CN113219980B - Robot global self-positioning method, device, computer equipment and storage medium - Google Patents
Robot global self-positioning method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113219980B CN113219980B CN202110533611.2A CN202110533611A CN113219980B CN 113219980 B CN113219980 B CN 113219980B CN 202110533611 A CN202110533611 A CN 202110533611A CN 113219980 B CN113219980 B CN 113219980B
- Authority
- CN
- China
- Prior art keywords
- map
- robot
- data
- effective
- value
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000007781 pre-processing Methods 0.000 claims abstract description 26
- 238000004590 computer program Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 6
- 238000005259 measurement Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000004659 sterilization and disinfection Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 239000000645 desinfectant Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 230000001954 sterilising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
Abstract
The embodiment of the invention discloses a robot global self-positioning method, a device, computer equipment and a storage medium. The method comprises the following steps: acquiring a request for starting global self-positioning; preprocessing a map loaded currently by the robot according to the request; acquiring laser radar data on a robot chassis, and removing data which do not meet the requirements according to the laser radar data to obtain effective data; generating a probability distribution map according to the effective data and the preprocessed map; and calculating a pixel value with the maximum probability in the probability distribution map, and converting the pixel value into a coordinate value to obtain the position of the robot. By implementing the method provided by the embodiment of the invention, the positioning accuracy of the robot is improved with low cost without adding hardware such as a sensor and the like.
Description
Technical Field
The present invention relates to a robot positioning method, and more particularly, to a global robot self-positioning method, a global robot self-positioning device, a computer device, and a storage medium.
Background
In the rapid development period of science and technology, the mobile intelligent robot has more important, and the mobile intelligent robot has multiple functions of perception, decision making and the like, so that the mobile intelligent robot has great potential in assisting or replacing human work. The autonomous mobility of the robot serves as an important index for measuring the intelligent degree of the robot, and the navigation task is a primary problem to be solved in practical application of most intelligent robots with mobility.
The universal mobile intelligent robot chassis can carry different modules to complete various works. Some special scenes have harm to people, the robots need to carry out repeated timing round-trip operation, such as carrying disinfectant by a mobile intelligent robot for disinfection and spraying, the robot carries an ultraviolet lamp for sterilization, but no matter what function of carrying the module is completed, the robot needs to be positioned and navigated, however, the existing positioning method of the robot basically adopts a local positioning method, the positioning accuracy is not high, so that the actual work of the robot is influenced, if the positioning accuracy needs to be improved, a plurality of sensors need to be added for detection and positioning, and the cost is high.
Therefore, it is necessary to design a new method to achieve low cost improvement of the positioning accuracy of the robot.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a global self-positioning method, a global self-positioning device, computer equipment and a storage medium of a robot.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the global self-positioning method of the robot comprises the following steps:
acquiring a request for starting global self-positioning;
preprocessing a map loaded currently by the robot according to the request;
acquiring laser radar data on a robot chassis, and removing data which do not meet the requirements according to the laser radar data to obtain effective data;
generating a probability distribution map according to the effective data and the preprocessed map;
and calculating a pixel value with the maximum probability in the probability distribution map, and converting the pixel value into a coordinate value to obtain the position of the robot.
The further technical scheme is as follows: the preprocessing of the map currently loaded by the robot according to the request comprises the following steps:
performing binarization processing on the map currently loaded by the robot according to the request to obtain a binarized map;
using a connected domain algorithm to the binarized map to only reserve an actually effective connected domain area, and removing an area which cannot be passed by a robot so as to obtain an effective binarized map;
and creating a likelihood domain map according to the effective binarization map.
The further technical scheme is as follows: and the pixel value corresponding to each grid in the likelihood domain map is a checkerboard distance value from the grid coordinate to the nearest black grid from the grid.
The further technical scheme is as follows: the obtaining the laser radar data on the robot chassis, and eliminating the data which does not meet the requirements according to the laser radar data to obtain effective data comprises the following steps:
and acquiring laser radar data on the robot chassis, and removing invalid values and ranging invalid distance values in the laser radar data to obtain valid data.
The further technical scheme is as follows: the generating a probability distribution map according to the effective data and the preprocessed map comprises the following steps:
calculating a matching error value for each area in the preprocessed map according to the effective data and the preprocessed map;
and extracting the maximum pixel value from the likelihood domain map, multiplying the maximum pixel value by the effective point number of the effective data to obtain a position maximum error value, and calculating the probability of each grid of the likelihood domain map according to the matching error value and the position maximum error value to obtain a probability distribution map.
