WO2020042426A1 - 机器人检测直边的方法和清洁机器人筛选参考墙边的方法 - Google Patents

机器人检测直边的方法和清洁机器人筛选参考墙边的方法 Download PDF

Info

Publication number
WO2020042426A1
WO2020042426A1 PCT/CN2018/120247 CN2018120247W WO2020042426A1 WO 2020042426 A1 WO2020042426 A1 WO 2020042426A1 CN 2018120247 W CN2018120247 W CN 2018120247W WO 2020042426 A1 WO2020042426 A1 WO 2020042426A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
straight
edge
straight line
slope
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.)
Ceased
Application number
PCT/CN2018/120247
Other languages
English (en)
French (fr)
Inventor
赖钦伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhuhai Amicro Semiconductor Co Ltd
Original Assignee
Zhuhai Amicro Semiconductor Co Ltd
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 Zhuhai Amicro Semiconductor Co Ltd filed Critical Zhuhai Amicro Semiconductor Co Ltd
Priority to US17/264,310 priority Critical patent/US11977390B2/en
Priority to EP18931950.2A priority patent/EP3845989B1/en
Publication of WO2020042426A1 publication Critical patent/WO2020042426A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
    • G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/481—Constructional features, e.g. arrangements of optical elements
    • G01S7/4817—Constructional features, e.g. arrangements of optical elements relating to scanning
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • 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
    • 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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
    • 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
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • 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
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/242—Means based on the reflection of waves generated by the vehicle
    • 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
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/243—Means capturing signals occurring naturally from the environment, e.g. ambient optical, acoustic, gravitational or magnetic signals
    • 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
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/247—Arrangements for determining position or orientation using signals provided by artificial sources external to the vehicle, e.g. navigation beacons
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G01S17/08—Systems determining position data of a target for measuring distance only
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G01S17/46—Indirect determination of position data
    • G01S17/48—Active triangulation systems, i.e. using the transmission and reflection of electromagnetic waves other than radio waves
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2105/00—Specific applications of the controlled vehicles
    • G05D2105/10—Specific applications of the controlled vehicles for cleaning, vacuuming or polishing
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2109/00—Types of controlled vehicles
    • G05D2109/10—Land vehicles
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2111/00—Details of signals used for control of position, course, altitude or attitude of land, water, air or space vehicles
    • G05D2111/10—Optical signals
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2111/00—Details of signals used for control of position, course, altitude or attitude of land, water, air or space vehicles
    • G05D2111/10—Optical signals
    • G05D2111/14—Non-visible signals, e.g. IR or UV signals
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2111/00—Details of signals used for control of position, course, altitude or attitude of land, water, air or space vehicles
    • G05D2111/50—Internal signals, i.e. from sensors located in the vehicle, e.g. from compasses or angular sensors
    • G05D2111/52—Internal signals, i.e. from sensors located in the vehicle, e.g. from compasses or angular sensors generated by inertial navigation means, e.g. gyroscopes or accelerometers

