CN113268062B - Human body curved surface modeling method, modeling device and modeling system - Google Patents
Human body curved surface modeling method, modeling device and modeling system Download PDFInfo
- Publication number
- CN113268062B CN113268062B CN202110600486.2A CN202110600486A CN113268062B CN 113268062 B CN113268062 B CN 113268062B CN 202110600486 A CN202110600486 A CN 202110600486A CN 113268062 B CN113268062 B CN 113268062B
- Authority
- CN
- China
- Prior art keywords
- human body
- robot
- waypoint
- scanning
- information
- 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 81
- 230000033001 locomotion Effects 0.000 claims abstract description 78
- 230000003068 static effect Effects 0.000 claims abstract description 62
- 230000008569 process Effects 0.000 claims abstract description 51
- 238000003287 bathing Methods 0.000 claims description 28
- 238000012544 monitoring process Methods 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 13
- 238000005259 measurement Methods 0.000 claims description 13
- 230000001133 acceleration Effects 0.000 claims description 12
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 claims description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 4
- DSCFFEYYQKSRSV-KLJZZCKASA-N D-pinitol Chemical compound CO[C@@H]1[C@@H](O)[C@@H](O)[C@H](O)[C@H](O)[C@H]1O DSCFFEYYQKSRSV-KLJZZCKASA-N 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 239000003642 reactive oxygen metabolite Substances 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Acoustics & Sound (AREA)
- Optics & Photonics (AREA)
- Electromagnetism (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to a human body curved surface modeling method, a modeling device and a modeling system. And then determining a motion path based on the scanning path and the static three-dimensional grid map, controlling the robot to move along the motion path, controlling a scanning module to perform SLAM three-dimensional laser scanning on the human body in the moving process of the robot to obtain human body scanning information, and obtaining human body point cloud data based on the human body scanning information. And finally, modeling the human body curved surface according to the human body point cloud data to obtain a human body model. The method can determine the motion path of the robot in real time, better complete the acquisition process of the human body point cloud data, reduce the influence of the water environment on the human body point cloud data acquisition to a certain extent, obtain the human body point cloud data with better quality, and ensure that the human body curved surface modeling process based on the human body point cloud data is more stable and the obtained human body model is better.
Description
Technical Field
The invention relates to the technical field of human body curved surface modeling, in particular to a human body curved surface modeling method, a human body curved surface modeling device and a human body curved surface modeling system.
Background
Since the 90 s of the 20 th century, with the rise of three-dimensional laser scanning technology and the wide application thereof in engineering, a large number of scholars have conducted intensive research on the processing process of point cloud data, so that the point cloud processing technology has been rapidly developed.
The SLAM technology (Simultaneous Localization And mapping) was proposed at the end of the 80's 20 th century, and was first applied to the field of robots, and mainly solves the problem that mobile devices such as robots sense the surrounding environment by using their own sensors, and locate themselves while drawing an environmental Map. In 2010, the SLAM technology enters a leading edge development stage, and simultaneously with the development of various sensors, the sensors used by the SLAM system are continuously expanded, from early sonar to later 2D/3D laser radar, single/double-eye cameras and the like, and the SLAM system based on the 3D laser radar sensor is an SLAM three-dimensional laser scanning system. The SLAM three-dimensional laser scanning system belongs to mobile laser scanning, but does not need a GPS and an inertial navigation system, does not need station changing and splicing, can acquire complete and coherent point cloud data of an object, and has the advantages of high data acquisition speed, high precision, simplicity in operation, convenience in data processing and the like.
At present, the existing SLAM three-dimensional laser scanning system cannot perform modeling operation stably under the water environment.
Disclosure of Invention
The invention aims to provide a human body curved surface modeling method, a human body curved surface modeling device and a human body curved surface modeling system, which can stably finish human body curved surface modeling by carrying out point cloud data acquisition on the surface of a human body in a bathing process.
In order to achieve the purpose, the invention provides the following scheme:
a method of modeling a human body surface, the modeling method comprising:
constructing a static three-dimensional grid map corresponding to a given area; the given area comprises a human body bathing area;
acquiring a scanning path, and determining a motion path based on the scanning path and the static three-dimensional grid map;
controlling the robot to move along the movement path, controlling a scanning module to perform SLAM three-dimensional laser scanning on a human body in the movement process of the robot to obtain human body scanning information, and obtaining human body point cloud data based on the human body scanning information;
and modeling a human body curved surface according to the human body point cloud data to obtain a human body model.
A human body curved surface modeling device comprises a robot, a scanning module, a control module and a monitoring terminal;
the scanning module is arranged on the robot; the scanning module and the robot are both in communication connection with the control module; the control module is in communication connection with the monitoring terminal;
the monitoring terminal is used for determining a scanning path according to the pose of the human body and transmitting the scanning path to the control module;
the control module is used for constructing a static three-dimensional grid map corresponding to a given area, determining a motion path according to the scanning path and the static three-dimensional grid map, and controlling the robot to move along the motion path; the given area comprises a human body bathing area;
the scanning module is used for carrying out SLAM three-dimensional laser scanning on a human body in the motion process of the robot to obtain human body scanning information and transmitting the human body scanning information to the control module;
the control module is also used for obtaining human body point cloud data based on the human body scanning information and carrying out human body curved surface modeling according to the human body point cloud data to obtain a human body model.
