WO2019076005A1 - 太阳能面板清扫机器人的边缘定位装置及其定位方法 - Google Patents

太阳能面板清扫机器人的边缘定位装置及其定位方法 Download PDF

Info

Publication number
WO2019076005A1
WO2019076005A1 PCT/CN2018/081991 CN2018081991W WO2019076005A1 WO 2019076005 A1 WO2019076005 A1 WO 2019076005A1 CN 2018081991 W CN2018081991 W CN 2018081991W WO 2019076005 A1 WO2019076005 A1 WO 2019076005A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
solar panel
image
line
vehicle body
Prior art date
Application number
PCT/CN2018/081991
Other languages
English (en)
French (fr)
Inventor
汪志祥
徐建荣
徐斐
Original Assignee
苏州瑞得恩光能科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 苏州瑞得恩光能科技有限公司 filed Critical 苏州瑞得恩光能科技有限公司
Priority to JP2019558440A priority Critical patent/JP6995881B2/ja
Priority to US16/611,497 priority patent/US11014131B2/en
Publication of WO2019076005A1 publication Critical patent/WO2019076005A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B08—CLEANING
    • B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
    • B08B13/00—Accessories or details of general applicability for machines or apparatus for cleaning
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J11/00—Manipulators not otherwise provided for
    • B25J11/008—Manipulators for service tasks
    • B25J11/0085—Cleaning
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
    • B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
    • B25J9/1666—Avoiding collision or forbidden zones
    • 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
    • G05D1/0246—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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • G06V10/12—Details of acquisition arrangements; Constructional details thereof
    • G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
    • G06V10/141—Control of illumination
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10048—Infrared image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G06T2207/30256—Lane; Road marking
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/50—Photovoltaic [PV] energy

