CN109579844A - Localization method and system - Google Patents
Localization method and system Download PDFInfo
- Publication number
- CN109579844A CN109579844A CN201811473786.3A CN201811473786A CN109579844A CN 109579844 A CN109579844 A CN 109579844A CN 201811473786 A CN201811473786 A CN 201811473786A CN 109579844 A CN109579844 A CN 109579844A
- Authority
- CN
- China
- Prior art keywords
- robot
- data
- pose data
- subsystem
- mobile robot
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000004807 localization Effects 0.000 title claims abstract description 15
- 230000033001 locomotion Effects 0.000 claims abstract description 10
- 230000000007 visual effect Effects 0.000 claims abstract description 9
- 238000011084 recovery Methods 0.000 claims abstract description 8
- 238000004804 winding Methods 0.000 claims description 25
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 11
- 238000013519 translation Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of localization method and systems, are related to robot localization technical field.This method includes that chassis control chip according to rotary speed data and angle-data obtains the first pose data of wheeled odometer model;Robot subsystem calculates the second pose data of visual odometry model according to the image data that monocular camera is got;First pose data and the second pose data are carried out timestamp alignment to robot subsystem and motion profile is aligned, and restores the optimal camera scale of monocular camera;Robot subsystem carries out scale recovery to the second pose data according to optimal camera scale;The second pose data after robot subsystem restores the first pose data with scale merge, and obtain the final pose data of wheeled mobile robot.Method and system disclosed by the invention can overcome the problems, such as that monocular camera does not have scale and poor robustness in position fixing process, can also solve the problems, such as that wheeled odometer accumulated error and wheels of robot are skidded.
Description
Technical field
The present invention relates to robot localization technical fields, more particularly, to a kind of localization method and system.
Background technique
Location navigation is that robot realizes one of intelligentized premise, is to confer to the key of robot perception and ability to act
Factor.
It is calculated currently, traditional robot localization method is often adopted by wheeled odometer, the advantages of wheeled odometer
It is that short time short-range positioning accuracy is very high, but the localization method of this reckoning can have accumulated error, and not
Error concealment can be carried out according to the information of itself, while the influence of the factors such as wheel slip can not be overcome.
Summary of the invention
In view of this, it is an object of the invention to propose a kind of localization method and system, to improve the above problem.
To achieve the goals above, the present invention adopts the following technical scheme:
In a first aspect, the positioning system the embodiment of the invention provides a kind of localization method, applied to wheeled mobile robot
System, the positioning system include encoder, gyroscope, monocular camera, chassis control chip and robot subsystem, described
Encoder is installed on the wheel of wheeled mobile robot, which comprises
The chassis control chip is acquired according to the rotary speed data of the collected wheel of the encoder and the gyroscope
To the angle-data of the wheeled mobile robot obtain the first pose data of wheeled odometer model, first pose
Data include first position and First Speed;
The robot subsystem calculates visual odometry according to the image data that the monocular camera is got
Second pose data of model, the second pose data packet include the second position and second speed;
The first pose data and the second pose data are carried out timestamp pair by the robot subsystem
The alignment of neat and motion profile, restores the optimal camera scale of the monocular camera;
The robot subsystem is extensive to the second pose data progress scale according to the optimal camera scale
It is multiple;
The robot subsystem the first pose data and scale are restored after the second pose data
It is merged, obtains the final pose data of the wheeled mobile robot.
Optionally, the method also includes:
The robot subsystem carries out winding detection to each of described image data key frame images;
When winding occurs, the robot subsystem carries out reorientation calculating to the wheeled mobile robot.
Optionally, the robot subsystem carries out winding to each of described image data key frame images
Detection, comprising:
The robot subsystem extracts multiple FAST angle points to each key frame images in described image data,
And calculate BRIEF description of each FAST angle point;
The robot subsystem describes son according to each FAST angle point and corresponding BRIEF, passes through DBoW2 algorithm
Calculate the similarity size of present frame with key frame before;
When similarity is greater than the threshold value of setting, winding then occurs for the robot subsystem judgement.
Optionally, the wheel count of the encoder and the wheeled mobile robot is multiple and corresponds, institute
Chassis control chip is stated according to the rotary speed data of the collected wheel of the encoder and the collected wheel of the gyroscope
The angle-data of formula mobile robot obtains the first pose data of wheeled odometer model, comprising:
The chassis control chip obtains described wheeled according to the rotary speed data of each collected wheel of encoder
Speed data and first attitude angle of the mobile robot under current coordinate system;
The chassis control chip calculates the wheeled mobile robot according to the gyro error model pre-established
Currently the second attitude angle under global coordinate system;
First attitude angle is carried out Kalman filtering with second attitude angle and merged by the chassis control chip, is obtained
To the final carriage angle of the wheeled mobile robot;
The chassis control chip resolves the wheeled mobile robot according to the speed data and the final carriage angle
Speed and location information of the people under world coordinate system, obtain the first pose data.
Optionally, the quantity of the wheel is 3, and angle between any two is 120 °, the wheeled mobile robot
Speed data under current coordinate system are as follows:
Wherein, vx、vyBe illustrated respectively in x-axis under current coordinate system and
The speed of y-axis, ω are indicated under current coordinate system around the rotation speed of itself geometric center, ω1、ω2、ω3Respectively indicate three
The rotation speed of wheel, L are the chassis radius of wheeled mobile robot, and R is radius of wheel.
Optionally, the robot subsystem calculates vision according to the image data that the monocular camera is got
Second pose data of odometer model, comprising:
The robot subsystem extracts FAST angle point to described image data, and carries out LK optical flow tracking, obtains
Image Feature Point Matching information;
The robot subsystem issues frequency according to preset image characteristic point and issues described image characteristic point
With information;
The first frame of described image data is set as key frame by the robot subsystem, other picture frames are according to working as
The feature of preceding image trace previous keyframe image is counted and the mean parallax of characteristic point determines whether to be set as key frame;
The robot subsystem establishes the sliding window of image trace;
The sliding window is calculated by Epipolar geometry, three-dimensional reconstruction, PnP algorithm in the robot subsystem
In the positional relationship of each frame image obtain spin matrix, and yaw angle is chosen as initial rotation to the spin matrix sought
Matrix is translated towards the translation measured in x-axis and y-axis horizontal plane, establishes re-projection error cost function, carries out 3DOF most
Smallization re-projection error calculates, and obtains the rotation and translation matrix for lacking scale between image key frame.