A human body surface modeling system, the modeling system comprising:
the construction unit is used for constructing a static three-dimensional grid map corresponding to a given area; the given area comprises a human body bathing area;
the determining unit is used for acquiring a scanning path and determining a motion path based on the scanning path and the static three-dimensional raster map;
the acquisition unit is used for controlling the robot to move along the movement path, controlling the scanning module to perform SLAM three-dimensional laser scanning on the human body in the movement process of the robot to obtain human body scanning information, and acquiring human body point cloud data based on the human body scanning information;
and the modeling unit is used for carrying out human body curved surface modeling according to the human body point cloud data to obtain a human body model.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
according to the human body curved surface modeling method, the modeling device and the modeling system, the static three-dimensional grid map corresponding to the given area is constructed, and the scanning path is obtained. And then determining a motion path based on the scanning path and the static three-dimensional grid map, controlling the robot to move along the motion path, controlling a scanning module to perform SLAM three-dimensional laser scanning on the human body in the moving process of the robot to obtain human body scanning information, and obtaining human body point cloud data based on the human body scanning information. And finally, modeling the human body curved surface according to the human body point cloud data to obtain a human body model. The method can determine the motion path of the robot in real time, better complete the acquisition process of the human body point cloud data, reduce the influence of the water environment on the human body point cloud data acquisition to a certain extent, obtain the human body point cloud data with better quality, ensure that the human body curved surface modeling process based on the human body point cloud data is more stable, obtain a better human body model and lay a good foundation for the next bathing work.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a method flowchart of a modeling method provided in embodiment 1 of the present invention.
Fig. 2 is a flowchart of a method for constructing a static three-dimensional grid map according to embodiment 1 of the present invention.
Fig. 3 is a block diagram of a modeling apparatus provided in embodiment 2 of the present invention.
Fig. 4 is a system block diagram of a modeling system provided in embodiment 3 of the present invention.
Description of the symbols:
1-a scanning module; 2-a control module; 3-a monitoring terminal; 4-a driving module; 5-a distance measuring module; 11-an inertial measurement unit; 12-an encoder; 13-a laser radar; 21-an upper computer; 22-a lower computer.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a human body curved surface modeling method, a human body curved surface modeling device and a human body curved surface modeling system, which can stably finish human body curved surface modeling by carrying out point cloud data acquisition on the surface of a human body in a bathing process.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Example 1:
the present embodiment is configured to provide a human body curved surface modeling method, as shown in fig. 1, for controlling a modeling apparatus shown in fig. 3 to work, where the modeling method includes:
s1: constructing a static three-dimensional grid map corresponding to a given area; the given area comprises a human body bathing area;
the purpose of S1 is to obtain the position information of the static obstacle in the given area, and to eliminate the influence of the static obstacle on the movement of the robot when the movement path of the robot is planned subsequently, so that the robot is not obstructed by the static obstacle. Specifically, as shown in fig. 2, S1 may include:
s11: controlling a robot to move in a given area, controlling a scanning module to perform SLAM three-dimensional laser scanning on the given area in the moving process of the robot to obtain environment scanning information, and obtaining environment point cloud data based on the environment scanning information;
note that the horizontal projection plane of the given area where the robot is located is E, E = W × L, where W is the length of the horizontal projection plane E and L is the width of the horizontal projection plane E. And recording the initial pose of the robot in the given area as a point O, starting the robot, and starting the robot to move from the point O under the artificial guidance. The given area comprises a human body bathing area, specifically, a bathing chair can be placed in the human body bathing area, and people can take a bath on the bathing chair in any pose, wherein the any pose comprises lying, sitting and side-facing.
In the motion process of the robot, the scanning module 1 carries out SLAM three-dimensional laser scanning on a given area in real time to obtain environment scanning information. Specifically, the position information of the static obstacle is acquired in real time through the laser radar 13, the acceleration information and the angular velocity information of the robot are acquired in real time through the inertia measurement unit 11, and the linear velocity information, the driving mileage information and the rotation angle information of the robot are acquired in real time through the encoder 12. The position information of the static obstacle, the acceleration information, the angular velocity information, the linear velocity information, the driving mileage information and the rotation angle information of the robot form environment scanning information. The control module 2 can obtain the environmental point cloud data according to the environmental scanning information.
More specifically, the control module 2 includes an upper computer 21 and a lower computer 22, the upper computer 21 is connected to the laser radar 13, and the laser radar 13 is used to obtain the position information of the obstacle. The lower computer 22 is connected with the inertia measurement unit 11 and the encoder 12, and is used for collecting acceleration information and angular speed information of the robot through the inertia measurement unit 11 and collecting linear speed information, mileage information and rotation angle information of the robot through the encoder 12. The lower computer 22 transmits the acquired acceleration information, angular velocity information, linear velocity information, mileage information and rotation angle information of the robot to the upper computer 21 through a serial port.
S12: constructing an initial static three-dimensional grid map by using a laser SLAM algorithm according to the environment point cloud data; the initial static three-dimensional grid map comprises a plurality of grids; the grid comprises a black grid and a white grid; the black grid is the grid where the static barrier is located;
according to the acquired environmental point cloud data, the upper computer 21 utilizes a laser SLAM algorithm to construct an initial static three-dimensional grid map with grid side length K in a given area. The laser SLAM algorithm can be a method of Gmiping, hector, cartographer, and the like. The initial static three-dimensional grid map is a map composed of black grids and white grids, the occupation state of each grid is represented by corresponding colors, the white grid represents the idle state, the black grid represents the occupied state, and the occupied state represents the position of the grid, which is a static obstacle in a given area. In this embodiment, a three-dimensional map coordinate system is established on the initial static three-dimensional grid map with the point O as the origin, the positive Y-axis direction of the three-dimensional map coordinate system is the direction pointed by the head of the human body, and a clockwise rotation of 90 ° in the positive Y-axis direction is the positive X-axis direction (which may be regarded as the direction corresponding to the length W).