Definitions

  • the invention relates to the technical field of intelligent robots, in particular to a method for detecting straight edges by a robot and a method for cleaning a reference wall edge by a cleaning robot.
  • Measuring the direction of the wall has a more important role for many robots, such as cleaning robots. After measuring the direction of the wall, the robot can walk parallel to the wall or perpendicular to the wall. The direction of walking is consistent with the terrain. Efficient.
  • the automatic cruise robot can plan its own path by measuring the obstacle information on the wall; the robot with the planned cleaning can measure the direction of the wall and can be used for the auxiliary positioning of the robot.
  • Measuring the wall surface is currently more commonly obtained by walking along the edge of the robot, or by rotating the laser. The former has a large error and takes a long time, and the latter has a high cost.
  • the laser head is generally on the upper surface of the machine. If the object is not detected, it still needs the machine's edge behavior to assist.
  • the invention provides a method for detecting a straight edge by a robot and a method for cleaning a reference wall edge by a cleaning robot, which can accurately detect the straight edges around the robot, and provide an effective reference for the robot to use the straight edges for subsequent operations.
  • the specific technical solutions described in the present invention are as follows:
  • a method for detecting a straight edge by a robot includes the following steps: the robot rotates in place and determines the position coordinates of each detection point according to the distance value detected by its distance sensor and the angle value detected by the angle sensor; based on each of the detections Position coordinates of the point, to determine whether the slope of a straight line formed by two adjacent detection points is within a preset error range, and if so, determine the edge corresponding to the detection point on a straight line with a slope within the preset error range It is a straight edge. If not, it is determined that the edge corresponding to the detection point on a straight line whose slope is not within a preset error range is not a straight edge.
  • i represents a natural number greater than or equal to 1.
  • the preset error value is r. Further, when the robot rotates in place, each time a preset angle value is rotated, the preset time is stopped, and the distance value is detected by the distance sensor multiple times within the preset time, and then the average value is taken as the robot to The distance value corresponding to the detection point.
  • the preset angle value is less than or equal to 30 °.
  • the method further includes the following step: using a least square method to straighten the slope whose slope is within the preset error range Calculation is performed on the detection points on the top to calculate an optimal straight line, and it is determined that the edge corresponding to the optimal straight line is the detected straight edge.
  • the robot before performing the in-situ rotation, the robot further includes the following steps: the robot walks a preset distance in a direction away from the obstacle, stops, and then performs the in-situ rotation.
  • the method further includes the following step: selecting the longest length among the determined straight edges as a reference. side.
  • the method further includes the step of analyzing an image captured by a vision sensor of the robot during rotation. , Analyze the straight edge in the image; use the straight edge corresponding to the detection point on the straight line with the slope corresponding to the longest straight edge in the image within the preset error range as the reference edge.
  • a method for a cleaning robot to screen a reference wall includes the following steps: Step 1: The cleaning robot rotates in place and determines the position coordinates of each detection point according to the distance value detected by its distance sensor and the angle value detected by the angle sensor. , And then enter step two; step two: based on the position coordinates of each of the detection points, determine whether the slope of a straight line formed by two adjacent detection points is within a preset error range, and if so, determine that the slope is within a predetermined range. Set the edge corresponding to the detection point on a straight line within the error range to be a straight edge, and go to step 3.
  • step 3 Analyze the image captured by the robot's vision sensor during the rotation process, analyze the straight edges in the image, and then proceed to step 4;
  • step 4 Set the slope of the longest straight edge in the image to the preset The straight edge corresponding to the detection point on the straight line within the error range is used as the reference wall edge.
  • the method for detecting straight edges by the robot determines the position coordinates of each detection point according to the distance value detected by the distance sensor and the angle value detected by the angle sensor, and then the slope of the straight line formed by two adjacent detection points is used to determine The final straight edge is determined, the detection accuracy and accuracy are high, and the robot does not need to determine the straight edge situation through the edge behavior, and the work efficiency is greatly improved.
  • the method for screening a reference wall edge by the cleaning robot after the straight edge is determined in the same manner, the straight edge is compared with the straight edge in the image captured by the vision sensor, and the longest straight edge is selected as a reference.
  • the wall edge provides accurate and effective reference for subsequent robots to perform positioning along the reference wall edge.
  • FIG. 1 is a schematic flowchart of a method for detecting straight edges by a robot according to the present invention.
  • FIG. 2 is a schematic diagram illustrating the analysis of a straight edge detected by a robot according to the present invention.
  • circuits may be shown in block diagrams to avoid obscuring the embodiments in unnecessary detail.
  • well-known circuits, structures, and techniques may not be shown in detail so as not to obscure the embodiments.
  • a method for detecting straight edges by a robot may be a mobile robot for industrial use, a home service robot, or other intelligent mobile equipment.
  • the method includes the following steps: first, the robot rotates in place and determines the position coordinates of each detection point according to the distance value detected by its distance sensor and the angle value detected by the angle sensor.
  • the distance sensor is disposed at the front end or the top of the robot body, a distance sensor may be provided, or a plurality of distance sensors may be provided at the same time.
  • the distance sensor may be a TOF sensor or a laser sensor with a triangular distance measurement.
  • the distance must be at least more than 1 meter, and can be selected according to the design requirements of the product.
  • the angle sensor uses a gyroscope or other sensors capable of detecting an angle, and the gyroscope can detect the change of its angle in real time as the robot rotates.
  • the robot can perform detection while rotating, or it can stop after rotating at a certain angle, and then continue rotating at a certain angle after completing the relevant detection, and then detect, and so on.
  • the robot rotates once to complete one inspection. Of course, in order to improve the detection accuracy, you can also take the average value as the inspection result after rotating for several weeks.
  • the detection point is a reflection point formed on the obstacle by the distance signal sent by the distance sensor and reflected by the obstacle.
  • the position coordinate of the detection point is the coordinate value of the position where the corresponding reflection point on the obstacle is located, and the coordinate value can be calculated through a trigonometric function relationship.
  • the coordinates are the coordinates of a map constructed by the robot. After determining the position coordinates of each detection point, the robot determines whether the slope of a straight line formed by two adjacent detection points is within a preset error range based on the position coordinates of each detection point.
  • the slope may be calculated using a slope formula of a straight line, that is, a difference between a Y coordinate of two points on the straight line is divided by a difference of an X coordinate.
  • the preset error range can be set according to specific product design requirements. The smaller the set range value, the higher the detection accuracy.
  • the difference between the angles corresponding to the two slopes is less than 0.5 °.
  • T it can be regarded as within the preset error range.
  • the slope of a straight line formed by two adjacent detection points is within a preset error range, it indicates that a straight line formed by connecting the straight lines formed by these detection points is relatively straight and does not have a large bend It is very likely that the points are on the same straight line, so it can be determined that the edge corresponding to the detection point on the straight line with a slope within a preset error range is a straight edge.
  • the straight edge refers to a straight line formed by objects that are flat on a single wall, a side wall of a sofa base, a side wall of a cabinet base, and the like, and the points detected by the distance sensor of the robot are connected in series.
  • the object corresponding to the straight edge can be used as a positioning reference, and the constructed map can be modified to improve the accuracy of the map.
  • the method for detecting straight edges by the robot determines the position coordinates of each detection point according to the distance value detected by the distance sensor and the angle value detected by the angle sensor, and then the slope of the straight line formed by two adjacent detection points is used to determine The final straight edge is determined, the detection accuracy and accuracy are high, and the robot does not need to determine the straight edge situation through the edge behavior, and the work efficiency is greatly improved.
  • the robot 10 rotates in a clockwise direction from the direction of the horizontal dotted line, and when it is rotated to the angle A1, the distance sensor detects that the distance from the robot 10 to the first detection point 21 in the wall 30 is L1; the robot continues When rotating to A2 angle, the distance sensor detects the distance between the robot 10 and the second detection point 22 in the wall edge 30 is L2; Similarly, when rotating to A3 angle, the distance sensor detects the robot 10 to the wall edge 30 The distance of the third detection point 23 is L3; and so on, until the robot rotates one revolution.
  • the method calculates the coordinates of each detection point through the relationship of the plane trigonometric function, and the calculation processing speed is fast, requiring less computing resources, and improving the data processing rate of the robot.
  • the preset error value can be set according to specific product design requirements, and can be set to any value from 0 to 2 °. As shown in FIG. 2, it is assumed that the position coordinates of the first detection point 21 are (70.7, 70.7) calculated by the above method.
  • the slope K3 2.4 between the fourth detection point and the third detection point 23, and its arc tangent value arctan (2.4) ⁇ 67.38 °, two angles
  • the formed straight lines are not on the same straight line and do not belong to the straight edges detected by the robot.
  • the method judges whether the connecting line formed by each detection point is a straight line by calculating the slope. The calculation is simple, the calculation speed is fast, and the data processing speed of the robot is relatively high.
  • the preset error value can be set to 1 °. If the set value is too large, the accuracy of detecting straight edges will be reduced. If the set value is too small, the original straight edge situation will often be mistaken. It is considered that it is not a straight edge, which causes the detection result to be wrong.
  • the preset error value is set to r to achieve the best detection effect. As one of the implementation manners, when the robot rotates in place, each time a preset angle value is rotated, the preset time is stopped, and the distance value is detected by the distance sensor multiple times during the preset time, and then averaged. The value is used as the distance from the robot to the corresponding detection point.
  • the preset angle value and the preset time can be set according to specific product design requirements, the preset angle value can be set to a value less than or equal to 45 °, and the preset time can be set to Any value from 0.3 seconds to 1 second.
  • the robot collects multiple data at each detection point, and can select the average value as the final detection result, thereby improving the accuracy of the robot detection, and providing a more accurate and effective method for subsequent robot analysis to detect whether a straight edge is detected. Reference.
  • the preset angle value is less than or equal to 30 °.
  • the robot can collect data of 36 detection points after one rotation.
  • the method further includes the following step: using the least square method to determine the slope within the preset error. The detection points on the straight line in the range are calculated to fit the optimal straight line, and it is determined that the edge corresponding to the optimal straight line is the detected straight edge.
  • the robot performs the least square method on these discrete detection points.
  • the calculation of can be based on an optimal straight line, which is the most consistent with the actual straight edge, thereby further improving the accuracy of the robot to detect straight edges.
  • the robot before performing the in-situ rotation, the robot further includes the following steps: the robot walks a predetermined distance in a direction away from the obstacle, stops, and then performs the in-situ rotation.
  • the preset distance can be set according to specific design requirements. Preferably, the preset distance can be set to 1 meter or 2 meters.
  • the robot can determine which direction is away from the obstacle by analyzing the map data. If the robot is relatively close to a straight edge obstacle such as a wall, when it performs rotation detection, the detection points collected on the straight edge obstacle such as a wall will have data that is far from the robot, and there are also distances from the robot that are very close. These data are prone to errors, so the robot can improve the accuracy of the detection by walking the preset distance in the direction away from the obstacle and then detecting the data.
  • the method further includes the following step: selecting the determined straight side with the longest length.
  • the long one serves as the reference side.
  • the robot rotates once, it may detect multiple straight-sided obstacles at the same time.
  • it is necessary to select and determine the longest straight edge as the reference edge.
  • the determined reference edge has higher reference value and accuracy.
  • the method further includes the step of analyzing the position of the vision sensor of the robot during the rotation.
  • the captured image analyzes the straight edges in the image; the straight edge corresponding to the detection point on the straight line with the slope corresponding to the longest straight edge in the image within the preset error range is used as the reference edge.
  • the method of parsing straight edges from an image can be based on the principle of Huff transform detection of straight lines.
  • the specific steps include: 1. Converting a color image to a grayscale image; 2. Denoising (Gaussian kernel); 3.
  • a method for screening a reference wall by a cleaning robot may be a sweeping robot or a mopping robot. Since the cleaning robot is prone to walking deviations due to internal components or the external environment during cleaning, at this time, the cleaning robot needs to perform error correction.
  • One of the effective correction methods is to walk along a straight wall to Make corrections. Therefore, before the calibration of the cleaning robot, the accurate and reliable reference wall edge is screened, which is the basis for effective calibration.
  • the method for screening a reference wall according to this embodiment includes the following steps: Step 1: The cleaning robot rotates in place, and determines the position coordinates of each detection point according to the distance value detected by its distance sensor and the angle value detected by the angle sensor.
  • step two based on the position coordinates of each of the detection points, determine whether the slope of a straight line formed by two adjacent detection points is within a preset error range, and if so, determine that the slope is within a predetermined range. Set the edge corresponding to the detection point on a straight line within the error range to be a straight edge, and go to step 3.
  • step 3 Analyze the image captured by the robot's vision sensor during the rotation process, analyze the straight edges in the image, and then proceed to step 4;
  • step 4 Set the slope of the longest straight edge in the image to the preset
  • the straight edge corresponding to the detection point on the straight line within the error range is used as the reference wall edge.
  • the method for screening a reference wall edge is similar to the above embodiment for detecting straight edges, and is not repeated here.
  • the cleaning robot will use the detected straight edge as a wall edge for screening, and the straight edge that is selected is the reference wall edge. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Electromagnetism (AREA)
  • Multimedia (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Optics & Photonics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Manipulator (AREA)

