CN109506641A - The pose loss detection and relocation system and robot of mobile robot - Google Patents
The pose loss detection and relocation system and robot of mobile robot Download PDFInfo
- Publication number
- CN109506641A CN109506641A CN201710829430.8A CN201710829430A CN109506641A CN 109506641 A CN109506641 A CN 109506641A CN 201710829430 A CN201710829430 A CN 201710829430A CN 109506641 A CN109506641 A CN 109506641A
- Authority
- CN
- China
- Prior art keywords
- pose
- mobile robot
- map
- robot
- subgraph
- 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
-
- 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
-
- 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
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
Abstract
The present invention proposes the pose loss detection and relocation system and robot of a kind of mobile robot, the system includes: data acquisition module, the data of the sensor for obtaining the map of mobile robot local environment, carrying on the obstacle information and robot of robot;Locating module, for obtaining pose of the mobile robot in map;Judgment module, data and map datum for being acquired according to sensor judge localization for Mobile Robot information whether mistake, i.e., locating module output pose and the actual pose of machine it is whether consistent;Module is relocated, for relocating according to preset reorientation algorithm to mobile robot, obtaining the correct pose of robot when location information mistake occurs for mobile robot.The present invention can effectively give the pose of mobile robot for change, promote the robustness for building figure and location algorithm, extend the validity period of map.
Description
Technical field
The present invention relates to robotic technology field, in particular to the pose loss detection and reorientation of a kind of mobile robot
System and robot.
Background technique
The pose for building robot in figure and location algorithm of current mobile robot is often lost, i.e., robot localization is wrong
Accidentally.Common strategy usually builds figure again, gives the pose of corresponding new map reference for change.But it will lead to map so frequently more
It changes, map cannot be saved for a long time, history work is mismatched with new map, and user also will relative to the interactive operation of map at this time
It fails therewith, brings inconvenience for user.
Summary of the invention
The present invention is directed at least solve one of above-mentioned technical problem.
For this purpose, an object of the present invention is to provide a kind of pose loss detections of mobile robot and reorientation system
System, the system can effectively give the pose of mobile robot for change, promote the robustness for building figure and location algorithm, extend map
Validity period.
Second object of the present invention is to propose a kind of robot.
To achieve the goals above, the pose that the embodiment of first aspect present invention proposes a kind of mobile robot is lost
Detection and relocation system, comprising: data acquisition module, for obtaining map, the machine of the mobile robot local environment
The data of the sensor carried on the obstacle information and robot of people's ambient enviroment;Locating module, for obtaining the movement
Pose of the robot in map;Judgment module, data and map datum judgement for being acquired according to the sensor
The localization for Mobile Robot information whether mistake, i.e., locating module output pose and the actual pose of machine it is whether consistent;
Module is relocated, is used for when location information mistake occurs for the mobile robot, according to preset reorientation algorithm to described
Mobile robot is relocated, and the correct pose of the robot is obtained.
In addition, the pose loss detection of mobile robot according to the above embodiment of the present invention and relocation system can be with
With following additional technical characteristic:
In some instances, in the data acquisition module, the method for obtaining ambient enviroment obstacle information includes: logical
It crosses distance measuring sensor and obtains barrier around the robot at a distance from fuselage, laser radar and/or line including rotation
The laser ranging module and/or binocular distance measurement module of the laser ranging module of battle array and/or face battle array;And/or pass through image
Sensor obtains the image information of the robot.
In some instances, the judgment module is used for: the data of the sensor acquisition and the map datum
Similarity;If similarity is lower than first threshold, determine that the mobile robot occurs pose and loses.
In some instances, the judgment module is also used to: judging whether the mobile robot is liftoff, and/or judgement
Whether the mobile robot collides, and/or judge the mobile robot whether wheel slip;If it is, determining
The mobile robot occurs pose and loses.
In some instances, data and map progress that the reorientation module is used to acquire the sensor
Match, to be relocated to the mobile robot, specifically include: the data and the moving machine acquired according to the sensor
The prediction pose of device people obtains the probability distribution of the pose of the mobile robot;Each pose is sampled respectively, is obtained
The similarity of each pose and the map;According to the similarity, the probability distribution of the pose is repeatedly adjusted, is obtained
To the alternative pose for being greater than second threshold with the similarity of the map;The mobile robot is obtained according to the alternative pose
Final pose.
In some instances, described that the final pose of the mobile robot is obtained according to the alternative pose, comprising: when
When the alternative pose is one, using the alternative pose as the final pose;When the alternative pose is multiple, obtain
The mobile robot is taken to enter the new pose after other default environment under multiple alternative poses respectively, and more by what is obtained
The acquisition data of corresponding sensor are matched with the map under a new pose, and by matching degree highest when corresponding position
Appearance is as the final pose.
In some instances, the reorientation module is used to carry out the mobile robot by the method for subgraph match
Reorientation, specifically includes: establishing subgraph, and obtain pose of the subgraph in the map;According to the subgraph described
Pose in map relocates the mobile robot.
In some instances, the pose for obtaining the subgraph in the map, comprising: calculate the subgraph and institute
The similarity of map is stated, and position of the subgraph in the map is obtained according to the similarity for stating subgraph and the map
Appearance;Or the characteristics of image of subgraph and map is extracted, and matched characteristic point pair is obtained according to described image feature, according to described
Matched characteristic point obtains corresponding model parameter using the criterion of least model error to translation rotating model matrix is established,
Pose of the subgraph in the map is obtained according to the model parameter.
In some instances, weight is carried out to the mobile robot by the method for subgraph match in the reorientation module
During positioning, when the map, which exists, to be lacked, subgraph is established in the zone of ignorance of the map.
