parameter of the two time.And according to the error parameter determine robot the target locally
Effective error region in figure.In the effective error region, multiple pixels are chosen, and obtain the corresponding thunder of each pixel
Up to data acquisition system.By each radar data progress in the current radar data of the robot and each radar data set
Match, determines the highest target radar data of similarity after matching.The corresponding object pose of target radar data is determined as machine
The true pose of people completes the reorientation to robot.
It should be noted that the use building scale identical with global map of local map, to guarantee matched
When, scale will not change, and reduce error when matching.
Using method provided in an embodiment of the present invention, environmental information is obtained by camera and radar data, to construct office
Portion's map and local message table.Determine the local map globally by the corresponding relationship of local message table and global information table
Corresponding target local map in figure is selected effective finally according to the error parameter between local map and target local map
Error band, by effective error region finally determine robot true pose, quickly to robot be presently in position into
Row accurately positioning, guarantees that robot is accurately positioned and is judged to ambient enviroment during the work time.
In method provided in an embodiment of the present invention, be based on above-mentioned steps S101, by call pre-set camera and
Laser radar obtains the environmental information that the robot is presently in, and specifically includes:
Pre-set camera is called, each of described robot is obtained and is identified the corresponding object of object
Body information, and by pre-set laser radar, determine each identified object relative to the opposite of the robot
Position;
Based on each identified corresponding object information of object and each identified object relative to the machine
The relative position of device people determines the environmental information that the robot is presently in.
In method provided in an embodiment of the present invention, content and step S102, described to generate the office based on the above embodiment
The corresponding local message table of portion's map, specifically includes:
Relative position based on each identified object relative to the robot determines each identified object
Local coordinate of the body in the local map;
According to the identified corresponding object information of object and each identified object in the local map
Local coordinate, generate corresponding with local map local message table.
In the method provided based on the above embodiment, building local map and the process such as Fig. 2 institute for generating local message table
Show, comprising:
S201: utilizing camera, obtains and is each identified the corresponding object information of object in robot;
In embodiments of the present invention, the specifying information that object is identified around robot, such as object are learnt by camera
Shape, color and title of body etc..
S202: utilizing laser radar, determines each identified relative position of the object relative to robot;
In embodiments of the present invention, by laser radar, each identified position of the object relative to robot is determined, i.e.,
In the distance between robot, angle etc..
S203: according to each identified corresponding object information of object and the relative position relative to robot, building with
The local map of the artificial origin of machine determines each identified local coordinate of the object in local map;
In embodiments of the present invention, the local map of a measurement scale identical as global map is constructed, and is determined every
Coordinate of a identified object in the local map.
S204: the object information according to each identified object and the local coordinate in local map generate and part
The corresponding local message table of map.
In embodiments of the present invention, one is generated with the corresponding object information of each identified object and local coordinate
Local message table.
In the method for robot reorientation provided in an embodiment of the present invention, by camera in robot
Object is identified, determines each identified corresponding object information of object.Wherein, object information include object title,
Shape, color of object of object etc..In determining robot current environment after the object information of each identified object,
Again by pre-set laser radar, each identified relative position of the object relative to the robot is determined.By each quilt
It identifies the corresponding object information of object and each identified relative position of the object relative to robot, determines that the robot is current
Locating environmental information.Wherein, when constructing local map, wash building local map according to the ring, and this locally
In figure, the local coordinate per individual identification objects is determined.By the corresponding object information of each identified object and in local map
In local coordinate, generate local message table.
Wherein, the process of local map is constructed are as follows: first initializing a value is the ash that pixel value is 127 expression zone of ignorances
Degree figure;Point where robot is origin O (0,0), first passes through camera and obtains each identified object in the zone of ignorance
After object information, then the point P (x0, y0) for being identified object is obtained by laser radar, it will be between line segment (0,0)-(x0, y0)
Area pixel value is assigned to 255 expression depletion regions, and the pixel value of point P (x0, y0) is assigned to 0 expression and is identified object;To all
The identified object that radar data scans similarly is operated, so that it may obtain one centered on robot locally
Figure.Wherein, the object in environment is identified by the identification module in camera, which is calculated using deep learning
Method is trained identification object.When recognizing an accurate object, according to the angle where the center of the object recognized,
Select laser radar in the coordinate position of the measurement data of corresponding angle, as local coordinate of the identification object on map, and
It is recorded in local message table.