Abstract

一种机器人检测直边的方法，根据距离传感器检测到的距离值和角度传感器检测到的角度值来确定各检测点的位置坐标，再由相邻两个检测点所构成的直线的斜率情况来确定最终的直边，检测精度和准确性较高，且不需要机器人通过沿边行为来确定直边情况，工作效率大大提高。一种清洁机器人筛选参考墙边的方法，采用与检测直边相同的方式确定直边以后，再将直边与视觉传感器所拍摄的图像中直边进行对比，筛选出最长的直边作为参考墙边，为后续机器人进行沿参考墙边进行定位等操作提供了准确有效的参考。

Description

[根据细则20.5改正22.01.2019]　机器人检测直边的方法和清洁机器人筛选参考墙边的方法 技术领域
[根据细则20.5改正22.01.2019]　
本发明涉及智能机器人技术领域，具体涉及一种机器人检测直边的方法和清洁机器人筛选参考墙边的方法。
背景技术
[根据细则20.5改正22.01.2019]　
测量墙面的走向对于很多机器人有比较重要的作用，例如清洁类机器人，测量了墙面的走向后，机器人就可以平行于墙面或者垂直于墙面行走，行走的方向与地形一致就会比较高效。自动巡航机器人，通过测量墙面障碍物信息，可以规划自己的路径；具有规划清扫的机器人，测量到了墙面的走向，可以用于机器人的辅助定位。测量墙面，目前比较常见的是通过机器人的沿边行走来获得，也可以通过旋转激光来获得，前者误差比较大，耗时也长，后者成本高，激光头一般在机器上表面，很多障碍物检测不到，还是需要机器自身的沿边行为来辅助。
发明内容
[根据细则20.5改正22.01.2019]　
本发明提供了一种机器人检测直边的方法和清洁机器人筛选参考墙边的方法，可以准确地检测机器人周围的直边，为机器人利用直边进行后续操作提供有效参考。本发明所述的具体技术方案如下：
[根据细则20.5改正22.01.2019]　
一种机器人检测直边的方法，包括如下步骤：机器人原地旋转，并根据其距离传感器检测到的距离值和角度传感器检测到的角度值，确定各检测点的位置坐标；基于各所述检测点的位置坐标，判断相邻两个所述检测点所构成的直线的斜率是否在预设误差范围内，如果是，则确定斜率在预设误差范围内的直线上的检测点所对应的边是直边，如果否，则确定斜率不在预设误差范围内的直线上的检测点所对应的边不是直边。
[根据细则20.5改正22.01.2019]　
进一步地，所述根据距离传感器检测到的距离值和角度传感器检测到的角度值，确定各检测点的位置坐标的步骤，具体包括如下步骤：确定机器人的角度传感器所检测到的角度值为Ai;确定机器人在角度Ai时，其距离传感器所检测到的距离值为Li;确定各检测点的位置坐标为(Xi=Li*cosAi，Yi=Li*sinAi)。
[根据细则20.5改正22.01.2019]　
其中，i表示大于或者等于1的自然数。
[根据细则20.5改正22.01.2019]　
进一步地，所述基于各所述检测点的位置坐标，判断相邻两个所述检测点所构成的直线的斜率是否在预设误差范围内的步骤，具体包括如下步骤：确定相邻的两个检测点的坐标为(Xi，Yi)和(X(i-1)，Y(i-1))，则这两个检测点的斜率为Ki=(Yi-Y(i-1))/(Xi-X(i-1));判断Ki的反正切值与K(i-1)的反正切值的差值是否小于或等于预设误差值，如果是，则确定相邻两个所述检测点所构成的直线的斜率在预设误差范围内，如果否，则确定相邻两个所述检测点所构成的直线的斜率不在预设误差范围内。
进一步地，所述预设误差值为r。
进一步地，所述机器人原地旋转时，每旋转一个预设角度值，停止预设时间，并在所述预设时间内由距离传感器进行多次距离值的检测，然后取平均值作为机器人至对应检测点的距离值。
[根据细则20.5改正22.01.2019]　
进一步地，所述预设角度值小于或等于30°。
[根据细则20.5改正22.01.2019]　
进一步地，在所述确定斜率在预设误差范围内的直线上的检测点所对应的边是直边的步骤之后，还包括如下步骤：采用最小二乘法对斜率在预设误差范围内的直线上的检测点进行计算，拟合出最优直线，并确定所述最优直线所对应的边为所检测的直边。
[根据细则20.5改正22.01.2019]　
进一步地，所述机器人在进行原地旋转之前，还包括如下步骤：机器人朝远离障碍物的方向行走预设距离后，停止，然后才进行原地旋转。
[根据细则20.5改正22.01.2019]　
进一步地，在所述确定斜率在预设误差范围内的直线上的检测点所对应的边是直边的步骤之后，还包括如下步骤：在所确定的直边中选取长度最长的作为参考边。
[根据细则20.5改正22.01.2019]　
进一步地，在所述确定斜率在预设误差范围内的直线上的检测点所对应的边是直边的步骤之后，还包括如下步骤：分析机器人的视觉传感器在旋转过程中所拍摄到的图像，解析出图像中的直边；将图像中的最长的直边所对应的斜率在预设误差范围内的直线上的检测点所对应的直边作为参考边。
[根据细则20.5改正22.01.2019]　
一种清洁机器人筛选参考墙边的方法，包括如下步骤：步骤一：清洁机器人原地旋转，并根据其距离传感器检测到的距离值和角度传感器检测到的角度值，确定各检测点的位置坐标，然后进入步骤二；步骤二：基于各所述检测点的位置坐标，判断相邻两个所述检测点所构成的直线的斜率是否在预设误差范围内，如果是，则确定斜率在预设误差范围内的直线上的检测点所对应的边是直边，并进入步骤三，如果否，则确定斜率不在预设误差范围内的直线上的检测点所对应的边不是直边；步骤三：分析机器人的视觉传感器在旋转过程中所拍摄到的图像，解析出图像中的直边，然后进入步骤四；步骤四：将图像中的最长的直边所对应的，斜率在预设误差范围内的直线上的检测点所对应的直边，作为参考墙边。
[根据细则20.5改正22.01.2019]　
所述机器人检测直边的方法，根据距离传感器检测到的距离值和角度传感器检测到的角度值来确定各检测点的位置坐标，再由相邻两个检测点所构成的直线的斜率情况来确定最终的直边，检测精度和准确性较高，且不需要机器人通过沿边行为来确定直边情况，工作效率大大提高。此外，所述清洁机器人筛选参考墙边的方法，采用相同的方式确定了直边以后，再将该直边与视觉传感器所拍摄的图像中直边进行对比,筛选出最长的直边作为参考墙边，为后续机器人进行沿参考墙边进行定位等操作提供了准确有效的参考。
附图说明
[根据细则20.5改正22.01.2019]　
图1为本发明所述机器人检测直边的方法流程示意图。