The pose loss detection and relocation system of mobile robot according to an embodiment of the present invention, can effectively give for change
The pose of mobile robot promotes the robustness for building figure and location algorithm, extends the validity period of map.
To achieve the goals above, the embodiment of second aspect of the present invention proposes a kind of robot, including in the present invention
State the pose loss detection and relocation system of mobile robot described in embodiment.
Robot according to an embodiment of the present invention can quickly and efficiently give pose for change when pose loss occurs, real
The high pose reorientation of existing accuracy.
Additional aspect and advantage of the invention will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 is the flow chart of the pose loss detection and method for relocating of mobile robot according to an embodiment of the present invention;
Fig. 2 is the pose loss detection of mobile robot according to an embodiment of the present invention and the structural frames of relocation system
Figure.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not considered as limiting the invention.
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction 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.In addition, term " first ", " second " are used for description purposes only, it is not understood to indicate or imply opposite
Importance.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;It can
To be mechanical connection, it is also possible to be electrically connected;It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
Pose loss detection and the reorientation side of mobile robot according to an embodiment of the present invention are described below in conjunction with attached drawing
Method, system and robot.
Fig. 1 is the pose loss detection of mobile robot according to an embodiment of the invention and the process of method for relocating
Figure.As shown in Figure 1, method includes the following steps:
Step S1: the map of mobile robot local environment, the obstacle information and machine of robot are obtained
The data of the sensor carried on people.
Specifically, such as by building figure and location algorithm the map of mobile robot local environment is established, and then obtaining should
Map.Wherein, the input data of figure and location algorithm is built as the acquisition data of the sensor of mobile robot.Wherein, moving machine
Device people is, for example, sweeper or other types mobile robot.
Further, the method for obtaining ambient enviroment obstacle information includes: to obtain robot week by distance measuring sensor
The barrier enclosed at a distance from fuselage, the laser ranging module of laser radar and/or linear array including rotation and/or face battle array
Laser ranging module and/or binocular distance measurement module;And/or the figure of robot is obtained by imaging sensor
As information.
Step S2: pose of the mobile robot in map is obtained.
Specifically, can for example be installed with mobile robot laser radar, depth camera, infrared distance measuring device,
The single or multiple sensings such as ultrasonic unit, IMU (Inertial measurement unit, Inertial Measurement Unit), odometer
The input data source (namely acquisition data of sensor) for building figure and location algorithm is realized in device combination.Record has shifting on the map
The region of the transportable clear of posture information, mobile robot of the barrier of mobile robot local environment and moving machine
The zone of ignorance (i.e. map datum) that device people does not explore.
Step S3: data and map datum for being acquired according to sensor judge whether localization for Mobile Robot information is wrong
Accidentally, i.e. whether the pose and the actual pose of machine of locating module output are consistent.In other words, the data acquired according to sensor
Judge whether mobile robot occurs pose and lose with map datum.
Specifically, mobile robot is in the process of moving, location algorithm may fail, as collision causes sensor different
Often, situations such as artificially moving robot, cumulative errors etc., can all cause location algorithm to fail, to lose mobile robot
Pose, it is therefore desirable to first detect whether mobile robot occurs pose loss, be lost in case of pose, then need to carry out again
Positioning.
Based on this, in one embodiment of the invention, judges whether mobile robot occurs pose loss, further wrap
It includes: detecting whether mobile robot occurs pose loss by matching detection algorithm.It specifically includes: more current mobile robot
Sensor acquisition data and map datum similarity;If similarity is lower than preset first threshold (i.e. similarity
It is low), then determine that mobile robot occurs pose and loses.
Alternatively, in another embodiment of the present invention, judging whether mobile robot occurs the method example of pose loss
Such as further include: liftoff detection sensor is installed in mobile robot, and judges whether mobile robot is liftoff;If it is,
Determine that mobile robot occurs pose and loses;And/or IMU is installed in mobile robot, and according to the acceleration of mobile robot
Degree judges whether mobile robot occurs strong collision or inclination;If it is, determining that mobile robot occurs pose and loses;
And/or judge whether robot fifth wheel skids, cause wheel measurement data and the practical travel distance of machine inconsistent;
If it is, determining that the raw pose of machine human hair is lost.
Step S4: it if location information mistake (i.e. pose loss) occurs for mobile robot, is reset according to preset
Position algorithm relocates mobile robot, obtains the correct pose of robot.
Specifically, in one embodiment of the invention, in step s 4, according to preset reorientation algorithm to moving machine
Device people relocates, and further comprises: in the case where there is map, the data that sensor acquires are matched with map,
It to be relocated to mobile robot, specifically includes: according to the prediction pose of the data of sensor acquisition and mobile robot
(i.e. mobile robot pose that may be present) obtains the probability distribution of the pose (i.e. position and posture) of mobile robot;Respectively
Each pose is sampled, the similarity of each pose Yu existing map is obtained;According to the similarity, to the probability point of pose
Cloth is repeatedly adjusted, and the alternative pose for being greater than preset second threshold with the similarity of map is obtained;It is obtained according to alternative pose
To the final pose of mobile robot.
Wherein, in above process, the final pose of mobile robot is obtained according to alternative pose, further comprises: when
When alternative pose is one, using alternative pose as final pose;When alternative pose is multiple, mobile robot difference is obtained
New pose after entering other default environment under multiple alternative poses, and by corresponding biography under obtained multiple new poses
The acquisition data of sensor are matched with map, and using matching degree highest when corresponding pose is as final pose.
