CN116466724A - Mobile positioning method and device of robot and robot - Google Patents
Mobile positioning method and device of robot and robot Download PDFInfo
- Publication number
- CN116466724A CN116466724A CN202310467208.3A CN202310467208A CN116466724A CN 116466724 A CN116466724 A CN 116466724A CN 202310467208 A CN202310467208 A CN 202310467208A CN 116466724 A CN116466724 A CN 116466724A
- Authority
- CN
- China
- Prior art keywords
- robot
- gps
- area
- moving
- obstacle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000008569 process Effects 0.000 claims abstract description 16
- 238000003062 neural network model Methods 0.000 claims description 24
- 239000011159 matrix material Substances 0.000 claims description 17
- 230000001133 acceleration Effects 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000000873 masking effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 11
- 230000000875 corresponding effect Effects 0.000 description 7
- 230000004888 barrier function Effects 0.000 description 6
- 230000001276 controlling effect Effects 0.000 description 6
- 238000011065 in-situ storage Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 241001494496 Leersia Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000007958 sleep Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000002759 z-score normalization Methods 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
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
-
- 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
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0225—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving docking at a fixed facility, e.g. base station or loading bay
-
- 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
- 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
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
Abstract
The invention discloses a moving positioning method, a moving positioning device and a robot of a robot, which relate to the field of position positioning, when the robot cannot accurately position by means of GPS signals, the current moving direction of the robot is determined by an inertial navigation device, the robot is controlled to move along the current moving direction, a front image of the robot is obtained in the moving process of the robot, whether an obstacle exists in front of the robot is judged according to the front image, the moving strategy of the robot is determined according to the judging result, a GPS strong signal area is an area where the robot can accurately position according to the GPS signals, and the obstacle comprises an actual obstacle and the boundary of an active area of the robot. The robot is controlled to keep the original direction to move continuously through inertial navigation, whether the front is blocked or not is identified through images, the robot can be controlled to move outside the GPS strong signal area, the robot can be prevented from leaving the active area, the practicability of the robot is improved, and potential safety hazards are avoided.
Description
Technical Field
The present invention relates to the field of position positioning, and in particular, to a method and an apparatus for positioning a robot.
Background
With the maturity of GPS (RTK) (Global Positioning System (Real time kinematic Positioning) technology, the real-time dynamic global positioning system) technology is mature, and the current mowing robots on the market widely apply GPS (RTK) to realize positioning, the main realization method is that the position of the mowing robot is not judged through GPS signals, a circle of area needing mowing is marked out in an electronic map of the mowing robot to serve as an active area of the mowing robot, and the high-precision positioning characteristic of the GPS (RTK) signals is utilized to ensure that the mowing robot moves in the active area. However, when there is a tall obstacle occlusion near the active area, it may result in a situation where the GPS signal strength is weak or lost in some part of the active area, such as when there is a tall building or tree occlusion near the lawn, and in addition, weather changes may result in sky being covered by a thicker cloud. When the GPS signal intensity is weak or the GPS signal is lost, the boundary of the active area in the electronic map is unstable, the position of the mowing robot body cannot be determined, the situation that the mowing robot leaves the active area is easy to occur, and potential safety hazards are caused.
At present, in order to avoid potential safety hazards, in the prior art, when a mowing robot detects that the strength of a GPS signal received by the mowing robot is weak or the GPS signal is lost, the mowing robot is stopped in situ and waits for a period of time, and if the strength of the GPS signal is recovered in the period of time, the operation is continued; otherwise, the user sleeps in situ. This approach, while avoiding potential safety hazards, can lead to reduced availability of the lawn mowing robot.
Disclosure of Invention
The invention aims to provide a mobile positioning method and device for a robot, and the robot, which can ensure that the robot moves continuously according to an original route in a GPS weak signal area, and ensure that the robot moves in an active area, thereby not only improving the practicability of the robot, but also avoiding potential safety hazards.
In order to solve the technical problems, the invention provides a mobile positioning method of a robot, comprising the following steps:
when the GPS signal is weak and the robot cannot be accurately positioned by means of the GPS signal, determining the current moving direction of the robot through the inertial navigation device;
controlling the robot to move along the current moving direction;
acquiring a front image of the robot in the moving process of the robot;
Judging whether an obstacle exists in front of the robot according to the front image;
determining a movement strategy of the robot according to a determination result of whether an obstacle exists in front;
wherein the obstacle comprises an actual obstacle and an active area boundary of the robot.
In some embodiments, determining, by an inertial navigation device, a current direction of movement of the robot comprises:
determining a current acceleration direction, a current course angle and a current speed direction of the robot through the inertial navigation device;
and determining the current moving direction of the robot according to the current acceleration direction, the current course angle and the current speed direction.
In some embodiments, determining whether there is an obstacle in front of the robot from the front image includes:
extracting image features in the front image;
transmitting the image features to a first preset neural network model so as to determine a grid matrix corresponding to the front image and obstacle correlation of each grid in the grid matrix, wherein the first preset neural network model is obtained by training a preset number of front images in advance;
masking the grid matrix to determine the grid scores of all grids in the grid matrix;
Taking the average value of each grid score as the identification score of the front image;
judging whether the identification score is larger than a preset score or not;
if yes, judging that the vehicle is in disorder;
if not, judging that the fault exists;
wherein, the numerical value of the grid score and the obstacle correlation of the grid corresponding to the grid score are positive correlations.
In some embodiments, after determining that there is an obstacle, further comprising:
if the judgment result of whether the front of the robot has the obstacle is continuous N times, sending the front image to a second preset neural network model so as to judge whether the acquired front image is an abnormal image, wherein the second preset neural network model is obtained by training a preset number of front images in advance; n is an integer not less than 2;
and if the abnormal image is the abnormal image, generating a prompt signal and sending the prompt signal to a prompt module so that the prompt module sends out prompt.