Definitions

  • the invention relates to the field of cleaning robots, in particular to an edge positioning device used by a solar panel cleaning robot and a positioning method thereof.
  • a solar panel is a device that converts solar energy directly into electrical energy using photovoltaics that occur under the illumination of semiconductor materials. Solar panels can generate electricity in places where there is sunlight, so solar panels are suitable for a variety of applications, from large power stations to small portable chargers.
  • the working environment of solar panels can only be outdoor, and the biggest problem affecting their work is not the wind and rain, but the dust accumulated all the year round. Dust or other attachments on the solar panel may affect the transmittance of the panel and impede the photoelectric efficiency, which will seriously affect the efficiency of the panel directly acquiring sunlight, reduce the energy absorption and conversion efficiency of the panel, and reduce the power generation efficiency.
  • the solar panel can only be manually and regularly cleaned up. Due to the large area of the solar panel and the large number of panels used by the large power station, the dust will accumulate repeatedly and need to be repeatedly cleaned; therefore, the labor cost is high. The cleaning efficiency is low and the cleaning effect is poor.
  • the solar panel has an edge position
  • the cleaning robot when the cleaning robot is in the edge position for cleaning, if it cannot find it in the edge position of the solar panel in time, it is likely to cause an accident due to the path planning problem. fall.
  • the solar panels are generally placed at a high place, if the cleaning robot falls off from it, it is likely to cause damage to the fuselage and cause a certain economic loss.
  • An object of the present invention is to provide an edge positioning device for a solar panel cleaning robot to solve the problem that the existing cleaning robot cannot be positioned at the edge of the solar panel in time.
  • the present invention provides an edge positioning device for a solar panel cleaning robot, wherein the solar panel cleaning robot includes a vehicle body that travels or resides on at least one solar panel.
  • the solar panel is rectangular, and has four border lines at its edges, and is provided with warp and weft lines perpendicular to each other, wherein the width of the border line is greater than the width of the warp and the weft.
  • the edge positioning device includes an image acquisition unit and an image recognition processing unit, wherein the image acquisition unit is disposed on the vehicle body for collecting surface image information of the solar panel on the vehicle body travel route, and The image information is transmitted to the image recognition processing unit.
  • the image recognition processing unit After receiving the surface image information of the solar panel, the image recognition processing unit collects target line information in the surface image information, and then compares the collected target line information with a preset data, and According to the comparison result of the two, it is judged whether the vehicle body is walking in the edge region of the solar panel in which it is located.
  • the surface image information of the solar panel includes line information of a warp, a weft, or a border line on the solar panel.
  • the collected target line information is line information in the image information, and then the collected line information is compared with a preset border line data, if the collected target line information is equal to or greater than The preset border line data is considered to have a border line in the image, thereby determining that the vehicle body is walking in an edge region of the solar panel.
  • the collected line information includes at least one of line width data or line area data
  • the preset border line data correspondingly includes border line width data or area. At least one of the data.
  • the image acquisition unit first sets effective four-point framing coordinates before performing image acquisition, and then collects surface image information of the solar panel within the four-point framing coordinate range. .
  • the image recognition processing unit after receiving the image transmitted by the image acquisition unit, the image recognition processing unit first converts the image into a black and white image, wherein the line graphic in the image is white.
  • the image recognition processing unit determines that the received border line is in the received image by using the width data or the area data of the continuous white line in the converted image. Width data or area data comparison in the border line data, if the width data of the collected line is equal to the width data in the preset border line data, or the collected area data is equal to or If the area data is larger than the preset border line data, the vehicle body is considered to be walking in the edge area of the solar panel.
  • the width data of the preset border line is 25 and the area data is 25 ⁇ 75
  • the related data of the collected white line is compared with one or two of the two data. Then, the judgment of the border line is performed according to the comparison result.
  • the image recognition processing unit determines that the vehicle body is walking in an edge region of the solar panel, and further calculates a side boundary of the collected solar panel surface image to the identification
  • the distance data of the border line is compared, and the calculated distance data is compared with a preset distance threshold. If the calculated distance data is greater than the preset distance threshold, an instruction indication is issued. Moving the vehicle body to the outside of the traveling route until the calculated distance length is equal to the distance threshold; and when the calculated distance data is less than the preset distance threshold, issuing an instruction to indicate the vehicle The body moves inside the walking route.
  • the manner of setting the distance ⁇ value of the collected side of the image to the border line may be various.
  • one of the distance values may be determined by the distance from the side of the collected image to the nearest side of the border line; or the distance threshold is The distance from the side of the captured image to the median line of the border line is determined; or the distance ⁇ value is the side of the collected image to the border line The distance from the far side is determined.
  • the edge positioning device further includes a light irradiation unit, and the light emitted by the light irradiation unit may appear in a surface image of the solar panel collected by the image acquisition unit.
  • the image recognition processing unit collects the length data of the illumination light in the received image information as target line information, and compares the length data of the illumination light with a stored preset length threshold data. And if the length data of the illumination light is less than the preset length threshold data, the vehicle body is considered to be walking in an edge region of the solar panel.
  • the light irradiation unit is preferably an infrared irradiation unit, but is not limited thereto.
  • an instruction is issued to indicate that the vehicle body is walking.
  • the vehicle body is further provided with a lighting unit for providing light illumination for the image collecting unit.
  • the lighting unit comprises an LED light.
  • the illumination unit is disposed behind the image acquisition unit.
  • the vehicle body includes a casing, and two sides of the vehicle body are provided with a walking device, the casing covers the walking device, and the image collecting unit collects The resulting image includes an image of the surface location of the solar panel between the housing and the travel device.
  • the image acquisition unit is disposed at a position between the traveling device and the housing.
  • the image acquisition unit includes a camera, and the lens of the camera is disposed in a direction toward the ground.
  • an edge positioning method for a solar panel cleaning robot including a panel image acquisition step and an image analysis step.
  • the solar panel in which the cleaning robot is located is rectangular, and has four border lines at its edges, and is provided with warp and weft lines perpendicular to each other, wherein the width of the border line is greater than the width of the warp and the weft in the same .
  • image capturing step surface image information of the solar panel on the traveling path of the cleaning robot body is acquired, and the surface image information is transmitted to the image recognition processing unit of the cleaning robot.
  • the image recognition processing unit After receiving the surface image information of the solar panel, the image recognition processing unit acquires target line information in the surface image information, and the target line information and a preset Comparing the data, and then judging whether the vehicle body is walking in the edge region of the solar panel in accordance with the comparison result of the two.
  • the collected surface image information of the solar panel includes line information of a warp, a weft or a border line on the solar panel.
  • the collected target line information is the line information in the collected surface image information, and then the collected line information is compared with the preset frame line data in the preset, if the collected target line information is If the frame line data is equal to or larger than the preset frame data, it is considered that there is a border line in the surface image, and then the vehicle body is determined to walk in an edge region of the solar panel.
  • the collected line information includes at least one of line width data or line area data
  • the preset border line data correspondingly includes border line width data or area. At least one of the data.
  • the collected surface image information of the solar panel includes an illumination light that is irradiated on the solar panel, the target line is the illumination light, and the length of the illumination light is extracted. Data, and then comparing the length data of the illumination light with a stored preset length threshold data. If the length data of the illumination light is less than the preset length threshold data, the vehicle body is considered to be The edge region of the solar panel walks.
  • an instruction is issued to instruct the vehicle body to travel to the route The external movement is until the detected length of the illumination light is equal to the length threshold; and when the detected illumination light length is less than the length threshold, an instruction is issued to indicate the internal movement of the vehicle body to the traveling path.
  • the invention has the advantages that the edge positioning device of the solar panel cleaning robot and the positioning method thereof are provided, and the width, area or length data of the line identified in the collected image information, and the preset border line data therein Or comparing the threshold value or the length threshold value, according to the comparison result, determining whether the cleaning robot is located at the edge position of the solar panel, so that the solar panel of the cleaning robot is effectively reduced. The risk of falling on, thus avoiding unnecessary property damage.
  • FIG. 1 is a schematic structural view of a cleaning robot according to an embodiment of the present invention, wherein a side portion of the vehicle body shown in the drawing is not shown with a housing portion thereof;
  • FIG. 2 is a schematic structural view of the cleaning robot shown in FIG. 1 at another angle;
  • FIG. 3 is a schematic view of the cleaning robot shown in FIG. 1 on a solar panel;
  • FIG. 4 is a schematic structural view of a cleaning robot according to still another embodiment of the present invention, which is disposed on a solar panel, and wherein a side portion of the vehicle body shown in the drawing is not illustrated with a casing portion thereof.
  • a component When a component is described as being “on” another component, the component can be placed directly on the other component; an intermediate component can also be present, the component being placed on the intermediate component, And the intermediate part is placed on another part.
  • a component When a component is described as “mounted to” or “connected to” another component, it can be understood as “directly” or “connected”, or a component is “mounted to” or “connected” through an intermediate component. To “another part.
  • the present invention provides an edge positioning device for a solar panel cleaning robot 100, wherein the solar panel cleaning robot 100 includes a vehicle body 10 that travels or resides on at least one solar panel 200.
  • the solar panel 200 is a rectangle having four border lines at its edges, and is provided with warp and weft lines perpendicular to each other, wherein the width of the border lines is greater than the width of the warp threads and the weft lines therein.
  • the edge locating device includes an image capturing unit 13 and an image recognition processing unit, wherein the image capturing unit 13 is disposed on the vehicle body 10 for collecting the solar panel 200 on the traveling path of the vehicle body 10. Surface image information, and the image information is transmitted to the image recognition processing unit.