Optionally, when the robot subsystem carries out the first pose data and the second pose data
Between stamp alignment and motion profile alignment, restore the optimal camera scale of the monocular camera, comprising:
The first pose data are aligned by the robot subsystem with the second pose data time stamp;
The robot subsystem timestamp is aligned after the first pose data and the second pose number
According to progress track alignment;
The robot subsystem obtains the monocular camera most by seeking the least square solution of loss function
Excellent camera scale.
Second aspect, the embodiment of the invention provides a kind of positioning systems, are applied to wheeled mobile robot, comprising: compile
Code device, gyroscope, monocular camera, chassis control chip and robot subsystem, the encoder are installed on wheel type mobile
On the wheel of robot;
The chassis control chip is used for rotary speed data and the gyroscope according to the collected wheel of the encoder
The angle-data of the collected wheeled mobile robot obtains the first pose data of wheeled odometer model, and described first
Pose data include first position and First Speed;
The robot subsystem according to the image data that the monocular camera is got for calculating in vision
Second pose data of journey meter model, the second pose data packet include the second position and second speed;
When the robot subsystem is also used to carry out the first pose data and the second pose data
Between stamp alignment and motion profile alignment, restore the optimal camera scale of the monocular camera;
The robot subsystem is also used to carry out the second pose data according to the optimal camera scale
Scale restores;
The robot subsystem is also used to the second after the first pose data and scale recovery
Appearance data are merged, and the final pose data of the wheeled mobile robot are obtained.
Optionally, the robot subsystem be also used to each of described image data image key frame into
The detection of row winding;And reorientation calculating is carried out to the wheeled mobile robot when winding occurs.
Optionally, the wheel count of the encoder and the wheeled mobile robot is multiple and corresponds;
The chassis control chip is used to be obtained according to the rotary speed data of each collected wheel of encoder described
Speed data and first attitude angle of the wheeled mobile robot under current coordinate system;
The chassis control chip is also used to calculate the wheel type mobile according to the gyro error model pre-established
Current the second attitude angle under global coordinate system of robot;
The chassis control chip is also used to first attitude angle and second attitude angle carrying out Kalman filtering
Fusion, obtains the final carriage angle of the wheeled mobile robot;
The chassis control chip is also used to resolve the wheeled shifting according to the speed data and the final carriage angle
Speed and location information of the mobile robot under world coordinate system, obtain the first pose data.
Compared with prior art, the beneficial effects of the present invention are:
Localization method provided by the invention and system can have accumulated error and cannot eliminate automatically for wheeled odometer,
Influence of the extraneous factors such as wheel slip to positioning accuracy advanced optimizes location information by the thought of sensor fusion,
Wheeled odometer is combined with monocular vision odometer, mutual disadvantage is overcome, retains respective advantage, it is fixed to overcome
Monocular camera does not have the problem of scale and poor robustness during position, while can solve asking for wheeled odometer accumulated error yet
Topic.
Detailed description of the invention
Fig. 1 is the structural schematic diagram for the positioning system that present pre-ferred embodiments provide.
Fig. 2 is the flow chart for the localization method that present pre-ferred embodiments provide.
Fig. 3 is the flow chart of the sub-step of step S101 in Fig. 2.
Fig. 4 is the flow chart of the sub-step of step S102 in Fig. 2.
Fig. 5 is the flow chart of the sub-step of step S103 in Fig. 2.
Fig. 6 is the flow chart of the sub-step of step S106 in Fig. 2.
Description of symbols: 110- encoder;120- gyroscope;130- monocular camera;140- chassis control chip;150-
Robot subsystem.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
Term " first ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relatively heavy
The property wanted.
Referring to Fig. 1, being the structural schematic diagram for the positioning system that present pre-ferred embodiments provide, the positioning system is answered
For wheeled mobile robot, positioning system includes encoder 110, gyroscope 120, monocular camera 130, chassis control chip
140 and robot subsystem 150, chassis control chip 140 respectively with encoder 110, gyroscope 120 and robot master control
Subsystem 150 is connected to carry out data communication or interaction, and robot subsystem 150 is connect to carry out with monocular camera 130
Data communication or interaction.
The chassis control chip 140 is used for according to the rotary speed data of the collected wheel of the encoder 110 and described
The angle-data of the collected wheeled mobile robot of gyroscope 120 obtains the first pose number of wheeled odometer model
According to.
In the embodiment of the present invention, the encoder 110 is installed on the wheel of wheeled mobile robot, for acquiring correspondence
The rotary speed data of wheel, and collected rotary speed data is sent to chassis control chip 140.The wheel of wheeled mobile robot
Quantity can be to be multiple, and the quantity of encoder 110 may be multiple at this time, multiple encoders 110 and multiple wheel count phases
Deng and be arranged in a one-to-one correspondence.When the quantity of encoder 110 is multiple, each encoder 110 is by collected corresponding wheel
Rotary speed data be sent to chassis control chip 140.Gyroscope 120 is installed on the chassis of wheeled mobile robot, for adopting
The angle-data of the wheeled mobile robot collected, and collected angle-data is sent to chassis control chip 140.
Chassis control chip 140 is collected wheeled according to the rotary speed data and gyroscope 120 of the collected wheel of each encoder 110
The angle-data of mobile robot carries out operation, obtains the first pose data of wheeled odometer model, the first pose data packet
Include first position and First Speed.