The further technical scheme is as follows: each region in the map after preprocessing calculates a matching error value according to the effective data and the map after preprocessing, and the matching error value comprises the following steps:
converting the pixel value of each grid of the preprocessed map into a corresponding estimated robot position;
converting the effective data into pixels of a likelihood domain map;
and extracting pixel values corresponding to the effective data from the likelihood domain map and summing the pixel values to obtain a matching error value corresponding to the estimated robot position.
The further technical scheme is as follows: the calculating the pixel value with the maximum probability in the probability distribution map and converting the pixel value into a coordinate value to obtain the position of the robot comprises the following steps:
traversing all feasible areas in the likelihood domain map, and screening out the position corresponding to the maximum value in the probability distribution map to obtain the position of the robot.
The invention also provides a robot global self-positioning device, which comprises:
a request acquisition unit, configured to acquire a request for starting global self-positioning;
the preprocessing unit is used for preprocessing the map loaded currently by the robot according to the request;
the data processing unit is used for acquiring laser radar data on the robot chassis and eliminating data which do not meet the requirements according to the laser radar data so as to obtain effective data;
the probability map generating unit is used for generating a probability distribution map according to the effective data and the preprocessed map;
and the position determining unit is used for calculating a pixel value with the maximum probability in the probability distribution map and converting the pixel value into a coordinate value so as to obtain the position of the robot.
The invention also provides a computer device which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the method when executing the computer program.
The present invention also provides a storage medium storing a computer program which, when executed by a processor, performs the above-described method.
Compared with the prior art, the invention has the beneficial effects that: according to the method, the global self-positioning is carried out through an externally initiated request for starting the global self-positioning, the loaded map is preprocessed to improve the matching accuracy, the probability distribution map is generated according to the laser radar data and the preprocessed map, and the maximum value is screened out from the probability distribution map to determine the position of the robot, so that hardware such as a sensor is not required to be added, and the positioning accuracy of the robot is improved at low cost.
The invention is further described below with reference to the drawings and specific embodiments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an application scenario of a global self-positioning method for a robot according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a global self-positioning method of a robot according to an embodiment of the present invention;
fig. 3 is a schematic sub-flowchart of a global self-positioning method of a robot according to an embodiment of the present invention;
fig. 4 is a schematic sub-flowchart of a global self-positioning method of a robot according to an embodiment of the present invention;
fig. 5 is a schematic sub-flowchart of a global self-positioning method of a robot according to an embodiment of the present invention;
FIG. 6 is a schematic block diagram of a robot global self-positioning device provided by an embodiment of the present invention;
FIG. 7 is a schematic block diagram of a preprocessing unit of the robot global self-positioning device provided by an embodiment of the present invention;
FIG. 8 is a schematic block diagram of a data processing unit of the robot global self-positioning device provided by an embodiment of the present invention;
FIG. 9 is a schematic block diagram of a match error value calculation subunit of the robot global self-positioning device provided by an embodiment of the present invention;
fig. 10 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic view of an application scenario of a global self-positioning method for a robot according to an embodiment of the present invention. Fig. 2 is a schematic flow chart of a robot global self-positioning method provided by an embodiment of the invention. The global self-positioning method of the robot is applied to a server, the server can be a controller of a chassis of the robot, the server can also be an independent server, the server performs data interaction with a laser radar sensor and a terminal, a global self-defined request of the robot is initiated through the terminal, the server preprocesses a map loaded currently by the robot according to the request of the terminal, and the optimal position of the robot is determined after acquiring detection data of the laser radar sensor borne on the chassis of the robot.
Fig. 2 is a flow chart of a global self-positioning method of a robot according to an embodiment of the present invention. As shown in fig. 2, the method includes the following steps S110 to S150.
S110, acquiring a request for starting global self-positioning.
In this embodiment, the request refers to a request initiated by the terminal to start the global custom algorithm by the driving robot.
Under the condition that the real environment of the robot chassis is consistent with the loaded current map, when the robot is started, and under the condition that the positions in the map are disordered, an external instruction such as a request initiated by a terminal is sent to a server to start the autonomous global self-positioning algorithm function of the robot.
S120, preprocessing the map loaded currently by the robot according to the request.
When the robot loads the current environment map, the server performs preprocessing on map information once, screens useful information in the map, optimizes the map information once and generates a likelihood domain map to improve the efficiency of autonomous matching and positioning at the back, speed up algorithm processing and improve the accuracy of matching at the back.