S13: determining the coordinate value of each grid, and replacing the coordinate values of all the black grids with preset fixed values to obtain a static three-dimensional grid map; the preset fixed value is larger than the coordinate values of all the grids.
The coordinate value of the grid is the coordinate of the diagonal intersection point of the grid on the three-dimensional map coordinate system, the coordinate value of each grid on the plane map coordinate system is determined, and the coordinate value of each black grid on the plane map coordinate system is set as a preset fixed value (W1, H1), wherein W1 is more than W1 max ，H1＞H max ，W max Is the maximum value of W in all grids, H max And obtaining a static three-dimensional grid map containing grid coordinate values for the maximum value of H in all grids.
S2: acquiring a scanning path, and determining a motion path based on the scanning path and the static three-dimensional grid map;
after obtaining the static three-dimensional grid map, the upper computer 21 stores the static three-dimensional grid map, and transmits the static three-dimensional grid map to the monitoring terminal 3 through wireless WIFI.
The scanning path is determined by the monitoring terminal 3 according to the pose of the human body, that is, the monitoring terminal 3 issues different scanning paths to the upper computer 21 according to the pose change of the human body. The positions of the person are sitting, side lying and lying, and the scanning paths are different due to the fact that the range of the person in different positions is different. The scanning path issued by the monitoring terminal 3 is an expected path, a static obstacle may exist on the expected path, and if the robot moves directly according to the scanning path, the robot may be blocked by the static obstacle in the moving process, so that the human body scanning process cannot be completed, the human body point cloud data cannot be obtained, and the human body curved surface reconstruction cannot be performed. Therefore, after the monitoring terminal 3 issues the scanning path, the upper computer 21 needs to perform the programmed execution and solution according to the scanning path to obtain the movement path of the robot capable of avoiding the static obstacle.
The process of determining the motion path may include:
and determining the end point according to the scanning path by taking the current position of the robot as a starting point, and particularly determining the end point according to the size of the bath chair. The motion path is a robot motion path which is planned on a static three-dimensional grid map by adopting an algorithm and can completely acquire human body point cloud data and moves from a starting point to a terminal point.
Taking each grid in the static three-dimensional grid map as a road point, taking the grid where the starting point is located as a starting road point Pinit, and taking the grid where the end point is located as a target road point Pgoal. If the number of cycles required from the starting waypoint Pinit to the target waypoint pgeal is N, and N current waypoints are generated, any one of the N cycles is recorded as a cycle i, and any one of the N current waypoints is recorded as a current waypoint Pi, i =1,2. Any one of the four waypoints around the current waypoint Pi is marked as a neighbor waypoint Pin, n =1,2,3,4. The four waypoints around the current waypoint Pi include: a waypoint adjacent to the current waypoint Pi on the left side, a waypoint adjacent to the current waypoint Pi on the right side, a waypoint adjacent to the current waypoint Pi on the front side, and a waypoint adjacent to the current waypoint Pi on the rear side. The four surrounding waypoints are the waypoints adjacent to the current waypoint Pi on the same horizontal plane with the current waypoint Pi in the static three-dimensional grid map. And establishing a first list and a second list, wherein the first list is used for storing the initial waypoint Pinit and the neighbor waypoint Pin, and the second list is used for storing the current waypoint Pi obtained in the motion path planning process.
Specifically, the planning process is as follows:
during the first circulation, the initial waypoint is placed in the first list, the initial waypoint is taken as the current waypoint P1, the adjacent waypoint of any initial waypoint is selected as the first adjacent waypoint, whether the first adjacent waypoint is added into the first list or not is judged according to the coordinate value of the first adjacent waypoint, and a first judgment result is obtained. Specifically, the determination process includes, if the coordinate value of the first neighbor waypoint is a preset fixed value, ignoring the first neighbor waypoint and not adding the first neighbor waypoint to the first list, otherwise, adding the first neighbor waypoint to the first list. And when the first judgment result is yes, namely the first neighbor waypoint is added into the first list, the first cycle is ended, at the moment, two waypoints exist in the first list, and the waypoint with the minimum cost estimation value in the first list is selected as the current waypoint of the 2 nd cycle. And when the first judgment result is negative, continuously selecting the adjacent waypoint of any one initial waypoint as the first neighbor waypoint, and ending the first circulation until the first judgment result is positive.
It should be noted that the neighboring waypoints of the starting waypoint and the starting waypoint are located on the same horizontal plane, and the first neighboring waypoint is the same as the neighboring waypoint, and is named as the first neighboring waypoint only for distinguishing from other circulation processes except the first circulation.
The process of the other cycles except the first cycle is as follows:
and selecting the waypoint with the minimum cost estimation value in the first list as the current waypoint Pi. At this time, i =2,3.
The current waypoint is moved from the first list to the second list, i.e., the current waypoint is added to the second list and deleted from the first list. And judging whether the current waypoint is the target waypoint or not to obtain a second judgment result.