  • the image recognition processing unit After receiving the surface image information of the solar panel, the image recognition processing unit collects target line information in the surface image information, and then compares the collected target line information with a preset data, and then According to the comparison result of the two, it is judged whether the vehicle body is walking in the edge region of the solar panel in which it is located.
  • the present invention correspondingly provides different technical solutions.
  • the target line in the surface image of the solar panel may be line information of the solar panel 200 itself, for example, a line of the border line 210.
  • the width of the border line 210 is larger than the width of the warp threads 211 and the weft threads 212, and the presence of the border line 210 indicates that the edge area of the solar panel is already present. Therefore, by collecting the lines of the border line 210 Information can be used to determine whether the vehicle body 10 is in the edge region of the solar panel 200 in which it is located.
  • the vehicle body 10 is traveling at an edge region of the solar panel 200 in which it is located by a change in the length of a line projected externally onto the solar panel 200.
  • the image collection unit 13 collects the The length of the illumination light included in the image information of the surface of the solar panel is also constant.
  • the length of the illumination light included in the image information of the surface of the solar panel collected by the image acquisition unit is correspondingly shortened, so that the vehicle body 10 can be judged. Whether it is in the edge area of the solar panel 200.
  • Embodiment 1 will be described with reference to FIGS. 1 to 3, and Embodiment 2 will be described with reference to FIG. 4.
  • the embodiment provides an edge positioning device for the solar panel cleaning robot 100.
  • the solar panel cleaning robot 100 includes a vehicle body 10 that travels or resides on at least one solar panel 200.
  • the solar panel 200 is rectangular, and has four border lines 210 at its edges, and is provided with warp threads 211 and weft lines 212 perpendicular to each other, wherein the width of the border lines 210 is larger than the warp threads 211 and the weft lines therein. The width of 212.
  • the edge locating device includes an image capturing unit 13 and an image recognition processing unit, wherein the image capturing unit 13 is disposed on the vehicle body 10 for collecting the solar panel 200 on the traveling path of the vehicle body 10.
  • Surface image information wherein the image information includes line information of the warp 211, the weft 212, or the border line 210 on the solar panel, and the collected image is sent to the image recognition processing unit.
  • the image acquisition unit 13 sets effective four-point view coordinates before performing image acquisition, and then collects image information within the four-point view coordinate range.
  • the image acquisition unit 13 may be a camera, but is not limited thereto.
  • the lens of the camera is disposed in a direction toward the ground, but is not limited thereto.
  • the lens of the camera may also be inclined at an angle, which may be determined as needed, without limitation.
  • the image recognition processing unit is preferably disposed on the vehicle body 10, but is not limited thereto. After receiving the surface image information of the solar panel, the image recognition processing unit collects the line information in the surface image information, and then compares the collected line information with a preset border line data. If the collected line information is equal to or larger than the preset border line data, it is considered that there is a border line in the image, and then the vehicle body 10 is determined to walk in an edge region of the solar panel 200.
  • the collected line information includes at least one of line width data or line area data
  • the preset border line data correspondingly includes border line width data or area. At least one of the data.
  • the image recognition processing unit first converts the image into a black and white color image, wherein the line graphic in the image is white.
  • the black and white image conversion method involved in use includes a two-position method, but is not limited thereto.
  • the image recognition processing unit determines that the received border line is in the received image by using the width data or the area data of the continuous white line in the converted image. Width data or area data comparison in the border line data, if the width data of the collected line is equal to the width data in the preset border line data, or the area data of the collected line If the area data in the preset border line data is equal to or greater than the preset, the vehicle body is considered to be walking at the edge of the solar panel.
  • the width data of the preset border line is 25 and the area data is 25 ⁇ 75
  • the related data of the collected white line is compared with one or two of the two data. Then, the judgment of the border line is performed according to the comparison result.
  • the side boundary of the image is further calculated to the identified a distance data of the frame, and comparing the calculated distance data with a preset distance threshold, and if the calculated distance data is greater than a preset distance threshold, an instruction is issued to indicate the car
  • the body 10 moves to the outside of the traveling route until the calculated distance length is equal to the distance threshold; and when the calculated distance data is smaller than the preset distance threshold, an instruction is issued to instruct the vehicle body 10 to The internal movement of the walking route.
  • the manner of setting the distance ⁇ of the collected side of the image to the border line 210 may be various. .
  • one of the distance ⁇ values may be determined by the distance from the side of the collected image to the nearest side of the border line 210; or the distance ⁇ value is Determining a distance from a side of the collected image to a median line of the border line 210; or, the distance threshold is a side of the collected image to the border The distance from the farthest side of line 210 is determined.
  • the vehicle body 10 includes a casing 11 on both sides of which a traveling device 12 is disposed, and the casing 11 covers the traveling device 12
  • the image collected by the image acquisition unit 13 includes the solar panel surface position image between the housing 11 and the traveling device 12.
  • the image pickup unit 13 is disposed at a position between the traveling device 12 and the casing 11.
  • a lighting unit 14 may be disposed on the vehicle body 10 to provide light illumination for the image capturing unit 13.
  • the illumination unit 14 may be disposed at the rear of the image acquisition unit 13 in the form of an LED lamp, but is not limited thereto.
  • the solar panel cleaning robot 100 includes a vehicle body 10 that travels or resides on at least one solar panel 200.
  • the edge locating device includes an infrared ray irradiation unit 15, an image acquisition unit 13, and an image recognition processing unit, wherein the infrared ray A emitted by the infrared ray irradiation unit 15 is irradiated on the solar panel 200 of the traveling path of the vehicle body 10 and has
  • the image acquisition unit 13 is configured to acquire a surface image of the solar panel 200 on the travel route of the vehicle body 10 and transmit the surface image to the image recognition processing unit of the edge positioning device.
  • the infrared rays irradiated on the surface of the solar panel 200 by the infrared ray irradiation unit 15 may appear in the surface image of the solar panel 200 collected by the image pickup unit 13.
  • the image acquisition unit 13 may be a camera, but is not limited thereto.
  • the lens of the camera is disposed in a direction toward the ground, but is not limited thereto.
  • the lens of the camera may also be inclined at an angle, which may be determined as needed, without limitation.
  • the image recognition processing unit is preferably disposed on the vehicle body 10, but is not limited thereto. After receiving the surface image information of the solar panel, the image recognition processing unit collects the length data of the infrared rays in the surface image information red, and compares the length data of the infrared rays with a stored preset length. The value data is compared. If the length data of the infrared rays is smaller than the preset length threshold data, the vehicle body 10 is considered to be traveling in an edge region of the solar panel 200.
  • the image recognition processing unit finds that the infrared length in the received image information is greater than the preset length threshold data, an instruction is issued to instruct the vehicle body 10 to move to the outside of the traveling route, so as to avoid The cleaning of the position of the opposite edge of the solar panel 200 is omitted until the detected infrared length is equal to the length threshold.
  • an instruction is issued to instruct the vehicle body 10 to move toward the inside of the traveling path to prevent falling from the edge of the solar panel 200 where it is located.
  • the vehicle body 10 includes a housing 11 , and two sides of the vehicle body 10 are provided with a traveling device 12 , and the housing 11 covers the traveling device 12 .
  • the image acquired by the image acquisition unit 13 includes a location of the solar panel surface between the housing 11 and the travel device 12.
  • the image pickup unit 13 is disposed at a position between the traveling device 12 and the casing 11.
  • the infrared ray irradiation unit 15 is disposed behind the image pickup unit 13 and obliquely illuminates the infrared ray toward the front at a certain angle.
  • a light unit 14 may be disposed on the vehicle body 10 to provide light illumination for the image capturing unit 13.
  • the lighting unit 14 may be disposed at the rear of the image collecting unit 13 in the form of an LED lamp, but is not limited thereto.
  • an edge positioning method for a solar panel cleaning robot 100 comprising a panel image acquisition step and an image analysis step.
  • the solar panel 200 in which the solar panel cleaning robot 100 is located is rectangular, and has four border lines at its edges, and is provided with warp and weft lines perpendicular to each other, wherein the width of the border line is larger than the warp and the Describe the width of the weft.
  • image capturing step surface image information of the solar panel on the traveling path of the cleaning robot body is collected and transmitted to the image recognition processing unit of the cleaning robot.
  • the image recognition processing unit After receiving the surface image information of the solar panel, the image recognition processing unit acquires target line information in the surface image information, and the target line information and a preset The data is compared, and then it is judged whether or not the vehicle body 10 is traveling in the edge region of the solar panel 200 in accordance with the comparison result of the two.
  • the collected surface image information of the solar panel 200 includes the line information of the warp 211, the weft 212, or the border line 210 on the solar panel 200.
  • the collected target line information is line information in the image information, and then the collected line information is compared with preset border line data, if the collected target line information is equal to or greater than When the preset border line data is described, it is considered that there is a border line in the image, and it is determined that the vehicle body 10 is walking in the edge region of the solar panel 200 where it is located.
  • the collected line information includes at least one of line width data or line area data
  • the preset border line data correspondingly includes border line width data or area. At least one of the data.
  • the collected surface image information of the solar panel includes an illumination light that is irradiated on the solar panel, the target line is the illumination light, and the illumination light is extracted. Length data, and then comparing the length data of the illumination light with a stored preset length threshold data, and if the length data of the illumination light is less than the preset length threshold data, the vehicle body is considered 10 walks in an edge region of the solar panel 200.
  • the illumination light is preferably infrared light, but is not limited thereto.
  • an instruction is issued to indicate that the vehicle body is walking.
  • the external movement of the route until the detected length of the illumination light is equal to the length threshold; and when the detected illumination light length is less than the length threshold, an instruction is issued to indicate the internal movement of the vehicle body to the traveling route .
  • the invention provides an edge positioning device for a solar panel cleaning robot and a positioning method thereof, which adopts the width, area or length data of the line identified in the collected image information, and the preset border line data or Is the distance ⁇ or the length ⁇ value compared, according to the comparison result, determining whether the cleaning robot is located at the edge position of the solar panel, so that the cleaning robot can be effectively reduced on the solar panel The risk of falling, thus avoiding unnecessary property damage.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Mechanical Engineering (AREA)
  • Robotics (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Electromagnetism (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Image Analysis (AREA)

