WO2019136808A1 - 机器人移动方法、机器人移动装置、扫地机器人 - Google Patents

机器人移动方法、机器人移动装置、扫地机器人 Download PDF

Info

Publication number
WO2019136808A1
WO2019136808A1 PCT/CN2018/077604 CN2018077604W WO2019136808A1 WO 2019136808 A1 WO2019136808 A1 WO 2019136808A1 CN 2018077604 W CN2018077604 W CN 2018077604W WO 2019136808 A1 WO2019136808 A1 WO 2019136808A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
robot
camera
moving
location
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/CN2018/077604
Other languages
English (en)
French (fr)
Inventor
王声平
周毕兴
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.)
Shenzhen Water World Co Ltd
Original Assignee
Shenzhen Water World 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 Shenzhen Water World Co Ltd filed Critical Shenzhen Water World Co Ltd
Publication of WO2019136808A1 publication Critical patent/WO2019136808A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A47L11/4011—Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/24—Floor-sweeping machines, motor-driven
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A47L11/4061—Steering means; Means for avoiding obstacles; Details related to the place where the driver is accommodated
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
    • A47L2201/04—Automatic control of the travelling movement; Automatic obstacle detection

Definitions

  • the present invention relates to the field of robot technology, and in particular, to a robot moving method, a robot moving device, and a sweeping robot.
  • Sweeping robot also known as automatic sweepers, smart vacuum cleaners, robot vacuum cleaners, etc., can automatically and autonomously complete the ground cleaning work in the room with a certain artificial intelligence.
  • the current sweeping robot also adds a voice recognition function. Through the voice recognition function, the sweeping robot can accept the user's voice command and perform corresponding actions according to the voice command. When the user is far away from the sweeping robot, the sweeping robot determines the position of the user through the sound source localization technology, and then moves to the user's location to receive the user's voice command.
  • the positioning accuracy of the sound source positioning is not high, and only the approximate position can be determined, so that the sweeping robot cannot move to the user in time and accurately, and there is often a situation in which there is no user-oriented or large distance from the user, thereby causing the sweeping robot to be inaccurate.
  • the main object of the present invention is to provide a robot moving method and apparatus, aiming at solving the technical problem that the robot cannot accurately move to the user.
  • an embodiment of the present invention provides a robot moving method, where the method includes the following steps:
  • Determining the location of the target by visually positioning the camera when the target is detected;
  • the camera is a monocular camera
  • the step of visually positioning the camera to determine the location of the target includes:
  • the location of the target is determined based on the images of the target acquired twice before and after.
  • the camera is a binocular camera
  • the step of visually positioning by the camera to determine the location of the target includes:
  • the step of detecting the target by the camera includes:
  • the obstacle obscuring the target is avoided until the target is detected.
  • the step of avoiding obstructing the obstacle of the target until the target is detected includes:
  • the step of avoiding obstructing the obstacle of the target until the target is detected comprises: moving laterally to the target direction until the target is detected.
  • the step of detecting the target by the camera includes:
  • the step of moving to the location of the target includes:
  • the method further includes re-planning the moving path when the location of the target changes.
  • the robot is a sweeping robot.
  • the embodiment of the invention simultaneously provides a robot moving device, the device comprising:
  • a direction determining module configured to perform sound source localization by the sound collecting device, and determine a direction of the target
  • a target detecting module configured to face the camera toward the target, and detect the target by the camera
  • a position determining module configured to perform visual positioning by the camera to determine a location of the target when the target is detected
  • a movement control module configured to control the movement of the robot to the location of the target.
  • the camera is a monocular camera
  • the location determining module includes:
  • a first collecting unit configured to collect an image of the target by using the monocular camera
  • a second collecting unit configured to control the robot to move a distance toward the target direction, and collect an image of the target again through the monocular camera
  • a first determining unit configured to determine a location of the target according to an image of the target acquired twice before and after.
  • the camera is a binocular camera
  • the location determining module includes:
  • a third collecting unit configured to collect an image of the target by using the binocular camera
  • a second determining unit configured to determine a location of the target according to the image of the target.
  • the device further includes an obstacle avoidance module, where the obstacle avoidance module is configured to:
  • the obstacle blocking the target is evaded until the target detection module detects the target.
  • the obstacle avoidance module includes:
  • a first moving unit configured to control the robot to move toward the target direction
  • a second moving unit configured to control the robot to move along a boundary of the obstacle when an obstacle is encountered until the target detecting module detects the target.
  • the obstacle avoidance module includes a third moving unit, where the third moving unit is configured to: control lateral movement of the robot to the target direction until the target detecting module detects the target .
  • the target detection module includes:
  • a face recognition unit configured to perform face recognition detection by using the camera
  • the target determining unit is configured to determine that the target is detected when the face is detected.
  • the mobile control module includes:
  • a path planning unit configured to plan a moving path with the current location as a starting point and the target location as an ending point;
  • a movement control unit for controlling the robot to move toward the end point along the moving path.
  • the mobility control module further includes a path update unit, where the path update unit is configured to re-plan the mobile path when the location of the target changes.
  • Embodiments of the present invention also provide a cleaning robot including a memory, a processor, and at least one application stored in the memory and configured to be executed by the processor, the application being configured to be used for The aforementioned robot movement method is executed.
  • a robot moving method provided by the embodiment of the present invention determines a target direction by sound source positioning to point the camera toward a target, and then uses a camera to perform visual positioning to determine an accurate position of the target, so that the robot can quickly and accurately move to the user (target ), solved the technical problem that the robot can not accurately move to the user, and realized the precise adjustment of the orientation relationship and distance relationship between the robot and the user, ensuring that the robot can receive the user's voice command better, greatly improving the user experience. .
  • FIG. 1 is a flow chart of a first embodiment of a robot moving method of the present invention
  • FIG. 2 is a schematic structural view of a robot in an embodiment of the present invention.
  • FIG. 3 is a schematic diagram of a camera of a robot facing a target in an embodiment of the present invention
  • Figure 4 is a flow chart showing a second embodiment of the robot moving method of the present invention.
  • FIG. 5 is a schematic diagram of an obstacle in which a robot avoids an occlusion target according to an embodiment of the present invention
  • FIG. 6 is another schematic diagram of an obstacle in which a robot avoids an occlusion target according to an embodiment of the present invention
  • Figure 7 is a block diagram showing a first embodiment of the robot moving device of the present invention.
  • Figure 8 is a block diagram of the target detection module of Figure 7;
  • Figure 9 is a block diagram of the position determining module of Figure 7;
  • FIG. 10 is another block diagram of the position determining module of FIG. 7;
  • FIG 11 is a block diagram of the mobile control module of Figure 7;
  • Figure 12 is a block diagram of the mobile control module of Figure 7;
  • Figure 13 is a block diagram showing a second embodiment of the robot moving device of the present invention.
  • FIG. 14 is a block diagram of the obstacle avoidance module of FIG.
  • the robot moving method and device according to the embodiment of the present invention can be applied to various robots, and is particularly suitable for a sweeping robot.
  • the following is an example of a sweeping robot.