When the second judgment result is yes, N cycles have been completed at this time, that is, the path planning from the starting waypoint to the target waypoint has been completed, and the second list stores other path waypoints except the starting waypoint, the target waypoint and the sequence among the waypoints, so that the movement path can be obtained according to the second list.
And when the second judgment result is negative, the circulation is not completed for N times, the adjacent waypoint of any current waypoint is selected as a second neighbor waypoint, whether the second neighbor waypoint is added into the first list is determined according to the coordinate value and the position of the second neighbor waypoint, the waypoint with the minimum cost estimation value in the first list is selected as the current waypoint, and the step of moving the current waypoint from the first list to the second list is returned.
It should be noted that the neighboring waypoint of the current waypoint and the current waypoint are located on the same horizontal plane, and the second neighboring waypoint is the same as the neighboring waypoint, and is named as the second neighboring waypoint only for distinguishing from the first cycle entry.
The cost estimation value is calculated according to the following formula:
F(i)＝G(i)+H(i)； (1)
in equation 1, F (i) is the cost estimation value, G (i) is the accumulated cost value from the starting waypoint Pinit to the neighboring waypoint Pin, and H (i) is the cost estimation from the neighboring waypoint Pin to the target waypoint Pgoal.
G(i)＝G(i-1)+G(i-1→i)； (2)
In equation 2, G (i-1) is the accumulated cost value from the starting waypoint Pinit to the current waypoint Pi, G (i-1 → i) is the cost value cost from the current waypoint Pi to the neighboring waypoint Pin, and the cost value cost is set to be a constant value with a value of L. In the process of calculating G (1), G (0) =0 is taken.
H(i)＝||Pin-Pgoal||； (3)
In formula 3, | Pin-Pgoal | | | represents the euclidean distance from the neighbor waypoint Pin to the target waypoint Pgoal.
Determining whether to add the second neighbor waypoint into the first list according to the coordinate value and the position of the second neighbor waypoint specifically includes: and judging whether the coordinate value of the second neighbor waypoint is a preset fixed value or not, and judging whether the second neighbor waypoint is in the first list or the second list or not. And if the coordinate value of the second neighbor waypoint is not a preset fixed value, and the second neighbor waypoint is not in the first list or the second list, adding the second neighbor waypoint into the first list. Otherwise, the second neighbor waypoint is not added to the first list.
Specifically, in case 1, if the neighbor waypoint Pin is already in the first list or the second list, the neighbor waypoint Pin is ignored. In case 2, if the coordinate value of the neighbor waypoint Pin is (W1, H1), the neighbor waypoint Pin is ignored. In case 3, if the neighbor waypoint Pin is neither in the first list nor in the second list and the neighbor waypoint coordinate value is not (W1, H1), the cost estimate F (i) of the neighbor waypoint is calculated and the neighbor waypoint Pin is added to the first list.
And after N times of circulation are carried out to obtain N current waypoints, a motion path from the starting waypoint to the target waypoint can be obtained.
S3: controlling the robot to move along the movement path, controlling a scanning module to perform SLAM three-dimensional laser scanning on a human body in the movement process of the robot to obtain human body scanning information, and obtaining human body point cloud data based on the human body scanning information;
the upper computer 21 sends the motion path to the lower computer 22 through the serial port, the lower computer 22 receives the motion path through the serial port, and sends a driving instruction with a driving speed of V to the driving module 4 through the IO port, and the driving module 4 controls the robot to drive according to the motion path. In the motion process of the robot, the scanning module 1 is controlled to carry out SLAM three-dimensional laser scanning on the human body, and real-time information is continuously acquired. The real-time information includes human body position information acquired by the laser radar 13, robot acceleration information and angular velocity information acquired by the inertial measurement unit 11, and robot linear velocity information, driving mileage information and rotation angle information acquired by the encoder 12.
Since a person may perform limb stretching during bathing, the person may be a dynamic obstacle during the movement of the robot along the movement path. Therefore, in this embodiment, the distance measuring module 5 is further used to collect the distance between the robot and the dynamic obstacle in real time, the lower computer 22 judges the magnitude relationship between the distance and the preset distance in real time, and when the distance is smaller than or equal to the preset distance, the robot is controlled to stop moving until the dynamic obstacle is eliminated, and the robot is controlled to move along the original moving path again. The preset distance is a set safe distance between the robot and the surface of the human body.
The lower computer 22 determines whether or not the robot touches the surface of the human body based on the ultrasonic sensor, and sets a safe distance. The lower computer 22 uses the obstacle avoidance function of ultrasonic waves to identify whether a dynamic obstacle exists in the safe distance in real time. If the dynamic obstacle exists, the dynamic obstacle is identified, a signal is sent to the lower computer 22 through the ultrasonic sensor, the robot stops moving, and after the dynamic obstacle does not exist, the robot is controlled to continue to keep the running speed to run along the motion path. And if no dynamic obstacle exists, the robot continues to keep running at the running speed.
S4: and modeling a human body curved surface according to the human body point cloud data to obtain a human body model.
Specifically, the characteristic points in the human body point cloud data are divided into five regions, for example, into a foot, a leg, an upper body, and a head. After the regions are divided, each region is modeled respectively, and the aim is that the human body model is separated into a plurality of parts so as to observe the shape of the human body more clearly.