Specifically, chassis control chip 140 is obtained according to the rotary speed data of the collected wheel of each encoder 110 first
Speed data and first attitude angle of the wheeled mobile robot under current coordinate system.For example, working as the number of wheel and encoder 110
Amount is 3, and the angle of wheel between any two is 120 °, speed data of the wheeled mobile robot under current coordinate system
Are as follows:Wherein, vx、vyThe x-axis that is illustrated respectively under current coordinate system and y-axis
Speed, ω are indicated under current coordinate system around the rotation speed of itself geometric center, ω1、ω2、ω3Respectively indicate three wheels
Rotation speed, L be wheeled mobile robot chassis radius, R is radius of wheel.
The angle-data and actual angle-data that chassis control chip 140 is arrived according to the preparatory repeated detection of gyroscope 120
Foundation has a gyro error model, chassis control chip 140 after obtaining the collected angle-data of gyroscope 120, according to
The gyro error model first established calculates second attitude angle of the wheeled mobile robot currently under global coordinate system,
Single-degree-of-freedom constraint is carried out to second attitude angle simultaneously, i.e. selection wheeled mobile robot is in the rotation angle around vertical axes
(yaw angle).
After obtaining the first attitude angle and the second attitude angle, chassis control chip 140 is by the first attitude angle and second appearance
State angle carries out Kalman filtering fusion, obtains the final carriage angle of wheeled mobile robot.Finally, chassis control chip 140
According to current the second solving of attitude wheel type mobile machine under global coordinate system of obtained velocity information and wheeled mobile robot
Speed and location information of the device people under world coordinate system, obtain the first pose data, and the first pose data include first
Position and First Speed.
Robot subsystem 150 is used to calculate vision mileage according to the image data that monocular camera 130 is got
The second pose data of model are counted, the second pose data packet includes the second position and second speed.
Monocular camera 130 is installed on wheeled mobile robot and connect with robot subsystem 150, wheel type mobile
In the process of moving, monocular camera 130 obtains the image data in its field of view and the picture number that will acquire for robot
According to being sent to robot subsystem 150.Robot subsystem 150 obtains the image data that monocular camera 130 is sent
Afterwards to image data extraction FAST angle point (Features from Accelerated Segment Test), and carry out LK streamer
Tracking, obtains Image Feature Point Matching information.Robot subsystem 150 issues frequency hair according to preset image characteristic point
Cloth described image Feature Points Matching information.Then, the first frame of image data is set as crucial by robot subsystem 150
Frame, other picture frames are counted according to the feature that present image tracks previous keyframe image and the mean parallax determination of characteristic point is
It is no to be set as key frame, and (counted according to the feature that current image frame tracks a upper picture frame and current according to key frame
The mean parallax of picture frame and a upper key frame) establish the sliding window of image trace.Finally, robot subsystem
150 are rotated by the positional relationship that each frame image in sliding window is calculated in Epipolar geometry, three-dimensional reconstruction, PnP algorithm
Matrix chooses yaw angle as initial rotation vector to the spin matrix sought, it is horizontal in x-axis and y-axis to be translated towards measurement
Re-projection error cost function is established in translation on face, is carried out 3DOF and is minimized re-projection error calculating, obtains image pass
Lack the rotation and translation matrix of scale, i.e. the second pose data of visual odometry model between key frame.
Robot subsystem 150 be also used to carry out the first pose data and the second pose data timestamp alignment and
Motion profile alignment, restores the optimal camera scale of monocular camera 130.
Specifically, robot subsystem 150 is by first after obtaining the first pose data and the second pose data
Appearance data are aligned with the second pose data time stamp.Then, first after timestamp is aligned by robot subsystem 150
Appearance data carry out track with the second pose data and are aligned.Finally, robot subsystem 150 is by seeking loss function most
Small two multiply solution, obtain the optimal camera scale of monocular camera 130.Wherein, optimal camera scale refers to, distance and reality in image
The corresponding relationship of border distance, such as every 100 pixel distances correspond to 1 meter of actual range.
Robot subsystem 150 is also used to carry out scale recovery to the second pose data according to optimal camera scale.
After obtaining the optimal camera scale of monocular camera 130, robot subsystem 150 can be according to the optimal camera
The 3D that scale recalculates a translation matrix and characteristic point of the key frame in world coordinate system in visual odometry model is sat
Mark.
The second pose data after robot subsystem 150 is also used to restore the first pose data and scale carry out
Fusion, obtains the final pose data of wheeled mobile robot.
After carrying out scale recovery to the second pose data, robot subsystem 150 is by the first pose data and scale
The second pose data after recovery are melted, and the final pose data of wheeled mobile robot are obtained.
Robot subsystem 150 is also used to carry out winding detection to each of image data image key frame,
And reorientation calculating is carried out to wheeled mobile robot when winding occurs.
In the embodiment of the present invention, the specific steps of winding detection and reorientation are as follows:
Step 1, robot subsystem 150 extracts multiple angles FAST to each key frame images in image data
Point, and BRIEF description of each FAST angle point is calculated, since BRIEF description has rotation scale invariability, and calculate
Speed is fast, so being adapted to do real-time Feature Points Matching.
Step 2, robot subsystem 150 describes son according to each FAST angle point and corresponding BRIEF, passes through
DBoW2 algorithm calculates the similarity size of present frame with key frame before.
Step 3, when the similarity similarity of present frame and key frame before is greater than the threshold value of setting, then robot master control
Winding then occurs for the judgement of subsystem 150, and according to winding candidate frame, (i.e. winding detects robot subsystem 150 at this time
Similarity is greater than the key frame of given threshold) position calculating is carried out, and correct the position of other key frames in winding.
In step 3, step is specifically calculated are as follows:
Step S31, the frame that the characteristic point of present frame and winding are detected and its nearby a few frames carry out BRIEF description son
Match, matching criterior is the Hamming distance of corresponding description.
Step S32 carries out the rejecting of RANSAC error hiding to obtained match point.