Using method provided in an embodiment of the present invention, the environmental information of robot is obtained by camera and laser radar,
And local message table is generated according to environmental information, position that robot is currently located further can be determined according to local message,
Position quickly is presently in robot accurately to be positioned, and it is quasi- to guarantee that robot during the work time carries out ambient enviroment
Determine position and judgement.
In method provided in an embodiment of the present invention, content and step S104, described by the part based on the above embodiment
Map is matched with the target local map, obtains the error ginseng between the local map and the target local map
Number, as shown in figure 3, specifically including:
S301: each local objects included in the target local map, each local objects and institute are determined
The each identified object stated in local map corresponds;
In embodiments of the present invention, global determining since there are corresponding relationships in local message table and global information table
In map after target local map corresponding with local map, according to global information table, determines and wrapped in the target local map
The each local objects contained.Wherein the identified object information in the local objects and local map in target local map is one by one
It is corresponding.For example, being identified object in local map includes a white desk and a white chair, then in target local map
Also comprising a white desk and a white chair.
S302: being based on the global information table, generates target local message table corresponding with the target local map, institute
It states in target local message table comprising true coordinate of each local objects in the global map;
In embodiments of the present invention, it is based on global information table, generates the corresponding target local message table of target local map.
The local objects contained in the target local message table true coordinate in global map.
S303: according to true coordinate of each local objects in the global map, the target part is calculated
Relative distance in map between each local objects;
In embodiments of the present invention, according to the true coordinate of local objects each in target local map, each office is calculated
Relative distance between portion's object.For example, local objects include object A, B, C, then distance of A to the B again from B to C: A-B- is calculated
C。
S304: according to local coordinate of each identified object in the local map, calculating is described locally
Relative distance in figure between each identified object;
In embodiments of the present invention, according to the true coordinate of identified object each in local map, calculating is each to be known
Relative distance between other object.For example, local objects include object A1, B1, C1, then calculate A1 to B1 again from B1 to C1 away from
From: A1-B1-C1.
S305: by the relative distance between each local objects and between each identified object it is opposite away from
From matching primitives are carried out, the error parameter between the local map and the target part is obtained.
In embodiments of the present invention, by the relative distance between each local objects and the phase between each identified object
It adjusts the distance and carries out matching primitives, determine error parameter between the two.
In robot method for relocating provided in an embodiment of the present invention, the local object for including in target local map is first determined
Body, and each identified object in each local objects in the target local map and local map corresponds.Pass through
Global information table generates target local message table.Pass through the true coordinate of each local objects in target local message table, meter again
Calculate the relative distance between each local objects;By the local coordinate of identified object each in local message table, calculate each
Relative distance between a identified object.By the relative distance between each local objects and between each identified object
Relative distance carries out matching primitives, obtains the error parameter between local map and target part.Such as: in target local map
There are first partial object A and the second local objects B, also there is the first identified identified object of object A1 and second in local map
B1;When target local message table is T_global and local information table is T_local;For two differences in T_local
Object A and B, calculate the actual range D_AB_local of A and B, and calculate two corresponding identified object A1 in T_global
And B1, the actual range D_A1B1_global of A1 and B1 is calculated, matching meter is carried out to D_A1B1_global and D_AB_local
It calculates, obtains error parameter e.
It should be noted that can only be selected two different when the identified object in local map is more than two
Identified object calculates the first distance between two selected identified objects, then corresponding selection target local map
In, and consistent two kinds of local objects of not identification object selected in local map, calculate two selected local objects it
Between second distance.The difference between first distance and second distance is calculated, first distance mistake corresponding with second distance is obtained
Poor parameter.
Optionally, based in above-mentioned steps S103, according to the corresponding relationship between local message table and global information table,
In global map select target local map corresponding with local map process, can by calculating object between distance,
Target local map corresponding with local map is selected in global map.Such as: it calculates in global information table and local information table
The intersection of collection of objects obtains the only new global information table comprising intersection object and local information table;Wherein, global information table
In comprising object information with local message table same object, while also including the object information of other objects.Then, for new
Global information table in the different classes of object A and B of any two, calculate the actual range D_AB of A and B, and search for local letter
Any two correspond to classification object A` and B` in breath table, the actual range D_A`B` of A` and B` are calculated, if D_A`B` and D_AB
Gap less than one preset threshold value of absolute value, then determine AB and A`B` in the environment and be likely to be with a pair of of object;
Then, pass through the coordinate conversion relation of AB and A`B`, the transformation relation of available local map and global map, according to this
Transformation relation can directly calculate local map corresponding target local map in global map.