In some embodiments, further comprising:
when a user instruction is received from a device communicated with the robot, controlling the robot to move according to the user instruction;
determining a moving route of the robot in the moving process of the robot, and storing the moving route on equipment communicated with the robot;
And taking the area surrounded by the moving route as the moving range of the robot.
In some embodiments, determining the path of movement of the robot comprises:
when the robot moves in the GPS strong signal area, drawing a moving route of the robot on a preset electronic map by using A line segments;
when the robot moves outside the GPS strong signal area, B line segments are used for drawing a moving route of the robot on the preset electronic map;
after the area surrounded by the moving route is used as the moving range of the robot, the method further comprises:
and sending the preset electronic map containing the movable range to a user terminal so that a user can determine the actual position of the GPS strong signal area.
In some embodiments, after determining whether the robot is outside the GPS strong signal region, further comprising:
when the robot was last determined to be within the GPS strong signal region and the robot was this time determined to be outside the GPS strong signal region,
or alternatively, the first and second heat exchangers may be,
when the robot is determined to be outside the GPS strong signal area the last time and the robot is determined to be inside the GPS strong signal area this time,
The position of the latest GPS signal positioning of the robot is used as a boundary point of the GPS strong signal area;
determining boundary lines of the GPS strong signal area according to a plurality of boundary points;
and sending the preset electronic map containing the boundary line to a user terminal so that a user can determine the boundary line of the GPS strong signal area.
The application also provides a mobile positioning device of robot, include:
a memory for storing a computer program;
and a processor for implementing the steps of the method for positioning the movement of the robot when executing the computer program.
The application also provides a robot, which comprises a robot body and a mobile positioning device of the robot;
the mobile positioning device of the robot is connected with the robot body.
In some embodiments, a camera is also included;
the camera is connected with the robot body and used for collecting images in front of the robot body.
The application provides a mobile positioning method, a mobile positioning device and a robot of a robot, which relate to the field of position positioning, when the robot is judged to be outside a GPS strong signal area, the current moving direction of the robot is determined through an inertial navigation device, the robot is controlled to move along the current moving direction, a front image of the robot is acquired in the moving process of the robot, whether the front of the robot is obstructed or not is judged according to the front image, the moving strategy of the robot is determined according to the judging result of whether the front is obstructed or not, the GPS strong signal area is an area in which the robot can accurately position according to GPS signals with enough quality, and the obstacle comprises an actual obstacle and the moving area boundary of the robot. The mowing robot is controlled to keep the original direction to move continuously through inertial navigation, whether the front is blocked or not is identified through images, the robot can be controlled to move outside the GPS strong signal area, the robot can be prevented from leaving the active area, the practicability of the robot is improved, and potential safety hazards are avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required in the prior art and the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only 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 flow chart of a control method in the case of a GPS weak signal in the prior art;
fig. 2 is a flowchart of a method for positioning movement of a robot provided in the present application;
FIG. 3 is a flow chart of another method for mobile positioning of a robot provided by the present application;
fig. 4 is an external schematic view of a robot provided in the present application;
FIG. 5 is a schematic view of an active area of a robot provided herein;
FIG. 6 is a schematic view of an active area of another robot provided herein;
fig. 7 is a schematic view of a moving route of a robot provided in the present application;
fig. 8 is a schematic structural diagram of a first preset neural network model of a robot provided in the present application;
fig. 9 is a schematic diagram of a robot capturing a front image provided in the present application;
Fig. 10 is a schematic structural diagram of a mobile positioning device of a robot provided in the present application.
Detailed Description
The invention provides a mobile positioning method and device for a robot, and the robot, which can ensure that the robot moves continuously according to an original route in a GPS weak signal area, and also ensure that the robot moves in an active area, thereby not only improving the practicability of the robot, but also avoiding potential safety hazards.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present 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 noted that, before the actual work of the mowing robot, the user needs to plan an area to be mowed, the area is an active area of the mowing robot, the robot stores the GPS (RTK) positioning coordinates of the boundary of the active area in the memory, and the area can be displayed on the mobile device connected with the robot through wireless communication through the APP program on the special device. The GPS strong signal area and the GPS weak signal area described later are the areas in the active area. The GPS strong signal area refers to an area where the robot can accurately position the electronic coordinates according to GPS signals with enough quality, and the GPS weak signal area is an area where the robot cannot accurately position by means of the GPS signals because the GPS signals are weak.
Currently, a mowing robot with a path planning function on the market generally relies on a GPS signal for positioning and navigation, the GPS (RTK) mainly relies on a signal sent by a satellite and a real-time differential algorithm, and the positioning (Differential Global Position System, differential global positioning system) is realized by adopting a DPGS, specifically, the position of the mowing robot is positioned according to the difference between the GPS signal received by the mowing robot and the signal received by a GPS base station, and the GPS base station can be understood as an origin of a coordinate system in a common sense. However, if there is a high obstruction such as a building or a tree around the area where the mowing robot is moving, or if there is a weather change that causes a cloud layer to become thicker (such as rainy weather), there may be a case where the GPS signal is weak or lost in some part or the whole area in the area where the mowing robot is moving. Since the active area of the mowing robot is based on the preset electronic map, in this case, the boundary of the active area in the electronic map becomes blurred and unstable, and the mowing robot may leave the predetermined active area, which may cause a safety problem.