It, can be by information (the i.e. mobile robot that observes current machine in other words, in the case where there is map
Sensor acquisition data) matched with map, to be relocated.The data and robot obtained according to observation may
Pose calculate the probability distribution of robot pose, sample pose respectively, calculate the similarity of each pose Yu existing map.
Further according to similarity, the probability distribution of pose is readjusted, and sample bits appearance and calculate similarity again.And so on, until
The robot pose with map similarity more than certain threshold value (i.e. second threshold) is found, using the pose as final pose.It needs
It is noted that multiple alternative poses can be found out if there are multiple places similar in map, machine can be made by mobile robot
Device people enters periphery others environment, and (this is by counting on the basis of the pose result of reorientation to the current pose of calculating robot
The new pose calculated) information that observes and that still matched calculated result of map be robot final pose.
Alternatively, in another embodiment of the present invention, in step s 4, according to preset reorientation algorithm to moving machine
The method that device people is relocated can be with are as follows: in the case where there is map, by the method for subgraph match to mobile machine
People relocates, and specifically includes: establishing subgraph, and obtains pose of the subgraph in map;According to position of the subgraph in map
Appearance relocates mobile robot.
Wherein, in above process, pose of the subgraph in map is obtained, further comprises: being calculated in subgraph and map
Each piece of similarity, and pose of the subgraph in map is obtained according to the similarity of subgraph and map;Or pass through image
Method, extracts the characteristics of image of subgraph and map, and obtains matched characteristic point pair according to characteristics of image, then according to matched
Characteristic point obtains corresponding model parameter using the criterion of least model error, according to mould to translation rotating model matrix is established
Shape parameter obtains pose of the subgraph in map.Wherein, the characteristics of image of subgraph and map for example, corner feature, texture
Feature etc..
Wherein, in above process, it such as can be built by the mobile a distance of mobile robot or a period of time
Vertical subgraph.
It should be noted that during being relocated by the method for subgraph match to mobile robot, it is local
When figure has missing, subgraph is established in the zone of ignorance of map.Specifically, when map exist missing in the case where, merely with
Current map matching may then can not find pose, i.e., can not be relocated.Figure and reorientation side can be built by part at this time
Formula gives pose for change, and map can be kept more perfect the map rejuvenation of former circumstances not known to historical map or atlas.The process is similar to aforementioned
The mode for establishing subgraph establishes subgraph in circumstances not known, and continuously attempt to relocate in this process, when mobile machine
When people reenters environment known to historical map or atlas, it will in repositioning, the pose of mobile robot can be obtained at this time, and
Subgraph can be superimposed or be updated to historical map or atlas in certain method.
Further, in one embodiment of the invention, if reorientation failure for a long time, further confirms with user
Environment whether has been replaced, and has replaced map.If there is part similar, then it is assumed that map may have partial movement to change, then use
Update map, increment builds the map that the methods of figure updates robot local environment.
That is, the pose loss detection and method for relocating of the mobile robot of the embodiment of the present invention, it can be automatic
Pose is lost and given for change to detection robot pose, and provides map modification strategy for the change of local environment.
To sum up, the pose loss detection and method for relocating of mobile robot according to an embodiment of the present invention, can be effective
The pose of mobile robot is given on ground for change, promotes the robustness for building figure and location algorithm, extends the validity period of map.
Fig. 2 is the pose loss detection of mobile robot according to an embodiment of the invention and the structure of relocation system
Block diagram.As shown in Fig. 2, the system 100 includes: data acquisition module 110, locating module 120, judgment module 130 and reorientation
Module 140.
Wherein, data acquisition module 110 is used to obtaining the map of mobile robot local environment, robot
The data of the sensor carried on obstacle information and robot.
Specifically, such as by building figure and location algorithm the map of mobile robot local environment is established, and then obtaining should
Map.Wherein, the input data of figure and location algorithm is built as the acquisition data of the sensor of mobile robot.Wherein, moving machine
Device people is, for example, sweeper or other types mobile robot.
Further, in data acquisition module 110, the method for obtaining ambient enviroment obstacle information includes: to pass through ranging
Sensor obtains the barrier around robot at a distance from fuselage, the Laser Measuring of laser radar and/or linear array including rotation
Laser ranging module and/or binocular distance measurement module away from module and/or face battle array;And/or it is obtained by imaging sensor
The image information of robot.
Locating module 120 is for obtaining pose of the mobile robot in map.
Specifically, can for example be installed with mobile robot laser radar, depth camera, infrared distance measuring device,
The single or multiple sensings such as ultrasonic unit, IMU (Inertial measurement unit, Inertial Measurement Unit), odometer
The input data source (namely acquisition data of sensor) for building figure and location algorithm is realized in device combination.Record has shifting on the map
Posture information, the mobile robot of the barrier of mobile robot local environment can move region and moving machine in clear
The zone of ignorance (i.e. map datum) that device people does not explore.
The data and map datum that judgment module 130 is used to be acquired according to sensor judge that localization for Mobile Robot information is
Whether the pose and the actual pose of machine of no mistake, i.e. locating module output are consistent.In other words, according to sensor acquisition
Data and map datum judge whether mobile robot occurs pose loss.
Specifically, mobile robot is in the process of moving, location algorithm may fail, as collision causes sensor different
Often, situations such as artificially moving robot, cumulative errors etc., can all cause location algorithm to fail, to lose mobile robot
Pose, it is therefore desirable to first detect whether mobile robot occurs pose loss, be lost in case of pose, then need to carry out again
Positioning.