Using in method provided in an embodiment of the present invention, by matching primitives, obtain between local map and target part
Error parameter, can carry out more accurate positioning to robot according to error parameter, guarantee robot during the work time
Ambient enviroment is accurately positioned and is judged.
In method provided in an embodiment of the present invention, it is based on above-mentioned steps S106, it is described to be based on the error parameter, determine institute
The effective error region that robot is in the global map is stated, is specifically included:
Origin in the local map is mapped in the target local map, it is described to determine that the origin maps to
The mapping point of target local map;
It based on the mapping point and the error parameter, determines using the mapping point as the center of circle, the error parameter is half
The effective error region of diameter, the effective error region are that the robot is in all possible positions in the global map
Region.
In robot method for relocating provided in an embodiment of the present invention, in determining global map belonging to local map
Position be target local map after, will be in local map according to the corresponding relationship between local map and target local map
Origin is mapped in target local map, determines that the origin originally in local map is mapped to the mapping after target local map
Point.Since target local map belongs to global map, the actual coordinate of the mapping point can be determined in global map.But by
There are errors between local map and target local map, then according to the error parameter between local map and global map with
And the actual coordinate of the mapping point, one is determined using the mapping point as the center of circle, and error parameter is an effective error area of radius
Domain.Wherein, which is the region that robot is in all possible positions in global map, that is, due to target office
There are errors between portion's map and local map, therefore the position in local map at robot is mapped to target locally
There is also certain errors for figure.
Using method provided in an embodiment of the present invention, by mapping point and error parameter, determine that robot is in globally
Effective error region in figure is robot to execute the process of above-mentioned steps S106~S108 according to the effective error region
Accurately positioned.
In method provided in an embodiment of the present invention, it is based on above-mentioned steps S107, each pixel of determination is in institute
State corresponding radar data set in global map, comprising:
It determines the pre-set search range of the robot, and according to described search range, each pixel is set
Point needs to carry out the search angle of search lighting;
According to described search range and search angle, determine that each pixel needs to carry out the search time of search lighting
Number, and according to described search number, the environment being presently in each pixel scans for, and obtains each pixel
Point radar data corresponding with each search angle in the global map, with each pixel of determination in the overall situation
Corresponding radar data set in map.
In robot method for relocating provided in an embodiment of the present invention, since pose of the robot in the overall situation has not really
It is qualitative, it can determine that each pixel needs to carry out the search angle of search lighting by pre-set search range.Its
In, search range can be 180 °, 270 ° or 360 ° etc.;The angle of aspect that needs scan for can be determined according to search range
Degree, such as search angle can be 0.1 ° or 1 ° etc.;Each pixel is used for true position of the dummy robot in global map
It sets.According to search range and search angle, determine that each pixel needs to carry out the searching times of search lighting.Such as search model
Enclosing is 360 °, and search angle is 0.1 °, then a pixel needs to carry out 3600 search lightings, and every search is primary, is changed
0.1 ° of search angle.According to searching times, each pixel current environment is scanned for, and obtains each pixel
The radar data obtained after search lighting is carried out according to search angle in global map, with each pixel of determination globally
Corresponding radar data set in figure.
It should be noted that a radar data set corresponds to a pixel, include in each radar data set
Multiple radar datas.Such as search range is 360 °, search angle is 0.1 °, then a pixel needs to carry out 3600 thunders
Up to search, every search is primary, changes 0.1 ° of search angle, therefore can get 3600 radar datas.Wherein, thunder is carried out every time
Up to search, search lighting is carried out by laser radar.
Using method provided in an embodiment of the present invention, according to pre-set search range and search angle, to each
Environment locating for pixel is accurately searched for, so that radar data is more accurate, it is more accurate to the positioning of robot.
The specific implementation process and its deriving mode of above-mentioned each embodiment, it is within the scope of the present invention.