The specific modeling process is as follows: before the teaching of the bathing robot, human body point cloud data is obtained, and the three-dimensional coordinates of each characteristic point are obtained through numerical calculation. And preprocessing the human body point cloud data to obtain an effective point cloud data set. The pre-processing may include filtering, denoising, etc. And obtaining a characteristic curve by adopting a proper function fitting and optimizing algorithm. For example Canny operators, and the optimization algorithm may use least squares. Determining the contour by contour detection, setting threshold and other methods, determining the positions of the characteristic points and the characteristic lines by a shape analysis method, reconstructing a curved surface, realizing position detection and obtaining a human body model. The surface reconstruction can adopt a mesh reconstruction method based on Delaunay triangulation.
The bathing robot performs bathing work after obtaining the human body model.
The curved surface modeling method is applied to a bathing process, establishes human body point cloud data by utilizing SLAM three-dimensional laser scanning, obtains a human body model, and then realizes automatic bathing and obstacle avoidance work of a robot on the established human body model. The human participation in the process is less, and because the pose of the human body changes in the bathing process, different scanning paths can be made according to different poses, so that the difficulty of human body curved surface modeling in human body movement is effectively solved. The embodiment is based on the ROS, and due to the distributed framework and a large number of open source codes of the ROS, the development difficulty of the laser scanning of the bathing robot is effectively reduced, and the development process is accelerated.
Example 2:
the present embodiment is configured to provide a human body curved surface modeling apparatus, as shown in fig. 3, which works by using the modeling method described in embodiment 1, and the modeling apparatus includes a robot, a scanning module 1, a control module 2, and a monitoring terminal 3.
The scanning module 1 is arranged on the robot, the scanning module 1 and the robot are both in communication connection with the control module 2, and the control module 2 is in communication connection with the monitoring terminal 3.
The monitoring terminal 3 is used for determining a scanning path according to the pose of the human body and transmitting the scanning path to the control module 2. The control module 2 is used for constructing a static three-dimensional grid map corresponding to a given area, determining a motion path according to the scanning path and the static three-dimensional grid map, and controlling the robot to move along the motion path. The given area comprises a human body bathing area.
The scanning module 1 is used for performing SLAM three-dimensional laser scanning on a human body in the movement process of the robot to obtain human body scanning information, and transmitting the human body scanning information to the control module 2. The control module 2 is also used for obtaining human body point cloud data based on the human body scanning information, and carrying out human body curved surface modeling according to the human body point cloud data to obtain a human body model.
When the control module 2 constructs the static three-dimensional grid map corresponding to the given area, the method specifically includes: the robot is controlled to move in a given area, the scanning module 1 is controlled to carry out SLAM three-dimensional laser scanning on the given area in the moving process of the robot, environment scanning information is obtained, and environment point cloud data are obtained based on the environment scanning information. According to the environmental point cloud data, an initial static three-dimensional grid map is constructed by utilizing a laser SLAM algorithm, the coordinates of each grid are determined, the coordinates of all black grids are replaced by preset fixed values, and the static three-dimensional grid map is obtained, wherein the preset fixed values are larger than the coordinate values of all the grids.
As an optional implementation manner, the control module 2 may include both the upper computer 21 and the lower computer 22, and the upper computer 21 and the lower computer 22 may be connected in a bidirectional manner through a serial port. The upper computer 21 can be an industrial personal computer, the operating system can be Linux and ROS, the functions of image building and information transmission are included, and the lower computer 22 can be an embedded development board. The specific components and functions of the device will be described by taking the example of including both the upper computer 21 and the lower computer 22.
The monitoring terminal 3 is in communication connection with the upper computer 21 through wireless WIFI. After obtaining the static three-dimensional grid map, the upper computer 21 transmits the static three-dimensional grid map to the monitoring terminal 3. The monitoring terminal 3 can be one or more of a PC (personal computer), a notebook, an industrial personal computer and a tablet personal computer, and the operating system of the monitoring terminal 3 is Linux or ROS (reactive oxygen species), and comprises online display of a scanning picture and designation of a scanning path.
The scanning module 1 comprises a first acquisition sub-module and a second acquisition sub-module. The first acquisition submodule is in communication connection with the lower computer 22, and the second acquisition submodule is in communication connection with the upper computer 21. The first acquisition submodule is used for acquiring the motion information of the robot in real time in the motion process of the robot, and the lower computer 22 transmits the acquired motion information of the robot to the upper computer 21 through a serial port. The second acquisition submodule is used for acquiring the position information of the human body in real time in the motion process of the robot. The human body scan information includes motion information and position information of the human body. The upper computer 21 is used for obtaining human body point cloud data according to the motion information and the position information of the human body.
Specifically, the first acquisition submodule includes an inertial measurement unit 11 and an encoder 12. The inertia measurement unit 11 is connected with the lower computer 22 in a unidirectional manner through an IIC interface, and the inertia measurement unit 11 is configured to acquire acceleration information and angular velocity information of the robot in real time during a motion process of the robot, and transmit the acceleration information and the angular velocity information to the lower computer 22. The encoder 12 is connected to the lower computer 22 through a GPI0 interface in a one-way manner, and the encoder 12 is configured to acquire linear velocity information, mileage information, and rotation angle information of the robot in real time during a movement process of the robot, and transmit the linear velocity information, mileage information, and rotation angle information to the lower computer 22. The motion information includes acceleration information, angular velocity information, linear velocity information, mileage information, and rotation angle information. The lower computer 22 transmits the received robot acceleration information, angular velocity information, linear velocity information, rotation angle information and mileage information to the upper computer 21.