In one embodiment, referring to fig. 3, the step S120 may include steps S121 to S123.
S121, performing binarization processing on the map currently loaded by the robot according to the request to obtain a binarized map.
In this embodiment, the binarized map refers to a map formed by black, gray and white grids formed by binarizing a map currently loaded by the robot.
The universal robot chassis performs preprocessing on map information once in the loaded current environment map information, and the map is composed of three colors, namely gray and white, wherein gray represents an unknown area, black represents an obstacle, and white represents a free passing area. In an actual running scene, the position of the robot in an unknown area and an obstacle area does not need to be considered, so that the map can be binarized, and only white and black are reserved.
The binarization processing of the map belongs to the prior art, and is not described here again.
S122, only the actually effective connected domain area is reserved for the binarized map by using a connected domain algorithm, and the area which cannot be passed by the robot is removed, so that the effective binarized map is obtained.
In this embodiment, the effective binarized map refers to a binarized map of an area where the outline of the robot is removed, only the actually effective connected domain area is reserved, and the area where the robot cannot pass through is removed.
The robot can be considered as a mass point, the maximum outline of the robot can be considered as the maximum outline of the robot, and as the robot can be considered as a grid point in a map in an algorithm, the image processing corrosion is used for processing a binarized map to reduce the actual effective area, the area of the outline of the robot is removed, only the actual effective connected domain area in the map is reserved by using a connected domain algorithm, the area which can not be passed by the robot is removed, and the area which needs to be matched in the map by the robot is effectively reduced to improve the efficiency of the autonomous matching positioning algorithm.
S123, creating a likelihood domain map according to the effective binarization map.
In this embodiment, the likelihood domain map refers to a map in which the pixel value corresponding to each grid is the checkerboard distance value from the grid coordinate to the nearest black grid to the grid.
Namely, the pixel value corresponding to each grid in the likelihood domain map is a checkerboard distance value from the grid coordinate to the nearest black grid from the grid. Useful information in the map is screened out, primary map information optimization is carried out, a likelihood domain map is generated, the efficiency of autonomous matching and positioning is improved, excessive sensors are not needed to be added, and the accuracy of robot self-positioning is improved with low cost.
S130, acquiring laser radar data on a robot chassis, and eliminating data which do not meet the requirements according to the laser radar data to obtain effective data.
In this embodiment, the valid data refers to the lidar data from which invalid values and ranging invalid distance values remain in the lidar data are removed.
Specifically, laser radar data on a robot chassis are acquired, invalid values and ranging invalid distance values in the laser radar data are removed, and effective data are obtained. The laser radar sensor data carried on the robot chassis is used, and the invalid points and the useless points are filtered out by preprocessing the laser radar data once so as to accelerate the matching speed.
The robot chassis collects surrounding detected obstacle information according to laser radar sensors configured by the robot chassis, the laser radar returns a distance value of the detected obstacle to a relative angle value, so that laser radar data are formed, measured invalid values such as the maximum value and the minimum value of the laser radar data, invalid measured data and a distance measurement invalid distance value such as a too large distance measurement value are removed according to the characteristics of the laser radar, and the distance measurement value is easily affected by the angle to cause large errors; thereby improving the accuracy of the user definition.
And S140, generating a probability distribution map according to the effective data and the preprocessed map.
In this embodiment, the probability distribution map refers to a map formed by estimating the probability of the robot at each grid.
In one embodiment, referring to fig. 4, the step S140 may include steps S141 to S142.
S141, calculating a matching error value according to the effective data and the preprocessed map.
In this embodiment, the matching error value refers to a matching error value of the estimated robot position.
In one embodiment, referring to fig. 5, the step S141 may include steps S1411 to S1413.
S1411, converting pixel values of each grid of the preprocessed map into corresponding estimated robot positions;
s1412, converting the valid data into pixels of a likelihood domain map;
s1413, extracting pixel values corresponding to the effective data from the likelihood domain map and summing the pixel values to obtain a matching error value corresponding to the estimated robot position.
In the embodiment, the binarization grids, namely the grids of the likelihood domain map are traversed, but each grid is not required to be traversed, only the grid offset traversing of the robots corresponding to the outline size is required, the matching results of the robots in the outline size are similar and time-consuming, and the calculation amount is reduced; according to the calculated current pixel value, the calculated pixel value is converted into a corresponding assumed robot coordinate, the pixel position of each laser radar data corresponding to the likelihood domain map can be obtained through cooperation with the effective data derivation, the pixel value of the pixel point corresponding to the effective data in the likelihood domain map is extracted and summed, and therefore the matching error value corresponding to the estimated robot position is obtained.