Step S33 solves to obtain present frame in world's seat by PnP algorithm for 3D world coordinates known to match point
Relative position in mark system, eliminates accumulated error.
Step S34, according in winding, the matching characteristic point of key frame is established and minimizes re-projection error majorized function, excellent
Change the spin matrix and translation matrix after obtaining the reorientation of each key frame, and updates characteristic point 3D coordinate.
In present example, the detection of winding and repositioning process are often successfully passed, so that it may wheeled to before
Odometer accumulated error is eliminated, and ensure that the precision of positioning, according to the quantity of characteristic point pair and two kinds of odometer models
Positional distance adjust fusion parameters, enhance the robustness of system, by the fusion of wheeled odometer and visual odometry, gram
The limitation of wheeled odometer has been taken, while system accuracy is further promoted.
Referring to Fig. 2, being the localization method applied to positioning system shown in FIG. 1 that present pre-ferred embodiments provide
Flow chart, process shown in Fig. 2 will be illustrated below.
Step S101, chassis control chip are collected according to the rotary speed data and gyroscope of the collected wheel of encoder
The angle-data of wheeled mobile robot obtains the first pose data of wheeled odometer model.
Referring to Fig. 3, step S101 includes following sub-step:
Sub-step S1011, chassis control chip obtain wheeled according to the rotary speed data of the collected wheel of each encoder
Speed data and first attitude angle of the mobile robot under current coordinate system.
Sub-step S1012, chassis control chip calculate wheel type mobile machine according to the gyro error model pre-established
Current the second attitude angle under global coordinate system of device people.
First attitude angle is carried out Kalman filtering with the second attitude angle and merged, obtained by sub-step S1013, chassis control chip
To the final carriage angle of wheeled mobile robot.
Sub-step S1014, chassis control chip resolve wheeled mobile robot according to speed data and final carriage angle and exist
Speed and location information under world coordinate system obtain the first pose data.
Step S102, robot subsystem calculate visual odometry according to the image data that monocular camera is got
Second pose data of model.
Referring to Fig. 4, step S102 includes following sub-step:
Sub-step S1021, robot subsystem carry out LK optical flow tracking to image data extraction FAST angle point,
Obtain Image Feature Point Matching information.
Sub-step S1022, robot subsystem issue frequency according to preset image characteristic point and issue characteristics of image
Point match information.
The first frame of image data is set as key frame by sub-step S1023, robot subsystem, other picture frame roots
Determine whether to be set as key frame according to the feature points of present image tracking previous keyframe image and the mean parallax of characteristic point.
Sub-step S1024, robot subsystem establish the sliding window of image trace.
Sub-step S1025, the positional relationship that robot subsystem calculates each frame image in sliding window are rotated
Matrix, and yaw angle is chosen as initial rotation vector, it is translated towards the translation measured in x-axis and y-axis horizontal plane, foundation is thrown again
Shadow error cost function carries out 3DOF and minimizes re-projection error calculating, obtains the rotation for lacking scale between image key frame
Turn and translation matrix.
Step S103, robot subsystem by the first pose data and the second pose data carry out timestamp alignment and
Motion profile alignment, restores the optimal camera scale of monocular camera.
Referring to Fig. 5, step S103 includes following sub-step:
First pose data are aligned by sub-step S1031, robot subsystem with the second pose data time stamp.
Sub-step S1032, robot subsystem timestamp is aligned after the first pose data and the second pose number
According to progress track alignment.
Sub-step S1033, robot subsystem obtain monocular camera by seeking the least square solution of loss function
Optimal camera scale.
Step S104, robot subsystem carry out scale recovery to the second pose data according to optimal camera scale.
Step S105, the second pose data after robot subsystem restores the first pose data and scale carry out
Fusion, obtains the final pose data of wheeled mobile robot.
Step S106, robot subsystem carry out winding detection to each of image data key frame images.
Referring to Fig. 6, step S106 includes following sub-step:
Sub-step S1061, robot subsystem extract multiple FAST to each key frame images in image data
Angle point, and calculate BRIEF description of each FAST angle point.
Sub-step S1062, robot subsystem describe son according to each FAST angle point and corresponding BRIEF, pass through
DBoW2 algorithm calculates the similarity size of present frame with key frame before.
Sub-step S1063, when similarity is greater than the threshold value of setting, winding then occurs for the judgement of robot subsystem.
Step S107, robot subsystem judges whether that winding occurs, if so, executing step S108.
Step S108, robot subsystem carry out reorientation calculating to wheeled mobile robot.
In conclusion localization method provided by the invention and system can have accumulated error for wheeled odometer and cannot
Automatic to eliminate, influence of the extraneous factors such as wheel slip to positioning accuracy is advanced optimized by the thought of sensor fusion
Wheeled odometer is combined with monocular vision odometer, overcomes mutual disadvantage, retain respective advantage by location information,
It can overcome the problems, such as that monocular camera 130 does not have scale and poor robustness in position fixing process, while also can solve wheeled mileage
The problem of counting accumulated error.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of localization method, applied to the positioning system of wheeled mobile robot, the positioning system includes encoder, gyro
Instrument, monocular camera, chassis control chip and robot subsystem, the encoder are installed on the vehicle of wheeled mobile robot
On wheel, which is characterized in that the described method includes:
The chassis control chip is collected according to the rotary speed data of the collected wheel of the encoder and the gyroscope
The angle-data of the wheeled mobile robot obtains the first pose data of wheeled odometer model, the first pose data
Including first position and First Speed;
The robot subsystem calculates visual odometry model according to the image data that the monocular camera is got
The second pose data, the second pose data packet includes the second position and second speed;
The robot subsystem by the first pose data and the second pose data carry out timestamp alignment and
Motion profile alignment, restores the optimal camera scale of the monocular camera;
The robot subsystem carries out scale recovery to the second pose data according to the optimal camera scale;
The second pose data after the robot subsystem restores the first pose data and scale carry out
Fusion, obtains the final pose data of the wheeled mobile robot.