[根据细则20.5改正22.01.2019]　
图2为本发明所述机器人检测直边的分析说明示意图。
具体实施方式
[根据细则20.5改正22.01.2019]　
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行详细描述。应当理解，下面所描述的具体实施例仅用于解释本发明，并不用于限定本发明。在下面的描述中，给出具体细节以提供对实施例的透彻理解。然而，本领域的普通技术人员将理解，可以在没有这些具体细节的情况下实施实施例。
[根据细则20.5改正22.01.2019]　
例如，电路可以在框图中显示，避免在不必要的细节中使实施例模糊。在其他情况下，为了不混淆实施例，可以不详细显示公知的电路、结构和技术。
[根据细则20.5改正22.01.2019]　
如图1所示，一种机器人检测直边的方法，所述机器人可以是工业使用的移动机器人，也可以是家用服务类机器人，也可以是其它智能移动机器设备。所述方法包括如下步骤：首先，机器人进行原地旋转，并根据其距离传感器检测到的距离值和角度传感器检测到的角度值，确定各检测点的位置坐标。其中，所述距离传感器设置在机器人机体的前端或者顶端，可以设置一个距离传感器，也可以同时设置多个距离传感器，所述距离传感器可以采用T0F传感器或者采用三角测距的激光传感器，所检测的距离至少要大于1米以上，具体可以根据产品的设计需求进行选择。所述角度传感器采用的是陀螺仪或者其它能够进行角度检测的传感器，陀螺仪可以随着机器人的转动实时检测其角度变化情况。机器人可以一边进行旋转一边进行检测，也可以旋转一定角度后，停止，完成相关检测后再继续旋转一定角度，再检测，以此类推。机器人旋转一周，完成一次检测，当然，为了提高检测精确度，还可以旋转几周后，取平均值作为一次检测结果。所述检测点是距离传感器发出测距信号，经过障碍物反射后，在障碍物上所形成的反射点。所述检测点的位置坐标就是障碍物上对应的反射点所在的位置的坐标值，该坐标值可以通过三角函数关系进行计算得出。所述坐标是机器人所构建的地图的坐标。在确定了各检测点的位置坐标之后，机器人再基于各所述检测点的位置坐标，判断相邻两个所述检测点所构成的直线的斜率是否在预设误差范围内。所述斜率可以采用直线的斜率公式进行计算，即采用直线上两个点的Y坐标之差除以X坐标之差。所述预设误差范围可以根据具体的产品设计需求进行相应设置，设置的范围值越小，检测精度越高，一般可以用角度来表示，例如两个斜率所对应的角度的差值小于0.5°或者T,即可认为在预设误差范围内。当相邻两个所述检测点所构成的直线的斜率在预设误差范围内，表明这些检测点所构成的直线连接起来所形成的连线相对比较平直，不会有较大的弯折，很有可能都是同一条直线上的点，所以，可以确定斜率在预设误差范围内的直线上的检测点所对应的边是直边。当相邻两个所述检测点所构成的直线的斜率不在预设误差范围内，表明这两个检测点所构成的直线与其它的检测点所构成的直线偏差比较大，会有明显的弯折，所以，这两个检测点与其它斜率在预设误差范围内的直线的检测点不在同一条直线上，可以确定斜率不在预设误差范围内的直线上的检测点所对应的边不是直边。所述直边是指在单面墙体、沙发底座的侧壁、柜子底座的侧壁等表面平直的物体，机器人的距离传感器在其表面检测到的点串连起来所构成的直线。如果机器人检测到了直边，则可以将该直边所对应的物体作为定位参考，还可以对所构建的地图进行修正，以提高地图的准确性。所述机器人检测直边的方法，根据距离传感器检测到的距离值和角度传感器检测到的角度值来确定各检测点的位置坐标，再由相邻两个检测点所构成的直线的斜率情况来确定最终的直边，检测精度和准确性较高，且不需要机器人通过沿边行为来确定直边情况，工作效率大大提高。
[根据细则20.5改正22.01.2019]　
优选的，所述根据距离传感器检测到的距离值和角度传感器检测到的角度值，确定各检测点的位置坐标的步骤，具体包括如下步骤：确定机器人的角度传感器所检测到的角度值为Ai;确定机器人在角度Ai时，其距离传感器所检测到的距离值为Li;确定各检测点的位置坐标为(Xi=Li*cosAi，Yi=Li*sinAi)；其中，i表示大于或者等于1的自然数。如图2所示，机器人10从水平虚线的方向开始沿拟时针方向旋转，转动至A1角度时，距离传感器检测到机器人10至墙边30中的第一检测点21的距离为L1;机器人继续旋转，转动至A2角度时，距离传感器检测到机器人10至墙边30中的第二检测点22的距离为L2;同样的，转动至A3角度时，距离传感器检测到机器人10至墙边30中的第三检测点23的距离为L3;以此类推，至机器人旋转一周。假设机器人当前的坐标是(0,0),Al=45°,Ll=200,则第一检测点21的位置坐标为(100*cos45°,100*sin45°)=(70.7,70.7),同理，可以计算其它检测点的坐标。所述方法通过平面三角函数的关系计算各检测点的坐标，运算处理速度快，只需要较少的运算资源，提高了机器人的数据处理速率。
[根据细则20.5改正22.01.2019]　
优选的，所述基于各所述检测点的位置坐标，判断相邻两个所述检测点所构成的直线的斜率是否在预设误差范围内的步骤，具体包括如下步骤：确定相邻的两个检测点的坐标为(Xi，Yi)和(X(i-1)，Y(i-1))，则这两个检测点的斜率为Ki=(Yi-Y(i-1))/(Xi-X(i-1))；判断Ki的反正切值与K(i-1)的反正切值的差值是否小于或等于预设误差值，如果是，则确定相邻两个所述检测点所构成的直线的斜率在预设误差范围内，如果否，则确定相邻两个所述检测点所构成的直线的斜率不在预设误差范围内。其中，所述预设误差值可以根据具体是产品设计需求进行相应设置，可以设置为0至2°中的任意一值。如图2所示，假设，通过上述方式计算得出，第一检测点21的位置坐标为(70.7,70.7)，由于检测误差的原因，第二检测点22的位置坐标可能会为(0,70.2),第三检测点23的位置坐标可能会为(-70.5，70.8)，则第一检测点21和第二检测点22所构成直线的斜率K1=0.0070721357，其反正切值arctan(0.0070721357)SS20.405°;第二检测点22和第三检测点23所构成直线的斜率K2=-0.0028288543，其反正切值arctan(-0.0028288543)~-0.162°，两个角度的差值为0.567°，如果预设误差值设置为2°，则0.567°<2°，表明这三个检测点所在的直线为同一条直线，即机器人检测到的为直边。假设第四检测点的坐标为(-100,0)时，则第四检测点与第三检测点23之间的斜率K3=2.4,其反正切值arctan(2.4)〜67.38°,两个角度的差值67.38°-(-0.162°)=67.542°,远远大于预设误差值，所以，可以认为第三检测点和第四检测点所构成的直线与第二检测点和第三检测点所构成的直线，不处于同一条直线上，不属于机器人所检测的直边。所述方法通过计算斜率的方式判断各检测点所构成的连接线是不是直线，计算简便，运算速度快，机器人的数据处理速度比较高。