It is corresponding with method described in Fig. 1, the embodiment of the invention also provides a kind of robot relocation device, for pair
The specific implementation of method in Fig. 1, robot relocation device provided in an embodiment of the present invention can be with application computer terminals or each
In kind mobile device, structural schematic diagram is as shown in figure 4, specifically include:
First acquisition unit 401, for calling pre-set camera and laser radar when robot starting
Obtain the environmental information that the robot is presently in;
Generation unit 402, the environmental information for being presently according to the robot construct current with the robot
Present position is the local map of origin, and generates the corresponding local message table of the local map;
Second acquisition unit 403, for obtaining pre-set global map and the corresponding global letter of the global map
Table is ceased, and based on the corresponding relationship between the local message table and the global information table, is selected in the global map
Target local map corresponding with the local map;
First matching unit 404 obtains described for matching the local map with the target local map
Error parameter between local map and the target local map;
First determination unit 405 determines that the robot is in the target locally for being based on the error parameter
Effective error region in figure;
Second determination unit 406 for choosing multiple pixels in the effective error region, and determines each described
Pixel corresponding radar data set in the global map;
Second matching unit 407, for determining the current radar data in environmental information that the robot is presently in,
And the current radar data are matched with each radar data in each radar data set, obtain with it is described
The highest target radar data of current radar data similarity;
Third determination unit 408, for obtaining the target of target position pixel corresponding with the target radar data
Pose determines that the object pose is the true pose of the robot, completes the reorientation to the robot.
In device provided in an embodiment of the present invention, the first acquisition unit 401, comprising:
It obtains subelement and obtains each quilt in the robot for calling pre-set camera
Identify the corresponding object information of object, and by pre-set laser radar, determine each identified object relative to
The relative position of the robot;
First determines subelement, for being based on each identified corresponding object information of object and each quilt
It identifies relative position of the object relative to the robot, determines the environmental information that the robot is presently in.
In device provided in an embodiment of the present invention, the generation unit 402, comprising:
Second determines subelement, for the relative position based on each identified object relative to the robot,
Determine local coordinate of each identified object in the local map;
First generates subelement, for according to the identified corresponding object information of object and each identified object
Local coordinate of the body in the local map generates local message table corresponding with the local map.
In device provided in an embodiment of the present invention, first matching unit 404, comprising:
Third determines subelement, for determining each local objects included in the target local map, Ge Gesuo
The each identified object stated in local objects and the local map corresponds;
Second generates subelement, for being based on the global information table, generates mesh corresponding with the target local map
Local message table is marked, includes true seat of each local objects in the global map in the target local message table
Mark;
First computation subunit, for the true coordinate according to each local objects in the global map, meter
Calculate the relative distance in the target local map between each local objects;
Second computation subunit, for the local coordinate according to each identified object in the local map,
Calculate the relative distance in the local map between each identified object;
Coupling subelement, for by between each local objects relative distance and each identified object it
Between relative distance carry out matching primitives, obtain the error parameter between the local map and the target part.
In device provided in an embodiment of the present invention, first determination unit 405, comprising:
4th determines subelement, for the origin in the local map to be mapped in the target local map, really
The fixed origin maps to the mapping point of the target local map;
5th determines subelement, for being based on the mapping point and the error parameter, determines that with the mapping point be circle
The heart, the error parameter are the effective error region of radius, and the effective error region is that the robot is in the overall situation
The region of all possible positions in map.
In device provided in an embodiment of the present invention, second determination unit 406, comprising:
6th determines subelement, for determining the pre-set search range of the robot, and according to described search model
It encloses, the search angle that each pixel needs to carry out search lighting is set;
Subelement is searched for, for determining that each pixel needs to carry out according to described search range and search angle
The searching times of search lighting, and according to described search number, the environment being presently in each pixel scans for,
Each pixel radar data corresponding with each search angle in the global map is obtained, it is each described to determine
Pixel corresponding radar data set in the global map.
First acquisition unit 401, generation unit in the above robot relocation device disclosed by the embodiments of the present invention
402, second acquisition unit 403, the first matching unit 404, the first determination unit 405, the matching of the second determination unit 406, second
The specific work process of unit 407 and third determination unit 408, reference can be made to robot disclosed in the above embodiment of the present invention is reset
Corresponding content in the method for position, is not discussed here.
The embodiment of the invention also provides a kind of storage medium, the storage medium includes the instruction of storage, wherein in institute
The above-mentioned robot of equipment execution where controlling the storage medium when instruction operation is stated to reset as method.