2. the method according to claim 1, wherein the method also includes:
The robot subsystem carries out winding detection to each of described image data key frame images;
When winding occurs, the robot subsystem carries out reorientation calculating to the wheeled mobile robot.
3. the method according to claim 1, wherein the robot subsystem is in described image data
Each key frame images carry out winding detection, comprising:
The robot subsystem extracts multiple FAST angle points to each key frame images in described image data, and counts
Calculate BRIEF description of each FAST angle point;
The robot subsystem describes son according to each FAST angle point and corresponding BRIEF, is calculated by DBoW2 algorithm
The similarity size of present frame and key frame before;
When similarity is greater than the threshold value of setting, winding then occurs for the robot subsystem judgement.
4. the method according to claim 1, wherein the wheel of the encoder and the wheeled mobile robot
Quantity is multiple and corresponds, the chassis control chip according to the rotary speed data of the collected wheel of the encoder and
The angle-data of the collected wheeled mobile robot of gyroscope obtains the first pose number of wheeled odometer model
According to, comprising:
The chassis control chip obtains the wheel type mobile according to the rotary speed data of each collected wheel of encoder
Speed data and first attitude angle of the robot under current coordinate system;
It is current that the chassis control chip according to the gyro error model pre-established calculates the wheeled mobile robot
The second attitude angle under global coordinate system;
First attitude angle is carried out Kalman filtering with second attitude angle and merged by the chassis control chip, obtains institute
State the final carriage angle of wheeled mobile robot;
The chassis control chip resolves the wheeled mobile robot according to the speed data and the final carriage angle and exists
Speed and location information under world coordinate system obtain the first pose data.
5. according to the method described in claim 4, it is characterized in that, the quantity of the wheel is 3, and angle between any two
It is 120 °, speed data of the wheeled mobile robot under current coordinate system are as follows:Wherein, vx、vyThe speed of the x-axis and y-axis that are illustrated respectively under current coordinate system
Degree, ω are indicated under current coordinate system around the rotation speed of itself geometric center, ω1、ω2、ω3Respectively indicate three wheels
Rotation speed, L are the chassis radius of wheeled mobile robot, and R is radius of wheel.
6. the method according to claim 1, wherein the robot subsystem is according to the monocular camera
The image data got calculates the second pose data of visual odometry model, comprising:
The robot subsystem extracts FAST angle point to described image data, and carries out LK optical flow tracking, obtains image
Feature Points Matching information;
The robot subsystem issues frequency publication described image Feature Points Matching letter according to preset image characteristic point
Breath;
The first frame of described image data is set as key frame by the robot subsystem, other picture frames are according to current figure
As the feature points of tracking previous keyframe image and the mean parallax of characteristic point determine whether to be set as key frame;
The robot subsystem establishes the sliding window of image trace;
The robot subsystem is calculated in the sliding window respectively by Epipolar geometry, three-dimensional reconstruction, PnP algorithm
The positional relationship of frame image obtains spin matrix, and chooses yaw angle as initial rotation square to the spin matrix sought
Battle array is translated towards the translation measured in x-axis and y-axis horizontal plane, establishes re-projection error cost function, and it is minimum to carry out 3DOF
Change re-projection error to calculate, obtains the rotation and translation matrix for lacking scale between image key frame.
7. the method according to claim 1, wherein the robot subsystem is by the first pose number
Timestamp alignment and motion profile alignment are carried out according to the second pose data, restores the optimal camera ruler of the monocular camera
Degree, comprising:
The first pose data are aligned by the robot subsystem with the second pose data time stamp;
The robot subsystem timestamp is aligned after the first pose data and the second pose data into
The alignment of row track;
The robot subsystem obtains the optimal phase of the monocular camera by seeking the least square solution of loss function
Machine scale.
8. a kind of positioning system is applied to wheeled mobile robot characterized by comprising encoder, gyroscope, monocular phase
Machine, chassis control chip and robot subsystem, the encoder are installed on the wheel of wheeled mobile robot;
The chassis control chip is used to be acquired according to the rotary speed data of the collected wheel of the encoder and the gyroscope
To the angle-data of the wheeled mobile robot obtain the first pose data of wheeled odometer model, first pose
Data include first position and First Speed;
The robot subsystem is used to calculate visual odometry according to the image data that the monocular camera is got
Second pose data of model, the second pose data packet include the second position and second speed;
The robot subsystem is also used to the first pose data and the second pose data carrying out timestamp
Alignment and motion profile alignment, restore the optimal camera scale of the monocular camera;
The robot subsystem is also used to carry out scale to the second pose data according to the optimal camera scale
Restore;
The robot subsystem is also used to the second pose number after the first pose data and scale recovery
According to being merged, the final pose data of the wheeled mobile robot are obtained.
9. positioning system according to claim 8, which is characterized in that the robot subsystem is also used to described
Each of image data image key frame carries out winding detection;And when winding occurs to the wheeled mobile robot
Carry out reorientation calculating.