  • the sound collecting device in the embodiment of the present invention is preferably a microphone array.
  • the cleaning robot 100 is provided with a microphone array composed of four microphones 101 and a camera 102.
  • the sweeping robot uses the microphone array to collect the sound emitted by the sound source, and uses the sound source localization technology to locate the sound source to determine the direction of the sound source, that is, the target.
  • the sound source localization technology is a relatively mature prior art and will not be described here.
  • the object here is mainly a person (user), and of course, other sounding substances that can be uttered, which are not limited by the present invention.
  • step S12 Point the camera toward the target and detect the target through the camera. It is judged whether or not the target is detected, when the target is detected, the process proceeds to step S13; when the target is not detected, the process is ended.
  • the sweeping robot points the camera toward the target, such as rotating the camera to aim at the target or rotating the entire robot to the target, and launching the camera to detect the target through the camera.
  • the camera 102 of the cleaning robot 100 is aimed at the target 200 such that the target 200 is within the field of view of the camera 102 (the range in which the two edges of the camera 102 extend).
  • the sweeping robot can perform face recognition detection through the camera, and when the face is detected, it is determined that the target is detected, otherwise it is determined that the target is not detected.
  • the face recognition technology is a relatively mature prior art and will not be described here.
  • the target detection can be achieved by identifying the visual feature of the utterance.
  • the sweeping robot uses the camera to visually locate the target through the visual positioning technology to determine the location of the target.
  • the cleaning robot can first collect the image of the target through the monocular camera in situ, then move a distance toward the target direction, and again collect the image of the target through the monocular camera, and finally according to the front and rear twice.
  • the image analysis of the acquired target calculates the three-dimensional coordinates of the target and determines the location of the target.
  • the specific method for calculating the three-dimensional coordinates of the target by the images acquired by the two positions is the same as that of the prior art, and will not be described here.
  • the cleaning robot can directly acquire the image of the target through the binocular camera in situ, acquire two images with parallax every time, and calculate the target by using two images with parallax.
  • the three-dimensional coordinates determine the location of the target.
  • the specific method for calculating the three-dimensional coordinates of the target by using two image analysiss with parallax is the same as the prior art, and will not be described herein.
  • the sweeping robot After determining the location of the target, the sweeping robot moves to the target position until it stops moving to a certain distance from the target, then stops the movement by the sound collecting device, and performs a corresponding action according to the voice command.
  • the sweeping robot When moving to the target position, the sweeping robot can plan the moving path with the current position as the starting point and the target position as the end point, and then move along the moving path to the end point, and finally reach the target position.
  • the cleaning robot re-plans the movement path and moves to the end point along the re-planned movement path.
  • the sweeping robot can also follow the target movement to achieve real-time tracking of the target.
  • the accurate position of the target is determined by the sound source positioning + visual positioning, so that the robot can quickly and accurately move to the user (target), solving the technical problem that the robot cannot accurately move to the user.
  • S21 Perform sound source localization through a sound collection device to determine a direction of the target.
  • step S22 Point the camera toward the target and detect the target through the camera. It is judged whether or not the target is detected, when the target is not detected, the process proceeds to step S23; and when the target is detected, the process proceeds to step S24.
  • step S23 when the cleaning robot does not detect the target in situ, the obstacle of the occlusion target is avoided until the target is detected, so that the cleaning robot can automatically avoid the obstacle from reaching the user even if it is blocked by the obstacle.
  • the sweeping robot can avoid obstacles that block the target by:
  • the cleaning robot 100 when the line of sight of the camera 102 of the cleaning robot 100 is blocked by the obstacle 300 and the target 200 cannot be detected, the cleaning robot 100 first moves toward the target 200, and when the obstacle 300 is hit, It moves along the boundary of the obstacle 300 until the target 200 is detected.
  • the camera 102 During movement along the boundary of the obstacle 300, the camera 102 is always facing the target 200, and when moving to the edge of the obstacle 300, the line of sight of the camera 102 (as indicated by the dashed line) avoids the obstacle 300 and reaches the target 200. So that the target 200 can be detected.
  • the cleaning robot 100 performs visual positioning by the camera 102, determines the position of the target 200, and moves to the position where the target 200 is located.
  • the cleaning robot 100 moves laterally in the direction of the target 200 until the target 200 is detected. until.
  • the lateral direction and the direction of the target 200 are preferably acute, such as between 45 and 90 degrees, to minimize the distance of movement, and of course may be a right angle or an obtuse angle.
  • the camera 102 is always facing the target 200, and when moving to the edge position of the obstacle 300, the line of sight of the camera 102 (as indicated by the dashed line) avoids the obstacle 300 and reaches the target 200, thereby The target 200 can be detected.
  • the cleaning robot 100 performs visual positioning by the camera 102, determines the position of the target 200, and moves to the position where the target 200 is located.
  • the robot moving method of the embodiment of the invention determines the target direction by the sound source positioning to point the camera toward the target, and then uses the camera to perform visual positioning to determine the accurate position of the target, so that the robot can quickly and accurately move to the user (target) to solve the problem.
  • the robot can not accurately move to the technical problems of the user, and achieves the precise adjustment of the orientation relationship and distance relationship between the robot and the user, ensuring that the robot can better receive the user's voice command, greatly improving the user experience.
  • the robot can also actively identify the user, implement follow-up operations, and the interactive experience is more abundant, and the user experience is better.
  • the device includes a direction determining module 10, a target detecting module 20, a position determining module 30, and a movement control module 40, wherein the direction determining module 10 is configured to pass
  • the sound collecting device performs sound source localization to determine the direction of the target;
  • the target detecting module 20 is configured to face the camera toward the target and detect the target through the camera;
  • the position determining module 30 is configured to perform visual inspection through the camera when the target is detected.
  • Positioning, determining the location of the target; the movement control module 40 is configured to control the movement of the robot to the location of the target.
  • the sound collecting device in the embodiment of the present invention is preferably a microphone array.
  • the cleaning robot 100 is provided with a microphone array composed of four microphones 101 and a camera 102.
  • the direction determining module 10 uses the microphone array to collect the sound emitted by the sound source, and uses the sound source localization technology to locate the sound source, thereby determining the direction of the sound source, that is, the target.
  • the sound source localization technology is a relatively mature prior art and will not be described here.
  • the object here is mainly a person (user), and of course, other sounding substances that can be uttered, which are not limited by the present invention.
  • the target detection module 20 After determining the direction of the target, the target detection module 20 directs the camera toward the target, such as rotating the camera to align the target or controlling the entire robot to rotate the alignment target, and activates the camera to detect the target through the camera. As shown in FIG. 3, the target detection module 20 controls the camera 102 of the cleaning robot 100 to align the target 200 such that the target 200 is within the field of view of the camera 102 (the range in which the two edges of the camera 102 extend).
  • the target detection module 20 can perform target detection by face recognition technology.