The embodiment of the invention also provides a kind of electronic equipment, structural schematic diagram is as shown in figure 5, specifically include memory
501 and one perhaps more than one 502 one of them or more than one instruction of instruction 502 be stored in memory 501
In, and be configured to by one or more than one processor 503 execute the one or more instruction 502 carry out with
Lower operation:
When robot starting, pre-set camera and laser radar is called to obtain the current institute, robot
The environmental information at place;
According to the environmental information that the robot is presently in, building is presently in position as origin using the robot
Local map, and generate the corresponding local message table of the local map;
Pre-set global map and the corresponding global information table of the global map are obtained, and is based on the part
Corresponding relationship between information table and the global information table is selected corresponding with the local map in the global map
Target local map;
The local map is matched with the target local map, obtains the local map and the target office
Error parameter between portion's map;
Based on the error parameter, the effective error region that the robot is in the target local map is determined;
Multiple pixels are chosen in the effective error region, and determine each pixel in the global map
In corresponding radar data set;
Determine the current radar data in environmental information that the robot is presently in, and by the current radar data
It is matched, is obtained with the current radar data similarity most with each radar data in each radar data set
High target radar data;
The object pose for obtaining target position pixel corresponding with the target radar data, determines the object pose
For the true pose of the robot, the reorientation to the robot is completed.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system or
For system embodiment, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to method
The part of embodiment illustrates.System and system embodiment described above is only schematical, wherein the conduct
The unit of separate part description may or may not be physically separated, component shown as a unit can be or
Person may not be physical unit, it can and it is in one place, or may be distributed over multiple network units.It can root
According to actual need that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.Ordinary skill
Personnel can understand and implement without creative efforts.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of robot method for relocating, which is characterized in that the method is applied to robot, comprising:
When robot starting, pre-set camera and laser radar is called to obtain what the robot was presently in
Environmental information;
According to the environmental information that the robot is presently in, building is presently in part of the position as origin using the robot
Map, and generate the corresponding local message table of the local map;
Pre-set global map and the corresponding global information table of the global map are obtained, and is based on the local message
Corresponding relationship between table and the global information table selectes target corresponding with the local map in the global map
Local map;
The local map is matched with the target local map, obtains the local map and the target locally
Error parameter between figure;
Based on the error parameter, the effective error region that the robot is in the target local map is determined;
Multiple pixels are chosen in the effective error region, and determine that each pixel is right in the global map
The radar data set answered;
Determine the current radar data in environmental information that the robot is presently in, and by current radar data and every
Each radar data in a radar data set is matched, and is obtained highest with the current radar data similarity
Target radar data;
The object pose for obtaining target position pixel corresponding with the target radar data, determines the object pose for institute
The true pose of robot is stated, the reorientation to the robot is completed.
2. the method according to claim 1, wherein described call pre-set camera and laser radar to obtain
The environmental information for taking the robot to be presently in, comprising:
Pre-set camera is called, each of described robot is obtained and is identified the corresponding object letter of object
Breath, and by pre-set laser radar, determine relative position of each identified object relative to the robot;
Based on each identified corresponding object information of object and each identified object relative to the robot
Relative position, determine the environmental information that the robot is presently in.
3. according to the method described in claim 2, it is characterized in that, described generate the corresponding local message of the local map
Table, comprising:
Relative position based on each identified object relative to the robot determines that each identified object exists
Local coordinate in the local map;
According to the office of the identified corresponding object information of object and each identified object in the local map
Portion's coordinate generates local message table corresponding with the local map.
4. according to the method described in claim 3, it is characterized in that, described by the local map and the target local map
It is matched, obtains the error parameter between the local map and the target part, comprising:
Determine each local objects included in the target local map, each local objects and the local map
In each identified object correspond;
Based on the global information table, target local message table corresponding with the target local map, the target office are generated
It include true coordinate of each local objects in the global map in portion's information table;
According to true coordinate of each local objects in the global map, calculate each in the target local map
Relative distance between the local objects;
According to local coordinate of each identified object in the local map, each institute in the local map is calculated
State the relative distance between identified object;
By the relative distance between each local objects and the progress of the relative distance between each identified object
With calculating, the error parameter between the local map and the target part is obtained.
5. determining the robot the method according to claim 1, wherein described be based on the error parameter
Effective error region in the global map, comprising:
Origin in the local map is mapped in the target local map, determines that the origin maps to the target
The mapping point of local map;
It based on the mapping point and the error parameter, determines using the mapping point as the center of circle, the error parameter is radius
Effective error region, the effective error region are the area that the robot is in all possible positions in the global map
Domain.