S142, extracting the maximum pixel value from the likelihood domain map, multiplying the maximum pixel value by the effective point number of the effective data to obtain a position maximum error value, and calculating the probability of each grid of the likelihood domain map according to the matching error value and the position maximum error value to obtain a probability distribution map.
Extracting the maximum grid pixel value from the likelihood domain map, multiplying the maximum grid pixel value by the effective point number of the effective data, namely the current laser radar data, and calculating the maximum error of the current estimated position as max_p; but is pre-arrangedEstimating a matching error value corresponding to the position of the robot as est_p; the smaller the value, the better the result of the matching calculation is considered, est p =0 is the ideal optimum value; the matching probability corresponding to the estimated robot position isAssigning the pixel value corresponding to the position in the probability distribution map; the above step S140 is repeated until all feasible regions in the likelihood domain map are traversed.
The method comprises the steps of performing traversal matching search on a likelihood domain map by using sensor data carried on a robot chassis and matching with the estimated position of a robot, and generating a probability distribution map relative to the likelihood domain map; each grid of the probability distribution map corresponds to the accuracy of the estimated position represented by each grid on the likelihood domain map; and selecting the grid point with the highest probability, namely the optimal position of the robot on the map.
S150, calculating a pixel value with the maximum probability in the probability distribution map, and converting the pixel value into a coordinate value to obtain the position of the robot.
In this embodiment, the position of the robot refers to the position of the robot determined through the global self-positioning algorithm.
Specifically, all feasible regions in the likelihood domain map are traversed, and the position corresponding to the maximum value in the probability distribution map is screened out, so that the position of the robot is obtained.
In the generated probability distribution map, traversing the place with the maximum probability, wherein the place with the maximum probability is the optimal position of the estimated robot, converting the pixel value with the maximum probability into the coordinate value of the robot, and setting the estimated optimal position as the position of the robot in the current map.
The robot does not need to move any, and can perform environment matching and generate the current optimal estimated position only according to the data collected by the current laser radar sensor. No extra hardware is needed, the operation is simple, and the global self-positioning can be triggered by only sending an instruction externally.
According to the embodiment, an additional sensor is not required to be added, so that the optimal position of the robot in the map can be automatically found under the condition that the position of the robot in the map is disordered; the robot does not need to move any, and the optimal position in the map can be automatically matched only according to the currently acquired laser radar data and the loaded map; and optimizing the map and the sensor data, and improving the calculation matching speed.
According to the robot global self-positioning method, the global self-positioning is carried out through the externally initiated request for starting the global self-positioning, the loaded map is preprocessed, so that the matching accuracy is improved, the probability distribution map is generated according to the laser radar data and the preprocessed map, and the maximum value is screened out from the probability distribution map, so that the position of the robot is determined, the hardware such as a sensor is not required to be added, and the positioning accuracy of the robot is improved at low cost.
Fig. 6 is a schematic block diagram of a robot global self-positioning device 300 according to an embodiment of the present invention. As shown in fig. 6, the present invention further provides a global self-positioning device 300 for a robot, corresponding to the above global self-positioning method for a robot. The robot global self-positioning device 300 comprises means for performing the above-described robot global self-positioning method, which device may be configured in a server. Specifically, referring to fig. 6, the robot global self-positioning device 300 includes a request acquisition unit 301, a preprocessing unit 302, a data processing unit 303, a probability map generation unit 304, and a position determination unit 305.
A request acquiring unit 301, configured to acquire a request for starting global self-positioning; a preprocessing unit 302, configured to preprocess a map currently loaded by the robot according to the request; the data processing unit 303 is configured to obtain laser radar data on the chassis of the robot, and reject data that does not meet the requirements according to the laser radar data, so as to obtain valid data; a probability map generating unit 304, configured to generate a probability distribution map according to the valid data and the preprocessed map; and a position determining unit 305, configured to calculate a pixel value with the largest probability in the probability distribution map, and convert the pixel value into a coordinate value, so as to obtain the position of the robot.
In one embodiment, as shown in fig. 7, the preprocessing unit 302 includes a binarization subunit 3021, a culling subunit 3022, and a creation subunit 3023.