Based on this, in one embodiment of the invention, judgment module 130 judges whether mobile robot occurs pose and lose
It loses, further comprises: detecting whether mobile robot occurs pose loss by matching detection algorithm.It specifically includes: comparing biography
The data of sensor acquisition and the similarity of map datum;If similarity is lower than first threshold (i.e. similarity is low), determine to move
Mobile robot occurs pose and loses.
Alternatively, in another embodiment of invention, judgment module 130 judges whether mobile robot occurs pose loss
Method for example further include: whether liftoff judge mobile robot, and/or judge whether mobile robot collides, and/or
Judge mobile robot whether wheel slip;If it is (i.e. mobile robot is liftoff and/or mobile robot collides,
And/or mobile robot wheel slip), then determine that mobile robot occurs pose and loses.
For example, installing liftoff detection sensor, in mobile robot to judge whether mobile robot is liftoff.In movement
IMU is installed in robot, judges whether mobile robot occurs strong collision with the acceleration according to mobile robot.It is moving
Speed measuring coder is installed on mobile robot wheel, with the machine observed according to wheel measurement data and robot other sensors
People's displacement information judges whether robot fifth wheel skids, and causes wheel measurement data and the practical travel distance of machine different
It causes.
Module 140 is relocated to be used for when location information mistake (i.e. pose loss) occurs for mobile robot, according to default
Reorientation algorithm mobile robot is relocated, obtain the correct pose of robot.
Specifically, in one embodiment of the invention, reorientation module 140 is according to preset reorientation algorithm to movement
Robot is relocated, and further comprises: in the case where there is map, by the data of sensor acquisition and map progress
Match, to be relocated to mobile robot, specifically include: according to the prediction bits of the data of sensor acquisition and mobile robot
Appearance (i.e. mobile robot pose that may be present) obtains the probability distribution of the pose (i.e. position and posture) of mobile robot;Point
It is other that each pose is sampled, obtain the similarity of each pose Yu existing map;According to similarity, to the probability point of pose
Cloth is repeatedly adjusted, and the alternative pose for being greater than preset second threshold with the similarity of map is obtained;It is obtained according to alternative pose
To the final pose of mobile robot.
Wherein, in above process, the final pose of mobile robot is obtained according to alternative pose, comprising: when alternative position
When appearance is one, using alternative pose as final pose;When alternative pose is multiple, mobile robot is obtained respectively multiple
New pose after entering other default environment under alternative pose, and by corresponding sensor under obtained multiple new poses
Acquisition data are matched with map, and using matching degree highest when corresponding pose is as final pose.
It, can be by information (the i.e. mobile robot that observes current machine in other words, in the case where there is map
Sensor acquisition data) matched with map, to be relocated.The data and robot obtained according to observation may
Pose calculate the probability distribution of robot pose, sample pose respectively, calculate the similarity of each pose Yu existing map.
Further according to similarity, the probability distribution of pose is readjusted, and sample bits appearance and calculate similarity again.And so on, until
The robot pose with map similarity more than certain threshold value (i.e. second threshold) is found, using the pose as final pose.It needs
It is noted that multiple alternative poses can be found out if there are multiple places similar in map, machine can be made by mobile robot
Device people enters periphery others environment, and (this is by counting on the basis of the pose result of reorientation to the current pose of calculating robot
The new pose calculated) information that observes and that still matched calculated result of map be robot final pose.
Alternatively, in another embodiment of the present invention, relocating module 140 according to preset reorientation algorithm to movement
The method that robot is relocated can be with are as follows: in the case where there is map, by the method for subgraph match to moving machine
Device people relocates, and specifically includes: establishing subgraph, and obtains pose of the subgraph in map;According to subgraph in map
Pose relocates mobile robot.
Wherein, in above process, obtain pose of the subgraph in map, comprising: each piece is calculated in subgraph and map
Similarity, and pose of the subgraph in map is obtained according to the similarity of subgraph and map;Or the method by image, it mentions
The characteristics of image of subgraph and map is taken, and matched characteristic point pair is obtained according to characteristics of image, then according to matched characteristic point
Rotating model matrix is translated to establishing, corresponding model parameter is obtained using the criterion of least model error, according to model parameter
Obtain pose of the subgraph in map.Wherein, the characteristics of image of subgraph and map for example, corner feature, textural characteristics etc..
Wherein, in above process, it such as can be built by the mobile a distance of mobile robot or a period of time
Vertical subgraph.
It should be noted that being relocated by the method for subgraph match to mobile robot in reorientation module 140
During, when map, which exists, to be lacked, subgraph is established in the zone of ignorance of map.Specifically, when there is missing in map
In the case of, it is matched with current map merely, pose may be can not find, i.e., can not be relocated.It can be built at this time by part
Figure and relocation loading mode give pose for change, and map can be kept more perfect the map rejuvenation of former circumstances not known to historical map or atlas.The mistake
Journey is similar to the aforementioned mode for establishing subgraph, i.e., subgraph is established in circumstances not known, and continuously attempts to determine again in this process
Position, when environment known to mobile robot reenters historical map or atlas, it will in repositioning, moving machine can be obtained at this time
The pose of device people, and subgraph can be superimposed or be updated to historical map or atlas in certain method.
Further, in one embodiment of the invention, if reorientation failure for a long time, further confirms with user
Environment whether has been replaced, and has replaced map.If there is part similar, then it is assumed that map may have partial movement to change, then use
Update map, increment builds the map that the methods of figure updates robot local environment.
That is, the pose loss detection and relocation system of the mobile robot of the embodiment of the present invention, it can be automatic
Pose is lost and given for change to detection robot pose, and provides map modification strategy for the change of local environment.