Abstract

一种太阳能面板清扫机器人的边缘定位装置及其定位方法。太阳能面板清扫机器人包括车体（10）和边缘定位装置，车体在至少一太阳能面板（200）上行驶或驻留。边缘定位装置包括图像采集单元（13）和图像识别处理单元，其中图像采集单元设置在车体上，用于采集车体行走路线上的太阳能面板的表面图像信息。图像识别处理单元用于处理图像信息，进而判断车体是否在太阳能面板的边缘区域行走。

Description

太阳能面板清扫机器人的边缘定位装置及其定位方法 技术领域
本发明涉及清扫机器人领域，特别涉及一种太阳能面板清扫机器人使用的边缘定位装置及其定位方法。
背景技术
在化石燃料日趋减少的情况下，作为一种新兴的可再生能源的太阳能已成为人类使用能源的重要组成部分，近十年来，太阳能应用技术在世界各国都得到迅猛发展。太阳能面板是指利用半导体材料在光照条件下发生的光生伏特效应(photovoltaic)将太阳能直接转换为电能的器件。有太阳光的地方就能发电，因此太阳能面板适用于从大型发电站到小型便携式充电器等多种场合，近年来得到飞速发展。
太阳能面板的工作环境只能是户外，影响其工作的最大问题并不是风雨雷电，而是常年累积的灰尘。太阳能面板上附着有灰尘或其它附着物，会影响面板板的透光率，阻碍光电效率，从而会严重影响面板直接获取阳光的效率，降低面板的能量吸收和转换效率，降低发电效率。现有技术的太阳能面板在使用中只能依靠人工定期完成清理工作，由于太阳能面板面积较大、大型电站同时使用的面板较多，而灰尘会反复累积，需要反复清洗；因此人力成本很高、清理效率低、清理效果较差。在很多场合，为了提高空间利用率，太阳能面板都是利用支架设置在高处，这就给清理工作带来更大的难度和风险。很多太阳能面板的用户为了降低清理成本只能选择不清理，这样只能被迫承担灰尘导致的电能损耗。这样，就需要有一个新的自动清理设备，对太阳能面板能够进行 自动清理。
对此，业界开发出了一种新型的清扫机器人来进行太阳能面板的清洁，具体可参看中国专利申请201610836028.8号所揭示的相关内容。但随着这种清扫机器人在实际中的不断使用，业界也发现其需要进行新型功能的研发，来克服实际遇到的各种问题，
例如，由于太阳能面板都是存在边缘位置，而当所述清扫机器人处于边缘位置进行清扫时，若是其自身不能及时发现其处于太阳能面板的边缘位置，则很可能会出现因路径规划问题而导致意外跌落。由于太阳能面板一般都是设置在高处，若是所述清扫机器人从其上跌落下来，则很可能会使得其机身损坏，造成一定的经济损失。
因此，确有必要来开发一种新型的太阳能面板清扫机器人的边缘定位装置，来克服现有技术中的缺陷。
发明内容
本发明的一个目的在于，提供一种太阳能面板清扫机器人的边缘定位装置，以解决现有清扫机器人不能及时在太阳能面板边缘处进行定位的问题。
为解决上述问题，本发明提供一种太阳能面板清扫机器人的边缘定位装置，其中所述太阳能面板清扫机器人包括车体，所述车体在至少一太阳能面板上行驶或驻留。所述太阳能面板为矩形，其边缘处设有四条边框线，其内设有彼此垂直的经线及纬线，其中所述边框线的宽度大于其内所述经线及所述纬线的宽度。所述边缘定位装置包括图像采集单元和图像识别处理单元，其中所述图像采集单元设置在所述车体上，用于采集所述车体行走路线上的太阳能面板的表面图像信息，并将所述图像信息发送给所述图像识别处理单元。所述图像 识别处理单元在接收到所述太阳能面板的表面图像信息后，采集所述表面图像信息中的目标线条信息，然后将采集到的所述目标线条信息与一预设的数据比较，并根据两者的比较结果判断所述车体是否在所在太阳能面板的边缘区域行走。
进一步的，在不同实施方式中，所述太阳能面板的表面图像信息包括太阳能面板上的经线、纬线或是边框线的线条信息。所述采集到的目标线条信息为所述图像信息中的线条信息，然后将采集到的所述线条信息与一预设的边框线数据比较，若是采集到的所述目标线条信息等于或是大于所述预设的边框线数据，则认为所述图像中存在边框线，进而判断所述车体在所在太阳能面板的边缘区域行走。
进一步的，在不同实施方式中，所述采集到的线条信息包括线条宽度数据或是线条面积数据中的至少一种，所述预设的边框线数据相应地也包括边框线宽度数据或是面积数据中的至少一种。
进一步的，在不同实施方式中，所述图像采集单元在进行图像采集前，会先设置出有效的四点取景坐标，然后在所述四点取景坐标范围内采集所述太阳能面板的表面图像信息。
进一步的，在不同实施方式中，所述图像识别处理单元在接收到由所述图像采集单元传送的图像后，将其先变换为黑白两色图像，其中所述图像中的线条图形为白色。
进一步的，在不同实施方式中，所述图像识别处理单元判断收到的所述图像中存在边框线条的方式是将转换后的所述图像中的连续白色线条的宽度数据或是面积数据与预设的所述边框线数据中的宽度数据或是面积数据比对， 若是采集到的线条的宽度数据与预设的所述边框线数据中的宽度数据相等，或者，采集到的面积数据等于或是大于预设的所述边框线数据中的面积数据，则认为所述车体在所在太阳能面板的边缘区域行走。
例如，所述预设的边框线的宽度数据是25、面积数据是25X75，则以此为基础将采集到的白色线条的相关数据与这两个数据中的一个或是两个进行比对，然后根据比对结果进行所述边框线的判断。以上列出的数值仅为举例性说明，并无任何限制。
进一步的，在不同实施方式中，所述图像识别处理单元判断出所述车体在所在太阳能面板的边缘区域行走后，进一步计算所述采集到的太阳能面板表面图像的侧边边界到所述识别出的边框线的距离数据，并将所述计算出的距离数据与一预设的距离阙值进行比较，若是计算出的距离数据大于所述预设的距离阙值时，则会发出指令指示所述车体向所在行走路线的外部移动，直到计算出的距离长度等于所述距离阙值；而当计算出的距离数据小于所述预设的距离阙值时，则发出指令指示所述车体向所在行走路线的内部移动。
进一步的，在不同实施方式中，由于所述边框线具有一定的宽度，因此，采集到的所述图像的侧边到所述边框线的距离阙值的设定方式，可以有多种。例如，其中一种可以是，所述距离阙值是以所述采集到的所述图像的侧边到所述边框线最近侧边的距离所确定；或者，所述距离阙值是以所述采集到的所述图像的侧边到所述边框线的中位线的距离所确定；又或者，所述距离阙值是以所述采集到的所述图像的侧边到所述边框线最远侧边的距离所确定。
进一步的，在不同实施方式中，所述边缘定位装置还包括一光线照射单元，所述光线照射单元照射出的光线会出现在所述图像采集单元采集到的所述 太阳能面板的表面图像中。所述图像识别处理单元采集收到的所述图像信息中的所述照射光线的长度数据作为目标线条信息，并将所述照射光线的长度数据与一存储的预设长度阙值数据进行比对，若是所述照射光线的长度数据小于所述预设长度阙值数据，则认为所述车体在所述太阳能面板的边缘区域行走。所述光线照射单元，优选为红外线照射单元，但不限于此。
进一步的，在不同实施方式中，当所述图像识别处理单元发现收到的图像中的所述照射光线长度大于所述预设长度阙值数据时，则发出指令指示所述车体向所在行走路线的外部移动，直到检测到的所述照射光线长度等于所述长度阙值；而当检测到的所述照射光线长度小于所述长度阙值时，则发出指令指示所述车体向所在行走路线的内部移动。
进一步的，在不同实施方式中，所述车体上还设置有照明单元，为所述图像采集单元提供光线照明。
进一步的，在不同实施方式中，所述照明单元包括LED灯。
进一步的，在不同实施方式中，所述照明单元设置在所述图像采集单元的后方。
进一步的，在不同实施方式中，所述车体包括一壳体，所述车体的两侧设置有行走装置，所述壳体将所述行走装置罩设于内，所述图像采集单元采集到的图像包括位于所述壳体与所述行走装置之间的所述太阳能面板的表面位置图像。
进一步的，在不同实施方式中，所述图像采集单元设置在所述行走装置和壳体之间的位置处。
进一步的，在不同实施方式中，所述图像采集单元包括摄像头，所述摄 像头的镜头是以朝向地面的方向设置。
进一步的，本发明的又一实施方式中，提供了一种太阳能面板清扫机器人的边缘定位方法，包括一面板图像采集步骤以及一图像分析步骤。所述清扫机器人所在的太阳能面板为矩形，其边缘处设有四条边框线，其内设有彼此垂直的经线及纬线，其中所述边框线的宽度大于其内所述经线及所述纬线的宽度。在所述图像采集步骤中，采集所述清扫机器人车体行走路线上的太阳能面板的表面图像信息，并将所述表面图像信息发送给所述清扫机器人的图像识别处理单元。在所述图像分析步骤中，所述图像识别处理单元在接收到所述太阳能面板的表面图像信息后，采集所述表面图像信息中的目标线条信息，并将所述目标线条信息与一预设的数据比较，然后根据两者的比较结果判断所述车体是否在所在太阳能面板的边缘区域行走。
进一步的，在不同实施方式中，采集到的所述太阳能面板的表面图像信息包括太阳能面板上的经线、纬线或是边框线的线条信息。所述采集到的目标线条信息为采集到的所述表面图像信息中的线条信息，然后将采集到的所述线条信息与其内预设的边框线数据比较，若是采集到的所述目标线条信息等于或是大于所述预设的边框线数据，则认为所述表面图像中存在边框线，进而判断所述车体在所在太阳能面板的边缘区域行走。
进一步的，在不同实施方式中，所述采集到的线条信息包括线条宽度数据或是线条面积数据中的至少一种，所述预设的边框线数据相应的也是包括边框线宽度数据或是面积数据中的至少一种。
进一步的，在不同实施方式中，采集到的所述太阳能面板的表面图像信息包括照射在所述太阳能面板上的一条照射光线，所述目标线条为所述照射光 线，并提取该照射光线的长度数据，然后将所述照射光线的长度数据与一存储的预设长度阙值数据进行比对，若是所述照射光线的长度数据小于所述预设长度阙值数据，则认为所述车体在所述太阳能面板的边缘区域行走。
进一步的，在不同实施方式中，当所述图像识别处理单元发现收到的图像中的照射光线长度大于所述预设长度阙值数据时，则会发出指令指示所述车体向所在行走路线的外部移动，直到检测到的照射光线长度等于所述长度阙值；而当检测到的照射光线长度小于所述长度阙值时，则发出指令指示所述车体向所在行走路线的内部移动。
本发明优点在于，提供一种太阳能面板清扫机器人的边缘定位装置及其定位方法，通过对采集到的图像信息中识别出的线条的宽度、面积或是长度数据，与其内预设的边框线数据或是距离阙值或是长度阙值相比对，根据比对结果，确定所述清扫机器人是否处在所处太阳能面板的边缘位置，如此，可有效的降低所述清扫机器人在所处太阳能面板上的跌落风险，从而避免不必要的财产损失。
附图说明
图1为本发明实施例中清扫机器人的结构示意图，其中图中所示车体的侧部未图示其壳体部分；
图2为图1所示的清扫机器人另一角度下的结构示意图；
图3为图1所示的清扫机器人在太阳能面板上的示意图；
图4为本发明又一实施例中清扫机器人的的结构示意图，其处在一太阳能面板上，且其中图中所示车体的侧部未图示其壳体部分。
图中部件编号如下：
太阳能面板清扫机器人100，太阳能面板200，边框线210，经线211，纬线212；车体10，壳体11，行走装置12，图像采集单元13，照明单元14，红外线照射单元15。
具体实施方式
以下参考说明书附图介绍本发明的优选实施例，证明本发明可以实施，所述实施例可以向本领域中的技术人员完整介绍本发明，使其技术内容更加清楚和便于理解。本发明可以通过许多不同形式的实施例来得以体现，本发明的保护范围并非仅限于文中提到的实施例。
在附图中，结构相同的部件以相同数字标号表示，各处结构或功能相似的组件以相似数字标号表示。附图所示的每一部件的尺寸和厚度是任意示出的，本发明并没有限定每个组件的尺寸和厚度。为了使图示更清晰，附图中有些地方适当夸大了部件的厚度。
本发明所提到的方向用语，例如「上」、「下」、「前」、「后」、「左」、「右」、「内」、「外」、「侧面」等，仅是附图中的方向，只是用来解释和说明本发明，而不是用来限定本发明的保护范围。
当某些部件被描述为“在”另一部件“上”时，所述部件可以直接置于所述另一部件上；也可以存在一中间部件，所述部件置于所述中间部件上，且所述中间部件置于另一部件上。当一个部件被描述为“安装至”或“连接至”另一部件时，二者可以理解为直接“安装”或“连接”，或者一个部件通过一中间部件间接“安装至”、或“连接至”另一个部件。