A binarization subunit 3021, configured to perform binarization processing on a map currently loaded by the robot according to the request, so as to obtain a binarized map; a culling subunit 3022, configured to use a connected domain algorithm to the binarized map to only reserve an actually valid connected domain area, and cull an area that cannot be passed by the robot, so as to obtain an effective binarized map; a creating subunit 3023 for creating a likelihood domain map from the effective binarized map.
In an embodiment, the data processing unit 303 is configured to obtain laser radar data on the chassis of the robot, and reject invalid values and ranging invalid distance values in the laser radar data to obtain valid data.
In one embodiment, as shown in fig. 8, the probability map generating unit 304 includes a match error value calculating subunit 3041 and a probability calculating subunit 3042.
A match error value calculation subunit 3041, configured to calculate a match error value for each area in the preprocessed map according to the valid data and the preprocessed map; the probability calculating subunit 3042 is configured to extract a maximum pixel value from the likelihood domain map, multiply the maximum pixel value by an effective point number of the effective data to obtain a position maximum error value, and calculate a probability of each grid of the likelihood domain map according to the matching error value and the position maximum error value to obtain a probability distribution map.
In an embodiment, as shown in fig. 9, the matching error value calculating subunit 3041 includes a numerical value converting module 3041, a data converting module 30112, and a summing module 3043.
The numerical conversion module 30411 is configured to convert the pixel value of each grid into a corresponding estimated robot position according to the preprocessed map; a data conversion module 30512 for converting the effective data into pixels of a likelihood domain map; and the summing module 3043 is configured to extract pixel values corresponding to the valid data from the likelihood domain map and sum the pixel values to obtain a matching error value corresponding to the estimated robot position.
In an embodiment, the position determining unit 305 is configured to traverse all feasible regions in the likelihood domain map, and screen out the position corresponding to the maximum value in the probability distribution map, so as to obtain the position of the robot.
It should be noted that, as will be clearly understood by those skilled in the art, the specific implementation process of the robot global self-positioning device 300 and each unit may refer to the corresponding description in the foregoing method embodiment, and for convenience and brevity of description, the description is omitted here.
The robotic global self-positioning device 300 described above may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 10.
Referring to fig. 10, fig. 10 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server, wherein the terminal may be an electronic device having a communication function, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster formed by a plurality of servers.
With reference to FIG. 10, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform a method of robot global self-localization.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the execution of a computer program 5032 in the non-volatile storage medium 503, which computer program 5032, when executed by the processor 502, causes the processor 502 to perform a method of robot global self-localization.
The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of a portion of the architecture in connection with the present application and is not intended to limit the computer device 500 to which the present application is applied, and that a particular computer device 500 may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
Wherein the processor 502 is configured to execute a computer program 5032 stored in a memory to implement the steps of:
acquiring a request for starting global self-positioning; preprocessing a map loaded currently by the robot according to the request; acquiring laser radar data on a robot chassis, and removing data which do not meet the requirements according to the laser radar data to obtain effective data; generating a probability distribution map according to the effective data and the preprocessed map; and calculating a pixel value with the maximum probability in the probability distribution map, and converting the pixel value into a coordinate value to obtain the position of the robot.
In an embodiment, when the preprocessing step is performed on the map currently loaded by the robot according to the request, the processor 502 specifically performs the following steps:
performing binarization processing on the map currently loaded by the robot according to the request to obtain a binarized map; using a connected domain algorithm to the binarized map to only reserve an actually effective connected domain area, and removing an area which cannot be passed by a robot so as to obtain an effective binarized map; and creating a likelihood domain map according to the effective binarization map.
And the pixel value corresponding to each grid in the likelihood domain map is a chessboard distance value from the grid coordinates to the nearest black grid from the grid.
In an embodiment, when the processor 502 performs the steps of obtaining the laser radar data on the robot chassis and removing the data that does not meet the requirements according to the laser radar data to obtain the valid data, the following steps are specifically implemented:
and acquiring laser radar data on the robot chassis, and removing invalid values and ranging invalid distance values in the laser radar data to obtain valid data.
In one embodiment, when the step of generating the probability distribution map according to the valid data and the preprocessed map is implemented by the processor 502, the following steps are specifically implemented:
calculating a matching error value for each area in the preprocessed map according to the effective data and the preprocessed map; and extracting the maximum pixel value from the likelihood domain map, multiplying the maximum pixel value by the effective point number of the effective data to obtain a position maximum error value, and calculating the probability of each grid of the likelihood domain map according to the matching error value and the position maximum error value to obtain a probability distribution map.