To sum up, the pose loss detection and relocation system of mobile robot according to an embodiment of the present invention, can be effective
The pose of mobile robot is given on ground for change, promotes the robustness for building figure and location algorithm, extends the validity period of map.
Further embodiment of the present invention proposes a kind of robot, including any one above-mentioned embodiment of the present invention is retouched
The pose loss detection and relocation system for the mobile robot stated.
Robot according to an embodiment of the present invention can quickly and efficiently give pose for change when pose loss occurs, real
The high pose reorientation of existing accuracy.
In addition, robot according to an embodiment of the present invention other compositions and effect for this field ordinary skill people
Member for be all it is known, in order to reduce redundancy, do not repeat them here.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: not
A variety of change, modification, replacement and modification can be carried out to these embodiments in the case where being detached from the principle of the present invention and objective, this
The range of invention is by claim and its equivalent limits.
Claims (10)
1. the pose loss detection and relocation system of a kind of mobile robot characterized by comprising
Data acquisition module, for obtaining the map of the mobile robot local environment, the barrier of robot
The data of the sensor carried in information and robot;
Locating module, for obtaining pose of the mobile robot in map;
Judgment module, data and the map datum for being acquired according to the sensor judge the localization for Mobile Robot
Information whether mistake, i.e., locating module output pose and the actual pose of machine it is whether consistent;
Module is relocated, is used for when location information mistake occurs for the mobile robot, according to preset reorientation algorithm pair
The mobile robot is relocated, and the correct pose of the robot is obtained.
2. system according to claim 1, which is characterized in that in the data acquisition module, obtain ambient enviroment barrier
The method for hindering object information includes:
The barrier around the robot is obtained at a distance from fuselage by distance measuring sensor, the laser radar including rotation,
And/or linear array laser ranging module and/or face battle array laser ranging module and/or binocular distance measurement module;
And/or the image information of the robot is obtained by imaging sensor.
3. system according to claim 1, which is characterized in that the judgment module is used for:
Compare the data of the sensor acquisition and the similarity of the map datum;
If similarity is lower than first threshold, determine that the mobile robot occurs pose and loses.
4. system according to claim 1, which is characterized in that the judgment module is also used to:
Whether liftoff judge the mobile robot, and/or judge whether the mobile robot collides, and/or judgement
The mobile robot whether wheel slip;
If it is, determining that the mobile robot occurs pose and loses.
5. the system as claimed in claim 1, which is characterized in that the number that the reorientation module is used to acquire the sensor
It is matched according to the map, to be relocated to the mobile robot, is specifically included:
The position of the mobile robot is obtained according to the prediction pose of the data of sensor acquisition and the mobile robot
The probability distribution of appearance;
Each pose is sampled respectively, obtains the similarity of each pose Yu the map;
According to the similarity, the probability distribution of the pose is repeatedly adjusted, is obtained big with the similarity of the map
In the alternative pose of second threshold;
The final pose of the mobile robot is obtained according to the alternative pose.
6. system as claimed in claim 2, which is characterized in that described to obtain the mobile robot according to the alternative pose
Final pose, comprising:
When the alternative pose is one, using the alternative pose as the final pose;
When the alternative pose is multiple, it is default into other under multiple alternative poses respectively to obtain the mobile robot
New pose after environment, and the acquisition data of corresponding sensor under obtained multiple new poses and the map are carried out
Matching, and using matching degree highest when corresponding pose is as the final pose.
7. system according to claim 1, which is characterized in that the reorientation module is used for the method by subgraph match
The mobile robot is relocated, is specifically included:
Subgraph is established, and obtains pose of the subgraph in the map;
According to pose of the subgraph in the map, the mobile robot is relocated.
8. system according to claim 4, which is characterized in that the pose for obtaining the subgraph in the map,
Include:
It calculates the similarity of the subgraph Yu the map, and is obtained according to the similarity for stating subgraph and the map described
Pose of the subgraph in the map;Or
The characteristics of image of subgraph and map is extracted, and matched characteristic point pair is obtained according to described image feature, according to described
The characteristic point matched obtains corresponding model parameter, root using the criterion of least model error to translation rotating model matrix is established
Pose of the subgraph in the map is obtained according to the model parameter.
9. system according to claim 4, which is characterized in that pass through the method pair of subgraph match in the reorientation module
During the mobile robot is relocated, when the map, which exists, to be lacked, built in the zone of ignorance of the map
Vertical subgraph.