6. the method according to claim 1, wherein each pixel of the determination is in the global map
In corresponding radar data set, comprising:
Determine the pre-set search range of the robot, and according to described search range, each pixel, which is arranged, to be needed
Carry out the search angle of search lighting;
According to described search range and search angle, determine that each pixel needs to carry out the searching times of search lighting,
And according to described search number, the environment being presently in each pixel is scanned for, and obtains each pixel
The radar data corresponding with each search angle in the global map, with each pixel of determination it is described globally
Corresponding radar data set in figure.
7. a kind of robot relocation device characterized by comprising
First acquisition unit, for calling pre-set camera and laser radar to obtain institute when robot starting
State the environmental information that robot is presently in;
Generation unit, the environmental information for being presently according to the robot, building are presently in position with the robot
It is set to the local map of origin, and generates the corresponding local message table of the local map;
Second acquisition unit, for obtaining pre-set global map and the corresponding global information table of the global map, and
Based on the corresponding relationship between the local message table and the global information table, selected and the office in the global map
The corresponding target local map of portion's map;
First matching unit, for the local map to be matched with the target local map, obtain it is described locally
Error parameter between figure and the target local map;
First determination unit determines that the robot is in the target local map for being based on the error parameter
Effective error region;
Second determination unit for choosing multiple pixels in the effective error region, and determines each pixel
The corresponding radar data set in the global map;
Second matching unit, for determining the current radar data in environmental information that the robot is presently in, and by institute
It states current radar data to be matched with each radar data in each radar data set, obtain and the current thunder
Up to the highest target radar data of data similarity;
Third determination unit, for obtaining the object pose of target position pixel corresponding with the target radar data, really
The fixed object pose is the true pose of the robot, completes the reorientation to the robot.
8. device according to claim 7, the first acquisition unit, comprising:
Subelement is obtained, for calling pre-set camera, it is identified to obtain each of described robot
The corresponding object information of object, and by pre-set laser radar, determine each identified object relative to described
The relative position of robot;
First determines subelement, for based on the corresponding object information of each identified object and each described identified
Relative position of the object relative to the robot determines the environmental information that the robot is presently in.
9. device according to claim 7, which is characterized in that the generation unit, comprising:
Second determines subelement, for the relative position based on each identified object relative to the robot, determines
Local coordinate of each identified object in the local map;
First generates subelement, for existing according to the identified corresponding object information of object and each identified object
Local coordinate in the local map generates local message table corresponding with the local map.
10. device according to claim 7, which is characterized in that first matching unit, comprising:
Third determines subelement, for determining each local objects included in the target local map, each office
Each identified object in portion's object and the local map corresponds;
Second generates subelement, for being based on the global information table, generates target office corresponding with the target local map
Portion's information table includes true coordinate of each local objects in the global map in the target local message table;
First computation subunit calculates institute for the true coordinate according to each local objects in the global map
State the relative distance in target local map between each local objects;
Second computation subunit is calculated for the local coordinate according to each identified object in the local map
Relative distance in the local map between each identified object;