In one embodiment, when the step of calculating the matching error value for each region in the preprocessed map according to the valid data and the preprocessed map is implemented by the processor 502, the following steps are specifically implemented:
converting the pixel value of each grid of the preprocessed map into a corresponding estimated robot position; converting the effective data into pixels of a likelihood domain map; and extracting pixel values corresponding to the effective data from the likelihood domain map and summing the pixel values to obtain a matching error value corresponding to the estimated robot position.
In an embodiment, when the processor 502 performs the step of calculating the pixel value with the greatest probability in the probability distribution map and converting the pixel value into the coordinate value to obtain the position of the robot, the following steps are specifically implemented:
traversing all feasible areas in the likelihood domain map, and screening out the position corresponding to the maximum value in the probability distribution map to obtain the position of the robot.
It should be appreciated that in embodiments of the present application, the processor 502 may be a central processing unit (Central Processing Unit, CPU), the processor 502 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Those skilled in the art will appreciate that all or part of the flow in a method embodying the above described embodiments may be accomplished by computer programs instructing the relevant hardware. The computer program comprises program instructions, and the computer program can be stored in a storage medium, which is a computer readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer readable storage medium. The storage medium stores a computer program which, when executed by a processor, causes the processor to perform the steps of:
acquiring a request for starting global self-positioning; preprocessing a map loaded currently by the robot according to the request; acquiring laser radar data on a robot chassis, and removing data which do not meet the requirements according to the laser radar data to obtain effective data; generating a probability distribution map according to the effective data and the preprocessed map; and calculating a pixel value with the maximum probability in the probability distribution map, and converting the pixel value into a coordinate value to obtain the position of the robot.
In an embodiment, when the processor executes the computer program to implement the preprocessing step for the map currently loaded by the robot according to the request, the following steps are specifically implemented:
performing binarization processing on the map currently loaded by the robot according to the request to obtain a binarized map; using a connected domain algorithm to the binarized map to only reserve an actually effective connected domain area, and removing an area which cannot be passed by a robot so as to obtain an effective binarized map; and creating a likelihood domain map according to the effective binarization map.
And the pixel value corresponding to each grid in the likelihood domain map is a chessboard distance value from the grid coordinates to the nearest black grid from the grid.
In an embodiment, when the processor executes the computer program to obtain the laser radar data on the robot chassis, and eliminates the data which does not meet the requirements according to the laser radar data to obtain the effective data, the processor specifically realizes the following steps:
and acquiring laser radar data on the robot chassis, and removing invalid values and ranging invalid distance values in the laser radar data to obtain valid data.
In one embodiment, when the processor executes the computer program to implement the step of generating a probability distribution map according to the valid data and the preprocessed map, the processor specifically implements the following steps:
calculating a matching error value for each area in the preprocessed map according to the effective data and the preprocessed map; and extracting the maximum pixel value from the likelihood domain map, multiplying the maximum pixel value by the effective point number of the effective data to obtain a position maximum error value, and calculating the probability of each grid of the likelihood domain map according to the matching error value and the position maximum error value to obtain a probability distribution map.
In one embodiment, when the processor executes the computer program to implement the step of calculating a matching error value for each region in the preprocessed map according to the valid data and the preprocessed map, the processor specifically implements the following steps:
converting the pixel value of each grid of the preprocessed map into a corresponding estimated robot position; converting the effective data into pixels of a likelihood domain map; and extracting pixel values corresponding to the effective data from the likelihood domain map and summing the pixel values to obtain a matching error value corresponding to the estimated robot position.
In one embodiment, when the processor executes the computer program to implement the step of calculating the pixel value with the highest probability in the probability distribution map and converting the pixel value into the coordinate value to obtain the position of the robot, the method specifically includes the following steps:
traversing all feasible areas in the likelihood domain map, and screening out the position corresponding to the maximum value in the probability distribution map to obtain the position of the robot.