10. a kind of robot, which is characterized in that the pose just like the described in any item mobile robots of claim 1-9 is arranged
Loss detection and relocation system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710829430.8A CN109506641A (en) | 2017-09-14 | 2017-09-14 | The pose loss detection and relocation system and robot of mobile robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710829430.8A CN109506641A (en) | 2017-09-14 | 2017-09-14 | The pose loss detection and relocation system and robot of mobile robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109506641A true CN109506641A (en) | 2019-03-22 |
Family
ID=65744710
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710829430.8A Pending CN109506641A (en) | 2017-09-14 | 2017-09-14 | The pose loss detection and relocation system and robot of mobile robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109506641A (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109993794A (en) * | 2019-03-29 | 2019-07-09 | 北京猎户星空科技有限公司 | A kind of robot method for relocating, device, control equipment and storage medium |
CN110046725A (en) * | 2019-04-23 | 2019-07-23 | 深圳市锐曼智能装备有限公司 | Mobile device is got lost control method and the mobile device of playbacking |
CN110146098A (en) * | 2019-05-06 | 2019-08-20 | 北京猎户星空科技有限公司 | A kind of robot map enlargement method, device, control equipment and storage medium |
CN110146068A (en) * | 2019-03-27 | 2019-08-20 | 深圳乐行天下科技有限公司 | A kind of robot recovery is damaged the method, apparatus and robot of map |
CN110187323A (en) * | 2019-05-14 | 2019-08-30 | 北京云迹科技有限公司 | Robot idle running recognition methods and device |
CN110196054A (en) * | 2019-06-18 | 2019-09-03 | 北京史河科技有限公司 | A kind of navigation methods and systems |
CN110304386A (en) * | 2019-06-28 | 2019-10-08 | 北京极智嘉科技有限公司 | Robot and robot lose the re-positioning method after code |
CN110772178A (en) * | 2019-09-25 | 2020-02-11 | 深圳市无限动力发展有限公司 | Sweeping method and device of sweeper, computer equipment and storage medium |
CN110900602A (en) * | 2019-11-26 | 2020-03-24 | 苏州博众机器人有限公司 | Positioning recovery method and device, robot and storage medium |
CN110986967A (en) * | 2019-12-20 | 2020-04-10 | 上海有个机器人有限公司 | Robot automatic repositioning method, medium, terminal and device |
CN111060113A (en) * | 2019-12-31 | 2020-04-24 | 歌尔股份有限公司 | Map updating method and device |
CN111580530A (en) * | 2020-06-16 | 2020-08-25 | 福勤智能科技(昆山)有限公司 | Positioning method, positioning device, autonomous mobile equipment and medium |
CN111580508A (en) * | 2020-04-14 | 2020-08-25 | 广东博智林机器人有限公司 | Robot positioning method and device, electronic equipment and storage medium |
CN111637877A (en) * | 2020-05-29 | 2020-09-08 | 拉扎斯网络科技(上海)有限公司 | Robot positioning method and device, electronic equipment and nonvolatile storage medium |
CN111739099A (en) * | 2020-07-20 | 2020-10-02 | 北京云迹科技有限公司 | Falling prevention method and device and electronic equipment |
CN111795701A (en) * | 2020-07-09 | 2020-10-20 | 上海有个机器人有限公司 | Remote recovery positioning method and device for robot |
CN112179353A (en) * | 2020-09-30 | 2021-01-05 | 深圳市银星智能科技股份有限公司 | Positioning method and device of self-moving robot, robot and readable storage medium |
CN112414391A (en) * | 2019-08-20 | 2021-02-26 | 北京京东乾石科技有限公司 | Robot repositioning method and device |
CN112450820A (en) * | 2020-11-23 | 2021-03-09 | 深圳市银星智能科技股份有限公司 | Pose optimization method, mobile robot and storage medium |
CN112558641A (en) * | 2020-12-08 | 2021-03-26 | 之江实验室 | Method for controlling robot to retrieve lost person based on figure intention calculation |
CN112965076A (en) * | 2021-01-28 | 2021-06-15 | 上海思岚科技有限公司 | Multi-radar positioning system and method for robot |
CN113124902A (en) * | 2021-04-19 | 2021-07-16 | 追创科技(苏州)有限公司 | Positioning correction method and device for mobile robot, storage medium, and electronic device |
CN113238557A (en) * | 2021-05-17 | 2021-08-10 | 珠海市一微半导体有限公司 | Mapping abnormity identification and recovery method, chip and mobile robot |
CN113419249A (en) * | 2021-06-18 | 2021-09-21 | 珠海市一微半导体有限公司 | Repositioning method, chip and mobile robot |
CN113907645A (en) * | 2021-09-23 | 2022-01-11 | 追觅创新科技(苏州)有限公司 | Mobile robot positioning method and device, storage medium and electronic device |
CN114012725A (en) * | 2021-11-05 | 2022-02-08 | 深圳拓邦股份有限公司 | Robot repositioning method, system, robot and storage medium |
CN114643579A (en) * | 2022-03-29 | 2022-06-21 | 深圳优地科技有限公司 | Robot positioning method and device, robot and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102138768A (en) * | 2010-01-28 | 2011-08-03 | 深圳先进技术研究院 | Positioning method and equipment for cleaning robot |
CN102866706A (en) * | 2012-09-13 | 2013-01-09 | 深圳市银星智能科技股份有限公司 | Cleaning robot adopting smart phone navigation and navigation cleaning method thereof |
CN103439973A (en) * | 2013-08-12 | 2013-12-11 | 桂林电子科技大学 | Household cleaning robot capable of establishing map by self and cleaning method |
CN103616021A (en) * | 2013-12-04 | 2014-03-05 | 苏州大学张家港工业技术研究院 | Global localization method and device |
CN104281840A (en) * | 2014-09-28 | 2015-01-14 | 无锡清华信息科学与技术国家实验室物联网技术中心 | Method and device for positioning and identifying building based on intelligent terminal |