本发明提供一种太阳能面板清扫机器人100的边缘定位装置，其中所述太阳能面板清扫机器人100包括一车体10，所述车体10在至少一太阳能面板 200上行驶或驻留。所述太阳能面板200为一矩形，其边缘处设有四条边框线，其内设有彼此垂直的经线及纬线，其中所述边框线的宽度大于其内所述经线及所述纬线的宽度。所述边缘定位装置包括一图像采集单元13和一图像识别处理单元，其中所述图像采集单元13设置在所述车体10上，用于采集所述车体10行走路线上的太阳能面板200的表面图像信息，并将所述图像信息发送给所述图像识别处理单元。所述图像识别处理单元在接收到所述太阳能面板的表面图像信息后，采集所述表面图像信息中的目标线条信息，然后将采集到的所述目标线条信息与一预设的数据比较，然后根据两者的比对结果判断所述车体是否在所在太阳能面板的边缘区域行走。
进一步的，对于所述采集到的所述太阳能面板的表面图像信息中的目标线条而言，可以是有不同的类型，根据这些不同类型的线条，本发明相应提供不同的技术方案。
具体来讲，所述太阳能面板表面图像中的目标线条，既可以是太阳能面板200上本身就具有的线条信息，例如，边框线210线条。所述边框线210的宽度比经线211及纬线212的宽度大，同时由于所述边框线210的存在即可表明此处已处于太阳能面板的边缘区域，因此，通过采集所述边框线210的线条信息，即可来判断所述车体10是否处在所在太阳能面板200的边缘区域。
又或者，通过外部投射到所述太阳能面板200上的线条的长度变化来判断所述车体10是否在所处太阳能面板200的边缘区域行走。具体来讲，当所述车体10在所在太阳能面板200上正常行走时，外部照射到所在太阳能面板200上的光线的长度是一定的，相应的，所述图像采集单元13采集到的所述太阳能面板表面的图像信息中包括的所述照射光线的长度也是一定的。而当所述 车体10在所在太阳能面板200的边缘处行走时，所述外部照射光线，因为所述车体10位于所在太阳能面板200的边缘区域，因此，部分照射光线可能已落在所在太阳能面板200之外，相应的，所述图像采集单元采集到的所述太阳能面板表面的图像信息中包括的所述照射光线的长度也会相应的缩短，如此，即可来判断所述车体10是否处在所在太阳能面板200的边缘区域。
进一步的，以下将结合附图和具体实施例，对上述这两种通过采集所在太阳能面板的表面图像信息包括的不同线条信息，可实现相同的处于所在太阳能面板边缘区域行走的判断结果，所采用的具体技术方案做进一步的详细说明。其中实施例一将结合附图1～3进行说明，实施例二将结合附图4进行说明。
实施例一
如图1、2及3所示，本实施例提供了一种太阳能面板清扫机器人100的边缘定位装置。所述太阳能面板清扫机器人100包括一车体10，所述车体10在至少一太阳能面板200上行驶或驻留。
所述太阳能面板200为矩形，其边缘处设有四条边框线210，其内设有彼此垂直的经线211及纬线212，其中所述边框线210的宽度大于其内所述经线211及所述纬线212的宽度。
所述边缘定位装置包括一图像采集单元13和一图像识别处理单元，其中所述图像采集单元13设置在所述车体10上，用于采集所述车体10行走路线上的太阳能面板200的表面图像信息，其中所述图像信息包括太阳能面板上的所述经线211、纬线212或是边框线210的线条信息，并将采集到的所述图像发送给所述图像识别处理单元。
进一步的，所述图像采集单元13在进行图像采集前，先设置出有效的四 点取景坐标，然后在所述四点取景坐标范围内采集图像信息。所述图像采集单元13可以是一摄像头，但不限于此。在一个具体实施方式中，所述摄像头的镜头是以朝向地面的方向设置，但不限于此。在其他实施方式中，所述摄像头的镜头也可以是以一定角度倾斜设置，具体可随需要而定，并无限制。
所述图像识别处理单元优选设置在所述车体10上，但不限于此。所述图像识别处理单元在接收到所述太阳能面板的表面图像信息后，采集所述表面图像信息中的所述线条信息，然后将采集到的所述线条信息与一预设的边框线数据比较，若是采集到的所述线条信息等于或是大于所述预设的边框线数据，则认为所述图像中存在边框线条，进而判断所述车体10在所在太阳能面板200的边缘区域行走。
进一步的，在不同实施方式中，所述采集到的线条信息包括线条宽度数据或是线条面积数据中的至少一种，所述预设的边框线数据相应的也是包括边框线宽度数据或是面积数据中的至少一种。
进一步的，所述图像识别处理单元在接收到由所述图像采集单元13传送的图像后，将所述图像先变换为黑白两色图像，其中所述图像中的线条图形为白色。涉及使用的黑白图像转化方法包括二位法，但不限于此。
进一步的，在不同实施方式中，所述图像识别处理单元判断收到的所述图像中存在边框线条的方式是将转换后的所述图像中的连续白色线条的宽度数据或是面积数据与预设的所述边框线数据中的宽度数据或是面积数据比对，若是采集到的线条的宽度数据与预设的所述边框线数据中的宽度数据相等，或者，采集到的线条的面积数据等于或是大于预设的所述边框线数据中的面积数据，则认为所述车体在所在太阳能面板的边缘处行走。
例如，所述预设的边框线的宽度数据是25、面积数据是25X75，则以此为基础将采集到的白色线条的相关数据与这两个数据中的一个或是两个进行比对，然后根据比对结果进行所述边框线的判断。以上列出的数值仅为举例性说明，并无任何限制。
进一步的，在不同实施方式中，所述述图像识别处理单元在判断出所述车体10在所在太阳能面板200的边缘处行走后，进一步计算所述图像的侧边边界到所述识别出的边框的距离数据，并将所述计算出的距离数据与一预设的距离阙值进行比较，若是计算出的距离数据大于其内预设的距离阙值时，则会发出指令指示所述车体10向所在行走路线的外部移动，直到计算出的距离长度等于所述距离阙值；而当计算出的距离数据小于所述预设距离阙值时，则发出指令指示所述车体10向所在行走路线的内部移动。
进一步的，在不同实施方式中，由于所述边框线210具有一定的宽度，因此，采集到的所述图像的侧边到所述边框线210的距离阙值的设定方式，可以有多种。例如，其中一种可以是，所述距离阙值是以所述采集到的所述图像的侧边到所述边框线210最近侧边的距离所确定；或者，所述距离阙值是以所述采集到的所述图像的侧边到所述边框线210的中位线的距离所确定；又或者，所述距离阙值是以所述采集到的所述图像的侧边到所述边框线210最远侧边的距离所确定。
进一步的，在一个优选实施方式中，所述车体10包括一壳体11，所述车体10的两侧设置有行走装置12，所述壳体11将所述行走装置12罩设于内，所述图像采集单元13采集到的图像包括位于所述壳体11与所述行走装置12之间的所述太阳能面板表面位置图像。或者可以说，其中所述图像采集单元13 设置在所述行走装置12和壳体11之间的位置处。
进一步的，为了保证所述图像采集单元13采集到的图像信息的清晰度，所述车体10上还可设置有一照明单元14，以为所述图像采集单元13提供光线照明。具体的，所述照明单元14可以是设置在所述图像采集单元13的后方，采用LED灯的形式，但不限于此。
实施例二
请参阅图4所示，本实施方式中提供了一种太阳能面板清扫机器人100的边缘定位装置。所述太阳能面板清扫机器人100包括一车体10，所述车体10在至少一太阳能面板200上行驶或驻留。
所述边缘定位装置包括一红外线照射单元15、一图像采集单元13和图像识别处理单元，其中所述红外线照射单元15发出的红外线A照射在所述车体10行进路线的太阳能面板200上并且具有一定的长度，所述图像采集单元13用于采集所述车体10行进路线上的太阳能面板200的表面图像并将所述表面图像发送给所述边缘定位装置的所述图像识别处理单元。所述红外线照射单元15照射在所述太阳能面板200表面上的红外线会出现在所述图像采集单元13的采集到的所述太阳能面板200的表面图像中。
所述图像采集单元13可以是一摄像头，但不限于此。在一个具体实施方式中，所述摄像头的镜头是以朝向地面的方向设置，但不限于此。在其他实施方式中，所述摄像头的镜头也可以是以一定角度倾斜设置，具体可随需要而定，并无限制。
所述图像识别处理单元优选设置在所述车体10上，但不限于此。所述图像识别处理单元在接收到所述太阳能面板的表面图像信息后，在所述表面图像 信息红采集所述红外线的长度数据，并将所述红外线的长度数据与一存储的预设长度阙值数据进行比对，若是所述红外线的长度数据小于所述预设长度阙值数据，则认为所述车体10在所述太阳能面板200的边缘区域行走。
进一步的，当所述图像识别处理单元发现收到的图像信息中的红外线长度大于所述预设长度阙值数据时，则会发出指令指示所述车体10向所在行走路线的外部移动，以免遗漏对所处太阳能面板200相对边缘的位置的清扫，直到检测到的红外线长度等于所述长度阙值。而当检测到的红外线长度小于所述长度阙值时，则发出指令指示所述车体10向所在行走路线的内部移动，以免从所处太阳能面板200的边缘掉落。
进一步的，在一个优选实施方式中，所述车体10包括壳体11，所述车体10的两侧设置有行走装置12，所述壳体11将所述行走装置12罩设于内，所述图像采集单元13采集到的图像包括位于所述壳体11与所述行走装置12之间的所述太阳能面板表面的位置。或者可以说，其中所述图像采集单元13设置在所述行走装置12和壳体11之间的位置处。所述红外线照射单元15设置在所述图像采集单元13的后方，并以一定角度向前方倾斜照射红外线。
进一步的，为了保证所述图像采集单元13采集到的图像信息的清晰度，其中所述车体10上还可设置有一照明单元14，为所述图像采集单元13提供光线照明。具体的，其中所述照明单元14可以是设置在所述图像采集单元13的后方，采用LED灯的形式，但不限于此。
进一步的，本发明的又一实施方式中，提供了一种太阳能面板清扫机器人100的边缘定位方法，所述方法包括一面板图像采集步骤以及一图像分析步骤。所述太阳能面板清扫机器人100所在的太阳能面板200为矩形，其边缘处 设有四条边框线，其内设有彼此垂直的经线及纬线，其中所述边框线的宽度大于其内所述经线及所述纬线的宽度。在所述图像采集步骤中，采集所述清扫机器人车体行走路线上的太阳能面板的表面图像信息，并将其发送给所述清扫机器人的图像识别处理单元。在所述图像分析步骤中，所述图像识别处理单元在接收到所述太阳能面板的表面图像信息后，采集所述表面图像信息中的目标线条信息，并将所述目标线条信息与一预设的数据比较，然后根据两者的比较结果判断所述车体10是否在所在太阳能面板200的边缘区域行走。
进一步的，在不同实施方式中，采集到的所述太阳能面板200的表面图像信息包括太阳能面板200上的经线211、纬线212或是边框线210的线条信息。所述采集到的目标线条信息为所述图像信息中的线条信息，然后将采集到的所述线条信息与预设的边框线数据比较，若是采集到的所述目标线条信息等于或是大于所述预设的边框线数据，则认为所述图像中存在边框线条，进而判断所述车体10在所在太阳能面板200的边缘区域行走。
进一步的，在不同实施方式中，所述采集到的线条信息包括线条宽度数据或是线条面积数据中的至少一种，所述预设的边框线数据相应的也是包括边框线宽度数据或是面积数据中的至少一种。
进一步的，在不同实施方式中，采集到的所述太阳能面板的表面图像信息包括照射在所述太阳能面板上的一条照射光线，所述目标线条为所述照射光线，并提取所述照射光线的长度数据，然后将所述照射光线的长度数据与一存储的预设长度阙值数据进行比对，若是所述照射光线的长度数据小于所述预设长度阙值数据，则认为所述车体10在所述太阳能面板200的边缘区域行走。其中所述照射光线优选为红外线照射光线，但不限于此。
进一步的，在不同实施方式中，当所述图像识别处理单元发现收到的图像中的照射光线长度大于其内预设的长度阙值数据时，则会发出指令指示所述车体向所在行走路线的外部移动，直到检测到的照射光线长度等于所述长度阙值；而当检测到的照射光线长度小于所述长度阙值时，则发出指令指示所述车体向所在行走路线的内部移动。
本发明提供的一种太阳能面板清扫机器人的边缘定位装置及其定位方法，其通过对采集到的图像信息中识别出的线条的宽度、面积或是长度数据，与其内预设的边框线数据或是距离阙值或是长度阙值相比对，根据比对结果，确定所述清扫机器人是否处在所处太阳能面板的边缘位置，如此，可有效的降低所述清扫机器人在所处太阳能面板上的跌落风险，从而避免不必要的财产损失。
以上所述仅是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员，在不脱离本发明原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。