Coupling subelement, for by the relative distance between each local objects and between each identified object
Relative distance carries out matching primitives, obtains the error parameter between the local map and the target part.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910561961.2A CN110207710B (en) | 2019-06-26 | 2019-06-26 | Robot repositioning method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910561961.2A CN110207710B (en) | 2019-06-26 | 2019-06-26 | Robot repositioning method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110207710A true CN110207710A (en) | 2019-09-06 |
CN110207710B CN110207710B (en) | 2021-03-16 |
Family
ID=67794736
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910561961.2A Active CN110207710B (en) | 2019-06-26 | 2019-06-26 | Robot repositioning method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110207710B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110716209A (en) * | 2019-09-19 | 2020-01-21 | 浙江大华技术股份有限公司 | Map construction method, map construction equipment and storage device |
CN111460065A (en) * | 2020-03-26 | 2020-07-28 | 杭州海康威视数字技术股份有限公司 | Method and device for positioning radar in map |
CN111678516A (en) * | 2020-05-08 | 2020-09-18 | 中山大学 | Bounded region rapid global positioning method based on laser radar |
CN111693053A (en) * | 2020-07-09 | 2020-09-22 | 上海大学 | Repositioning method and system based on mobile robot |
CN112231427A (en) * | 2020-10-13 | 2021-01-15 | 上海美迪索科电子科技有限公司 | Map construction method, device, medium and equipment |
CN112269386A (en) * | 2020-10-28 | 2021-01-26 | 深圳拓邦股份有限公司 | Method and device for repositioning symmetric environment and robot |
CN112509027A (en) * | 2020-11-11 | 2021-03-16 | 深圳市优必选科技股份有限公司 | Repositioning method, robot, and computer-readable storage medium |
CN114088099A (en) * | 2021-11-18 | 2022-02-25 | 北京易航远智科技有限公司 | Semantic relocation method and device based on known map, electronic equipment and medium |
CN114383622A (en) * | 2021-12-27 | 2022-04-22 | 广州视源电子科技股份有限公司 | Robot positioning method, robot, and computer-readable storage medium |
CN114674307A (en) * | 2022-05-26 | 2022-06-28 | 苏州魔视智能科技有限公司 | Repositioning method and electronic equipment |
CN114383622B (en) * | 2021-12-27 | 2024-04-19 | 广州视源电子科技股份有限公司 | Robot positioning method, robot, and computer-readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120323431A1 (en) * | 2011-06-14 | 2012-12-20 | INRO Technologies Limited | Method and apparatus for sharing map data associated with automated industrial vehicles |
CN103941264A (en) * | 2014-03-26 | 2014-07-23 | 南京航空航天大学 | Positioning method using laser radar in indoor unknown environment |
JP2017097402A (en) * | 2015-11-18 | 2017-06-01 | 株式会社明電舎 | Surrounding map preparation method, self-location estimation method and self-location estimation device |
CN108981701A (en) * | 2018-06-14 | 2018-12-11 | 广东易凌科技股份有限公司 | A kind of indoor positioning and air navigation aid based on laser SLAM |
CN109141437A (en) * | 2018-09-30 | 2019-01-04 | 中国科学院合肥物质科学研究院 | A kind of robot global method for relocating |
CN109144056A (en) * | 2018-08-02 | 2019-01-04 | 上海思岚科技有限公司 | The global method for self-locating and equipment of mobile robot |
-
2019
- 2019-06-26 CN CN201910561961.2A patent/CN110207710B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120323431A1 (en) * | 2011-06-14 | 2012-12-20 | INRO Technologies Limited | Method and apparatus for sharing map data associated with automated industrial vehicles |
CN103941264A (en) * | 2014-03-26 | 2014-07-23 | 南京航空航天大学 | Positioning method using laser radar in indoor unknown environment |
JP2017097402A (en) * | 2015-11-18 | 2017-06-01 | 株式会社明電舎 | Surrounding map preparation method, self-location estimation method and self-location estimation device |
CN108981701A (en) * | 2018-06-14 | 2018-12-11 | 广东易凌科技股份有限公司 | A kind of indoor positioning and air navigation aid based on laser SLAM |
CN109144056A (en) * | 2018-08-02 | 2019-01-04 | 上海思岚科技有限公司 | The global method for self-locating and equipment of mobile robot |
CN109141437A (en) * | 2018-09-30 | 2019-01-04 | 中国科学院合肥物质科学研究院 | A kind of robot global method for relocating |
Non-Patent Citations (4)
Title |
---|
TANG JIAN,ETC: "NAVIS-An UGV Indoor Positioning System Using Laser Scan Matching for Large-Area Real-Time Applications", 《SENSORS》 * |
李晨曦,等: "激光雷达SLAM技术及其在无人车中的应用研究进展", 《北京联合大学学报》 * |
陈群英: "移动机器人同时定位与地图构建方法研究", 《自动化与仪器仪表》 * |
马跃龙,等: "一种基于点云地图的机器人室内实时重定位方法", 《系统仿真学报》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110716209A (en) * | 2019-09-19 | 2020-01-21 | 浙江大华技术股份有限公司 | Map construction method, map construction equipment and storage device |