CN105652871A (en) * | 2016-02-19 | 2016-06-08 | 深圳杉川科技有限公司 | Repositioning method for mobile robot |
CN105928505A (en) * | 2016-04-19 | 2016-09-07 | 深圳市神州云海智能科技有限公司 | Determination method and apparatus for position and orientation of mobile robot |
CN106092104A (en) * | 2016-08-26 | 2016-11-09 | 深圳微服机器人科技有限公司 | The method for relocating of a kind of Indoor Robot and device |
WO2017007089A1 (en) * | 2015-07-03 | 2017-01-12 | 한국과학기술원 | Method and device for relocating mobile robot in indoor environment |
CN106406338A (en) * | 2016-04-14 | 2017-02-15 | 中山大学 | Omnidirectional mobile robot autonomous navigation apparatus and method based on laser range finder |
CN106504289A (en) * | 2016-11-02 | 2017-03-15 | 深圳乐行天下科技有限公司 | A kind of indoor objects detection method and device |
CN107063264A (en) * | 2017-04-13 | 2017-08-18 | 杭州申昊科技股份有限公司 | A kind of robot map creating method suitable for extensive substation |
-
2017
- 2017-09-14 CN CN201710829430.8A patent/CN109506641A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102138768A (en) * | 2010-01-28 | 2011-08-03 | 深圳先进技术研究院 | Positioning method and equipment for cleaning robot |
CN102866706A (en) * | 2012-09-13 | 2013-01-09 | 深圳市银星智能科技股份有限公司 | Cleaning robot adopting smart phone navigation and navigation cleaning method thereof |
CN103439973A (en) * | 2013-08-12 | 2013-12-11 | 桂林电子科技大学 | Household cleaning robot capable of establishing map by self and cleaning method |
CN103616021A (en) * | 2013-12-04 | 2014-03-05 | 苏州大学张家港工业技术研究院 | Global localization method and device |
CN104281840A (en) * | 2014-09-28 | 2015-01-14 | 无锡清华信息科学与技术国家实验室物联网技术中心 | Method and device for positioning and identifying building based on intelligent terminal |
WO2017007089A1 (en) * | 2015-07-03 | 2017-01-12 | 한국과학기술원 | Method and device for relocating mobile robot in indoor environment |
CN105652871A (en) * | 2016-02-19 | 2016-06-08 | 深圳杉川科技有限公司 | Repositioning method for mobile robot |
CN106406338A (en) * | 2016-04-14 | 2017-02-15 | 中山大学 | Omnidirectional mobile robot autonomous navigation apparatus and method based on laser range finder |
CN105928505A (en) * | 2016-04-19 | 2016-09-07 | 深圳市神州云海智能科技有限公司 | Determination method and apparatus for position and orientation of mobile robot |
CN106092104A (en) * | 2016-08-26 | 2016-11-09 | 深圳微服机器人科技有限公司 | The method for relocating of a kind of Indoor Robot and device |
CN106504289A (en) * | 2016-11-02 | 2017-03-15 | 深圳乐行天下科技有限公司 | A kind of indoor objects detection method and device |
CN107063264A (en) * | 2017-04-13 | 2017-08-18 | 杭州申昊科技股份有限公司 | A kind of robot map creating method suitable for extensive substation |
Non-Patent Citations (3)
Title |
---|
刘洞波: "《移动机器人粒子滤波定位与地图创建》", 30 September 2016, 湘潭大学出版社 * |
南京航空航天大学科技部: "《南京航空航天大学论文集2010年 第44册 其他 第2分册》", 31 May 2011 * |
胡来招: "《无源定位》", 31 January 2004 * |
Cited By (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110146068B (en) * | 2019-03-27 | 2021-02-09 | 深圳乐行天下科技有限公司 | Method and device for recovering damaged map by robot and robot |
CN110146068A (en) * | 2019-03-27 | 2019-08-20 | 深圳乐行天下科技有限公司 | A kind of robot recovery is damaged the method, apparatus and robot of map |
CN109993794A (en) * | 2019-03-29 | 2019-07-09 | 北京猎户星空科技有限公司 | A kind of robot method for relocating, device, control equipment and storage medium |
CN110046725A (en) * | 2019-04-23 | 2019-07-23 | 深圳市锐曼智能装备有限公司 | Mobile device is got lost control method and the mobile device of playbacking |
CN110146098A (en) * | 2019-05-06 | 2019-08-20 | 北京猎户星空科技有限公司 | A kind of robot map enlargement method, device, control equipment and storage medium |
CN110187323A (en) * | 2019-05-14 | 2019-08-30 | 北京云迹科技有限公司 | Robot idle running recognition methods and device |
CN110196054A (en) * | 2019-06-18 | 2019-09-03 | 北京史河科技有限公司 | A kind of navigation methods and systems |
CN110304386A (en) * | 2019-06-28 | 2019-10-08 | 北京极智嘉科技有限公司 | Robot and robot lose the re-positioning method after code |
CN112414391A (en) * | 2019-08-20 | 2021-02-26 | 北京京东乾石科技有限公司 | Robot repositioning method and device |
CN110772178A (en) * | 2019-09-25 | 2020-02-11 | 深圳市无限动力发展有限公司 | Sweeping method and device of sweeper, computer equipment and storage medium |
CN110900602A (en) * | 2019-11-26 | 2020-03-24 | 苏州博众机器人有限公司 | Positioning recovery method and device, robot and storage medium |
CN110986967A (en) * | 2019-12-20 | 2020-04-10 | 上海有个机器人有限公司 | Robot automatic repositioning method, medium, terminal and device |
CN110986967B (en) * | 2019-12-20 | 2023-05-05 | 上海有个机器人有限公司 | Automatic repositioning method, medium, terminal and device for robot |
CN111060113B (en) * | 2019-12-31 | 2022-04-08 | 歌尔股份有限公司 | Map updating method and device |
CN111060113A (en) * | 2019-12-31 | 2020-04-24 | 歌尔股份有限公司 | Map updating method and device |
CN111580508A (en) * | 2020-04-14 | 2020-08-25 | 广东博智林机器人有限公司 | Robot positioning method and device, electronic equipment and storage medium |
CN111637877A (en) * | 2020-05-29 | 2020-09-08 | 拉扎斯网络科技(上海)有限公司 | Robot positioning method and device, electronic equipment and nonvolatile storage medium |
CN111580530A (en) * | 2020-06-16 | 2020-08-25 | 福勤智能科技(昆山)有限公司 | Positioning method, positioning device, autonomous mobile equipment and medium |