Claims (18)

  1. 一种太阳能面板清扫机器人的边缘定位装置，其中所述太阳能面板清扫机器人包括一车体，所述车体在至少一太阳能面板上行驶或驻留；所述太阳能面板为矩形，其边缘处设有四条边框线，其内设有彼此垂直的经线及纬线，其中所述边框线的宽度大于其内所述经线及所述纬线的宽度；其中，
    所述边缘定位装置包括一图像采集单元和一图像识别处理单元，其中所述图像采集单元设置在所述车体上，用于采集所述车体行走路线上的太阳能面板的表面图像信息，并将所述图像信息发送给所述图像识别处理单元；
    所述图像识别处理单元在接收到所述太阳能面板的表面图像信息后，采集所述图像信息中的目标线条信息，然后将采集到的所述目标线条信息与一预设的数据比较，并根据比较结果判断所述车体是否在所在太阳能面板的边缘区域行走。
  2. 如权利要求1所述的边缘定位装置，其中所述太阳能面板的表面图像信息包括太阳能面板上的经线、纬线或是边框线的线条信息；所述目标线条信息为所述图像信息中的线条信息，然后将采集到的所述线条信息与一预设的边框线数据比较，若是采集到的所述目标线条信息等于或是大于所述预设的边框线数据，则认为所述图像中存在边框线，进而判断所述车体在所在太阳能面板的边缘区域行走。
  3. 如权利要求2所述的边缘定位装置，其中所述采集到的线条信息包括线条宽度数据或是线条面积数据中的至少一种，所述预设的边框线数据相应的也包括边框线宽度数据或是面积数据中的至少一种。
  4. 如权利要求1所述的边缘定位装置，其中所述图像采集单元在进行图像采集前，先设置出有效的四点取景坐标，然后在所述四点取景坐标范围内采集所述太阳能面板的表面图像信息。
  5. 如权利要求2所述的边缘定位装置，其中所述图像识别处理单元在接收到由所述图像采集单元传送的图像后，将所述图像先变换为黑白两色图像，其中所述图像中的线条图形为白色。
  6. 如权利要求5所述的边缘定位装置，其中所述图像识别处理单元判断收到的所述图像中存在边框线条的方式是，将转换后的所述图像中的连续白色线条的宽度数据或是面积数据与预设的所述边框线数据中的宽度数据或是面积数据比对，若是采集到的线条的宽度数据与预设的所述边框线数据中的宽度数据相等，或者，线条的面积数据等于或是大于预设的所述边框线数据中的面积数据，则认为所述车体在所在太阳能面板的边缘区域行走。
  7. 如权利要求2所述的边缘定位装置，其中所述图像识别处理单元在判断出所述车体在所在太阳能面板的边缘区域行走后，进一步计算所述采集到的太阳能面板表面图像的侧边边界到所述识别出的边框线的距离数据，并将所述计算出的距离数据与其内预设的距离阙值进行比较，若是计算出的距离数据大于其内预设的距离阙值时，则会发出指令指示所述车体向所在行走路线的外部移动，直到计算出的距离长度等于所述距离阙值；而当计算出的距离数据小于所述预设距离阙值时，则发出指令指示所述车体向所在行走路线的内部移动。
  8. 如权利要求1所述的边缘定位装置，还包括一光线照射单元，所述光线照射单元照射出的光线出现在所述图像采集单元采集到的所述太阳能面板的表面图像中；所述图像识别处理单元采集收到的所述图像信息中的所述照射光线的长度数据为目标线条信息，并将所述所述照射光线的长度数据与一存储的预设长度阙值数据进行比对，若是所述照射光线的长度数据小于所述预设长度阙值数据，则认为所述车体在所述太阳能面板的边缘区域行走。
  9. 如权利要求8所述的边缘定位装置，其中当所述图像识别处理单元发现收到的图像中的所述照射光线长度大于所述预设长度阙值数据时，则会发出指令指示所述车体向所在行走路线的外部移动，直到检测到的所述照射光线长度等于所述预设长度阙值数据；而当检测到的所述照射光线长度小于所述预设长度阙值数据时，则发出指令指示所述车体向所在行走路线的内部移动。
  10. 如权利要求1所述的边缘定位装置，其中所述车体上还设置有一照明单元，为所述图像采集单元提供光线照明。
  11. 如权利要求1所述的边缘定位装置，其中所述车体包括一壳体，所述车 体的两侧设置有行走装置，所述壳体将所述行走装置罩设于内，所述图像采集单元采集到的图像包括位于所述壳体与所述行走装置之间的所述太阳能面板的表面位置图像。
  12. 如权利要求11所述的边缘定位装置，其中所述图像采集单元设置在所述行走装置和壳体之间的位置处。
  13. 如权利要求1所述的边缘定位装置，其中所述图像采集单元包括摄像头，所述摄像头的镜头是以朝向地面的方向设置。
  14. 一种太阳能面板清扫机器人的边缘定位方法，其中所述清扫机器人所在的太阳能面板为矩形，其边缘处设有四条边框线，其内设有彼此垂直的经线及纬线，其中所述边框线的宽度大于其内所述经线及所述纬线的宽度；所述边缘定位方法包括一面板图像采集步骤以及一图像分析步骤；
    在所述图像采集步骤中，采集所述清扫机器人车体行走路线上的太阳能面板的表面图像信息，并将所述表面图像信息发送给所述清扫机器人的图像识别处理单元；
    在所述图像分析步骤中，所述图像识别处理单元在接收到所述太阳能面板的表面图像信息后，采集所述表面图像信息中的目标线条信息，并将目标线条信息与一预设的数据比较，然后根据两者的比较结果判断所述车体是否在所在太阳能面板的边缘区域行走。
  15. 如权利要求14所述的边缘定位方法，其中采集到的所述太阳能面板的表面图像信息包括所述太阳能面板上的经线、纬线或是边框线的线条信息；所述采集到的目标线条信息为所述图像信息中的线条信息，然后将采集到的所述线条信息与其内预设的边框线数据比较，若是采集到的所述目标线条信息等于或是大于所述预设的边框线数据，则认为采集到的所述表面图像中存在边框线，进而判断所述车体在所在太阳能面板的边缘区域行走。
  16. 如权利要求15所述的边缘定位方法，其中所述采集到的线条信息包括线条宽度数据或是线条面积数据中的至少一种，所述预设的边框线数据相应的也是包括边框线宽度数据或是面积数据中的至少一种。
  17. 如权利要求14所述的边缘定位方法，其中采集到的所述太阳能面板的表面图像信息包括照射在所述太阳能面板上的一条照射光线，所述目标线条为所述照射光线，并提取所述照射光线的长度数据，然后将所述照射光线的长度数据与一存储的预设长度阙值数据进行比对，若是所述照射光线的长度数据小于所述预设长度阙值数据，则认为所述车体在所述太阳能面板的边缘区域行走。
  18. 如权利要求17所述的边缘定位方法，其中当所述图像识别处理单元发现收到的所述表面图像中的照射光线长度大于所述预设长度阙值数据时，则会发出指令指示所述车体向所在行走路线的外部移动，直到检测到的照射光线长度等于所述长度阙值数据；而当检测到的照射光线长度小于所述预设长度阙值时，则发出指令指示所述车体向所在行走路线的内部移动。
PCT/CN2018/081991 2017-10-20 2018-04-04 太阳能面板清扫机器人的边缘定位装置及其定位方法 WO2019076005A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2019558440A JP6995881B2 (ja) 2017-10-20 2018-04-04 太陽光パネル清掃ロボットの辺縁測位装置及びその測位方法
US16/611,497 US11014131B2 (en) 2017-10-20 2018-04-04 Edge positioning apparatus for solar panel cleaning robot, and positioning method thereof