The storage medium may be a U-disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, or other various computer-readable storage media that can store program codes.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be combined, divided and deleted according to actual needs. In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The integrated unit may be stored in a storage medium if implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a terminal, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (5)
1. The global self-positioning method of the robot is characterized by comprising the following steps:
acquiring a request for starting global self-positioning;
preprocessing a map loaded currently by the robot according to the request;
acquiring laser radar data on a robot chassis, and removing data which do not meet the requirements according to the laser radar data to obtain effective data;
generating a probability distribution map according to the effective data and the preprocessed map;
calculating a pixel value with the maximum probability in the probability distribution map, and converting the pixel value into a coordinate value to obtain the position of the robot;
the preprocessing of the map currently loaded by the robot according to the request comprises the following steps:
performing binarization processing on the map currently loaded by the robot according to the request to obtain a binarized map;
using a connected domain algorithm to the binarized map to only reserve an actually effective connected domain area, and removing an area which cannot be passed by a robot so as to obtain an effective binarized map;
creating a likelihood domain map according to the effective binarization map;
the pixel value corresponding to each grid in the likelihood domain map is a chessboard distance value from the grid coordinates to the nearest black grid;
the obtaining the laser radar data on the robot chassis, and eliminating the data which does not meet the requirements according to the laser radar data to obtain effective data comprises the following steps:
acquiring laser radar data on a robot chassis, and removing invalid values and ranging invalid distance values in the laser radar data to obtain valid data;
the generating a probability distribution map according to the effective data and the preprocessed map comprises the following steps:
calculating a matching error value for each area in the preprocessed map according to the effective data and the preprocessed map;
extracting the maximum pixel value from the likelihood domain map, multiplying the maximum pixel value by the effective point number of the effective data to obtain a position maximum error value, and calculating the probability of each grid of the likelihood domain map according to the matching error value and the position maximum error value to obtain a probability distribution map;
each region in the map after preprocessing calculates a matching error value according to the effective data and the map after preprocessing, and the matching error value comprises the following steps:
converting the pixel value of each grid of the preprocessed map into a corresponding estimated robot position;
converting the effective data into pixels of a likelihood domain map;
and extracting pixel values corresponding to the effective data from the likelihood domain map and summing the pixel values to obtain a matching error value corresponding to the estimated robot position.
2. The method according to claim 1, wherein calculating the pixel value with the largest probability in the probability distribution map and converting the pixel value into a coordinate value to obtain the position of the robot comprises:
traversing all feasible areas in the likelihood domain map, and screening out the position corresponding to the maximum value in the probability distribution map to obtain the position of the robot.
3. Robot global self-positioning device, its characterized in that includes:
a request acquisition unit, configured to acquire a request for starting global self-positioning;
the preprocessing unit is used for preprocessing the map loaded currently by the robot according to the request;
the data processing unit is used for acquiring laser radar data on the robot chassis and eliminating data which do not meet the requirements according to the laser radar data so as to obtain effective data;
the probability map generating unit is used for generating a probability distribution map according to the effective data and the preprocessed map;
the position determining unit is used for calculating a pixel value with the maximum probability in the probability distribution map and converting the pixel value into a coordinate value so as to obtain the position of the robot;
the preprocessing unit comprises a binarization subunit, a rejection subunit and a creation subunit;
the binarization subunit is used for carrying out binarization processing on the map currently loaded by the robot according to the request so as to obtain a binarized map; the removing subunit is used for using a connected domain algorithm to the binarized map to only reserve the actually effective connected domain area and remove the area which cannot be passed by the robot so as to obtain an effective binarized map; a creating subunit, configured to create a likelihood domain map according to the effective binarized map;
the data processing unit is used for acquiring laser radar data on the robot chassis, and eliminating invalid values and ranging invalid distance values in the laser radar data to obtain valid data;
the probability map generation unit comprises a matching error value calculation subunit and a probability calculation subunit;
a matching error value calculation subunit, configured to calculate a matching error value for each region in the preprocessed map according to the valid data and the preprocessed map; the probability calculation subunit is used for extracting the maximum pixel value from the likelihood domain map, multiplying the maximum pixel value by the effective point number of the effective data to obtain a position maximum error value, and calculating the probability of each grid of the likelihood domain map according to the matching error value and the position maximum error value to obtain a probability distribution map;
the matching error value calculation subunit comprises a numerical value conversion module, a data conversion module and a summation module;
the numerical conversion module is used for converting the pixel value of each grid into a corresponding estimated robot position according to the preprocessed map; the data conversion module is used for converting the effective data into pixels of a likelihood domain map; and the summing module is used for extracting pixel values corresponding to the effective data from the likelihood domain map and summing the pixel values so as to obtain a matching error value corresponding to the estimated robot position.
4. A computer device, characterized in that it comprises a memory on which a computer program is stored and a processor which, when executing the computer program, implements the method according to any of claims 1-2.