The second acquisition sub-module comprises a lidar 13. Laser radar 13 is fixed on the top of vertical arm, and the laser head can 360 rotations, and the laser head links to each other with the intelligent control ware of installing on the main control computer. The laser radar 13 is connected with the upper computer 21 in a one-way mode through a serial port, and the laser radar 13 is used for collecting position information of a human body in real time in the moving process of the robot and transmitting the position information of the human body to the upper computer 21.
In the embodiment, the scanning module based on the laser radar is used for finishing the scanning work of the surface of the human body in the bathing process, if too much water vapor influences the use of the laser radar, great interference is generated in point cloud processing, the scanning module based on the ultrasonic radar can be adopted for replacing the scanning module based on the laser radar, and the point cloud operation in the curved surface modeling is finished through the penetrability and the anti-interference performance of ultrasonic waves.
When the robot is controlled to move along the movement path, the following specific examples may be: the lower computer 22 receives the motion path issued by the upper computer 21 and sends a driving instruction to the robot, and the robot runs according to the motion path and performs SLAM three-dimensional laser scanning on the human body by using the scanning module 1. The lower computer 22 is connected with the driving module 4 in a one-way mode through an IO line, the driving module 4 comprises a driving circuit and a driving motor, and the driving circuit controls the driving motor according to the driving instruction after receiving the driving instruction sent by the lower computer 22, so that the robot moves.
The modeling device further comprises a distance measuring module 5, the distance measuring module 5 is arranged on the robot, and the distance measuring module 5 can be an ultrasonic distance measuring module and is connected with the lower computer 22 through an IO line.
The distance measuring module 5 is configured to acquire a distance between the robot and a dynamic obstacle located on a moving path in real time during a moving process of the robot, specifically, measure a distance between an end of an actuator of the robot and a surface of a human body, and transmit the distance to the lower computer 22. The lower computer 22 is further configured to compare the distance with a preset distance, and when the distance is greater than or equal to the preset distance, control the robot to stop moving until the dynamic obstacle is eliminated. The dynamic barrier is a moving human body.
The human body point cloud data comprises dynamic point cloud data and static point cloud data, the static point cloud data comprises point cloud data acquired when a person keeps still, and the dynamic point cloud data comprises point cloud data acquired when the person moves on the chair and changes the pose of the human body caused by the change of the chair.
The modeling device of the embodiment further comprises a power supply module, which is used for supplying power to the upper computer 21, the lower computer 22, the driving module 4, the encoder 12, the inertia measurement unit 11 and the laser radar 13.
In the bathing process, the pose of the human body changes along with the change of the bathing state, so that the human body can also move due to the fact that curved surface modeling work with different poses is carried out, scanning paths with different modes are adopted in the embodiment, laser scanning point cloud processing is carried out, the human body curved surface modeling work is completed, and the function of protecting the human body is achieved by matching with a robot while bathing.
Example 3:
this embodiment is configured to provide a human body surface modeling system, as shown in fig. 4, which operates by using the modeling method described in embodiment 1, and the modeling system includes:
the building unit M1 is used for building a static three-dimensional grid map corresponding to a given area; the given area comprises a human body bathing area;
the determining unit M2 is used for acquiring a scanning path and determining a motion path based on the scanning path and the static three-dimensional grid map;
the acquisition unit M3 is used for controlling the robot to move along the movement path, controlling the scanning module to perform SLAM three-dimensional laser scanning on the human body in the movement process of the robot to obtain human body scanning information, and acquiring human body point cloud data based on the human body scanning information;
and the modeling unit M4 is used for carrying out human body curved surface modeling according to the human body point cloud data to obtain a human body model.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (9)
1. A human body curved surface modeling method is characterized by comprising the following steps:
constructing a static three-dimensional grid map corresponding to a given area; the given area comprises a human body bathing area;
acquiring a scanning path, and determining a motion path based on the scanning path and the static three-dimensional grid map; the scanning path is determined by the monitoring terminal according to the pose of the human body; the motion path is a robot motion path which is planned in the static three-dimensional grid map and moves from a starting point to an end point and can completely acquire human body point cloud data; the starting point is the current position of the robot, and the end point is determined according to the scanning path;
controlling a robot to move along the movement path, controlling a scanning module to perform SLAM three-dimensional laser scanning on a human body in the movement process of the robot to obtain human body scanning information, and obtaining human body point cloud data based on the human body scanning information;
modeling a human body curved surface according to the human body point cloud data to obtain a human body model; and carrying out region division on the human body point cloud data, and respectively carrying out human body curved surface modeling on each region obtained by division to obtain a human body model.
2. The modeling method according to claim 1, wherein the constructing a static three-dimensional grid map corresponding to a given area specifically comprises:
controlling a robot to move in a given area, controlling a scanning module to perform SLAM three-dimensional laser scanning on the given area in the moving process of the robot to obtain environment scanning information, and obtaining environment point cloud data based on the environment scanning information;
constructing an initial static three-dimensional grid map by using a laser SLAM algorithm according to the environmental point cloud data; the initial static three-dimensional grid map comprises a plurality of grids; the grid comprises a black grid and a white grid; the black grid is the grid where the static barrier is located;
determining the coordinate value of each grid, and replacing the coordinate values of all the black grids with preset fixed values to obtain a static three-dimensional grid map; the preset fixed value is larger than the coordinate values of all the grids.