In order to avoid the safety problem, referring to fig. 1, fig. 1 is a flowchart of a control method in the prior art when a GPS weak signal is generated, when a mowing robot is moving, whether in a first planning active area link or an actual working link, when the situation that the GPS signal is weak or the GPS signal is lost is encountered, there are two general methods: one method is to adopt an exploration mode, when the GPS signal is weak or the GPS signal disappears, the mowing robot rotates in situ or moves within a limited distance, if the mowing robot finds a region with strong GPS signal within a certain time, the mowing robot continues to work, if the mowing robot does not find the region with strong GPS signal within a certain time, the mowing robot stops in situ or returns to a nearby charging pile; in another method, once the GPS signal is weak or the GPS signal is lost, the mowing robot is stopped in situ, a period of time is waited for to see whether the strength of the GPS signal is recovered, if so, the mowing robot can continue to work, and if not, the mowing robot is stopped in situ or returns to a nearby charging pile.
According to the prior art, if the GPS signal is weak or the GPS signal disappears due to weather changes, it is indicated that the signal strength of the GPS weak signal area may be increased due to better weather; however, if the signal strength of the GPS weak signal area is basically impossible to be strong due to the shielding of the obstacle, the limitation of the prior art is large, and the practicability of the mowing robot is limited.
Moreover, the prior art relies on GPS signals completely, no matter when the mowing robot plans the movable range, actually works, or returns to the process of charging the pile, the conditions that the GPS signal strength is weakened or the GPS signal disappears suddenly can cause the mowing robot to move according to the original plan, and then the conditions that the mowing robot collides, falls off and cannot find the charging pile can occur.
In order to solve the above technical problems, please refer to fig. 2 and 4, fig. 2 is a flowchart of a mobile positioning method of a robot provided in the present application, and fig. 4 is an external schematic view of a robot (especially a mowing robot) provided in the present application, where the positioning method is applied to a processor in the mowing robot, and includes:
s1: when the GPS signal is weak and the robot cannot accurately position by means of the GPS signal, determining the current moving direction of the robot through the inertial navigation device;
referring to fig. 5, fig. 5 is a schematic diagram of an active area of a robot provided in the present application, in fig. 5, a closed area under several buildings and a diagonal area are equal to an active area of a mowing robot, and a blank area is relatively open, and has no shielding object and no obstacle nearby, so that the blank area is a GPS strong signal area; the building shielding is arranged near the oblique line area, so that the area is a GPS weak signal area. Obviously, if the actual active area of the mowing robot is only in the blank area, the GPS signal can be well positioned, but when a part of the actual active area of the mowing robot or the whole actual active area is in the oblique line area, the mowing robot cannot obtain the accurate GPS signal. In the prior art, either the robot need to be manually moved out of the diagonal area in fig. 5, or the active area needs to be re-planned to exclude the diagonal area in fig. 5, obviously both can affect the practicability of the robot, limit the active range of the robot, not only can not meet the user's requirement, but also the user has to plan the active area several times to avoid the diagonal area.
The method for detecting the strength of the GPS signal and how to determine that the robot cannot accurately position by means of the GPS signal in the present application are not limited in this application. However, as an embodiment, it may be determined whether the robot can accurately position by means of the GPS signal at this time simply according to the signal strength of the GPS: in the running process of the mowing robot, detecting the GPS signal intensity of the mowing robot in real time, and if the current intensity of the GPS signal is lower than a certain threshold value, judging that the mowing robot cannot accurately position by means of the GPS signal; similarly, if the current strength of the detected GPS signal is higher than the threshold value, the robot can accurately position by means of the GPS signal. In addition, the position difference between the positioning coordinates of the GPS signals of the mowing robot and the positioning coordinates of the GPS signals of the GPS base station can be detected in real time, if the position difference is very large, the fact that the GPS signals have large errors at the moment is indicated, and the fact that the mowing robot cannot accurately position by means of the GPS signals can be indirectly indicated; similarly, if the GPS signal of the GPS base station is not detected or if the GPS signal is erroneous, this can be explained.
As another example, it may also be implemented using differential GPS. The principle of differential GPS is: the satellite can send GPS coordinate signals corresponding to the two to the mowing robot and the GPS base station at the same time, the mowing robot accurately determines the position of the mowing robot on the electronic map according to the coordinates of the mowing robot and the coordinates of the GPS base station, the GPS base station can understand the origin of the coordinate system in the normal sense, the mowing robot is a certain point on the coordinate system, the coordinate difference between the two points is calculated, the distance between the mowing robot and the base station can be obtained, and the specific position of the mowing robot can be further obtained. Based on this, since the active area of the mowing robot is limited and the position of the GPS base station is fixed, a coordinate difference value or a distance difference value, which is equal to a distance difference between the GPS base station and a point of the active area farthest from the base station in actual use, may be set in advance according to the actual size of the active area. If the calculated coordinate difference between the two points is too large, the distance between the mowing robot and the GPS base station exceeds the distance between the base station and the point, farthest from the base station, of the active area, and at the moment, the problem of positioning of the GPS base station or the problem of positioning of the mowing robot can be indicated, namely, the problem of positioning of the GPS base station is indicated, namely, the GPS signal strength is weak.
In the prior art, after detecting that the mowing robot leaves the GPS strong signal area, the mowing robot usually cannot work continuously, but in the application, an inertial navigation device is additionally arranged in the mowing robot, and the inertial navigation device is a device capable of detecting the motion characteristics of the mowing robot and mainly comprises a compass, a gyroscope, a mileage sensor, a speed sensor, an acceleration sensor and other equipment and is used for detecting parameters such as the motion direction, the speed, the distance and the like of the mowing robot in real time. The inertial navigation device can always detect the motion parameters of the mowing robot no matter in which area the mowing robot moves, so as to assist the movement of the mowing robot, determine the original moving direction of the mowing robot through the motion parameters when detecting that the mowing robot is not in a GPS strong signal area, and control the mowing robot to continuously move along the original moving direction so as to get rid of the limitation of the GPS signal intensity. Specifically, the compass can point out the included angle of the facing direction of the mowing robot relative to the south pole direction, the gyroscope, the speed sensor and the acceleration sensor can point out the speed direction of the mowing robot, and the mileage sensor is mainly combined with other devices, and the distance and the route of the mowing robot in the GPS weak signal area are utilized to determine and calculate the locus of the mowing robot.