CN111580530B (en) * | 2020-06-16 | 2021-10-26 | 福勤智能科技(昆山)有限公司 | Positioning method, positioning device, autonomous mobile equipment and medium |
CN111795701A (en) * | 2020-07-09 | 2020-10-20 | 上海有个机器人有限公司 | Remote recovery positioning method and device for robot |
CN111739099A (en) * | 2020-07-20 | 2020-10-02 | 北京云迹科技有限公司 | Falling prevention method and device and electronic equipment |
CN112179353A (en) * | 2020-09-30 | 2021-01-05 | 深圳市银星智能科技股份有限公司 | Positioning method and device of self-moving robot, robot and readable storage medium |
CN112450820A (en) * | 2020-11-23 | 2021-03-09 | 深圳市银星智能科技股份有限公司 | Pose optimization method, mobile robot and storage medium |
CN112450820B (en) * | 2020-11-23 | 2022-01-21 | 深圳市银星智能科技股份有限公司 | Pose optimization method, mobile robot and storage medium |
CN112558641A (en) * | 2020-12-08 | 2021-03-26 | 之江实验室 | Method for controlling robot to retrieve lost person based on figure intention calculation |
CN112965076A (en) * | 2021-01-28 | 2021-06-15 | 上海思岚科技有限公司 | Multi-radar positioning system and method for robot |
CN113124902A (en) * | 2021-04-19 | 2021-07-16 | 追创科技(苏州)有限公司 | Positioning correction method and device for mobile robot, storage medium, and electronic device |
WO2022222345A1 (en) * | 2021-04-19 | 2022-10-27 | 追觅创新科技(苏州)有限公司 | Positioning correction method and apparatus for mobile robot, storage medium, and electronic apparatus |
CN113238557A (en) * | 2021-05-17 | 2021-08-10 | 珠海市一微半导体有限公司 | Mapping abnormity identification and recovery method, chip and mobile robot |
CN113419249A (en) * | 2021-06-18 | 2021-09-21 | 珠海市一微半导体有限公司 | Repositioning method, chip and mobile robot |
WO2023045644A1 (en) * | 2021-09-23 | 2023-03-30 | 追觅创新科技(苏州)有限公司 | Positioning method and device for mobile robot, storage medium and electronic device |
CN113907645A (en) * | 2021-09-23 | 2022-01-11 | 追觅创新科技(苏州)有限公司 | Mobile robot positioning method and device, storage medium and electronic device |
CN114012725A (en) * | 2021-11-05 | 2022-02-08 | 深圳拓邦股份有限公司 | Robot repositioning method, system, robot and storage medium |
CN114012725B (en) * | 2021-11-05 | 2023-08-08 | 深圳拓邦股份有限公司 | Robot repositioning method, system, robot and storage medium |
CN114643579A (en) * | 2022-03-29 | 2022-06-21 | 深圳优地科技有限公司 | Robot positioning method and device, robot and storage medium |
CN114643579B (en) * | 2022-03-29 | 2024-01-16 | 深圳优地科技有限公司 | Robot positioning method and device, robot and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109506641A (en) | The pose loss detection and relocation system and robot of mobile robot | |
EP3168705B1 (en) | Domestic robotic system | |
EP3278937B1 (en) | Charger, and map-constructing-based charger finding method, device and system | |
KR101698939B1 (en) | Three dimensional scanning beam system and method | |
EP2590042B1 (en) | Walking robot performing position recognition using several local filters and a fusion filter | |
KR100877072B1 (en) | Method and apparatus of building map for a mobile robot and cleaning simultaneously | |
Pathak et al. | Online three‐dimensional SLAM by registration of large planar surface segments and closed‐form pose‐graph relaxation | |
Kelly et al. | Combined visual and inertial navigation for an unmanned aerial vehicle | |
CN101479082B (en) | Robot device and robot device control method | |
EP2972084B1 (en) | System and method for positioning a tool in a work space | |
CN104236548A (en) | Indoor autonomous navigation method for micro unmanned aerial vehicle | |
US20130166137A1 (en) | Mobile apparatus and localization method thereof | |
CN106339001A (en) | Map Production Method, Mobile Robot, And Map Production System | |
WO2013049597A1 (en) | Method and system for three dimensional mapping of an environment | |
KR101705601B1 (en) | Apparatus and method for estimating the location of autonomous robot based on three-dimensional depth information | |
JP5016399B2 (en) | Map information creation device and autonomous mobile device equipped with the map information creation device | |
JP5276931B2 (en) | Method for recovering from moving object and position estimation error state of moving object | |
Zhang et al. | Lidar-IMU and wheel odometer based autonomous vehicle localization system | |
Belter et al. | Estimating terrain elevation maps from sparse and uncertain multi-sensor data | |
CN108052103A (en) | The crusing robot underground space based on depth inertia odometer positions simultaneously and map constructing method | |
CN208323361U (en) | A kind of positioning device and robot based on deep vision | |
KR101645005B1 (en) | System and method for detecting location of underwater operating device using welding line of underwater structure | |
CN112476433A (en) | Mobile robot positioning method based on array boundary identification | |
CN110864692A (en) | Pose determination method of heading machine | |
Karam et al. | Integrating a low-cost mems imu into a laser-based slam for indoor mobile mapping |
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 |
Application publication date: 20190322 |
|
RJ01 | Rejection of invention patent application after publication |