CN111460065A (en) * | 2020-03-26 | 2020-07-28 | 杭州海康威视数字技术股份有限公司 | Method and device for positioning radar in map |
CN111460065B (en) * | 2020-03-26 | 2023-12-01 | 杭州海康威视数字技术股份有限公司 | Positioning method and device of radar in map |
CN111678516A (en) * | 2020-05-08 | 2020-09-18 | 中山大学 | Bounded region rapid global positioning method based on laser radar |
CN111693053A (en) * | 2020-07-09 | 2020-09-22 | 上海大学 | Repositioning method and system based on mobile robot |
CN112231427A (en) * | 2020-10-13 | 2021-01-15 | 上海美迪索科电子科技有限公司 | Map construction method, device, medium and equipment |
CN112269386A (en) * | 2020-10-28 | 2021-01-26 | 深圳拓邦股份有限公司 | Method and device for repositioning symmetric environment and robot |
CN112269386B (en) * | 2020-10-28 | 2024-04-02 | 深圳拓邦股份有限公司 | Symmetrical environment repositioning method, symmetrical environment repositioning device and robot |
CN112509027B (en) * | 2020-11-11 | 2023-11-21 | 深圳市优必选科技股份有限公司 | Repositioning method, robot, and computer-readable storage medium |
WO2022099889A1 (en) * | 2020-11-11 | 2022-05-19 | 深圳市优必选科技股份有限公司 | Relocation method, robot, and computer-readable storage medium |
CN112509027A (en) * | 2020-11-11 | 2021-03-16 | 深圳市优必选科技股份有限公司 | Repositioning method, robot, and computer-readable storage medium |
CN114088099A (en) * | 2021-11-18 | 2022-02-25 | 北京易航远智科技有限公司 | Semantic relocation method and device based on known map, electronic equipment and medium |
CN114383622A (en) * | 2021-12-27 | 2022-04-22 | 广州视源电子科技股份有限公司 | Robot positioning method, robot, and computer-readable storage medium |
CN114383622B (en) * | 2021-12-27 | 2024-04-19 | 广州视源电子科技股份有限公司 | Robot positioning method, robot, and computer-readable storage medium |
CN114674307A (en) * | 2022-05-26 | 2022-06-28 | 苏州魔视智能科技有限公司 | Repositioning method and electronic equipment |
CN114674307B (en) * | 2022-05-26 | 2022-09-27 | 苏州魔视智能科技有限公司 | Repositioning method and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN110207710B (en) | 2021-03-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110207710A (en) | Robot method for relocating and device | |
CN109141437A (en) | A kind of robot global method for relocating | |
CN106092104B (en) | A kind of method for relocating and device of Indoor Robot | |
CN106254848B (en) | A kind of learning method and terminal based on augmented reality | |
CN111488824B (en) | Motion prompting method, device, electronic equipment and storage medium | |
Lambrecht et al. | Spatial programming for industrial robots through task demonstration | |
Saxena et al. | Learning to grasp novel objects using vision | |
CN107328420A (en) | Localization method and device | |
CN107449427B (en) | Method and equipment for generating navigation map | |
CN105825193A (en) | Method and device for position location of center of palm, gesture recognition device and intelligent terminals | |
CN103930944A (en) | Adaptive tracking system for spatial input devices | |
Taylor et al. | Visual perception and robotic manipulation: 3D object recognition, tracking and hand-eye coordination | |
US11263818B2 (en) | Augmented reality system using visual object recognition and stored geometry to create and render virtual objects | |
CN104866824A (en) | Manual alphabet identification method based on Leap Motion | |
CN107027168A (en) | Localization method and device | |
CN107690303A (en) | Generate threedimensional model | |
WO2021204587A1 (en) | Aligning and augmenting a partial subspace of a physical infrastructure with at least one information element | |
CN109858402B (en) | Image detection method, device, terminal and storage medium | |
CN111006672A (en) | Indoor navigation model construction and navigation method and system based on augmented reality | |
Xompero et al. | Multi-view shape estimation of transparent containers | |
JP2023109570A (en) | Information processing device, learning device, image recognition device, information processing method, learning method, and image recognition method | |
CN110415171B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
Aleotti et al. | Grasp programming by demonstration in virtual reality with automatic environment reconstruction | |
Liu | Semantic mapping: a semantics-based approach to virtual content placement for immersive environments | |
CN110598605B (en) | Positioning method, positioning device, terminal equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Robot relocation method and device Effective date of registration: 20210907 Granted publication date: 20210316 Pledgee: Zhongguancun Beijing technology financing Company limited by guarantee Pledgor: Beijing Dog Intelligent Robot Technology Co.,Ltd. Registration number: Y2021990000811 |