S2: controlling the robot to move along the current moving direction;
s3: acquiring a front image of the robot in the moving process of the robot;
s4: judging whether the front of the robot has an obstacle according to the front image;
in order to avoid that the mowing robot collides with obstacles such as stones and trees in the active area, in the application, a camera is further arranged on the mowing robot, an image in front of the moving direction of the mowing robot is acquired through the camera, whether the front of the mowing robot is obstructed or whether the front is about to leave the active area is identified through the image, and it is understood that the mowing robot usually works on a lawn, and whether the front of the mowing robot is obstructed or not can be simply identified according to the color observed by the camera because the lawn is usually green. For the specific process of image recognition, the content contained in the front image may be determined based on semantic segmentation, or whether the front image contains an obstacle or is out of the active area may be determined based on a neural network model or a machine learning model. Referring to fig. 9, fig. 9 is a schematic diagram of a front image captured by a robot provided in the present application, in fig. 9, an image captured by a camera is divided into 12 image blocks (of course, not limited to 12 in practical application), by the above methods of color judgment, semantic segmentation judgment, and learning model judgment, the lower 3 rows of 9 image blocks can be distinguished to be grasslands, and the upper 1 rows of 3 image blocks are distinguished to be not grasslands, then the boundary between the image blocks not being grasslands and the image blocks not being grasslands can be used as the boundary of the active area of the mowing robot, and the image blocks not being grasslands can be determined as obstacles.
In addition, if the shooting angle of the camera is wider, or the camera is rotatable, images of all directions around the mowing robot can be acquired, so that the processor comprehensively analyzes the images, and the mowing robot can be controlled to rotate in which direction when the front obstacle is determined.
S5: determining a movement strategy of the robot according to a determination result of whether the front is obstructed;
wherein the obstacle comprises an actual obstacle and an active area boundary of the robot.
When the mowing robot moves in the GPS weak signal area, if no obstacle is detected in front of the mowing robot through the image, the mowing robot can continue to move forward according to the original route, if the front of the mowing robot is determined to have the obstacle or the mowing robot is about to leave the active area (namely, reach the boundary of the active area) according to the front image, at the moment, the mowing robot needs to be controlled according to specific conditions, and when the obstacle in front is smaller, the mowing robot can continue to move forward by bypassing the obstacle; when the front obstacle is large, the vehicle can bypass and return; when the front is the active area boundary, then a return is required.
Specifically, taking a case that an obstacle is large or the front is the boundary of the active area as an example, when detecting that the front is difficult to bypass by the mowing robot, the processor controls the mowing robot to turn around and return to the original direction according to the reverse direction of the original direction so as to enable the mowing robot to return to the GPS strong signal area. When the mowing robot turns around, the turning-around position of the mowing robot is recorded, so that the obstacle in front of the mowing robot can be accurately determined based on the position during subsequent operation. Further, referring to fig. 7, fig. 7 is a schematic diagram of a moving route of a robot provided in the present application, when the robot walks to an area B with weak GPS signals along a straight path 1A, the robot walks along an extended path 1B of the straight path 1A, when the robot turns around, the robot can rotate 90 degrees first, then move a small distance, then rotate 90 degrees to turn around, and then turn around along another path 1B1 parallel to the original path 1B, which is equivalent to making the robot walk an arcuate route, so that the robot can cut grass with a larger area in one round.
In addition, in order to facilitate charging of the mowing robot, a circle of circuit can be surrounded and electrified near the charging pile so as to generate a magnetic field near the charging pile, and the positive and negative of the magnetic field take the circle of circuit as a boundary, namely the polarity of the magnetic field inside the charging pile is different from the polarity of the magnetic field outside the charging pile, and when the mowing robot detects that the polarity of the magnetic field received by the mowing robot is changed, the mowing robot is closer to the charging pile. Furthermore, the position of the charging pile can be accurately positioned by guiding the mowing robot by adopting image recognition or arranging an electromagnetic track on the ground. Currently, in order to further ensure the safety of the mowing robot, please refer to fig. 3, fig. 3 is a flowchart of another mobile positioning method of the robot provided in the application, if a charging pile is near when the mowing robot leaves the GPS strong signal area, the mowing robot can also go to the charging pile to wait for the recovery of the GPS signal intensity.
In summary, when it is determined that the robot is out of the GPS strong signal area, determining a current moving direction of the robot by the inertial navigation device, controlling the robot to move along the current moving direction, acquiring a front image of the robot during the moving process of the robot, determining whether there is an obstacle in front of the robot according to the front image, and determining a moving strategy of the robot according to a determination result of whether there is an obstacle in front, wherein the GPS strong signal area is an area in which the robot can perform accurate electronic coordinate position location according to GPS signals of sufficient quality, and the obstacle includes an actual obstacle and an active area boundary of the robot. The mowing robot is controlled to keep the original direction to move continuously through inertial navigation, whether the front is blocked or not is identified through images, the robot can be controlled to move outside the GPS strong signal area, the robot can be prevented from leaving the active area, the practicability of the robot is improved, and potential safety hazards are avoided.
Based on the above embodiments:
as a preferred embodiment, determining the current movement direction of the robot by the inertial navigation device comprises:
determining a current acceleration direction, a current course angle and a current speed direction of the robot through an inertial navigation device;
and determining the current moving direction of the robot according to the current acceleration direction, the current course angle and the current speed direction.