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710981171.0A CN107553497B (zh) 2017-10-20 2017-10-20 太阳能面板清扫机器人的边缘定位装置及其定位方法
CN201710981171.0 2017-10-20

Publications (1)

Publication Number Publication Date
WO2019076005A1 true WO2019076005A1 (zh) 2019-04-25

Family

ID=60986843

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/081991 WO2019076005A1 (zh) 2017-10-20 2018-04-04 太阳能面板清扫机器人的边缘定位装置及其定位方法

Country Status (4)

Country Link
US (1) US11014131B2 (zh)
JP (1) JP6995881B2 (zh)
CN (1) CN107553497B (zh)
WO (1) WO2019076005A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110882967A (zh) * 2019-11-22 2020-03-17 深圳怪虫机器人有限公司 一种连续作业的光伏清洁机器人
CN110882969A (zh) * 2019-11-22 2020-03-17 深圳怪虫机器人有限公司 一种沿桥面自动行走的光伏清洁机器人
CN111687858A (zh) * 2020-06-20 2020-09-22 深圳怪虫机器人有限公司 一种具有检测光伏面板底纹类型的光伏清洁机器人

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107553497B (zh) 2017-10-20 2023-12-22 苏州瑞得恩光能科技有限公司 太阳能面板清扫机器人的边缘定位装置及其定位方法
US11638939B2 (en) * 2018-11-27 2023-05-02 Steam Tech, Llc Mobile panel cleaner
USD1010257S1 (en) * 2019-02-27 2024-01-02 Suzhou Radiant Photovoltaic Technology Co., Ltd Robot cleaner
USD938114S1 (en) * 2019-03-22 2021-12-07 Sungrow Power Supply Co., Ltd. Intelligent cleaning robot
CN110212856B (zh) * 2019-06-06 2020-11-24 深圳怪虫机器人有限公司 一种光伏机器人跨缝作业的方法
CN110180851B (zh) * 2019-06-06 2020-11-03 深圳怪虫机器人有限公司 一种跨障红外快门及跨障光伏清洁机器人
CN110162061B (zh) * 2019-06-06 2022-06-24 深圳怪虫机器人有限公司 一种光伏清洁机器人直线清洁路径的方法
CN110882968A (zh) * 2019-11-22 2020-03-17 深圳怪虫机器人有限公司 一种光伏清洁机器人
CN110882970B (zh) * 2019-11-22 2024-09-13 深圳怪虫机器人有限公司 一种具有光伏板检测组件的光伏清洁机器人
USD974679S1 (en) * 2019-12-25 2023-01-03 Zhejiang Weibin 3d Technology Co., Ltd. Cleaning machine
CN112381852A (zh) * 2020-11-11 2021-02-19 苏州瑞得恩光能科技有限公司 清洁机器人的定位方法及存储介质
CN113198765B (zh) * 2021-05-03 2024-06-07 深圳怪虫机器人有限公司 一种可自动返航以及续航的光伏清洁机器人
CN113305858B (zh) * 2021-06-07 2022-05-03 仲恺农业工程学院 一种清除原水管道中贝类的视觉机器人方法及其装置
CN114104131B (zh) * 2021-12-30 2022-12-27 苏州瑞得恩光能科技有限公司 履带和履带式行进装置
US11833677B2 (en) 2022-04-20 2023-12-05 Inventus Holdings Llc Semi-autonomous exoskeleton apparatus for solar panel installation
CN114942635A (zh) 2022-04-30 2022-08-26 苏州瑞得恩光能科技有限公司 一种机器人及其直线行进控制方法、数据处理设备
CN118123848B (zh) * 2024-05-08 2024-06-28 广东汇博机器人技术有限公司 一种可远程控制的光伏清洁机器人

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102773862A (zh) * 2012-07-31 2012-11-14 山东大学 用于室内移动机器人的快速精确定位系统及其工作方法
WO2015076593A1 (en) * 2013-11-20 2015-05-28 Samsung Electronics Co., Ltd. Cleaning robot and method for controlling the same
KR20160033615A (ko) * 2014-09-16 2016-03-28 성균관대학교산학협력단 태양광 패널용 세척 로봇 및 이를 이용한 태양광 패널의 세척방법
WO2017118973A1 (en) * 2016-01-05 2017-07-13 Evermore United S.A. Solar panel cleaning system capable of cleaning a plurality of solar arrays
CN107553497A (zh) * 2017-10-20 2018-01-09 苏州瑞得恩光能科技有限公司 太阳能面板清扫机器人的边缘定位装置及其定位方法