  • the object detection module 20 includes a face recognition unit 21 and a target determination unit 22, wherein: a face recognition unit 21 is configured to perform face recognition detection by a camera; and a target determination unit 22 is configured to detect when When the face is determined, it is determined that the target is detected, otherwise it is determined that the target is not detected.
  • the face recognition technology is a relatively mature prior art and will not be described here.
  • the target detection module 20 can also identify other visible features of the human body to achieve target detection, and the present invention will not be repeated here.
  • the target detection module 20 can achieve the target detection by identifying the visual feature of the utterance.
  • the position determining module 30 visually locates the target by using a visual positioning technology to determine the location of the target.
  • the position determining module 30 includes a first acquiring unit 31, a second collecting unit 32, and a first determining unit 33, as shown in FIG. 9, wherein: the first collecting unit 31 uses The image of the target is collected by the monocular camera; the second collecting unit 32 is configured to control the robot to move a distance toward the target direction, and collect the image of the target again through the monocular camera; the first determining unit 33 is configured to collect the image according to the front and the back.
  • the image analysis of the target calculates the three-dimensional coordinates of the target and determines the location of the target.
  • the specific method for calculating the three-dimensional coordinates of the target by the images acquired by the two positions is the same as that of the prior art, and will not be described here.
  • the position determining module 30 includes a third acquiring unit 34 and a second determining unit 35, as shown in FIG. 10, wherein: the third collecting unit 34 is configured to collect by the binocular camera.
  • the image of the target acquires two images with parallax for each acquisition;
  • the second determining unit 35 is configured to determine the location of the target according to the image of the target, for example, calculating the three-dimensional coordinates of the target by using two image analysiss with parallax, Determine where the target is located.
  • the specific method for calculating the three-dimensional coordinates of the target by using two image analysiss with parallax is the same as the prior art, and will not be described herein.
  • the motion control module 40 controls the robot to move to the target location until it stops moving after reaching a certain distance from the target. Then, the robot can receive the voice command of the target through the sound collecting device, and perform corresponding actions according to the voice command.
  • the mobile control module 40 includes a path planning unit 41 and a mobile control unit 42, wherein: the path planning unit 41 is configured to plan a moving path with the current location as the starting point and the target location as the ending point; the mobile control unit 42 , used to control the robot to move to the end point along the moving path, and finally reach the target location.
  • the mobility control module 40 may further include a path update unit 43 for re-planning the movement path when the location of the target changes.
  • the movement control unit 42 then moves toward the end point along the re-planned movement path.
  • the sweeping robot can also follow the target movement to achieve real-time tracking of the target.
  • the accurate position of the target is determined by the sound source positioning + visual positioning, so that the robot can quickly and accurately move to the user (target), solving the technical problem that the robot cannot accurately move to the user.
  • a second embodiment of the robot moving device of the present invention is proposed.
  • the present embodiment adds an obstacle avoidance module 50 to the first embodiment, and the obstacle avoidance module 50 is configured to: when the target detecting module 20 does not detect When the target is in the target, the obstacle blocking the target is avoided until the target detecting module 20 detects the target, so that the cleaning robot can automatically avoid the obstacle from reaching the user even if it is blocked by the obstacle.
  • the obstacle avoidance module 50 includes a first moving unit 51 and a second moving unit 52, as shown in FIG. 14, wherein: the first moving unit 51 is configured to control the robot to move toward the target direction; and the second mobile unit 52. For controlling the robot to move along the boundary of the obstacle when the obstacle is hit, until the target detecting module 20 detects the target.
  • the first moving unit 51 controls the robot 100 to move toward the target 200 when encountering an obstacle.
  • the second moving unit 52 controls the robot 100 to move along the boundary of the obstacle 300 until the target detecting module 20 detects the target 200.
  • the camera 102 is always facing the target 200.
  • the target detection module 20 can detect the target 200.
  • the obstacle avoidance module 50 includes a third mobile unit for controlling lateral movement of the robot in the target direction until the target detection module 20 detects the target.
  • the third moving unit controls the lateral movement of the robot 100 in the direction of the target 200 until detection. Go to goal 200.
  • the lateral direction and the direction of the target 200 are preferably acute, such as between 45 and 90 degrees, to minimize the distance of movement, and of course may be a right angle or an obtuse angle.
  • the camera 102 is always facing the target 200.
  • the line of sight of the camera 102 avoids the obstacle 300 and reaches the target 200.
  • the target detection module 20 is able to detect the target 200.
  • the robot moving device of the embodiment of the invention determines the target direction by sound source positioning to point the camera toward the target, and then uses the camera to perform visual positioning to determine the accurate position of the target, so that the robot can quickly and accurately move to the user (target) to solve the problem.
  • the robot can not accurately move to the technical problems of the user, and achieves the precise adjustment of the orientation relationship and distance relationship between the robot and the user, ensuring that the robot can better receive the user's voice command, greatly improving the user experience.
  • the invention also proposes a cleaning robot comprising a memory, a processor and at least one application stored in the memory and configured to be executed by the processor, the application being configured to perform a robot movement method.
  • the robot moving method includes the following steps: positioning a sound source by a sound collecting device, determining a direction of the target; pointing the camera toward the target, and detecting the target through the camera; and when detecting the target, performing visual positioning by the camera to determine the target position ; Move to the location of the target.
  • the robot moving method described in this embodiment is the robot moving method according to the above embodiment of the present invention, and details are not described herein again.
  • the present invention includes apparatus that is directed to performing one or more of the operations described herein. These devices may be specially designed and manufactured for the required purposes, or may also include known devices in a general purpose computer. These devices have computer programs stored therein that are selectively activated or reconfigured.
  • Such computer programs may be stored in a device (eg, computer) readable medium or in any type of medium suitable for storing electronic instructions and coupled to a bus, respectively, including but not limited to any Types of disks (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access) Memory, random access memory), EPROM (Erasable Programmable Read-Only Memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or light card.
  • a readable medium includes any medium that is stored or transmitted by a device (eg, a computer) in a readable form.
  • each block of the block diagrams and/or block diagrams and/or flow diagrams and combinations of blocks in the block diagrams and/or block diagrams and/or flow diagrams can be implemented by computer program instructions. .
  • these computer program instructions can be implemented by a general purpose computer, a professional computer, or a processor of other programmable data processing methods, such that the processor is executed by a computer or other programmable data processing method.
  • steps, measures, and solutions in the various operations, methods, and processes that have been discussed in the present invention may be alternated, changed, combined, or deleted. Further, other steps, measures, and schemes of the various operations, methods, and processes that have been discussed in the present invention may be alternated, modified, rearranged, decomposed, combined, or deleted. Further, the steps, measures, and solutions in the prior art having various operations, methods, and processes disclosed in the present invention may also be alternated, changed, rearranged, decomposed, combined, or deleted.