In order to accurately determine the current moving direction of the mowing robot, in the application, an inertial navigation device is arranged in the mowing robot, and the inertial navigation device mainly comprises a gyroscope, a compass, a mileage device, a speed sensor and an acceleration sensor, wherein the heading angle of the mowing robot is determined through the rotation position of the gyroscope and the pointing direction of the compass, and the current moving direction of the mowing robot is determined by combining the acceleration direction detected by the acceleration sensor and the speed direction detected by the speed sensor. In practical application, the inertial navigation device is required to work all the time no matter in which area the mowing robot is located, and in the GPS strong signal area, the inertial navigation device not only can assist GPS signals to position the mowing robot, but also can enable the mowing robot to continue moving according to the moving direction finally determined by the inertial navigation device in time when the mowing robot leaves the GPS strong signal area. Based on this, the current moving direction of the mowing robot can be accurately determined.
As a preferred embodiment, judging whether there is an obstacle in front of the robot based on the front image includes:
extracting image features in the front image;
transmitting the image characteristics to a first preset neural network model so as to determine a grid matrix corresponding to the front image and obstacle correlation of each grid in the grid matrix, wherein the first preset neural network model is obtained by training a preset number of front images in advance;
masking the grid matrix to determine the grid scores of the grids in the grid matrix;
taking the average value of each grid score as the identification score of the front image;
judging whether the identification score is larger than a preset score;
if yes, judging that the vehicle is in disorder;
if not, judging that the fault exists;
wherein, the numerical value of the grid score and the obstacle correlation of the grid corresponding to the grid score are positively correlated.
In order to accurately judge whether an obstacle exists in front of the mowing robot or reaches the boundary of the active area, a neural network model is introduced to perform image recognition. Specifically, referring to fig. 9, fig. 9 is a schematic diagram of a front image captured by a robot provided in the present application, after the front image is obtained, the image is subjected to z-score normalization processing to obtain image features of the front image, the front image is divided into a plurality of grids as shown in fig. 9, the possibility of an obstacle in each grid is identified through the model, after the grid matrix of the front image is output by the model, a mask with a fixed shape is used as a sliding window on the grid matrix, so as to calculate the score of each grid, and the score is directly related to the possibility of whether the obstacle exists in the grids, such as that the score of 3 grids in the upper 1 row in fig. 9 is very high, and the scores of other grids are relatively low. Further, multiple grids may be linked to score together, with the score of one grid being very low if the grid itself and its surrounding other grids are grasslands (e.g., the image blocks of the bottom two rows in fig. 9), and relatively high if the grid itself is grasslands but there are obstacles in the surrounding other grids (e.g., the image blocks of the second row from top to bottom in fig. 9). And finally, calculating the average value of the scores of all the grids to serve as the identification score of the whole front image, if the identification score is larger than the preset score, indicating that the front of the mowing robot is obstructed, otherwise, indicating that no obstacle exists. In the neural network model, a two-classification method is adopted, one is that barriers exist, the other is that no barriers exist, the grass edges are classified into the barriers, it is understood that lawns are usually green and yellow, common barriers such as stones or trees are usually gray or brown, and areas outside the lawns such as sidewalks or walls are usually not green, so that whether the barriers exist can be judged based on colors. Further, it is possible to judge whether there is an obstacle according to the outline of the object in the image, in addition to the color. Based on this, it can be accurately determined whether there is an obstacle in front of the mowing robot or the moving area boundary is reached.
Referring to fig. 8, fig. 8 is a schematic structural diagram of a first preset neural network model of a robot provided by the present application, where the first preset neural network model may be a model composed of a Backbone network model backhaul and a classification header Classification head, between which a Neck layer for fusing features of different stages may be added, and for an actually used Backbone network model, a model such as ResNet, vggNet, googleNet may be used, a model based on a transducer such as ViT, swin transducer, mobile ViT, or a hybrid model combining a convolutional neural network and a transducer, such as DETR (DEtection Transformer, object detection).
In addition, in order to determine which side of the robot rotates to turn around when the robot encounters an obstacle, the front image may be divided into two images with the same size, and the two images may be input into the first preset neural network model together, so that the model processes the two images respectively, and finally the grid matrices of the two images are combined into a large grid matrix as the grid matrix of the front image. When it is determined that there is an obstacle in front of the robot, the robot rotates in a direction in which the score in the left and right images is low. For example, the left and right images may be output as two 3x3 grid matrices, respectively, and then spliced into a 6x3 large matrix, which is equivalent to uniformly dividing the entire front image into 18 small grids, each of which has its recognition result.
As a preferred embodiment, after determining that there is an obstacle, the method further comprises:
if the judging results of whether the front of the robot has the obstacle are all obstacle or not, sending the front image to a second preset neural network model so as to judge whether the acquired front image is an abnormal image or not, wherein the second preset neural network model is obtained by training a preset number of front images in advance; n is an integer not less than 2;
if the image is an abnormal image, a prompt signal is generated and sent to the prompt module, so that the prompt module sends out prompts.
In order to determine whether the camera is normal, in the application, the situation that the camera is damaged or shielded possibly occurs in practical application is considered, for example, a mowing robot splashes on the camera because of a smooth path in the running process, so that the camera is broken by the soil or shielded by the soil, and a processor mistakenly thinks that an obstacle exists in front of the mowing robot. Because the mowing robot can start turning when encountering an obstacle, the direction without the obstacle can be found as long as the mowing robot rotates by a certain angle under normal conditions, but when a camera is in a problem, the mowing robot can be considered to have the obstacle in front no matter how the mowing robot rotates. Based on this, when recognizing that there is an obstacle in front of the mowing robot through the camera, the method can also begin to record the time length for recognizing that there is an obstacle in front, if the mowing robot continues to detect that there is an obstacle in front for a period of time, the method necessarily indicates that the camera has a problem, at this time, the image shot by the camera is sent to a second preset neural network model, the quality score of the image shot by the camera is calculated, the quality score is in direct proportion to the definition degree of the image shot by the camera and the easy identification degree of the content of the image, if the quality score is higher, the image shot by the camera has no problem, and if the quality score is lower, the image shot by the camera may have the following conditions: the illumination intensity is low, so that the content of the image is difficult to identify; the damage of the camera causes that the camera can not focus, and the obtained image is blurred; the camera is stained with things, so that the camera is shielded. When the model outputs the result of low quality score of the image, a prompt signal is generated to prompt the user in time, and whether the camera is normal can be determined in this way.