3. The modeling method of claim 1, wherein the determining a motion path based on the scan path and the static three-dimensional grid map specifically comprises:
determining an end point according to the scanning path by taking the current position of the robot as a starting point;
taking each grid in the static three-dimensional grid map as a road point, taking the grid where the starting point is located as an initial road point, and taking the grid where the end point is located as a target road point;
placing the starting waypoint in a first list;
selecting an adjacent waypoint of any one of the starting waypoints as a first neighbor waypoint, and judging whether to add the first neighbor waypoint into the first list according to the coordinate value of the first neighbor waypoint to obtain a first judgment result; the adjacent waypoints of the starting waypoint and the starting waypoint are positioned on the same horizontal plane;
when the first judgment result is yes, selecting the waypoint with the minimum cost estimation value in the first list as the current waypoint;
moving the current waypoint from the first list to a second list, and judging whether the current waypoint is the target waypoint or not to obtain a second judgment result;
when the second judgment result is yes, obtaining a motion path according to the second list;
when the second judgment result is negative, selecting an adjacent waypoint of any one current waypoint as a second neighbor waypoint, determining whether to add the second neighbor waypoint into the first list according to the coordinate value and the position of the second neighbor waypoint, selecting the waypoint with the minimum cost estimation value in the first list as the current waypoint, and returning to the step of moving the current waypoint from the first list to the second list; the adjacent waypoint of the current waypoint and the current waypoint are positioned on the same horizontal plane;
and when the first judgment result is negative, returning to the step of selecting the adjacent waypoint of any one starting waypoint as the first neighbor waypoint until the first judgment result is positive.
4. The modeling method according to claim 3, wherein the determining whether to add the second neighbor waypoint to the first list according to the coordinate values and the positions of the second neighbor waypoints specifically includes:
judging whether the coordinate value of the second neighbor waypoint is a preset fixed value or not, and judging whether the second neighbor waypoint is in the first list or the second list or not;
if the coordinate value of the second neighbor waypoint is not a preset fixed value, and the second neighbor waypoint is not in the first list or the second list, adding the second neighbor waypoint into the first list;
otherwise, the second neighbor waypoint is not added to the first list.
5. The human body curved surface modeling device is characterized by comprising a robot, a scanning module, a control module and a monitoring terminal;
the scanning module is arranged on the robot; the scanning module and the robot are both in communication connection with the control module; the control module is in communication connection with the monitoring terminal;
the monitoring terminal is used for determining a scanning path according to the pose of the human body and transmitting the scanning path to the control module;
the control module is used for constructing a static three-dimensional grid map corresponding to a given area, determining a motion path according to the scanning path and the static three-dimensional grid map, and controlling the robot to move along the motion path; the given area comprises a human body bathing area; the motion path is a robot motion path which is planned in the static three-dimensional grid map, moves from a starting point to an end point and can completely acquire human body point cloud data; the starting point is the current position of the robot, and the end point is determined according to the scanning path;
the scanning module is used for carrying out SLAM three-dimensional laser scanning on a human body in the motion process of the robot to obtain human body scanning information and transmitting the human body scanning information to the control module;
the control module is also used for obtaining human body point cloud data based on the human body scanning information and carrying out human body curved surface modeling according to the human body point cloud data to obtain a human body model; and carrying out region division on the human body point cloud data, and respectively carrying out human body curved surface modeling on each region obtained by division to obtain a human body model.
6. The modeling apparatus of claim 5, wherein the scan module includes a first acquisition sub-module and a second acquisition sub-module; the first acquisition submodule and the second acquisition submodule are in communication connection with the control module;
the first acquisition submodule is used for acquiring the motion information of the robot in real time in the motion process of the robot; the second acquisition submodule is used for acquiring the position information of a human body in real time in the motion process of the robot; the human body scanning information comprises the motion information and the position information of the human body;
the control module is used for obtaining human body point cloud data according to the motion information and the position information of the human body.
7. The modeling apparatus of claim 6, wherein the first acquisition submodule includes an inertial measurement unit and an encoder; the inertial measurement unit and the encoder are both in communication connection with the control module;
the inertia measurement unit is used for acquiring acceleration information and angular velocity information of the robot in real time in the motion process of the robot and transmitting the acceleration information and the angular velocity information to the control module; the encoder is used for acquiring linear velocity information, mileage information and rotation angle information of the robot in real time in the moving process of the robot and transmitting the linear velocity information, the mileage information and the rotation angle information to the control module; the motion information includes the acceleration information, the angular velocity information, the linear velocity information, the mileage information, and the rotation angle information;
the second acquisition submodule comprises a laser radar; the laser radar is in communication connection with the control module;
the laser radar is used for collecting position information of a human body in real time in the moving process of the robot.
8. The modeling apparatus of claim 5, further comprising a ranging module; the distance measuring module is arranged on the robot and is in communication connection with the control module;
the distance measurement module is used for acquiring the distance between the robot and a dynamic obstacle on the running path in real time in the moving process of the robot and transmitting the distance to the control module;
the control module is further used for comparing the distance with a preset distance and controlling the robot to stop moving until the dynamic barrier is eliminated when the distance is greater than or equal to the preset distance; the dynamic barrier is a moving human body.