Landscapes

  • Manipulator (AREA)

Abstract

本发明揭示了一种机器人移动方法，所述方法包括以下步骤：通过声音采集装置进行声源定位，确定目标的方向；将摄像头朝向目标，并通过摄像头检测目标；当检测到目标时，通过摄像头进行视觉定位，确定目标所在位置；向目标所在位置移动，从而实现了精确调整机器人与用户的朝向关系和距离关系，保证机器人能够更好的接收用户的语音指令，极大的提升了用户体验。

Description

机器人移动方法、机器人移动装置、扫地机器人 技术领域
本发明涉及机器人技术领域，特别是涉及到一种机器人移动方法、机器人移动装置、扫地机器人。
 背景技术
随着科技的发展，越来越多的智能生活电器进入了家庭，大大提高了人们的生活舒适性和便利性，其中，扫地机器人是最受广大用户青睐的智能生活电器之一。扫地机器人，又称自动打扫机、智能吸尘器、机器人吸尘器等，能凭借一定的人工智能，自动、自主地在房间内完成地面清理工作。
目前的扫地机器人还增加了语音识别功能，通过语音识别功能，扫地机器人能够接受用户的语音指令，并根据语音指令执行相应的动作。当用户离扫地机器人较远时，扫地机器人则通过声源定位技术来确定用户的位置，再移动到用户所在位置接收用户的语音指令。
然而，声源定位的定位精度不高，只能确定大致的位置，使得扫地机器人不能及时准确的移动到用户跟前，常常出现没有面向用户或者与用户距离较大的情形，从而导致扫地机器人无法准确的接收用户的语音指令，影响用户体验。
 技术问题
本发明的主要目的为提供一种机器人移动方法和装置，旨在解决机器人无法准确的移动到用户跟前的技术问题。
 技术解决方案
为达以上目的，本发明实施例提出一种机器人移动方法，所述方法包括以下步骤：
通过声音采集装置进行声源定位，确定目标的方向；
将摄像头朝向所述目标，并通过所述摄像头检测所述目标；
当检测到所述目标时，通过所述摄像头进行视觉定位，确定所述目标所在位置；
向所述目标所在位置移动。
可选地，所述摄像头为单目摄像头，所述通过所述摄像头进行视觉定位，确定所述目标所在位置的步骤包括：
通过所述单目摄像头采集所述目标的图像；
朝所述目标方向移动一段距离，再次通过所述单目摄像头采集所述目标的图像；
根据前后两次采集的所述目标的图像确定所述目标所在位置。
可选地，所述摄像头为双目摄像头，所述通过所述摄像头进行视觉定位，确定所述目标所在位置的步骤包括：
通过所述双目摄像头采集所述目标的图像；
根据所述目标的图像确定所述目标所在位置。
可选地，所述通过所述摄像头检测所述目标的步骤包括：
当没有检测到所述目标时，躲避遮挡所述目标的障碍物，直到检测到所述目标为止。
可选地，所述躲避遮挡所述目标的障碍物，直到检测到所述目标为止的步骤包括：
朝所述目标方向移动；
当碰到障碍物时，沿着所述障碍物的边界移动，直到检测到所述目标为止。
可选地，所述躲避遮挡所述目标的障碍物，直到检测到所述目标为止的步骤包括：往所述目标方向的侧向移动，直到检测到所述目标为止。
可选地，所述通过所述摄像头检测所述目标的步骤包括：
通过所述摄像头进行人脸识别检测；
当检测到人脸时，确定检测到所述目标。
可选地，所述向所述目标所在位置移动的步骤包括：
以当前所在位置为起点、所述目标所在位置为终点规划移动路径；
沿着所述移动路径向所述终点移动。
可选地，所述方法还包括：当所述目标的位置发生变化时，重新规划所述移动路径。
可选地，所述机器人为扫地机器人。
本发明实施例同时提出一种机器人移动装置，所述装置包括：
方向确定模块，用于通过声音采集装置进行声源定位，确定目标的方向；
目标检测模块，用于将摄像头朝向所述目标，并通过所述摄像头检测所述目标；
位置确定模块，用于当检测到所述目标时，通过所述摄像头进行视觉定位，确定所述目标所在位置；
移动控制模块，用于控制所述机器人向所述目标所在位置移动。
可选地，所述摄像头为单目摄像头，所述位置确定模块包括：
第一采集单元，用于通过所述单目摄像头采集所述目标的图像；
第二采集单元，用于控制所述机器人朝所述目标方向移动一段距离，再次通过所述单目摄像头采集所述目标的图像；
第一确定单元，用于根据前后两次采集的所述目标的图像确定所述目标所在位置。
可选地，所述摄像头为双目摄像头，所述位置确定模块包括：
第三采集单元，用于通过所述双目摄像头采集所述目标的图像；
第二确定单元，用于根据所述目标的图像确定所述目标所在位置。
可选地，所述装置还包括避障模块，所述避障模块用于：
当没有检测到所述目标时，躲避遮挡所述目标的障碍物，直到所述目标检测模块检测到所述目标为止。
可选地，所述避障模块包括：
第一移动单元，用于控制所述机器人朝所述目标方向移动；
第二移动单元，用于当碰到障碍物时，控制所述机器人沿着所述障碍物的边界移动，直到所述目标检测模块检测到所述目标为止。
可选地，所述避障模块包括第三移动单元，所述第三移动单元用于：控制所述机器人往所述目标方向的侧向移动，直到所述目标检测模块检测到所述目标为止。
可选地，目标检测模块包括：
人脸识别单元，用于通过所述摄像头进行人脸识别检测；
目标确定单元，用于当检测到人脸时，确定检测到所述目标。
可选地，所述移动控制模块包括：
路径规划单元，用于以当前所在位置为起点、所述目标所在位置为终点规划移动路径；
移动控制单元，用于控制所述机器人沿着所述移动路径向所述终点移动。
可选地，所述移动控制模块还包括路径更新单元，所述路径更新单元用于：当所述目标的位置发生变化时，重新规划所述移动路径。
本发明实施例还提出一种扫地机器人，其包括存储器、处理器和至少一个被存储在所述存储器中并被配置为由所述处理器执行的应用程序，所述应用程序被配置为用于执行前述机器人移动方法。
 有益效果
本发明实施例所提供的一种机器人移动方法，通过声源定位确定目标方向以将摄像头朝向目标，再利用摄像头进行视觉定位来确定目标的准确位置，使得机器人能够快速准确的移动到用户（目标）跟前，解决了机器人无法准确的移动到用户跟前的技术问题，实现了精确调整机器人与用户的朝向关系和距离关系，保证机器人能够更好的接收用户的语音指令，极大的提升了用户体验。
 附图说明
图1是本发明的机器人移动方法第一实施例的流程图；
图2是本发明实施例中机器人的结构示意图；
图3是本发明实施例中机器人的摄像头朝向目标的示意图；
图4是本发明的机器人移动方法第二实施例的流程图；
图5是本发明实施例中机器人躲避遮挡目标的障碍物的示意图；
图6是本发明实施例中机器人躲避遮挡目标的障碍物的又一示意图；
图7是本发明的机器人移动装置第一实施例的模块示意图；
图8是图7中的目标检测模块的模块示意图；
图9是图7中的位置确定模块的模块示意图；
图10是图7中的位置确定模块的又一模块示意图；
图11是图7中的移动控制模块的模块示意图；
图12是图7中的移动控制模块的模块示意图；
图13是本发明的机器人移动装置第二实施例的模块示意图；
图14是图13中的避障模块的模块示意图。
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
 本发明的最佳实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
下面详细描述本发明的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本发明，而不能解释为对本发明的限制。
本技术领域技术人员可以理解，除非特意声明，这里使用的单数形式“一”、“一个”、“所述”和“该”也可包括复数形式。应该进一步理解的是，本发明的说明书中使用的措辞“包括”是指存在所述特征、整数、步骤、操作、元件和/或组件，但是并不排除存在或添加一个或多个其他特征、整数、步骤、操作、元件、组件和/或它们的组。应该理解，当我们称元件被“连接”或“耦接”到另一元件时，它可以直接连接或耦接到其他元件，或者也可以存在中间元件。此外，这里使用的“连接”或“耦接”可以包括无线连接或无线耦接。这里使用的措辞“和/或”包括一个或更多个相关联的列出项的全部或任一单元和全部组合。