10. positioning system according to claim 8, which is characterized in that the encoder and the wheeled mobile robot
Wheel count be it is multiple and correspond;
The chassis control chip is described wheeled for being obtained according to the rotary speed data of each collected wheel of encoder
Speed data and first attitude angle of the mobile robot under current coordinate system;
The chassis control chip is also used to calculate the wheeled mobile robot according to the gyro error model pre-established
Current the second attitude angle under global coordinate system of people;
The chassis control chip is also used to first attitude angle carrying out Kalman filtering with second attitude angle to merge,
Obtain the final carriage angle of the wheeled mobile robot;
The chassis control chip is also used to resolve the wheel type mobile machine according to the speed data and the final carriage angle
Speed and location information of the device people under world coordinate system, obtain the first pose data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811473786.3A CN109579844B (en) | 2018-12-04 | 2018-12-04 | Positioning method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811473786.3A CN109579844B (en) | 2018-12-04 | 2018-12-04 | Positioning method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109579844A true CN109579844A (en) | 2019-04-05 |
CN109579844B CN109579844B (en) | 2023-11-21 |
Family
ID=65926961
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811473786.3A Active CN109579844B (en) | 2018-12-04 | 2018-12-04 | Positioning method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109579844B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110108269A (en) * | 2019-05-20 | 2019-08-09 | 电子科技大学 | AGV localization method based on Fusion |
CN110132277A (en) * | 2019-05-14 | 2019-08-16 | 北京云迹科技有限公司 | Robot idle running recognition methods and device |
CN110471407A (en) * | 2019-07-02 | 2019-11-19 | 盐城华昱光电技术有限公司 | A kind of adaptive location system and method for mould group automatic adjustment |
CN110779511A (en) * | 2019-09-23 | 2020-02-11 | 北京汽车集团有限公司 | Pose variation determination method, device and system and vehicle |
CN111699363A (en) * | 2019-05-28 | 2020-09-22 | 深圳市大疆创新科技有限公司 | Ground movable platform and motion information detection method and system thereof |
CN111829473A (en) * | 2020-07-29 | 2020-10-27 | 威步智能科技(苏州)有限公司 | Method and system for ranging moving chassis during traveling |
CN112102646A (en) * | 2019-06-17 | 2020-12-18 | 北京初速度科技有限公司 | Parking lot entrance positioning method and device in parking positioning and vehicle-mounted terminal |
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 |
CN112476433A (en) * | 2020-11-23 | 2021-03-12 | 深圳怪虫机器人有限公司 | Mobile robot positioning method based on array boundary identification |
CN112697153A (en) * | 2020-12-31 | 2021-04-23 | 广东美的白色家电技术创新中心有限公司 | Positioning method of autonomous mobile device, electronic device and storage medium |
CN113223007A (en) * | 2021-06-28 | 2021-08-06 | 浙江华睿科技股份有限公司 | Visual odometer implementation method and device and electronic equipment |
CN113390408A (en) * | 2021-06-30 | 2021-09-14 | 深圳市优必选科技股份有限公司 | Robot positioning method and device, robot and storage medium |
CN114964270A (en) * | 2022-05-17 | 2022-08-30 | 驭势科技(北京)有限公司 | Fusion positioning method and device, vehicle and storage medium |
CN117392518A (en) * | 2023-12-13 | 2024-01-12 | 南京耀宇视芯科技有限公司 | Low-power-consumption visual positioning and mapping chip and method thereof |
CN110458885B (en) * | 2019-08-27 | 2024-04-19 | 纵目科技(上海)股份有限公司 | Positioning system and mobile terminal based on stroke perception and vision fusion |
Citations (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1997049065A1 (en) * | 1996-06-19 | 1997-12-24 | Arch Development Corporation | Method and apparatus for three-dimensional reconstruction of coronary vessels from angiographic images |
US6539278B1 (en) * | 1999-09-20 | 2003-03-25 | General Electric Company | Method and apparatus for resin formulations with improved streaking performance |
US20060206324A1 (en) * | 2005-02-05 | 2006-09-14 | Aurix Limited | Methods and apparatus relating to searching of spoken audio data |
US20090141973A1 (en) * | 2005-12-01 | 2009-06-04 | Wallack Aaron S | Method of pattern location using color image data |
CN102254299A (en) * | 2010-05-20 | 2011-11-23 | 索尼公司 | System and method of image processing |
CN102509327A (en) * | 2011-09-30 | 2012-06-20 | 北京航空航天大学 | Multiscale global sampling method for filling image void |
WO2013086255A1 (en) * | 2011-12-07 | 2013-06-13 | Viewdle, Inc. | Motion aligned distance calculations for image comparisons |
US20140327792A1 (en) * | 2013-05-02 | 2014-11-06 | Qualcomm Incorporated | Methods for facilitating computer vision application initialization |
CN104765739A (en) * | 2014-01-06 | 2015-07-08 | 南京宜开数据分析技术有限公司 | Large-scale face database searching method based on shape space |
CN105856230A (en) * | 2016-05-06 | 2016-08-17 | 简燕梅 | ORB key frame closed-loop detection SLAM method capable of improving consistency of position and pose of robot |
GB201612767D0 (en) * | 2016-07-22 | 2016-09-07 | Imp College Of Science Tech And Medicine | Estimating dimensions for an enclosed space using a multi-directional camera |
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 |
CN106556412A (en) * | 2016-11-01 | 2017-04-05 | 哈尔滨工程大学 | The RGB D visual odometry methods of surface constraints are considered under a kind of indoor environment |
WO2017067130A1 (en) * | 2015-10-21 | 2017-04-27 | 华中科技大学 | Aero-optical heat radiation noise correction method and system |
CN106767833A (en) * | 2017-01-22 | 2017-05-31 | 电子科技大学 | A kind of robot localization method of fusion RGBD depth transducers and encoder |
CN106954024A (en) * | 2017-03-28 | 2017-07-14 | 成都通甲优博科技有限责任公司 | A kind of unmanned plane and its electronic image stabilization method, system |