In addition, for the second preset neural network model actually adopted, the second preset neural network model and the first preset neural network model can be the same model or any one of optional models thereof.
As a preferred embodiment, further comprising:
when a user instruction is received from a device communicated with the robot, controlling the robot to move according to the user instruction;
determining a moving route of the robot in the moving process of the robot, and storing the moving route on equipment in communication with the robot;
the area surrounded by the moving route is used as the moving range of the robot.
In order to conveniently determine the movable range of the mowing robot, in the application, when the mowing robot is put into use for the first time, or when a user wants to change the movable range of the mowing robot, the field size and the position needed to mow are different according to different requirements of different users, so that the areas which are the movable areas of the mowing robot need to be set according to the requirements of the users. Specifically, referring to fig. 6, fig. 6 is a schematic view of an activity area of another robot provided in the present application, a user may remotely control movement of the mowing robot through a device (for example, a handheld mobile device connected to the robot through wireless communication), the user controls the mowing robot to move in a desired direction, and the user himself/herself walks with the mowing robot while remotely controlling the robot with the handheld mobile device at the back. The mowing robot is enabled to move along the edge of the area required by the user for one circle through remote control of the user, the mowing robot maps coordinate points of the current position of the mowing robot to a coordinate system corresponding to the electronic map in real time while moving, a moving route of the mowing robot is formed through a plurality of continuous coordinate points, and in fig. 6, the moving route of the mowing robot is the edge of the moving area of the mowing robot. When the movable range of the mowing robot is determined, the mowing robot can start to work, that is, the functions and steps in the embodiment are executed, and the GPS strong signal area and the GPS weak signal area refer to the areas in the movable range of the mowing robot. Further, when determining the active area, the camera can be started, objects such as a reference object, an obstacle and the like in the active area and in the vicinity of the outside of the active area are identified through the camera, and the distance between the objects and the origin of the coordinate system is roughly calculated so as to determine the positions of the objects in advance. Based on this, according to the user instruction, the movable range of mowing robot is convenient to confirm.
As a preferred embodiment, determining a moving route of the robot includes:
when the robot moves in the GPS strong signal area, drawing a moving route of the robot on a preset electronic map by using A line segments;
when the robot moves outside the GPS strong signal area, B line segments are used for drawing a moving route of the robot on a preset electronic map;
after the area surrounded by the moving route is used as the moving range of the robot, the method further comprises:
and sending the preset electronic map containing the movable range to the user terminal so that the user can determine the actual position of the GPS strong signal area.
In order to make the user clearly know which part of the active area is the GPS weak signal area, in the application, when the user remotely controls the movement of the mowing robot to draw a moving route, the mowing robot needs to determine the positioning of the mowing robot so as to determine the coordinate point of the mowing robot on the coordinate system corresponding to the electronic map, so that the mowing robot also needs to acquire the GPS signal in real time when drawing the moving route. Referring to fig. 6, fig. 6 is a schematic diagram of an active area of another robot provided in the present application, when the mowing robot detects that the strength of the GPS signal acquired by the mowing robot is strong, a line segment of a type a is used for scribing, for example, a solid line is used for scribing, so as to indicate that an area around the line segment is a GPS strong signal area, and in fig. 6, EF, FA, and AB line segments are all solid line segments; in addition, the inertial navigation device is required to be driven by the mowing robot in real time to determine the moving direction of the mowing robot, when the mowing robot detects that the strength of the GPS signal acquired by the mowing robot is weak, the actual position of the mowing robot is required to be calculated through the actual speed and the speed direction detected by the inertial navigation device, so that the coordinates of the mowing robot on a coordinate system are determined, and when the strength of the GPS signal is weak, the mowing robot is required to be marked by line segments of B types, such as a dashed line, so as to indicate that the area around the line segment is a GPS weak signal area, and the BC, CD and DE line segments are all dashed line segments in fig. 6. Based on the above, the active area is divided by the line segments with different patterns, so that a user can clearly know which part of the active area is the GPS weak signal area.
As a preferred embodiment, after determining whether the robot is outside the GPS strong signal area, further comprising:
when the robot is judged to be in the GPS strong signal area and the robot is judged to be out of the GPS strong signal area at the last time, the position of the robot, which is positioned by the GPS signal at the last time, is taken as a boundary point of the GPS strong signal area;
determining boundary lines of the GPS strong signal area according to the plurality of boundary points;
and sending the preset electronic map containing the boundary line to the user terminal so that the user can determine the boundary line of the GPS strong signal area.