[根据细则20.5改正22.01.2019]　
具体的，所述预设误差值可以设置为1°，如果设置的值过大，检测出直边的准确度就会降低，如果设置的值过小，往往会把原本是直边的情况误认为不是直边，导致检测结果出错。预设误差值设置为r，则可以达到最佳的检测效果。
作为其中一种实施方式，所述机器人原地旋转时，每旋转一个预设角度值，停止预设时间，并在所述预设时间内由距离传感器进行多次距离值的检测，然后取平均值作为机器人至对应检测点的距离值。其中，所述预设角度值和所述预设时间可以根据具体的产品设计需求进行相应设置，所述预设角度值可以设置为小于或等于45°的值，所述预设时间可以设置为0.3秒至1秒中的任意一值。所述机器人通过在每个检测点上进行多次数据的采集，可以选取平均值作为最终检测结果，从而提高了机器人检测的准确性，为后续机器人分析是否检测到直边提供了更准确有效的参考依据。
[根据细则20.5改正22.01.2019]　
优选的，所述预设角度值小于或等于30°。当所述预设角度值设置为10°，则机器人旋转一周可以采集36个检测点的数据。
作为其中一种实施方式，在所述确定斜率在预设误差范围内的直线上的检测点所对应的边是直边的步骤之后，还包括如下步骤：采用最小二乘法对斜率在预设误差范围内的直线上的检测点进行计算，拟合出最优直线，并确定所述最优直线所对应的边为所检测的直边。对于初步检测结果在同一条直线上的检测点比较多的情况下，由于这些检测点具有一定的离散性，而实际只存在一条直边，所以，机器人通过对这些离散的检测点进行最小二乘法的运算，可以拟合出于最优直线，这条最优直线是与实际直边最相符的，由此进一步提高了机器人检测直边的准确性。
[根据细则20.5改正22.01.2019]　
作为其中一种实施方式，所述机器人在进行原地旋转之前，还包括如下步骤：机器人朝远离障碍物的方向行走预设距离后，停止，然后才进行原地旋转。其中，所述预设距离可以根据具体设计需求进行相应设置，优选的，可以设置为1米或者2米。机器人可以通过分析地图数据判断哪个方向是远离障碍物的方向。如果机器人在距离墙体等直边障碍物比较近的情况下，其进行旋转检测时，在墙体等直边障碍物上采集到的检测点会有距离机器人很远的数据，也有距离机器人很近的数据，这些数据容易产生误差，所以，机器人通过朝远离障碍物的方向行走预设距离后，再进行数据的检测，可以提高检测的准确性。
[根据细则20.5改正22.01.2019]　
作为其中一种实施方式，在所述确定斜率在预设误差范围内的直线上的检测点所对应的边是直边的步骤之后，还包括如下步骤：在所确定的直边中选取长度最长的作为参考边。由于机器人旋转一周，其可能会同时检测到多个直边障碍物，此时，为了后续机器人更高效地利用直边，所以，需要选择并确定长度最长的直边作为参考边，如此，所确定的参考边的参考价值和准确性更高。
作为其中一种实施方式，在所述确定斜率在预设误差范围内的直线上的检测点所对应的边是直边的步骤之后，还包括如下步骤：分析机器人的视觉传感器在旋转过程中所拍摄到的图像，解析出图像中的直边;将图像中的最长的直边所对应的斜率在预设误差范围内的直线上的检测点所对应的直边作为参考边。从图像中解析直边的方法，可以基于霍夫变换检测直线的原理，具体步骤包括：1、彩色图像转变为灰度图；2、去噪（高斯核）；3、边缘提取（梯度算子、拉普拉斯算子、canny、sobel）;4、二值化（判断此处是否为边缘点，就看灰度值==255）;5、映射到霍夫空间（准备两个容器，一个用来展示hough-space概况，一个数组hough-space用来储存voting的值，因为投票过程往往有某个极大值超过阈值，多达几千，不能直接用灰度图来记录投票信息）；6、取局部极大值，设定阈值，过滤千扰直线；7、绘制直线、标定角点。
[根据细则20.5改正22.01.2019]　
所述机器人通过结合图像分析，所确定出来的参考边，准确性和参考价值更高。
[根据细则20.5改正22.01.2019]　
一种清洁机器人筛选参考墙边的方法，所述清洁机器人可以是扫地机器人或者拖地机器人。由于清洁机器人在清扫过程中容易因为内部器件或者外部环境等因素，导致行走出现偏差，此时，清洁机器人就需要进行误差校正，其中一种有效的校正方式就是通过沿平直的墙边行走以进行校正。所以，清洁机器人在进行校正之前，筛选出准确可靠的参考墙边，是有效进行校正的基础。本实施例所述筛选参考墙边的方法包括如下步骤：步骤一：清洁机器人原地旋转，并根据其距离传感器检测到的距离值和角度传感器检测到的角度值，确定各检测点的位置坐标，然后进入步骤二；步骤二：基于各所述检测点的位置坐标，判断相邻两个所述检测点所构成的直线的斜率是否在预设误差范围内，如果是，则确定斜率在预设误差范围内的直线上的检测点所对应的边是直边，并进入步骤三，如果否，则确定斜率不在预设误差范围内的直线上的检测点所对应的边不是直边；步骤三：分析机器人的视觉传感器在旋转过程中所拍摄到的图像，解析出图像中的直边，然后进入步骤四；步骤四：将图像中的最长的直边所对应的，斜率在预设误差范围内的直线上的检测点所对应的直边，作为参考墙边。所述筛选参考墙边的方法与上述检测直边的实施例相似，此处不再赘述，清洁机器人会把所检测到的直边作为墙边进行筛选，所筛选出来的直边就是参考墙边。
[根据细则20.5改正22.01.2019]　
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。这些程序可以存储于计算机可读取存储介质（比如ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质）中。该程序在执行时，执行包括上述各方法实施例的步骤。最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims (11)