CN107220932A (en) * | 2017-04-18 | 2017-09-29 | 天津大学 | Panorama Mosaic method based on bag of words |
CN107255476A (en) * | 2017-07-06 | 2017-10-17 | 青岛海通胜行智能科技有限公司 | A kind of indoor orientation method and device based on inertial data and visual signature |
CN107272677A (en) * | 2017-06-07 | 2017-10-20 | 东南大学 | A kind of structure-changeable self-adaptive Trajectory Tracking Control method of mobile robot |
CN107516326A (en) * | 2017-07-14 | 2017-12-26 | 中国科学院计算技术研究所 | Merge monocular vision and the robot localization method and system of encoder information |
CN107577646A (en) * | 2017-08-23 | 2018-01-12 | 上海莫斐信息技术有限公司 | A kind of high-precision track operation method and system |
CN107886129A (en) * | 2017-11-13 | 2018-04-06 | 湖南大学 | A kind of mobile robot map closed loop detection method of view-based access control model bag of words |
CN108036797A (en) * | 2017-11-30 | 2018-05-15 | 深圳市隐湖科技有限公司 | Mileage projectional technique based on four motorized wheels and combination IMU |
CN108108716A (en) * | 2017-12-29 | 2018-06-01 | 中国电子科技集团公司信息科学研究院 | A kind of winding detection method based on depth belief network |
CN108151745A (en) * | 2017-12-25 | 2018-06-12 | 千寻位置网络有限公司 | NMEA tracks difference automatically analyze and identification method |
CN108519102A (en) * | 2018-03-26 | 2018-09-11 | 东南大学 | A kind of binocular vision speedometer calculation method based on reprojection |
CN108829116A (en) * | 2018-10-09 | 2018-11-16 | 上海岚豹智能科技有限公司 | Barrier-avoiding method and equipment based on monocular cam |
CN108846867A (en) * | 2018-08-29 | 2018-11-20 | 安徽云能天智能科技有限责任公司 | A kind of SLAM system based on more mesh panorama inertial navigations |
-
2018
- 2018-12-04 CN CN201811473786.3A patent/CN109579844B/en active Active
Patent Citations (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1997049065A1 (en) * | 1996-06-19 | 1997-12-24 | Arch Development Corporation | Method and apparatus for three-dimensional reconstruction of coronary vessels from angiographic images |
US6539278B1 (en) * | 1999-09-20 | 2003-03-25 | General Electric Company | Method and apparatus for resin formulations with improved streaking performance |
US20060206324A1 (en) * | 2005-02-05 | 2006-09-14 | Aurix Limited | Methods and apparatus relating to searching of spoken audio data |
US20090141973A1 (en) * | 2005-12-01 | 2009-06-04 | Wallack Aaron S | Method of pattern location using color image data |
CN102254299A (en) * | 2010-05-20 | 2011-11-23 | 索尼公司 | System and method of image processing |
CN102509327A (en) * | 2011-09-30 | 2012-06-20 | 北京航空航天大学 | Multiscale global sampling method for filling image void |
WO2013086255A1 (en) * | 2011-12-07 | 2013-06-13 | Viewdle, Inc. | Motion aligned distance calculations for image comparisons |
US20140327792A1 (en) * | 2013-05-02 | 2014-11-06 | Qualcomm Incorporated | Methods for facilitating computer vision application initialization |
CN104765739A (en) * | 2014-01-06 | 2015-07-08 | 南京宜开数据分析技术有限公司 | Large-scale face database searching method based on shape space |
WO2017067130A1 (en) * | 2015-10-21 | 2017-04-27 | 华中科技大学 | Aero-optical heat radiation noise correction method and system |
CN105856230A (en) * | 2016-05-06 | 2016-08-17 | 简燕梅 | ORB key frame closed-loop detection SLAM method capable of improving consistency of position and pose of robot |
GB201612767D0 (en) * | 2016-07-22 | 2016-09-07 | Imp College Of Science Tech And Medicine | Estimating dimensions for an enclosed space using a multi-directional camera |
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 |
CN106556412A (en) * | 2016-11-01 | 2017-04-05 | 哈尔滨工程大学 | The RGB D visual odometry methods of surface constraints are considered under a kind of indoor environment |
CN106767833A (en) * | 2017-01-22 | 2017-05-31 | 电子科技大学 | A kind of robot localization method of fusion RGBD depth transducers and encoder |
CN106954024A (en) * | 2017-03-28 | 2017-07-14 | 成都通甲优博科技有限责任公司 | A kind of unmanned plane and its electronic image stabilization method, system |
CN107220932A (en) * | 2017-04-18 | 2017-09-29 | 天津大学 | Panorama Mosaic method based on bag of words |
CN107272677A (en) * | 2017-06-07 | 2017-10-20 | 东南大学 | A kind of structure-changeable self-adaptive Trajectory Tracking Control method of mobile robot |
CN107255476A (en) * | 2017-07-06 | 2017-10-17 | 青岛海通胜行智能科技有限公司 | A kind of indoor orientation method and device based on inertial data and visual signature |
CN107516326A (en) * | 2017-07-14 | 2017-12-26 | 中国科学院计算技术研究所 | Merge monocular vision and the robot localization method and system of encoder information |
CN107577646A (en) * | 2017-08-23 | 2018-01-12 | 上海莫斐信息技术有限公司 | A kind of high-precision track operation method and system |
CN107886129A (en) * | 2017-11-13 | 2018-04-06 | 湖南大学 | A kind of mobile robot map closed loop detection method of view-based access control model bag of words |
CN108036797A (en) * | 2017-11-30 | 2018-05-15 | 深圳市隐湖科技有限公司 | Mileage projectional technique based on four motorized wheels and combination IMU |
CN108151745A (en) * | 2017-12-25 | 2018-06-12 | 千寻位置网络有限公司 | NMEA tracks difference automatically analyze and identification method |
CN108108716A (en) * | 2017-12-29 | 2018-06-01 | 中国电子科技集团公司信息科学研究院 | A kind of winding detection method based on depth belief network |
CN108519102A (en) * | 2018-03-26 | 2018-09-11 | 东南大学 | A kind of binocular vision speedometer calculation method based on reprojection |
CN108846867A (en) * | 2018-08-29 | 2018-11-20 | 安徽云能天智能科技有限责任公司 | A kind of SLAM system based on more mesh panorama inertial navigations |
CN108829116A (en) * | 2018-10-09 | 2018-11-16 | 上海岚豹智能科技有限公司 | Barrier-avoiding method and equipment based on monocular cam |
Non-Patent Citations (1)
Title |
---|