In order to enable a user to clearly know the boundary between the GPS strong signal area and the GPS weak signal area, in the application, when the mowing robot runs in real time, the electronic map is required to be updated in real time. Specifically, each time the mowing robot passes through two areas, that is, each time the mowing robot detects that the mowing robot leaves the area with the GPS strong signal or enters the area with the GPS strong signal, the coordinate of the mowing robot is marked on the electronic map to indicate that the mowing robot enters the area from one area to the other, please refer to fig. 7, fig. 7 is a schematic diagram of a moving route of the mowing robot, when the mowing robot moves in the area A, the moving route of the mowing robot is represented by a solid line because the GPS signal of the area is good, and similarly, when the mowing robot moves in the area B, the moving route is represented by a dotted line, and when the mowing robot is detected to leave the area A, that is, when the mowing robot enters the area 1B from the straight line path 1A, the intersection point between the areas 1A and 1B is marked, and similarly, when the mowing robot enters the area A along the straight line path 2B, the intersection point between the areas 2B and 2B is marked; combining the multiple intersection points marked by the mowing robot can obtain a dividing transverse line between the area A and the area B in the figure 7, wherein the transverse line is the boundary between the GPS strong signal area and the GPS weak signal area. It is to be understood that the actual movable range of the mowing robot in practical application has a relatively wide variety of shapes, and the strength of the GPS signal varies from place to place within the movable area, so fig. 7 is only an example of a straight line segment, and the movable range boundary line and the dividing line in practical application may have any shape.
When the mowing robot leaves the GPS strong signal area, the mowing robot can also receive an accurate GPS signal at the previous moment, so that the positioning of the GPS signal at the previous moment can be used as a mark on a coordinate system, or the coordinate position of the mowing robot at the moment when the mowing robot leaves the GPS strong signal area can be calculated according to the GPS signal at the previous moment and the current speed and the moving direction of the mowing robot, and the coordinate position is marked on the coordinate system; when the mowing robot enters the GPS strong signal area from the GPS weak signal area, the total moving distance of the mowing robot needs to be continuously recorded after the mowing robot leaves the GPS strong signal area last time, the actual position of the mowing robot needs to be calculated according to the last position of the mowing robot in the GPS weak signal area and the last position of the mowing robot leaving the GPS strong signal area last time in the GPS weak signal area in the moving process of the mowing robot in the GPS weak signal area, so that the moving distance of the mowing robot in the GPS weak signal area is determined, and on the basis of the moving distance, the moving direction is detected according to the last moving distance of the mowing robot in the GPS weak signal area when the mowing robot enters the GPS strong signal area from the GPS weak signal area, and the moving distance and the total moving distance are combined to determine which point of the mowing robot on a coordinate system enters the GPS strong signal area. Further, after entering the GPS strong signal area, the moving direction and speed of the mowing robot can be defined according to the moving direction and total distance and speed detected by the mowing robot in the GPS weak signal area last time.
In summary, as the mowing robot continuously runs, every time the mowing robot passes through two areas, the passing points of the mowing robot at the positions are marked in the coordinate system, adjacent passing points can be connected and mapped into the electronic map, and a user can clearly see the boundary between the GPS weak signal area and the GPS strong signal area.
Referring to fig. 10, fig. 10 is a schematic structural diagram of a mobile positioning device of a robot provided in the present application, including:
a memory 21 for storing a computer program;
a processor 22 for implementing the steps of the method for mobile positioning of a robot as described above when executing a computer program.
For a detailed description of the mobile positioning device of the robot provided in the present application, please refer to an embodiment of the mobile positioning method of the robot, and the detailed description is omitted herein.
The application also provides a robot, which comprises a robot body and a mobile positioning device of the robot;
the mobile positioning device of the robot is connected with the robot body.
The body of the mowing robot at least comprises a power supply, a moving part, a mowing part and a motor, other parts and the motor are powered by the power supply, the motor drives the moving part to act so as to enable the mowing robot to move actually, and the mowing part continuously works in the moving process to mow. The camera is arranged at a certain position on the front face of the movement direction of the mowing robot and is used for observing images of the advancing direction of the mowing robot. The inertial navigation device and the positioning device are arranged inside the mowing robot, the antenna is arranged at the top of the mowing robot, and the inertial navigation device and the positioning device are fixed on the mowing robot body relative to the gesture in the horizontal direction. The camera, the antenna and the inertial navigation device can all send the information acquired by the camera, the antenna and the inertial navigation device to the positioning device so that the camera, the antenna and the inertial navigation device can control the action of the mowing robot. The mowing robot works in a mode of combining GPS signals, inertial navigation and image recognition.
For detailed description of the functions of the mowing robot, please refer to the embodiment of the mobile positioning method of the robot, and the detailed description is omitted herein.
As a preferred embodiment, the camera is further included;
the camera is connected with the robot body and used for collecting images in front of the robot body.
The camera used in the application can be a common camera, a panoramic camera, a rotatable camera or an infrared camera, and the like, and the application is not limited to this, so long as the function of collecting images in the above embodiment can be realized and the collected images can enable the neural network model to clearly determine whether the front of the robot has a barrier or not.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Claims (10)
1. A method for mobile positioning of a robot, comprising:
when the GPS signal is weak and the robot cannot be accurately positioned by means of the GPS signal, determining the current moving direction of the robot through the inertial navigation device;
controlling the robot to move along the current moving direction;
acquiring a front image of the robot in the moving process of the robot;
judging whether an obstacle exists in front of the robot according to the front image;
determining a movement strategy of the robot according to a determination result of whether an obstacle exists in front;
wherein the obstacle comprises an actual obstacle and an active area boundary of the robot.
2. The method of mobile positioning of a robot according to claim 1, wherein determining a current direction of movement of the robot by an inertial navigation device comprises:
determining a current acceleration direction, a current course angle and a current speed direction of the robot through the inertial navigation device;
and determining the current moving direction of the robot according to the current acceleration direction, the current course angle and the current speed direction.
3. The method of moving and positioning a robot according to claim 1, wherein determining whether there is an obstacle in front of the robot based on the front image, comprises:
Extracting image features in the front image;
transmitting the image features to a first preset neural network model so as to determine a grid matrix corresponding to the front image and obstacle correlation of each grid in the grid matrix, wherein the first preset neural network model is obtained by training a preset number of front images in advance;
masking the grid matrix to determine the grid scores of all grids in the grid matrix;
taking the average value of each grid score as the identification score of the front image;
judging whether the identification score is larger than a preset score or not;
if yes, judging that the vehicle is in disorder;
if not, judging that the fault exists;
wherein, the numerical value of the grid score and the obstacle correlation of the grid corresponding to the grid score are positive correlations.