  1. 一种机器人检测直边的方法，其特征在于，包括如下步骤：
    机器人原地旋转，并根据其距离传感器检测到的距离值和角度传感器检测到的角度值，确定各检测点的位置坐标；
    基于各所述检测点的位置坐标，判断相邻两个所述检测点所构成的直线的斜率是否在预设误差范围内，如果是，则确定斜率在预设误差范围内的直线上的检测点所对应的边是直边，如果否，则确定斜率不在预设误差范围内的直线上的检测点所对应的边不是直边。
  2. 根据权利要求1所述的方法，其特征在于，所述根据距离传感器检测到的距离值和角度传感器检测到的角度值，确定各检测点的位置坐标的步骤，具体包括如下步骤：
    确定机器人的角度传感器所检测到的角度值为Ai；
    确定机器人在角度Ai时，其距离传感器所检测到的距离值为Li；
    确定各检测点的位置坐标为(Xi＝Li*cosAi，Yi＝Li*sinAi)；
    其中，i表示大于或者等于1的自然数。
  3. 根据权利要求1所述的方法，其特征在于，所述基于各所述检测点的位置坐标，判断相邻两个所述检测点所构成的直线的斜率是否在预设误差范围内的步骤，具体包括如下步骤：
    确定相邻的两个检测点的坐标为(Xi，Yi)和(X(i-1)，Y(i-1))，则这两个检测点的斜率为Ki＝(Yi-Y(i-1))/(Xi-X(i-1))；
    判断Ki的反正切值与K(i-1)的反正切值的差值是否小于或等于预设误差值，如果是，则确定相邻两个所述检测点所构成的直线的斜率在预设误差范围内，如果否，则确定相邻两个所述检测点所构成的直线的斜率不在预设误差范围内。
  4. 根据权利要求3所述的方法，其特征在于：所述预设误差值为1。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于：所述机器 人原地旋转时，每旋转一个预设角度值，停止预设时间，并在所述预设时间内由距离传感器进行多次距离值的检测，然后取平均值作为机器人至对应检测点的距离值。
  6. 根据权利要求5所述的方法，其特征在于：所述预设角度值小于或等于30。
  7. 根据权利要求1至4中任一项所述的方法，其特征在于，在所述确定斜率在预设误差范围内的直线上的检测点所对应的边是直边的步骤之后，还包括如下步骤：
    采用最小二乘法对斜率在预设误差范围内的直线上的检测点进行计算，拟合出最优直线，并确定所述最优直线所对应的边为所检测的直边。
  8. 根据权利要求1至4中任一项所述的方法，其特征在于，所述机器人在进行原地旋转之前，还包括如下步骤：
    机器人朝远离障碍物的方向行走预设距离后，停止，然后才进行原地旋转。
  9. 根据权利要求1至4中任一项所述的方法，其特征在于，在所述确定斜率在预设误差范围内的直线上的检测点所对应的边是直边的步骤之后，还包括如下步骤：
    在所确定的直边中选取长度最长的作为参考边。
  10. 根据权利要求1至4中任一项所述的方法，其特征在于，在所述确定斜率在预设误差范围内的直线上的检测点所对应的边是直边的步骤之后，还包括如下步骤：
    分析机器人的视觉传感器在旋转过程中所拍摄到的图像，解析出图像中的直边；
    将图像中的最长的直边所对应的斜率在预设误差范围内的直线上的检测点所对应的直边作为参考边。
  11. 一种清洁机器人筛选参考墙边的方法，其特征在于，包括如下步骤：
    步骤一：清洁机器人原地旋转，并根据其距离传感器检测到的距离值和角度传感器检测到的角度值，确定各检测点的位置坐标，然后进入步骤二；
    步骤二：基于各所述检测点的位置坐标，判断相邻两个所述检测点所构成的直线的斜率是否在预设误差范围内，如果是，则确定斜率在预设误差范围内的直线上的检测点所对应的边是直边，并进入步骤三，如果否，则确定斜率不在预设误差范围内的直线上的检测点所对应的边不是直边；
    步骤三：分析机器人的视觉传感器在旋转过程中所拍摄到的图像，解析出图像中的直边，然后进入步骤四；
    步骤四：将图像中的最长的直边所对应的，斜率在预设误差范围内的直线上的检测点所对应的直边，作为参考墙边。
PCT/CN2018/120247 2018-08-27 2019-01-22 机器人检测直边的方法和清洁机器人筛选参考墙边的方法 Ceased WO2020042426A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US17/264,310 US11977390B2 (en) 2018-08-27 2019-01-22 Method for straight edge detection by robot and method for reference wall edge selection by cleaning robot
EP18931950.2A EP3845989B1 (en) 2018-08-27 2019-01-22 Method for detecting straight side by robot, and method for screening reference wall side by cleaning robot