张国良,等: "《移动机器人的SLAM与VSLAM方法》", 西安交通大学出版社, pages: 5 * |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110132277A (en) * | 2019-05-14 | 2019-08-16 | 北京云迹科技有限公司 | Robot idle running recognition methods and device |
CN110108269A (en) * | 2019-05-20 | 2019-08-09 | 电子科技大学 | AGV localization method based on Fusion |
WO2020237495A1 (en) * | 2019-05-28 | 2020-12-03 | 深圳市大疆创新科技有限公司 | Ground mobile platform and motion information detection method and system therefor |
CN111699363A (en) * | 2019-05-28 | 2020-09-22 | 深圳市大疆创新科技有限公司 | Ground movable platform and motion information detection method and system thereof |
CN112102646B (en) * | 2019-06-17 | 2021-12-31 | 北京初速度科技有限公司 | Parking lot entrance positioning method and device in parking positioning and vehicle-mounted terminal |
CN112102646A (en) * | 2019-06-17 | 2020-12-18 | 北京初速度科技有限公司 | Parking lot entrance positioning method and device in parking positioning and vehicle-mounted terminal |
CN110471407B (en) * | 2019-07-02 | 2022-09-06 | 无锡真源科技有限公司 | Self-adaptive positioning system and method for automatic adjustment of module |
CN110471407A (en) * | 2019-07-02 | 2019-11-19 | 盐城华昱光电技术有限公司 | A kind of adaptive location system and method for mould group automatic adjustment |
CN110458885B (en) * | 2019-08-27 | 2024-04-19 | 纵目科技(上海)股份有限公司 | Positioning system and mobile terminal based on stroke perception and vision fusion |
CN110779511B (en) * | 2019-09-23 | 2021-09-21 | 北京汽车集团有限公司 | Pose variation determination method, device and system and vehicle |
CN110779511A (en) * | 2019-09-23 | 2020-02-11 | 北京汽车集团有限公司 | Pose variation determination method, device and system and vehicle |
CN111829473A (en) * | 2020-07-29 | 2020-10-27 | 威步智能科技(苏州)有限公司 | Method and system for ranging moving chassis during traveling |
CN111829473B (en) * | 2020-07-29 | 2022-04-26 | 威步智能科技(苏州)有限公司 | Method and system for ranging moving chassis during traveling |
CN112476433B (en) * | 2020-11-23 | 2023-08-04 | 深圳怪虫机器人有限公司 | Mobile robot positioning method based on identification array boundary |
WO2022105933A1 (en) * | 2020-11-23 | 2022-05-27 | 深圳怪虫机器人有限公司 | Positioning method for mobile robot based on array boundary recognition |
CN112476433A (en) * | 2020-11-23 | 2021-03-12 | 深圳怪虫机器人有限公司 | Mobile robot positioning method based on array boundary identification |
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 |
CN112697153A (en) * | 2020-12-31 | 2021-04-23 | 广东美的白色家电技术创新中心有限公司 | Positioning method of autonomous mobile device, electronic device and storage medium |
CN113223007A (en) * | 2021-06-28 | 2021-08-06 | 浙江华睿科技股份有限公司 | Visual odometer implementation method and device and electronic equipment |
CN113390408A (en) * | 2021-06-30 | 2021-09-14 | 深圳市优必选科技股份有限公司 | Robot positioning method and device, robot and storage medium |
CN114964270A (en) * | 2022-05-17 | 2022-08-30 | 驭势科技(北京)有限公司 | Fusion positioning method and device, vehicle and storage medium |
CN114964270B (en) * | 2022-05-17 | 2024-04-26 | 驭势科技(北京)有限公司 | Fusion positioning method, device, vehicle and storage medium |
CN117392518A (en) * | 2023-12-13 | 2024-01-12 | 南京耀宇视芯科技有限公司 | Low-power-consumption visual positioning and mapping chip and method thereof |
CN117392518B (en) * | 2023-12-13 | 2024-04-09 | 南京耀宇视芯科技有限公司 | Low-power-consumption visual positioning and mapping chip and method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN109579844B (en) | 2023-11-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109579844A (en) | Localization method and system | |
CN111739063B (en) | Positioning method of power inspection robot based on multi-sensor fusion | |
US20230116849A1 (en) | Six degree of freedom tracking with scale recovery and obstacle avoidance | |
US9122916B2 (en) | Three dimensional fingertip tracking | |
CN106017463B (en) | A kind of Aerial vehicle position method based on orientation sensing device | |
CN102087530B (en) | Vision navigation method of mobile robot based on hand-drawing map and path | |
CN109166149A (en) | A kind of positioning and three-dimensional wire-frame method for reconstructing and system of fusion binocular camera and IMU | |
CN102313547B (en) | Vision navigation method of mobile robot based on hand-drawn outline semantic map | |
Scaramuzza | Performance evaluation of 1‐point‐RANSAC visual odometry | |
CN107478214A (en) | A kind of indoor orientation method and system based on Multi-sensor Fusion | |
CN108051002A (en) | Transport vehicle space-location method and system based on inertia measurement auxiliary vision | |
CN107990899A (en) | A kind of localization method and system based on SLAM | |
CN112734841B (en) | Method for realizing positioning by using wheel type odometer-IMU and monocular camera | |
CN107687850A (en) | A kind of unmanned vehicle position and orientation estimation method of view-based access control model and Inertial Measurement Unit | |
US10802606B2 (en) | Method and device for aligning coordinate of controller or headset with coordinate of binocular system | |
CN108733039A (en) | The method and apparatus of navigator fix in a kind of robot chamber | |
CN110675453B (en) | Self-positioning method for moving target in known scene | |
CN107688184A (en) | A kind of localization method and system | |
CN106197429A (en) | A kind of Multi-information acquisition location equipment and system | |
CN109141410A (en) | The Multi-sensor Fusion localization method of AGV integrated navigation | |
CN107909614A (en) | Crusing robot localization method under a kind of GPS failures environment | |
CN206990800U (en) | A kind of alignment system | |
CN104864849B (en) | Vision navigation method and device and robot | |
CN106574836A (en) | A method for localizing a robot in a localization plane | |
CN110533719A (en) | Augmented reality localization method and device based on environmental visual Feature point recognition technology |
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 |