4. The method for moving and positioning a robot according to claim 3, further comprising, after determining that there is an obstacle:
if the judgment result of whether the front of the robot has the obstacle is continuous N times, sending the front image to a second preset neural network model so as to judge whether the acquired front image is an abnormal image, wherein the second preset neural network model is obtained by training a preset number of front images in advance; n is an integer not less than 2;
And if the abnormal image is the abnormal image, generating a prompt signal and sending the prompt signal to a prompt module so that the prompt module sends out prompt.
5. The mobile positioning method of a robot according to any one of claims 1 to 4, further comprising:
when a user instruction is received from a device communicated with the robot, controlling the robot to move according to the user instruction;
determining a moving route of the robot in the moving process of the robot, and storing the moving route on equipment communicated with the robot;
and taking the area surrounded by the moving route as the moving range of the robot.
6. The method of mobile positioning of a robot according to claim 5, wherein determining a movement route of the robot comprises:
when the robot moves in the GPS strong signal area, drawing a moving route of the robot on a preset electronic map by using A line segments;
when the robot moves outside the GPS strong signal area, B line segments are used for drawing a moving route of the robot on the preset electronic map;
after the area surrounded by the moving route is used as the moving range of the robot, the method further comprises:
And sending the preset electronic map containing the movable range to a user terminal so that a user can determine the actual position of the GPS strong signal area.
7. The method of mobile positioning of a robot according to claim 6, further comprising, after determining whether the robot is outside a GPS strong signal area:
when the robot was last determined to be within the GPS strong signal region and the robot was this time determined to be outside the GPS strong signal region,
or alternatively, the first and second heat exchangers may be,
when the robot is determined to be outside the GPS strong signal area the last time and the robot is determined to be inside the GPS strong signal area this time,
the position of the latest GPS signal positioning of the robot is used as a boundary point of the GPS strong signal area;
determining boundary lines of the GPS strong signal area according to a plurality of boundary points;
and sending the preset electronic map containing the boundary line to a user terminal so that a user can determine the boundary line of the GPS strong signal area.
8. A mobile positioning device for a robot, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for mobile positioning of a robot according to any of claims 1 to 7 when executing said computer program.
9. A robot comprising a robot body and further comprising a mobile positioning device of the robot of claim 8;
the mobile positioning device of the robot is connected with the robot body.
10. The robot of claim 9, further comprising a camera;
the camera is connected with the robot body and used for collecting images in front of the robot body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310467208.3A CN116466724A (en) | 2023-04-25 | 2023-04-25 | Mobile positioning method and device of robot and robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310467208.3A CN116466724A (en) | 2023-04-25 | 2023-04-25 | Mobile positioning method and device of robot and robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116466724A true CN116466724A (en) | 2023-07-21 |
Family
ID=87175196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310467208.3A Pending CN116466724A (en) | 2023-04-25 | 2023-04-25 | Mobile positioning method and device of robot and robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116466724A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116736868A (en) * | 2023-08-11 | 2023-09-12 | 松灵机器人(深圳)有限公司 | Robot movement control method, device, equipment and storage medium |
-
2023
- 2023-04-25 CN CN202310467208.3A patent/CN116466724A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116736868A (en) * | 2023-08-11 | 2023-09-12 | 松灵机器人(深圳)有限公司 | Robot movement control method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112584697A (en) | Autonomous machine navigation and training using vision system | |
| EP2169503B1 (en) | Multi-vehicle high intensity perception | |
| US20150163993A1 (en) | Autonomous gardening vehicle with camera | |
| CN107223261A (en) | Man-machine hybrid decision method and device | |
| CN113128747B (en) | Intelligent mowing system and autonomous image building method thereof | |
| CN111077890A (en) | Implementation method of agricultural robot based on GPS positioning and automatic obstacle avoidance | |
| CN116466724A (en) | Mobile positioning method and device of robot and robot | |
| US11882787B1 (en) | Automatic sensitivity adjustment for an autonomous mower | |
| CN114322980A (en) | Method for obtaining position coordinates and drawing electronic map, computer-readable storage medium, and autonomous operating apparatus | |
| WO2023055383A1 (en) | Vehicle row follow system | |
| CN116203606B (en) | RTK and vision fusion technology-based grass cutting robot navigation method and device | |
| CN114937258B (en) | Control method for mowing robot, and computer storage medium | |
| US20230069475A1 (en) | Autonomous machine navigation with object detection and 3d point cloud | |
| CN114545948A (en) | Mowing robot control method, chip and mowing robot | |
| JP2019185213A (en) | Autonomous movement robot and control method thereof | |
| WO2021139683A1 (en) | Self-moving device | |
| Andersen | Mobile robot navigation | |
| CN105922258B (en) | A kind of Omni-mobile manipulator autonomous navigation method based on iGPS | |
| Inoue et al. | Autonomous Navigation and Obstacle Avoidance in an Orchard Using Machine Vision Techniques for a Robotic Mower | |
| WO2023274339A1 (en) | Self-propelled working system | |
| US20230320263A1 (en) | Method for determining information, remote terminal, and mower | |
| CN109285202A (en) | Vehicle track method and system for planning | |
| CN116088533B (en) | Information determination method, remote terminal, device, mower and storage medium | |
| CN115741684B (en) | Control method and system for fire extinguishing robot in petroleum exploration area and electronic equipment | |
| CN114935929B (en) | Agricultural machinery informatization monitoring management system |
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 |