Family Cites Families (48)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4128562B2 (ja) * 2004-11-30 2008-07-30 本田技研工業株式会社 車両周辺監視装置
CN101566471B (zh) * 2007-01-18 2011-08-31 上海交通大学 基于地面纹理的智能车视觉全局定位方法
JP5178276B2 (ja) * 2008-03-27 2013-04-10 ダイハツ工業株式会社 画像認識装置
JP2010282393A (ja) 2009-06-04 2010-12-16 Panasonic Corp 移動装置
US9020636B2 (en) * 2010-12-16 2015-04-28 Saied Tadayon Robot for solar farms
US9931009B2 (en) * 2012-12-25 2018-04-03 Miraikikai, Inc. Autonomous-travel cleaning robot
WO2014129941A1 (en) * 2013-02-20 2014-08-28 Husqvarna Ab A robotic work tool configured for improved turning in a slope, a robotic work tool system, and a method for use in the robot work tool.
JP6132659B2 (ja) 2013-02-27 2017-05-24 シャープ株式会社 周囲環境認識装置、それを用いた自律移動システムおよび周囲環境認識方法
WO2014173290A1 (zh) * 2013-04-22 2014-10-30 苏州宝时得电动工具有限公司 自动行走设备及其工作区域判断方法
CN104111651A (zh) * 2013-04-22 2014-10-22 苏州宝时得电动工具有限公司 自动行走设备及其向停靠站回归的方法
JP2015013281A (ja) 2013-06-03 2015-01-22 シンフォニアテクノロジー株式会社 ソーラーパネル清掃装置
JP6299231B2 (ja) 2014-01-22 2018-03-28 シンフォニアテクノロジー株式会社 ソーラーパネル清掃装置
JP6179346B2 (ja) * 2013-10-24 2017-08-16 シンフォニアテクノロジー株式会社 ソーラーパネル清掃装置
JP2015138854A (ja) 2014-01-22 2015-07-30 シンフォニアテクノロジー株式会社 ソーラーパネル清掃装置およびソーラーパネル清掃装置の洗浄方法
CN104914857A (zh) * 2014-03-10 2015-09-16 宝时得机械(中国)有限公司 智能边界柱
CN103984037B (zh) * 2014-04-30 2017-07-28 深圳市墨克瑞光电子研究院 基于视觉的移动机器人障碍物检测方法和装置
KR101776620B1 (ko) * 2014-06-17 2017-09-11 주식회사 유진로봇 검색 기반 상관 매칭을 이용하여 이동 로봇의 위치를 인식하기 위한 장치 및 그 방법
WO2015194868A1 (ko) * 2014-06-17 2015-12-23 (주)유진로봇 광각 카메라가 탑재된 이동 로봇의 주행을 제어하기 위한 장치 및 그 방법
WO2015194867A1 (ko) * 2014-06-17 2015-12-23 (주)유진로봇 다이렉트 트래킹을 이용하여 이동 로봇의 위치를 인식하기 위한 장치 및 그 방법
KR101776621B1 (ko) * 2014-06-17 2017-09-11 주식회사 유진로봇 에지 기반 재조정을 이용하여 이동 로봇의 위치를 인식하기 위한 장치 및 그 방법
JP6404348B2 (ja) * 2014-06-25 2018-10-17 株式会社未来機械 自走式ロボット
WO2016000622A1 (zh) * 2014-07-02 2016-01-07 苏州宝时得电动工具有限公司 自动行走设备
JP6826804B2 (ja) 2014-08-29 2021-02-10 東芝ライフスタイル株式会社 自律走行体
GB201419883D0 (en) * 2014-11-07 2014-12-24 F Robotics Acquisitions Ltd Domestic robotic system and method
US9704043B2 (en) * 2014-12-16 2017-07-11 Irobot Corporation Systems and methods for capturing images and annotating the captured images with information
CN105785986A (zh) * 2014-12-23 2016-07-20 苏州宝时得电动工具有限公司 自动工作设备
CN105512377B (zh) * 2015-11-30 2017-12-12 腾讯科技（深圳）有限公司 实时虚拟场景中圆柱碰撞体与凸体碰撞探测的方法和系统
CN106934813A (zh) * 2015-12-31 2017-07-07 沈阳高精数控智能技术股份有限公司 一种基于视觉定位的工业机器人工件抓取实现方法
CN105881555B (zh) * 2016-06-17 2019-03-19 南京仁义机器人有限公司 基于风机直接除尘的光伏电站清扫机器人及其工作方法
US10118292B2 (en) * 2016-08-18 2018-11-06 Saudi Arabian Oil Company Systems and methods for configuring field devices using a configuration device
CN106272420B (zh) * 2016-08-30 2019-07-02 北京小米移动软件有限公司 机器人及机器人控制方法
CN106238369B (zh) * 2016-09-21 2018-08-28 苏州瑞得恩光能科技有限公司 液体分发容器及清扫机器人
CN106325276B (zh) * 2016-09-21 2019-06-25 苏州瑞得恩光能科技有限公司 机器人在斜坡平面上直线行驶的判定方法及控制方法
CN106269624B (zh) 2016-09-21 2019-03-08 苏州瑞得恩光能科技有限公司 太阳能面板清扫机器人
CN106182015A (zh) * 2016-09-21 2016-12-07 苏州瑞得恩自动化设备科技有限公司 太阳能面板清扫机器人控制系统
CN108481320B (zh) * 2017-01-09 2020-03-27 广东宝乐机器人股份有限公司 一种机器人的移动控制方法及机器人
CN106774346B (zh) * 2017-02-10 2023-11-24 苏州瑞得恩光能科技有限公司 用于太阳能面板清扫机器人的定位装置及其定位方法
KR102017148B1 (ko) * 2017-03-03 2019-09-02 엘지전자 주식회사 장애물을 학습하는 인공지능 이동 로봇 및 그 제어방법
US10583561B2 (en) * 2017-08-31 2020-03-10 Neato Robotics, Inc. Robotic virtual boundaries
WO2019096264A1 (zh) * 2017-11-16 2019-05-23 南京德朔实业有限公司 智能割草系统
KR102479492B1 (ko) * 2018-01-08 2022-12-20 삼성전자주식회사 차량 주변의 이미지를 제공하는 전자 장치 및 방법
US11141863B2 (en) * 2018-10-11 2021-10-12 Pixart Imaging Inc. Cleaning robot capable of detecting 2D depth information and operating method thereof
TWI676090B (zh) * 2018-10-19 2019-11-01 廣達電腦股份有限公司 用於多個機器人之移動控制方法以及其系統
EP3907575B1 (en) * 2019-01-03 2023-09-06 Ecovacs Robotics Co., Ltd. Dynamic region division and region channel identification method, and cleaning robot
WO2019172733A2 (ko) * 2019-05-08 2019-09-12 엘지전자 주식회사 감지대상체와 상호작용이 가능한 이동로봇 및 이동로봇과 감지대상체의 상호작용 방법
KR20190100085A (ko) * 2019-08-05 2019-08-28 엘지전자 주식회사 인공 지능을 이용하여, 위험 상황을 감지할 수 있는 로봇 및 그의 동작 방법
KR20190104937A (ko) * 2019-08-22 2019-09-11 엘지전자 주식회사 주행 금지 구역을 회피할 수 있는 이동로봇 및 이동로봇의 주행 금지 구역 회피 방법
CN111012254A (zh) * 2019-12-30 2020-04-17 北京太坦科技有限公司 智能扫地机器人

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102773862A (zh) * 2012-07-31 2012-11-14 山东大学 用于室内移动机器人的快速精确定位系统及其工作方法
WO2015076593A1 (en) * 2013-11-20 2015-05-28 Samsung Electronics Co., Ltd. Cleaning robot and method for controlling the same
KR20160033615A (ko) * 2014-09-16 2016-03-28 성균관대학교산학협력단 태양광 패널용 세척 로봇 및 이를 이용한 태양광 패널의 세척방법
WO2017118973A1 (en) * 2016-01-05 2017-07-13 Evermore United S.A. Solar panel cleaning system capable of cleaning a plurality of solar arrays
CN107553497A (zh) * 2017-10-20 2018-01-09 苏州瑞得恩光能科技有限公司 太阳能面板清扫机器人的边缘定位装置及其定位方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110882967A (zh) * 2019-11-22 2020-03-17 深圳怪虫机器人有限公司 一种连续作业的光伏清洁机器人
CN110882969A (zh) * 2019-11-22 2020-03-17 深圳怪虫机器人有限公司 一种沿桥面自动行走的光伏清洁机器人
CN111687858A (zh) * 2020-06-20 2020-09-22 深圳怪虫机器人有限公司 一种具有检测光伏面板底纹类型的光伏清洁机器人

Also Published As

Publication number Publication date
CN107553497B (zh) 2023-12-22
CN107553497A (zh) 2018-01-09
JP2020518072A (ja) 2020-06-18
US20200238348A1 (en) 2020-07-30
JP6995881B2 (ja) 2022-01-17
US11014131B2 (en) 2021-05-25

Similar Documents

Publication Publication Date Title
WO2019076005A1 (zh) 太阳能面板清扫机器人的边缘定位装置及其定位方法
WO2019076004A1 (zh) 太阳能面板清扫机器人直行判定装置及其判定方法
JP6860180B2 (ja) 太陽光パネル清掃ロボットの測位装置及びその測位方法
CN109878552B (zh) 基于机器视觉的轨道交通站台门与列车间异物监测装置
CN106873587B (zh) 用于太阳能面板清扫机器人的导航系统及其导航方法
CN106952260A (zh) 一种基于cis图像采集的太阳能电池片缺陷检测系统和方法
CN104165653B (zh) 用于采集轴承滚动体端面和倒角图像的装置及其采集方法
CN111687859A (zh) 一种光伏清洁机器人获取最优作业路径的方法
CN106018409A (zh) 一种机场跑道异物和裂纹的识别系统及其检测识别方法
CN109911205B (zh) 一种桥墩检测无人机装置及检测方法
CN206541195U (zh) 用于太阳能面板清扫机器人的导航系统
KR20080004376A (ko) 태양 에너지 계통 관리 시스템
CN206489451U (zh) 用于太阳能面板清扫机器人的定位装置
KR101530979B1 (ko) 태양광 추적 센서 유닛
CN115051647B (zh) 一种免拆卸光伏电池隐裂检测系统
CN203535655U (zh) 一种用于采集煤岩图像的装置
CN114915258A (zh) 光伏电站多机协同智慧清洗系统
CN209280592U (zh) 一种用于纺织品疵点检测的图像采集系统
CN210123967U (zh) 一种基于环境气象因素的热斑监测装置
CN114914843A (zh) 一种输电线路漂浮异物自动识别瞄准算法及激光远程清除系统
CN206974385U (zh) 一种太阳能硅片视觉检测装置
CN211669123U (zh) 热斑成像检测设备
CN111390975A (zh) 具有摘风管功能的巡检智能机器人及其巡检方法
CN218829854U (zh) 一种分布式光伏电站组件电致发光检测系统
CN217132999U (zh) 一种光学检测仪

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18868107

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019558440

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18868107

Country of ref document: EP

Kind code of ref document: A1