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810979482.8A CN109085834B (zh) 2018-08-27 2018-08-27 机器人确定参考边的方法和机器人筛选参考墙边的方法
CN201810979482.8 2018-08-27

Publications (1)

Publication Number Publication Date
WO2020042426A1 true WO2020042426A1 (zh) 2020-03-05

Family

ID=64794812

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/120247 Ceased WO2020042426A1 (zh) 2018-08-27 2019-01-22 机器人检测直边的方法和清洁机器人筛选参考墙边的方法

Country Status (4)

Country Link
US (1) US11977390B2 (zh)
EP (1) EP3845989B1 (zh)
CN (1) CN109085834B (zh)
WO (1) WO2020042426A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114747827A (zh) * 2022-04-28 2022-07-15 上海卓菡科技有限公司 安全帽、临边防护方法、装置、电子设备及存储介质

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109085834B (zh) 2018-08-27 2019-09-03 珠海市一微半导体有限公司 机器人确定参考边的方法和机器人筛选参考墙边的方法
CN109782296A (zh) * 2019-02-01 2019-05-21 广东博智林机器人有限公司 具有建筑工地室内定位智能装置的机器人及其控制方法
CN110279352B (zh) * 2019-06-28 2021-09-17 苏州瑞久智能科技有限公司 一种基于双psd传感器的扫地机器人沿墙行走方法
CN110316558A (zh) * 2019-06-28 2019-10-11 武汉闻道复兴智能科技有限责任公司 一种搬运机器人夹具位置控制方法和系统
KR102385611B1 (ko) * 2019-12-06 2022-04-12 엘지전자 주식회사 이동 로봇 시스템 및 이동 로봇 시스템의 경계 정보 생성 방법
CN111158364B (zh) * 2019-12-30 2024-02-09 深圳市优必选科技股份有限公司 机器人重定位方法、装置及终端设备
CN111552290B (zh) * 2020-04-30 2023-09-05 珠海一微半导体股份有限公司 一种机器人沿墙找直线的方法及清扫方法
CN111906779B (zh) * 2020-06-30 2022-05-10 珠海一微半导体股份有限公司 一种越障结束判断方法、越障控制方法、芯片及机器人
CN112432612B (zh) * 2020-10-22 2022-08-16 中国计量科学研究院 一种基于单目视觉的高精度微小旋转角度测量方法
CN113936023B (zh) * 2021-10-21 2025-05-13 四川阿泰因机器人智能装备有限公司 一种强光条件下的粮仓走道板边沿直线检测方法
CN114587218B (zh) * 2021-12-31 2023-07-21 北京石头创新科技有限公司 一种清洁机器人的状态判断方法及装置
GB2618104B (en) * 2022-04-27 2024-10-30 Dyson Technology Ltd Method for edge cleaning
US12304085B2 (en) 2022-05-03 2025-05-20 Stmicroelectronics (Shenzhen) R&D Co. Ltd. Cliff detection in robotic devices
CN115145276B (zh) * 2022-06-29 2025-09-16 深圳市云鼠科技开发有限公司 机器人沿边运动方法、设备、机器人及存储介质
CN115096241B (zh) * 2022-07-27 2023-11-10 无锡苏广汽车部件科技有限公司 一种汽车部件快速智能检测方法及其检测系统
CN114998752B (zh) * 2022-08-04 2023-01-06 深圳市海清视讯科技有限公司 地质灾害的识别方法、装置、设备及存储介质
CN118570235B (zh) * 2024-05-10 2025-03-11 钛玛科（北京）工业科技有限公司 一种基于卷积神经网络的物体边沿位置检测方法