9. A human body surface modeling system, the modeling system comprising:
the building unit is used for building a static three-dimensional grid map corresponding to a given area; the given area comprises a human body bathing area;
the determination unit is used for acquiring a scanning path and determining a motion path based on the scanning path and the static three-dimensional grid map; the scanning path is determined by the monitoring terminal according to the pose of the human body; the motion path is a robot motion path which is planned in the static three-dimensional grid map and moves from a starting point to an end point and can completely acquire human body point cloud data; the starting point is the current position of the robot, and the end point is determined according to the scanning path;
the acquisition unit is used for controlling the robot to move along the movement path, controlling the scanning module to carry out SLAM three-dimensional laser scanning on a human body in the movement process of the robot to obtain human body scanning information, and acquiring human body point cloud data based on the human body scanning information;
the modeling unit is used for carrying out human body curved surface modeling according to the human body point cloud data to obtain a human body model; and carrying out region division on the human body point cloud data, and respectively carrying out human body curved surface modeling on each region obtained by division to obtain a human body model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110600486.2A CN113268062B (en) | 2021-05-31 | 2021-05-31 | Human body curved surface modeling method, modeling device and modeling system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110600486.2A CN113268062B (en) | 2021-05-31 | 2021-05-31 | Human body curved surface modeling method, modeling device and modeling system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113268062A CN113268062A (en) | 2021-08-17 |
| CN113268062B true CN113268062B (en) | 2022-10-14 |
Family
ID=77233632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110600486.2A Active CN113268062B (en) | 2021-05-31 | 2021-05-31 | Human body curved surface modeling method, modeling device and modeling system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113268062B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102178530A (en) * | 2011-01-24 | 2011-09-14 | 天津大学 | Method for automatically measuring human body dimensions on basis of three-dimensional point cloud data |
| CN106725498A (en) * | 2016-12-28 | 2017-05-31 | 尹志军 | 3D anthropometric scanning apparatus and system |
| CN110122958A (en) * | 2019-05-06 | 2019-08-16 | 大有智能科技(嘉兴)有限公司 | Three-dimensional scanner and application method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709947B (en) * | 2016-12-20 | 2020-06-19 | 西安交通大学 | Three-dimensional human body rapid modeling system based on RGBD camera |
| CN107144236A (en) * | 2017-05-25 | 2017-09-08 | 西安交通大学苏州研究院 | A kind of robot automatic scanner and scan method |
| TWM606669U (en) * | 2019-05-02 | 2021-01-21 | 八豐盟有限公司 | Three-dimensional human body scanning device |
| CN112066989B (en) * | 2020-08-19 | 2022-07-29 | 合肥工业大学 | Indoor AGV automatic navigation system and method based on laser SLAM |
| CN113376649A (en) * | 2021-06-30 | 2021-09-10 | 华中科技大学 | Robot automatic local scanning planning method based on global rough scanning imaging |
-
2021
- 2021-05-31 CN CN202110600486.2A patent/CN113268062B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102178530A (en) * | 2011-01-24 | 2011-09-14 | 天津大学 | Method for automatically measuring human body dimensions on basis of three-dimensional point cloud data |
| CN106725498A (en) * | 2016-12-28 | 2017-05-31 | 尹志军 | 3D anthropometric scanning apparatus and system |
| CN110122958A (en) * | 2019-05-06 | 2019-08-16 | 大有智能科技(嘉兴)有限公司 | Three-dimensional scanner and application method |
Non-Patent Citations (1)
| Title |
|---|
| 激光扫描技术在运动员三维人体模型建立中的应用;依博亮;《激光杂志》;20161225(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113268062A (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109890573B (en) | Control method and device for mobile robot, mobile robot and storage medium | |
| CN108247647B (en) | Cleaning robot | |
| US10481265B2 (en) | Apparatus, systems and methods for point cloud generation and constantly tracking position | |
| Baltzakis et al. | Fusion of laser and visual data for robot motion planning and collision avoidance | |
| US7865267B2 (en) | Environment recognizing device, environment recognizing method, route planning device, route planning method and robot | |
| CN102448681B (en) | Operating space presentation device, operating space presentation method, and program | |
| CN108283021A (en) | Locating a robot in an environment using detected edges of a camera image from a camera of the robot and detected edges derived from a three-dimensional model of the environment | |
| CN106845515A (en) | Robot target identification and pose reconstructing method based on virtual sample deep learning | |
| RU2662913C2 (en) | Method of robot localization in localization plane | |
| WO2015024407A1 (en) | Power robot based binocular vision navigation system and method based on | |
| CN101261118A (en) | Rapid automatized three-dimensional appearance on-line measurement method and system based on robot | |
| CN108563220A (en) | The motion planning of apery Soccer robot | |
| CN111182174B (en) | Method and device for supplementing light for sweeping robot | |
| CN106708037A (en) | Autonomous mobile equipment positioning method and device, and autonomous mobile equipment | |
| CN115793649B (en) | Automatic cable pit inspection device and inspection method | |
| CN115932882A (en) | System for providing 3D detection of an environment through an autonomous robotic vehicle | |
| JP2018173707A (en) | Person estimation system and estimation program | |
| CN113268062B (en) | Human body curved surface modeling method, modeling device and modeling system | |
| KR100784125B1 (en) | Method for extracting coordinates of landmark of mobile robot with a single camera | |
| CN111369669A (en) | Method for automatically leveling sprayed surface | |
| CN114529585A (en) | Mobile equipment autonomous positioning method based on depth vision and inertial measurement | |
| CN110857861B (en) | Track planning method and system | |
| CN114911223A (en) | Robot navigation method and device, robot and storage medium | |
| Hakim et al. | Asus Xtion Pro Camera Performance in Constructing a 2D Map Using Hector SLAM Method | |
| Wang et al. | 3d slam applied to an autonomous interior finishing robot |
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 |