本技术领域技术人员可以理解，除非另外定义，这里使用的所有术语（包括技术术语和科学术语），具有与本发明所属领域中的普通技术人员的一般理解相同的意义。还应该理解的是，诸如通用字典中定义的那些术语，应该被理解为具有与现有技术的上下文中的意义一致的意义，并且除非像这里一样被特定定义，否则不会用理想化或过于正式的含义来解释。
本发明实施例的机器人移动方法和装置，可以应用于各种机器人，尤其适用于扫地机器人。以下以扫地机器人为例进行详细说明。
参照图1，提出本发明的机器人移动方法第一实施例，所述方法包括以下步骤：
S11、通过声音采集装置进行声源定位，确定目标的方向。
本发明实施例中的声音采集装置优选为麦克风阵列，如图2所示，扫地机器人100上设置有由四个麦克风101组成的麦克风阵列和一个摄像头102。扫地机器人利用麦克风阵列采集声源发出的声音，采用声源定位技术进行声源定位，从而确定声源即目标的方向。声源定位技术是比较成熟的现有技术，在此不再赘述。
这里的目标主要指人（用户），当然也可以是其他能够发声的发声物，本发明对此不作限定。
S12、将摄像头朝向目标，并通过摄像头检测目标。判断是否检测到目标，当检测到目标时，进入步骤S13；当没有检测到目标时，结束流程。
当确定了目标的方向后，扫地机器人则将摄像头朝向目标，如旋转摄像头使其对准目标或者整个机器人旋转对准目标，并启动摄像头，通过摄像头检测目标。如图3所示，扫地机器人100的摄像头102对准目标200，以使目标200在摄像头102的视野范围内（摄像头102延伸的两个边线所在范围）。
当目标为人时，扫地机器人可以通过摄像头进行人脸识别检测，当检测到人脸时，则确定检测到目标，否则确定没有检测到目标。人脸识别技术是比较成熟的现有技术，在此不再赘述。
除了采用人脸识别技术对人进行识别检测外，还可以识别检测人体的其它可视特征来实现目标检测，本发明在此不再一一列举赘述。
当目标为其他的发声物，则可以通过识别检测该发声物的可视特征来实现目标检测。
S13、通过摄像头进行视觉定位，确定目标所在位置。
当检测到目标时，扫地机器人则通过摄像头采用视觉定位技术对目标进行视觉定位，确定目标所在位置。
可选地，当摄像头为单目摄像头时，扫地机器人可以先在原地通过单目摄像头采集目标的图像，接着朝目标方向移动一段距离，再次通过单目摄像头采集目标的图像，最后根据前后两次采集的目标的图像分析计算出目标的三维坐标，确定目标所在位置。通过两个位置采集的图像计算出目标的三维坐标的具体方法与现有技术相同，在此不赘述。
可选地，当摄像头为双目摄像头时，扫地机器人可以直接在原地通过双目摄像头采集目标的图像，每采集一次均获取具有视差的两幅图像，利用具有视差的两幅图像分析计算出目标的三维坐标，确定目标所在位置。利用具有视差的两幅图像分析计算出目标的三维坐标的具体方法与现有技术相同，在此不赘述。
S14、向目标所在位置移动。
当确定了目标所在位置后，扫地机器人则向目标所在位置移动，直到移动到与目标保持一定距离后停止移动，然后通过声音采集装置接收目标的语音指令，根据语音指令执行相应的动作。
向目标所在位置移动时，扫地机器人可以以当前所在位置为起点、目标所在位置为终点规划移动路径，然后沿着移动路径向终点移动，最终到达目标所在位置。
进一步地，当在移动过程中目标的位置发生变化时，扫地机器人则重新规划移动路径，沿着重新规划的移动路径向终点移动。从而当目标移动时，扫地机器人也能跟随目标移动，实现对目标的实时跟踪随行。
从而，通过声源定位+视觉定位的方式来确定目标的准确位置，使得机器人能够快速准确的移动到用户（目标）跟前，解决了机器人无法准确的移动到用户跟前的技术问题。
参照图4，提出本发明的机器人移动方法第二实施例，所述方法包括以下步骤：
S21、通过声音采集装置进行声源定位，确定目标的方向。
S22、将摄像头朝向目标，并通过摄像头检测目标。判断是否检测到目标，当没有检测到目标时，进入步骤S23；当检测到目标时，进入步骤S24。
S23、躲避遮挡目标的障碍物，直到检测到目标为止。
S24、通过摄像头进行视觉定位，确定目标所在位置。
S25、向目标所在位置移动。
考虑到扫地机器人与目标之间可能有障碍物，当扫地机器人在原地没有检测到目标时，说明扫地机器人的摄像头的视野被障碍物所遮挡，因此本实施例在第一实施例的基础上增加了步骤S23， 当扫地机器人在原地没有检测到目标时，则躲避遮挡目标的障碍物，直到检测到目标为止，从而使得扫地机器人即使被障碍物遮挡也能自动躲避障碍物到达用户身边。
扫地机器人可以通过以下方式躲避遮挡目标的障碍物：
可选地，如图5所示，当扫地机器人100的摄像头102的视线被障碍物300遮挡，无法检测到目标200时，扫地机器人100先朝目标200方向移动，当碰到障碍物300时，再沿着障碍物300的边界移动，直到检测到目标200为止。在沿着障碍物300的边界移动过程中，摄像头102始终朝向目标200，当移动到障碍物300的边缘时，摄像头102的视线（如虚线所示）就避开了障碍物300并到达目标200，从而能够检测到目标200。当检测到目标200时，扫地机器人100则通过摄像头102进行视觉定位，确定目标200所在位置，并向目标200所在位置移动。
可选地，如图6所示，当扫地机器人100的摄像头102的视线被障碍物300遮挡，无法检测到目标200时，扫地机器人100则往目标200方向的侧向移动，直到检测到目标200为止。侧向与目标200方向优选呈锐角，如45-90度角之间，以尽量减少移动距离，当然也可以呈直角或钝角。在往侧向移动过程中，摄像头102是始终朝向目标200的，当移动到障碍物300边缘位置时，摄像头102的视线（如虚线所示）就避开了障碍物300并到达目标200，从而能够检测到目标200。当检测到目标200时，扫地机器人100则通过摄像头102进行视觉定位，确定目标200所在位置，并向目标200所在位置移动。
本发明实施例的机器人移动方法，通过声源定位确定目标方向以将摄像头朝向目标，再利用摄像头进行视觉定位来确定目标的准确位置，使得机器人能够快速准确的移动到用户（目标）跟前，解决了机器人无法准确的移动到用户跟前的技术问题，实现了精确调整机器人与用户的朝向关系和距离关系，保证机器人能够更好的接收用户的语音指令，极大的提升了用户体验。
并且，本发明实施例中，机器人还能够主动识别用户，实现跟随等操作，交互体验更加丰富，用户体验更佳。
参照图7，提出本发明的机器人移动装置第一实施例，所述装置包括方向确定模块10、目标检测模块20、位置确定模块30和移动控制模块40，其中：方向确定模块10，用于通过声音采集装置进行声源定位，确定目标的方向；目标检测模块20，用于将摄像头朝向所述目标，并通过摄像头检测目标；位置确定模块30，用于当检测到目标时，通过摄像头进行视觉定位，确定目标所在位置；移动控制模块40，用于控制机器人向目标所在位置移动。
本发明实施例中的声音采集装置优选为麦克风阵列，如图2所示，扫地机器人100上设置有由四个麦克风101组成的麦克风阵列和一个摄像头102。方向确定模块10利用麦克风阵列采集声源发出的声音，采用声源定位技术进行声源定位，从而确定声源即目标的方向。声源定位技术是比较成熟的现有技术，在此不再赘述。这里的目标主要指人（用户），当然也可以是其他能够发声的发声物，本发明对此不作限定。
当确定了目标的方向后，目标检测模块20则将摄像头朝向目标，如旋转摄像头使其对准目标或者控制整个机器人旋转对准目标，并启动摄像头，通过摄像头检测目标。如图3所示，目标检测模块20控制扫地机器人100的摄像头102对准目标200，以使目标200在摄像头102的视野范围内（摄像头102延伸的两个边线所在范围）。
当目标为人时，目标检测模块20可以通过人脸识别技术进行目标检测。如图8所示，目标检测模块20包括人脸识别单元21和目标确定单元22，其中：人脸识别单元21，用于通过摄像头进行人脸识别检测；目标确定单元22，用于当检测到人脸时，确定检测到目标，否则确定没有检测到目标。人脸识别技术是比较成熟的现有技术，在此不再赘述。
目标检测模块20除了采用人脸识别技术对人进行识别检测外，还可以识别检测人体的其它可视特征来实现目标检测，本发明在此不再一一列举赘述。
当目标为其他的发声物，目标检测模块20则可以通过识别检测该发声物的可视特征来实现目标检测。
当检测到目标时，位置确定模块30则通过摄像头采用视觉定位技术对目标进行视觉定位，确定目标所在位置。
可选地，当摄像头为单目摄像头时，位置确定模块30如图9所示，包括第一采集单元31、第二采集单元32和第一确定单元33，其中：第一采集单元31，用于通过单目摄像头采集目标的图像；第二采集单元32，用于控制机器人朝目标方向移动一段距离，再次通过单目摄像头采集目标的图像；第一确定单元33，用于根据前后两次采集的目标的图像分析计算出目标的三维坐标，确定目标所在位置。通过两个位置采集的图像计算出目标的三维坐标的具体方法与现有技术相同，在此不赘述。
可选地，当摄像头为双目摄像头时，位置确定模块30如图10所示，包括第三采集单元34和第二确定单元35，其中：第三采集单元34，用于通过双目摄像头采集目标的图像，每采集一次均获取具有视差的两幅图像；第二确定单元35，用于根据目标的图像确定目标所在位置，如：利用具有视差的两幅图像分析计算出目标的三维坐标，确定目标所在位置。利用具有视差的两幅图像分析计算出目标的三维坐标的具体方法与现有技术相同，在此不赘述。
当确定了目标所在位置后，移动控制模块40则控制机器人向目标所在位置移动，直到移动到与目标保持一定距离后停止移动。然后机器人则可以通过声音采集装置接收目标的语音指令，根据语音指令执行相应的动作。
移动控制模块40如图11所示，包括路径规划单元41和移动控制单元42，其中：路径规划单元41，用于以当前所在位置为起点、目标所在位置为终点规划移动路径；移动控制单元42，用于控制机器人沿着移动路径向终点移动，最终到达目标所在位置。
进一步地，如图12所示，移动控制模块40还可以包括路径更新单元43，该路径更新单元43用于：当目标的位置发生变化时，重新规划移动路径。移动控制单元42则沿着重新规划的移动路径向终点移动。从而当目标移动时，扫地机器人也能跟随目标移动，实现对目标的实时跟踪随行。
从而，通过声源定位+视觉定位的方式来确定目标的准确位置，使得机器人能够快速准确的移动到用户（目标）跟前，解决了机器人无法准确的移动到用户跟前的技术问题。
参照图13，提出本发明的机器人移动装置第二实施例，本实施例在第一实施例的基础上增加了避障模块50，该避障模块50用于：当目标检测模块20没有检测到目标时，躲避遮挡目标的障碍物，直到目标检测模块20检测到目标为止，从而使得扫地机器人即使被障碍物遮挡也能自动躲避障碍物到达用户身边。
本发明实施例中，避障模块50如图14所示，包括第一移动单元51和第二移动单元52，其中：第一移动单元51，用于控制机器人朝目标方向移动；第二移动单元52，用于当碰到障碍物时，控制机器人沿着障碍物的边界移动，直到目标检测模块20检测到目标为止。
如图5所示，当机器人100的摄像头102的视线被障碍物300遮挡，目标检测模块20无法检测到目标200时，第一移动单元51则控制机器人100朝目标200方向移动，当碰到障碍物300时，第二移动单元52再控制机器人100沿着障碍物300的边界移动，直到目标检测模块20检测到目标200为止。机器人100在沿着障碍物300的边界移动过程中，摄像头102是始终朝向目标200的，当移动到障碍物300的边缘时，摄像头102的视线（如虚线所示）就避开了障碍物300并到达目标200，从而目标检测模块20就能够检测到目标200。
在另一些实施例中，避障模块50包括第三移动单元，该第三移动单元用于：控制机器人往目标方向的侧向移动，直到目标检测模块20检测到目标为止。
如图6所示，当机器人100的摄像头102的视线被障碍物300遮挡，目标检测模块20无法检测到目标200时，第三移动单元则控制机器人100往目标200方向的侧向移动，直到检测到目标200为止。侧向与目标200方向优选呈锐角，如45-90度角之间，以尽量减少移动距离，当然也可以呈直角或钝角。机器人100在往侧向移动过程中，摄像头102是始终朝向目标200的，当移动到障碍物300边缘位置时，摄像头102的视线（如虚线所示）就避开了障碍物300并到达目标200，从而目标检测模块20就能够检测到目标200。
本发明实施例的机器人移动装置，通过声源定位确定目标方向以将摄像头朝向目标，再利用摄像头进行视觉定位来确定目标的准确位置，使得机器人能够快速准确的移动到用户（目标）跟前，解决了机器人无法准确的移动到用户跟前的技术问题，实现了精确调整机器人与用户的朝向关系和距离关系，保证机器人能够更好的接收用户的语音指令，极大的提升了用户体验。
本发明同时提出一种扫地机器人，其包括存储器、处理器和至少一个被存储在存储器中并被配置为由处理器执行的应用程序，所述应用程序被配置为用于执行机器人移动方法。所述机器人移动方法包括以下步骤：通过声音采集装置进行声源定位，确定目标的方向；将摄像头朝向目标，并通过摄像头检测目标；当检测到目标时，通过摄像头进行视觉定位，确定目标所在位置；向目标所在位置移动。本实施例中所描述的机器人移动方法为本发明中上述实施例所涉及的机器人移动方法，在此不再赘述。
本领域技术人员可以理解，本发明包括涉及用于执行本申请中所述操作中的一项或多项的设备。这些设备可以为所需的目的而专门设计和制造，或者也可以包括通用计算机中的已知设备。这些设备具有存储在其内的计算机程序，这些计算机程序选择性地激活或重构。这样的计算机程序可以被存储在设备（例如，计算机）可读介质中或者存储在适于存储电子指令并分别耦联到总线的任何类型的介质中，所述计算机可读介质包括但不限于任何类型的盘（包括软盘、硬盘、光盘、CD-ROM、和磁光盘）、ROM（Read-Only Memory，只读存储器）、RAM（Random Access Memory，随机存储器）、EPROM（Erasable Programmable Read-Only Memory，可擦写可编程只读存储器）、EEPROM（Electrically Erasable Programmable Read-Only Memory，电可擦可编程只读存储器）、闪存、磁性卡片或光线卡片。也就是，可读介质包括由设备（例如，计算机）以能够读的形式存储或传输信息的任何介质。
本技术领域技术人员可以理解，可以用计算机程序指令来实现这些结构图和/或框图和/或流图中的每个框以及这些结构图和/或框图和/或流图中的框的组合。本技术领域技术人员可以理解，可以将这些计算机程序指令提供给通用计算机、专业计算机或其他可编程数据处理方法的处理器来实现，从而通过计算机或其他可编程数据处理方法的处理器来执行本发明公开的结构图和/或框图和/或流图的框或多个框中指定的方案。
本技术领域技术人员可以理解，本发明中已经讨论过的各种操作、方法、流程中的步骤、措施、方案可以被交替、更改、组合或删除。进一步地，具有本发明中已经讨论过的各种操作、方法、流程中的其他步骤、措施、方案也可以被交替、更改、重排、分解、组合或删除。进一步地，现有技术中的具有与本发明中公开的各种操作、方法、流程中的步骤、措施、方案也可以被交替、更改、重排、分解、组合或删除。
以上所述仅为本发明的优选实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。

Claims (20)

  1. 一种机器人移动方法，其特征在于，包括以下步骤：
    通过声音采集装置进行声源定位，确定目标的方向；
    将摄像头朝向所述目标，并通过所述摄像头检测所述目标；
    当检测到所述目标时，通过所述摄像头进行视觉定位，确定所述目标所在位置；
    向所述目标所在位置移动。
  2. 根据权利要求1所述的机器人移动方法，其特征在于，所述摄像头为单目摄像头，所述通过所述摄像头进行视觉定位，确定所述目标所在位置的步骤包括：
    通过所述单目摄像头采集所述目标的图像；
    朝所述目标方向移动一段距离，再次通过所述单目摄像头采集所述目标的图像；
    根据前后两次采集的所述目标的图像确定所述目标所在位置。
  3. 根据权利要求1所述的机器人移动方法，其特征在于，所述摄像头为双目摄像头，所述通过所述摄像头进行视觉定位，确定所述目标所在位置的步骤包括：
    通过所述双目摄像头采集所述目标的图像；
    根据所述目标的图像确定所述目标所在位置。
  4. 根据权利要求1-3任一项所述的机器人移动方法，其特征在于，所述通过所述摄像头检测所述目标的步骤包括：
    当没有检测到所述目标时，躲避遮挡所述目标的障碍物，直到检测到所述目标为止。
  5. 根据权利要求4所述的机器人移动方法，其特征在于，所述躲避遮挡所述目标的障碍物，直到检测到所述目标为止的步骤包括：
    朝所述目标方向移动；
    当碰到障碍物时，沿着所述障碍物的边界移动，直到检测到所述目标为止。
  6. 根据权利要求4所述的机器人移动方法，其特征在于，所述躲避遮挡所述目标的障碍物，直到检测到所述目标为止的步骤包括：
    往所述目标方向的侧向移动，直到检测到所述目标为止。
  7. 根据权利要求1所述的机器人移动方法，其特征在于，所述通过所述摄像头检测所述目标的步骤包括：
    通过所述摄像头进行人脸识别检测；
    当检测到人脸时，确定检测到所述目标。
  8. 根据权利要求1所述的机器人移动方法，其特征在于，所述向所述目标所在位置移动的步骤包括：
    以当前所在位置为起点、所述目标所在位置为终点规划移动路径；
    沿着所述移动路径向所述终点移动。
  9. 根据权利要求8所述的机器人移动方法，其特征在于，所述方法还包括：当所述目标的位置发生变化时，重新规划所述移动路径。
  10. 根据权利要求1所述的机器人移动方法，其特征在于，所述机器人为扫地机器人。
  11. 一种机器人移动装置，其特征在于，包括：
    方向确定模块，用于通过声音采集装置进行声源定位，确定目标的方向；
    目标检测模块，用于将摄像头朝向所述目标，并通过所述摄像头检测所述目标；
    位置确定模块，用于当检测到所述目标时，通过所述摄像头进行视觉定位，确定所述目标所在位置；
    移动控制模块，用于控制所述机器人向所述目标所在位置移动。
  12. 根据权利要求11所述的机器人移动装置，其特征在于，所述摄像头为单目摄像头，所述位置确定模块包括：
    第一采集单元，用于通过所述单目摄像头采集所述目标的图像；
    第二采集单元，用于控制所述机器人朝所述目标方向移动一段距离，再次通过所述单目摄像头采集所述目标的图像；
    第一确定单元，用于根据前后两次采集的所述目标的图像确定所述目标所在位置。
  13. 根据权利要求11所述的机器人移动装置，其特征在于，所述摄像头为双目摄像头，所述位置确定模块包括：
    第三采集单元，用于通过所述双目摄像头采集所述目标的图像；
    第二确定单元，用于根据所述目标的图像确定所述目标所在位置。
  14. 根据权利要求11-13任一项所述的机器人移动装置，其特征在于，所述装置还包括避障模块，所述避障模块用于：
    当没有检测到所述目标时，躲避遮挡所述目标的障碍物，直到所述目标检测模块检测到所述目标为止。
  15. 根据权利要求14所述的机器人移动装置，其特征在于，所述避障模块包括：
    第一移动单元，用于控制所述机器人朝所述目标方向移动；
    第二移动单元，用于当碰到障碍物时，控制所述机器人沿着所述障碍物的边界移动，直到所述目标检测模块检测到所述目标为止。
  16. 根据权利要求14所述的机器人移动装置，其特征在于，所述避障模块包括第三移动单元，所述第三移动单元用于：控制所述机器人往所述目标方向的侧向移动，直到所述目标检测模块检测到所述目标为止。
  17. 根据权利要求11所述的机器人移动装置，其特征在于，目标检测模块包括：
    人脸识别单元，用于通过所述摄像头进行人脸识别检测；
    目标确定单元，用于当检测到人脸时，确定检测到所述目标。
  18. 根据权利要求11所述的机器人移动装置，其特征在于，所述移动控制模块包括：
    路径规划单元，用于以当前所在位置为起点、所述目标所在位置为终点规划移动路径；
    移动控制单元，用于控制所述机器人沿着所述移动路径向所述终点移动。
  19. 根据权利要求18所述的机器人移动装置，其特征在于，所述移动控制模块还包括路径更新单元，所述路径更新单元用于：
    当所述目标的位置发生变化时，重新规划所述移动路径。
  20. 一种扫地机器人，包括存储器、处理器和至少一个被存储在所述存储器中并被配置为由所述处理器执行的应用程序，其特征在于，所述应用程序被配置为用于执行权利要求1所述的机器人移动方法。
PCT/CN2018/077604 2018-01-15 2018-02-28 机器人移动方法、机器人移动装置、扫地机器人 Ceased WO2019136808A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810036671.1A CN108245099A (zh) 2018-01-15 2018-01-15 机器人移动方法和装置
CN201810036671.1 2018-01-15

Publications (1)

Publication Number Publication Date
WO2019136808A1 true WO2019136808A1 (zh) 2019-07-18

Family

ID=62727331

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/077604 Ceased WO2019136808A1 (zh) 2018-01-15 2018-02-28 机器人移动方法、机器人移动装置、扫地机器人

Country Status (2)

Country Link
CN (1) CN108245099A (zh)
WO (1) WO2019136808A1 (zh)

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019109853A (ja) * 2017-12-20 2019-07-04 東芝ライフスタイル株式会社 自律走行体および自律走行体システム
CN112703504A (zh) * 2018-10-19 2021-04-23 深圳新物种科技有限公司 对象识别方法、装置、电子设备及计算机可读存储介质
CN111067354B (zh) * 2018-10-19 2022-06-07 佛山市顺德区美的饮水机制造有限公司 饮水机及其移动方法与装置
CN110916576A (zh) * 2018-12-13 2020-03-27 成都家有为力机器人技术有限公司 基于声音和图像识别指令的清洁方法及清洁机器人
TWI731331B (zh) * 2019-05-10 2021-06-21 中興保全科技股份有限公司 移動式保全裝置
WO2021062681A1 (zh) * 2019-09-30 2021-04-08 中新智擎科技有限公司 一种自动送餐的方法、装置及机器人
CN111008571B (zh) * 2019-11-15 2023-04-18 万翼科技有限公司 室内垃圾处理方法及相关产品
CN111012252A (zh) * 2019-12-20 2020-04-17 小狗电器互联网科技（北京）股份有限公司 一种扫地机控制方法及装置
CN110946518A (zh) * 2019-12-20 2020-04-03 小狗电器互联网科技（北京）股份有限公司 一种扫地机控制方法及装置
CN110881909A (zh) * 2019-12-20 2020-03-17 小狗电器互联网科技（北京）股份有限公司 一种扫地机控制方法及装置
CN110946519A (zh) * 2019-12-20 2020-04-03 小狗电器互联网科技（北京）股份有限公司 一种扫地机控制方法及装置
CN112043206A (zh) * 2020-09-01 2020-12-08 珠海格力电器股份有限公司 一种扫拖一体机及其清洁方法
CN112656309A (zh) * 2020-12-25 2021-04-16 北京小狗吸尘器集团股份有限公司 扫地机的功能执行方法、装置、可读存储介质及电子设备
CN112597910B (zh) * 2020-12-25 2024-05-07 北京小狗吸尘器集团股份有限公司 利用扫地机器人对人物活动进行监控的方法和装置
CN112842180A (zh) * 2020-12-31 2021-05-28 深圳市杉川机器人有限公司 扫地机器人及其测距避障方法、装置及可读存储介质
CN113679298B (zh) * 2021-08-27 2022-05-10 美智纵横科技有限责任公司 机器人的控制方法、控制装置、机器人和可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140156125A1 (en) * 2012-12-05 2014-06-05 National Chiao Tung University Autonomous electronic apparatus and navigation method thereof
CN105929827A (zh) * 2016-05-20 2016-09-07 北京地平线机器人技术研发有限公司 移动机器人及其定位方法
CN106210511A (zh) * 2016-06-30 2016-12-07 纳恩博（北京）科技有限公司 一种定位用户的方法和装置
CN106203259A (zh) * 2016-06-27 2016-12-07 旗瀚科技股份有限公司 机器人的交互方向调整方法及装置
CN107515606A (zh) * 2017-07-20 2017-12-26 北京格灵深瞳信息技术有限公司 机器人实现方法、控制方法及机器人、电子设备

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6971066B2 (en) * 1997-08-18 2005-11-29 National Instruments Corporation System and method for deploying a graphical program on an image acquisition device
KR20050108923A (ko) * 2004-05-14 2005-11-17 삼성광주전자 주식회사 모빌로봇, 모빌로봇 시스템, 및 그 경로보정방법
CN101295016B (zh) * 2008-06-13 2011-04-27 河北工业大学 一种声源自主搜寻定位方法
CN102138769B (zh) * 2010-01-28 2014-12-24 深圳先进技术研究院 清洁机器人及其清扫方法
CN103054522B (zh) * 2012-12-31 2015-07-29 河海大学 一种清洁机器人系统及其测控方法
CN104188598B (zh) * 2014-09-15 2016-09-07 湖南格兰博智能科技有限责任公司 一种自动地面清洁机器人
US9744670B2 (en) * 2014-11-26 2017-08-29 Irobot Corporation Systems and methods for use of optical odometry sensors in a mobile robot
CN104887155B (zh) * 2015-05-21 2017-05-31 南京创维信息技术研究院有限公司 智能扫地机
CN106527444B (zh) * 2016-11-29 2020-04-14 深圳市元征科技股份有限公司 清洁机器人的控制方法及清洁机器人
CN107491069B (zh) * 2017-08-31 2020-09-15 珠海市一微半导体有限公司 机器人遇到障碍物的处理方法及芯片

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140156125A1 (en) * 2012-12-05 2014-06-05 National Chiao Tung University Autonomous electronic apparatus and navigation method thereof
CN105929827A (zh) * 2016-05-20 2016-09-07 北京地平线机器人技术研发有限公司 移动机器人及其定位方法
CN106203259A (zh) * 2016-06-27 2016-12-07 旗瀚科技股份有限公司 机器人的交互方向调整方法及装置
CN106210511A (zh) * 2016-06-30 2016-12-07 纳恩博（北京）科技有限公司 一种定位用户的方法和装置
CN107515606A (zh) * 2017-07-20 2017-12-26 北京格灵深瞳信息技术有限公司 机器人实现方法、控制方法及机器人、电子设备

Also Published As

Publication number Publication date
CN108245099A (zh) 2018-07-06

Similar Documents

Publication Publication Date Title
CN108245099A (zh) 机器人移动方法和装置
CN109733384B (zh) 泊车路径设置方法及系统
CN106527444B (zh) 清洁机器人的控制方法及清洁机器人
WO2020140271A1 (zh) 移动机器人的控制方法、装置、移动机器人及存储介质
CN113675923B (zh) 充电方法、充电装置及机器人
CN105929827B (zh) 移动机器人及其定位方法
CN109933061A (zh) 基于人工智能的机器人及控制方法
WO2017071372A1 (zh) 具有自动返回充电功能的机器人、系统及对应方法
WO2019128109A1 (zh) 一种基于人脸追踪的动向投影方法、装置及电子设备
CN113679298B (zh) 机器人的控制方法、控制装置、机器人和可读存储介质
CN115542889B (zh) 机器人术前导航方法、系统、存储介质及计算机设备
CN109199240B (zh) 一种基于手势控制的扫地机器人控制方法及系统
CN110559127A (zh) 基于听觉与触觉引导的智能助盲系统及方法
CN110881909A (zh) 一种扫地机控制方法及装置
JP2008087140A (ja) 音声認識ロボットおよび音声認識ロボットの制御方法
CN109685709A (zh) 一种智能机器人的照明控制方法及装置
CN110897567A (zh) 一种基于目标物识别的清洁方法及清洁机器人
JP2008126329A (ja) 音声認識ロボットおよび音声認識ロボットの制御方法
CN112099500A (zh) 一种基于语音控制的家用智能垃圾桶、系统及其控制方法
CN108008394B (zh) 仿生声纳二维经历图绘制方法、存储介质及设备
CN103472434A (zh) 一种机器人声音定位方法
CN118058658A (zh) 清洁机器人的移动控制方法和清洁机器人
CN116380061B (zh) 一种移动机器人视听觉融合感知与导航方法
CN113520246B (zh) 移动机器人补偿清洁方法及系统
CN206170100U (zh) 机器人

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: 18900197

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18900197

Country of ref document: EP

Kind code of ref document: A1