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090292394A1 (en) * 2008-05-21 2009-11-26 Samsung Electronics Co., Ltd. Apparatus for locating moving robot and method for the same
JP2012088135A (ja) * 2010-10-19 2012-05-10 Advanced Telecommunication Research Institute International 距離センサのキャリブレーション装置、キャリブレーションプログラムおよびキャリブレーション方法
CN102798359A (zh) * 2012-08-30 2012-11-28 首钢京唐钢铁联合有限责任公司 非接触式倾角测量装置及方法
CN106123780A (zh) * 2016-06-14 2016-11-16 北京交通大学 非接触式空间曲线精密测量方法和装置
JP2017036981A (ja) * 2015-08-10 2017-02-16 日産自動車株式会社 段差検出装置及び段差検出方法
CN106843239A (zh) * 2017-04-11 2017-06-13 珠海市微半导体有限公司 基于地图预测的机器人运动控制方法
CN106959695A (zh) * 2017-04-24 2017-07-18 广东宝乐机器人股份有限公司 移动机器人在工作区域内的角度修正方法及移动机器人
CN107315426A (zh) * 2017-08-31 2017-11-03 珠海市微半导体有限公司 一种旋转测距传感装置和机器人
CN107704801A (zh) * 2017-08-18 2018-02-16 电子科技大学 基于分段直线加分段贝塞尔曲线的曲线车道线检测方法
CN108415432A (zh) * 2018-03-09 2018-08-17 珠海市微半导体有限公司 机器人基于直边的定位方法
CN109085834A (zh) * 2018-08-27 2018-12-25 珠海市微半导体有限公司 机器人检测直边的方法和清洁机器人筛选参考墙边的方法

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3536747A1 (de) * 1984-10-15 1986-04-24 Tokico Ltd., Kawasaki, Kanagawa Gelenkmechanismus
US5576947A (en) * 1994-06-30 1996-11-19 Siemens Corporate Research, Inc. Robot hallway traveler
KR102071947B1 (ko) * 2013-05-10 2020-01-31 삼성전자주식회사 청소 로봇 및 그 제어방법
JP5897517B2 (ja) * 2013-08-21 2016-03-30 シャープ株式会社 自律移動体
CN203687993U (zh) * 2014-01-28 2014-07-02 北京山地生态科技研究所 一种边坡监测系统
KR101649665B1 (ko) * 2015-04-29 2016-08-30 엘지전자 주식회사 이동 로봇 및 그 제어방법
CN106527424B (zh) * 2016-09-20 2023-06-09 深圳银星智能集团股份有限公司 移动机器人及移动机器人的导航方法
CN207216430U (zh) * 2017-08-31 2018-04-10 珠海市一微半导体有限公司 一种旋转测距传感装置和机器人
CN107443385B (zh) * 2017-09-26 2020-02-21 珠海市一微半导体有限公司 基于视觉的机器人直线导航的检测方法和芯片及机器人

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090292394A1 (en) * 2008-05-21 2009-11-26 Samsung Electronics Co., Ltd. Apparatus for locating moving robot and method for the same
JP2012088135A (ja) * 2010-10-19 2012-05-10 Advanced Telecommunication Research Institute International 距離センサのキャリブレーション装置、キャリブレーションプログラムおよびキャリブレーション方法
CN102798359A (zh) * 2012-08-30 2012-11-28 首钢京唐钢铁联合有限责任公司 非接触式倾角测量装置及方法
JP2017036981A (ja) * 2015-08-10 2017-02-16 日産自動車株式会社 段差検出装置及び段差検出方法
CN106123780A (zh) * 2016-06-14 2016-11-16 北京交通大学 非接触式空间曲线精密测量方法和装置
CN106843239A (zh) * 2017-04-11 2017-06-13 珠海市微半导体有限公司 基于地图预测的机器人运动控制方法
CN106959695A (zh) * 2017-04-24 2017-07-18 广东宝乐机器人股份有限公司 移动机器人在工作区域内的角度修正方法及移动机器人
CN107704801A (zh) * 2017-08-18 2018-02-16 电子科技大学 基于分段直线加分段贝塞尔曲线的曲线车道线检测方法
CN107315426A (zh) * 2017-08-31 2017-11-03 珠海市微半导体有限公司 一种旋转测距传感装置和机器人
CN108415432A (zh) * 2018-03-09 2018-08-17 珠海市微半导体有限公司 机器人基于直边的定位方法
CN109085834A (zh) * 2018-08-27 2018-12-25 珠海市微半导体有限公司 机器人检测直边的方法和清洁机器人筛选参考墙边的方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3845989A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114747827A (zh) * 2022-04-28 2022-07-15 上海卓菡科技有限公司 安全帽、临边防护方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
US11977390B2 (en) 2024-05-07
EP3845989B1 (en) 2024-06-05
EP3845989A1 (en) 2021-07-07
CN109085834A (zh) 2018-12-25
US20210302964A1 (en) 2021-09-30
EP3845989A4 (en) 2022-08-17
CN109085834B (zh) 2019-09-03

Similar Documents

Publication Publication Date Title
WO2020042426A1 (zh) 机器人检测直边的方法和清洁机器人筛选参考墙边的方法
US11537142B2 (en) Method for robot repositioning
US9157757B1 (en) Methods and systems for mobile-agent navigation
CN110587597B (zh) 一种基于激光雷达的slam闭环检测方法及检测系统
US9208395B2 (en) Position and orientation measurement apparatus, position and orientation measurement method, and storage medium
CN110850859B (zh) 一种机器人及其避障方法和避障系统
CN116399349A (zh) 机器人的定位方法
CN110216715A (zh) 机器人导航性能测试方法、系统、测试终端及存储介质
Iocchi et al. Self-localization in the RoboCup environment
WO2017008742A1 (en) Method and device for determining indoor approachable area
CN108663041A (zh) 一种绘制导航地图的方法及装置
WO2022222291A1 (zh) 光轴检测系统的光轴标定方法、装置、终端、系统和介质
WO2025195415A1 (zh) 自移动设备的控制方法及装置、设备、介质与程序产品
WO2025108214A1 (zh) 一种警戒带距离的确定方法、装置、电子设备及存储介质
WO2019237434A1 (zh) 扫地机器人位置校准方法及系统
WO2021103065A1 (zh) 一种扫地机器人的充电桩定位方法及装置
JP2020184725A (ja) 追跡装置及び情報処理プログラム
CN105975975A (zh) 一种环境线特征提取方法
Nielsen Robust lidar-based localization in underground mines
US11802947B1 (en) Calibration of lidar angular offset through a dynamic environment
CN115393393B (zh) 一种多传感器融合的障碍物跟踪方法、装置、设备及介质
CN117562443A (zh) 机器人的控制方法、机器人、清洁系统及存储介质
Bhadouria et al. Stereo image to graphics conversion for indoor environments
CN103985132A (zh) 基于k近邻图的误匹配点迭代检测方法
CN119689496B (zh) 机器人的位姿确定方法、机器人及存储介质

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: 18931950

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018931950

Country of ref document: EP

Effective date: 20210329