5. A storage medium storing a computer program which, when executed by a processor, performs the method of any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110533611.2A CN113219980B (en) | 2021-05-14 | 2021-05-14 | Robot global self-positioning method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110533611.2A CN113219980B (en) | 2021-05-14 | 2021-05-14 | Robot global self-positioning method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113219980A CN113219980A (en) | 2021-08-06 |
| CN113219980B true CN113219980B (en) | 2024-04-12 |
Family
ID=77092324
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110533611.2A Active CN113219980B (en) | 2021-05-14 | 2021-05-14 | Robot global self-positioning method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113219980B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110097584A (en) * | 2019-03-18 | 2019-08-06 | 国网浙江省电力有限公司信息通信分公司 | The method for registering images of combining target detection and semantic segmentation |
| CN111060888A (en) * | 2019-12-31 | 2020-04-24 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile robot repositioning method fusing ICP and likelihood domain model |
| CN111754566A (en) * | 2020-05-12 | 2020-10-09 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Robot scene positioning method and construction operation method |
| CN112180931A (en) * | 2020-09-30 | 2021-01-05 | 小狗电器互联网科技（北京）股份有限公司 | Sweeping path planning method and device of sweeper and readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE112020001131T5 (en) * | 2019-03-08 | 2022-01-27 | Osram Gmbh | Component for a lidar sensor system, lidar sensor system, lidar sensor device, method for a lidar sensor system, and method for a lidar sensor device |
-
2021
- 2021-05-14 CN CN202110533611.2A patent/CN113219980B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110097584A (en) * | 2019-03-18 | 2019-08-06 | 国网浙江省电力有限公司信息通信分公司 | The method for registering images of combining target detection and semantic segmentation |
| CN111060888A (en) * | 2019-12-31 | 2020-04-24 | 芜湖哈特机器人产业技术研究院有限公司 | Mobile robot repositioning method fusing ICP and likelihood domain model |
| CN111754566A (en) * | 2020-05-12 | 2020-10-09 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Robot scene positioning method and construction operation method |
| CN112180931A (en) * | 2020-09-30 | 2021-01-05 | 小狗电器互联网科技（北京）股份有限公司 | Sweeping path planning method and device of sweeper and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113219980A (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635816B (en) | Lane line generation method, apparatus, device, and storage medium | |
| CN110207671B (en) | Space-based intelligent imaging system | |
| CN111696196B (en) | Three-dimensional face model reconstruction method and device | |
| US11841421B2 (en) | Synthetic aperture radar image analysis system, synthetic aperture radar image analysis method, and synthetic aperture radar image analysis program | |
| CN113761999A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN112200884A (en) | Method and device for generating lane line | |
| CN103679167A (en) | Method for processing CCD images | |
| CN116168351B (en) | Inspection method and device for power equipment | |
| KR20180127567A (en) | System for unmanned aircraft image auto geometric correction | |
| CN111582032A (en) | Pedestrian detection method and device, terminal equipment and storage medium | |
| CN113219980B (en) | Robot global self-positioning method, device, computer equipment and storage medium | |
| CN116682286B (en) | Ship early warning method and system based on offshore target detection | |
| CN110728172B (en) | Point cloud-based face key point detection method, device and system and storage medium | |
| CN107767366A (en) | A kind of transmission line of electricity approximating method and device | |
| CN109858341B (en) | Rapid multi-face detection and tracking method based on embedded system | |
| CN116642490A (en) | Visual positioning navigation method based on hybrid map, robot and storage medium | |
| CN108062752B (en) | Method, medium, device and computing equipment for judging azimuth of main light source | |
| Xie et al. | Ofvl-ms: Once for visual localization across multiple indoor scenes | |
| CN116415652A (en) | Data generation method and device, readable storage medium and terminal equipment | |
| US20220075059A1 (en) | Learning data generation device, learning data generation method, learning data generation program, learning device, learning method, learning program, inference device, inference method, inference program, learning system, and inference system | |
| CN115496923A (en) | Multi-modal fusion target detection method and device based on uncertainty perception | |
| CN115063760A (en) | Vehicle travelable area detection method, device, equipment and storage medium | |
| CN114005110A (en) | 3D detection model training method and device, and 3D detection method and device | |
| CN108917768B (en) | Unmanned aerial vehicle positioning navigation method and system | |
| CN112528847A (en) | Target detection method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |