WO2023197822A1 - 机器人控制方法、装置、机器人及存储介质 - Google Patents

机器人控制方法、装置、机器人及存储介质 Download PDF

Info

Publication number
WO2023197822A1
WO2023197822A1 PCT/CN2023/082092 CN2023082092W WO2023197822A1 WO 2023197822 A1 WO2023197822 A1 WO 2023197822A1 CN 2023082092 W CN2023082092 W CN 2023082092W WO 2023197822 A1 WO2023197822 A1 WO 2023197822A1
Authority
WO
WIPO (PCT)
Prior art keywords
obstacle
preset
robot
cross
type
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/CN2023/082092
Other languages
English (en)
French (fr)
Inventor
孙樱日
邬芮璠
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.)
Dreame Innovation Technology Suzhou Co Ltd
Original Assignee
Dreame Innovation Technology Suzhou 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 Dreame Innovation Technology Suzhou Co Ltd filed Critical Dreame Innovation Technology Suzhou Co Ltd
Publication of WO2023197822A1 publication Critical patent/WO2023197822A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1679—Program controls characterised by the tasks executed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
    • B25J19/0058—Means for cleaning manipulators, e.g. dust removing means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1602—Program controls characterised by the control system, structure, architecture
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1674—Program controls characterised by safety, monitoring, diagnostic
    • B25J9/1676—Avoiding collision or forbidden zones
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1694—Program controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
    • B25J9/1697—Vision controlled systems
    • 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

Definitions

  • the present disclosure belongs to the field of robot technology, and in particular relates to a robot control method, device, robot and storage medium.
  • the present disclosure proposes a robot control method, device, robot and storage medium.
  • This method does not require too many sensors to work together. It only needs to use a certain type of sensor or a certain type of sensor that can achieve the same function to collect cross-sectional data of obstacles.
  • the type of obstacle can be determined by analyzing the cross-sectional data, especially furniture can be accurately identified. Such objects can be quickly cleaned in areas where such obstacles are located.
  • a robot control method which method includes:
  • the obstacle information includes point cloud data of the cross-section of the obstacle
  • determining whether there is an obstacle that satisfies the preset first type based on the point cloud data of the cross-section of the obstacle specifically includes:
  • determining that the cross-sectional distribution satisfies a preset distribution situation specifically includes:
  • Determining that there is an obstacle that satisfies the preset first type includes:
  • the obstacle corresponding to the cross section constituting the rectangle or triangle of the preset size is determined as an obstacle that satisfies the preset first type.
  • the obstacle information also includes height information of the obstacle's bottom surface from the ground determined based on the obstacle's bottom surface point cloud data and the obstacle's bottom surface area;
  • the method also includes:
  • the corresponding cleaning mode is obtained and the robot is controlled to perform cleaning work according to the cleaning mode.
  • determining whether there is an obstacle that satisfies the preset second type based on the height information of the obstacle bottom surface from the ground and the bottom surface area of the obstacle specifically includes:
  • the cleaning mode includes a normal cleaning mode and an enhanced cleaning mode
  • the numerical values of the working parameters of the enhanced cleaning mode are greater than the numerical values of the working parameters of the normal cleaning mode; the working parameters include suction power;
  • Obtaining the corresponding cleaning mode and controlling the robot to perform cleaning work according to the cleaning mode specifically includes:
  • controlling the robot to perform cleaning work according to the movement strategy specifically includes:
  • a cleaning edge is determined based on the point cloud data of the cross-section of the obstacle, and the robot is controlled to clean within the area determined by the cleaning edge.
  • the method further includes:
  • the obstacle is marked in the preset map model based on the determined location information of the obstacle.
  • a robot control device which device includes:
  • An acquisition module used to acquire obstacle information during the movement of the robot; wherein the obstacle information includes point cloud data of the cross-section of the obstacle;
  • a processing module configured to determine whether there is an obstacle that satisfies a preset first type based on the point cloud data of the cross-section of the obstacle;
  • a control module configured to obtain a corresponding movement strategy and control the robot to perform cleaning work according to the movement strategy when it is determined that there is an obstacle that satisfies the preset first type.
  • a robot including a memory, a processor, and a computer program stored in the memory and executable on the processor.
  • the processor executes the computer program, the steps described in the first aspect are implemented. method described.
  • a computer-readable storage medium stores a computer program.
  • the computer program is executed by a processor, the method as described in the first aspect is implemented.
  • This disclosure uses point cloud data of the cross-section of the obstacle to determine the type of obstacle currently encountered. After determining the type, the robot is controlled to move accordingly. Compared with the existing technology, there is no need for too many sensors to work together. There is no need to use complex identification algorithms. You only need to use a certain type of sensor or a certain type of sensor that can achieve the same function to collect the cross-sectional data of the above obstacles. By analyzing the cross-sectional data, you can realize the identification of tables and chairs. The entire The identification process is efficient and fast, and it can also control the robot to perform cleaning work based on the corresponding movement strategy according to the characteristics of this type of obstacle;
  • This disclosure determines whether the obstacle is furniture such as tables and chairs by analyzing the width and distribution of the cross section.
  • the algorithm is simple and can achieve accurate identification;
  • This disclosure can also determine the type of obstacle based on the height information of the bottom of the obstacle from the ground and the area of the bottom of the obstacle, thereby achieving effective identification of beds and sofas, and at the same time, it can also quickly identify the location of such obstacles. Cleaning of the area;
  • this disclosure first makes a preliminary judgment on the height information of the bottom surface of the obstacle from the ground. When the height meets the conditions, the bottom surface area of the obstacle is judged again. Only when the bottom surface Only when the area meets the preset conditions will the current obstacle be determined as bed or sofa furniture. The entire judgment process ensures the accuracy of obstacle identification;
  • the cleaning mode is changed and the enhanced cleaning mode is used to control the robot to clean, making the area cleaner;
  • the present disclosure also realizes the position marking of obstacles, so that when the obstacle is encountered again later, the type can be quickly determined based on the pre-stored information to achieve cleaning work.
  • Figure 1 is an exemplary flow chart of a robot control method according to an embodiment of the present disclosure
  • Figure 2 is a schematic structural diagram of a robot control device according to an embodiment of the present disclosure
  • Figure 3 is a schematic structural diagram of a robot according to an embodiment of the present disclosure.
  • the inventor of the present disclosure creatively thought of using a depth camera to obtain point cloud data of obstacles for analysis and identification.
  • the point cloud data of the leg cross-section is used for identification and judgment.
  • the point cloud data such as the height of the edge from the bottom and the area of the bottom are used. Make identification and judgment, so that the cleaning work of the area where different types of furniture are located can be realized.
  • FIG. 1 shows an exemplary flow chart of a robot control method according to an embodiment of the present disclosure.
  • the details of the robot control method are as follows:
  • Step 101 Obtain obstacle information during the movement of the robot; wherein the obstacle information includes point cloud data of the cross-section of the obstacle.
  • the above obstacle information can be collected by sensing elements installed on the robot body.
  • a depth camera is used as the above-mentioned sensing element, specifically including a structured light camera, a TOF camera, etc. It should be understood that those skilled in the art can select corresponding depth cameras according to actual needs, and are not limited to structured light cameras and TOF cameras.
  • a depth camera is installed directly in front of the robot to obtain information about the front of the robot.
  • the cross section described in this embodiment refers to the pattern formed by the outer surface of the obstacle obtained within the reachable range of the sensing element. For example, if the obstacle is a tall column (for example, 2 meters), then since the entire column cannot be obtained within the reach of the sensing element, only partial area information can be collected. Therefore, the obtained The cross-section of some columns is a rectangle; if the obstacle is a door, the cross-section obtained by the sensor within the reachable range is also a rectangle. The difference from the above-mentioned columns is that the sizes of the two cross-sections are different. .
  • a structured light camera When a structured light camera is installed directly in front of the robot, if there is an obstacle such as a table in front of the robot, first, the projector of the structured light camera actively emits structural information to the surface of the obstacle (structural information can be laser stripes, Gray codes, sine stripes, etc. ), since the legs of the table are usually long, the structured light camera cannot project to the table, but can only project to the surface of the table legs; then, the surface of the table legs is photographed by its camera to obtain the structured light image of the table legs; finally, the The obtained structured light image of the table leg is processed to obtain the point cloud data of the cross-section of the table leg.
  • structural information can be laser stripes, Gray codes, sine stripes, etc.
  • TOF technology is different from structured light technology, it emits a continuous "area light source", so the light will be reflected when it encounters impenetrable objects.
  • TOF technology is different from structured light technology, it emits a continuous "area light source", so the light will be reflected when it encounters impenetrable objects.
  • the known light speed and light wavelength you can quickly calculate the distance between the current robot and the table leg, thereby obtaining a 3D image of the table leg, and then convert the table leg The 3D image is converted into point cloud data of the cross-section of the table leg.
  • the depth image collection of the table leg can be realized. After the coordinate change, the depth image can be converted into point cloud data of the cross section of the table leg, which facilitates subsequent use of the cross section. Point cloud data is analyzed and processed.
  • Step 102 Determine whether there is an obstacle that satisfies the preset first type based on the point cloud data of the obstacle's cross section.
  • the above-mentioned point cloud data based on the cross-section of the obstacle determines whether there is a preset first type
  • the obstacles specifically include:
  • the first type is a table and chair furniture type.
  • the robot when the robot is cleaning, there may be a variety of obstacles in front of it.
  • the data can be initially screened and the cross-sections can be extracted. All cross-sections whose widths meet the preset first threshold range.
  • the first threshold range can be set to 0 to 10 cm.
  • the distribution position of the cross-section of the obstacles after the initial screening is analyzed and processed. For example, it is possible that the obstacle has only one cross-section, then it is obviously not part of the table and chair furniture to be identified, so it will be excluded. Only when it is determined that the cross-sectional distribution satisfies the preset distribution situation, can it be determined that there is an obstacle that satisfies the preset first type, that is, it is determined that the current obstacle belongs to table and chair furniture.
  • the obstacle corresponding to the cross section constituting the rectangle or triangle of the preset size is determined as an obstacle that satisfies the preset first type.
  • tables and chairs are usually composed of four or three legs, so the corresponding cross-sectional distribution must also form a rectangle or triangle, and the size of the rectangle or triangle needs to meet certain conditions, such as a rectangle Or the side length of the triangle (straight-line distance between cross sections) is within the range of 40 to 80cm.
  • the obstacle corresponding to the cross-section constituting the rectangle or triangle of the preset size can be determined as an obstacle that satisfies the preset first type. , namely tables and chairs furniture.
  • the obstacles can also be classified based on the cross-sectional width.
  • the processing can be accelerated after classification; in addition, obstacles can be further distinguished, and for some furniture whose positions are easy to change (such as chairs) etc.), there may be no need to modify the current bit Mark the location to avoid affecting subsequent judgments.
  • This disclosure determines whether the obstacle is furniture such as tables and chairs by analyzing the width and distribution of the cross section.
  • the algorithm is simple and can achieve accurate identification.
  • Step 103 When it is determined that there is an obstacle that meets the preset first type, obtain the corresponding movement strategy and control the robot to perform cleaning work according to the movement strategy.
  • control of the robot to perform cleaning work according to the movement strategy specifically includes:
  • the edge of the obstacle in contact with the ground is determined, and the robot is controlled to clean the edge of the obstacle;
  • the cleaning edge is determined based on the point cloud data of the cross-section of the obstacle, and the robot is controlled to clean within the area determined by the cleaning edge.
  • the robot when the robot is cleaning, it first cleans the edge where the table legs are in contact with the ground.
  • the robot can be controlled to clean the above-mentioned area based on rotation, and then, it is determined that the edge formed by the table legs The cleaning edge controls the robot to clean in the area determined by the cleaning edge.
  • the current obstacle is a furniture type such as a table or chair
  • the entire floor area ensures the cleaning effect of the area.
  • the above-mentioned obstacle information also includes height information of the obstacle's bottom surface from the ground determined based on the obstacle's bottom surface point cloud data and the obstacle's bottom surface area;
  • the corresponding cleaning mode is obtained and the robot is controlled to perform cleaning work according to the cleaning mode.
  • the second type is a bed or sofa type furniture.
  • the above obstacle information can be collected by a depth camera installed on the robot body. Specifically, it can be any one of lidar, structured light camera, TOF camera, etc.
  • the above determination is based on the height information of the bottom surface of the obstacle from the ground and the area of the bottom surface of the obstacle. Whether there are obstacles that meet the preset second type includes:
  • a preliminary judgment is made on the height information of the bottom surface of the obstacle from the ground to complete the preliminary screening of obstacles. For example, if the second threshold range is 15 to 30 cm, then when the obtained height of the bottom surface of the obstacle from the ground is 25 cm, it can be determined that the current obstacle initially meets the preset conditions. It is then further analyzed to determine its base area. For example, if the third threshold range is 1 square meter to 2 square meters, when the obtained bottom area of the obstacle is 1 square meter, it can be determined that the specific type of the current obstacle is a bed, sofa and other furniture, and the entire processing process ensures that The accuracy of obstacle judgment is improved.
  • the cleaning mode includes a normal cleaning mode and an enhanced cleaning mode
  • the values of the working parameters of the enhanced cleaning mode are greater than the values of the working parameters of the normal cleaning mode; the working parameters include suction power;
  • the details include:
  • the suction power is a very important working parameter of most cleaning robots.
  • the suction power is large, the actual use effect of the cleaning robot can be good.
  • the cleaning mode is changed and the enhanced cleaning mode is used to control the robot to perform deep cleaning of the bottom area of such obstacles. Makes the area cleaner.
  • the robot control method of the embodiment of the present disclosure further includes:
  • the obstacle is marked in the preset map model based on the determined location information of the obstacle.
  • the present disclosure also realizes the labeling of obstacles, so that when the obstacle is encountered later, the type can be quickly determined based on the pre-stored information to achieve cleaning work.
  • This disclosure uses point cloud data of the obstacle cross-section to determine the type of obstacle currently encountered. After determining the type, the robot is controlled to move accordingly. Compared with the existing technology, there is no need for too many sensors to work together and no need for Using complex identification algorithms, you only need to use a certain type of sensor or a certain type of sensor that can achieve the same function to collect cross-sectional data of the above obstacles. By analyzing the cross-sectional data, you can realize the identification of tables and chairs.
  • the robot can be controlled to perform cleaning work based on the corresponding movement strategy according to the characteristics of this type of obstacle; this disclosure can also determine the location of the obstacle based on the height information of the bottom surface of the obstacle from the ground and the area of the bottom surface of the obstacle. type, thereby realizing It can effectively identify existing furniture such as beds and sofas, and can also quickly clean the area where such obstacles are located.
  • FIG. 2 As an implementation of the method shown in Figure 1 above, an embodiment of a robot control device is provided.
  • the device embodiment corresponds to the method embodiment shown in Figure 1.
  • this The robot control device of the embodiment includes:
  • the acquisition module 201 is used to acquire obstacle information during the movement of the robot; wherein the obstacle information includes point cloud data of the cross-section of the obstacle;
  • the processing module 202 is configured to determine whether there is an obstacle that satisfies the preset first type based on the point cloud data of the cross-section of the obstacle;
  • the control module 203 is configured to obtain the corresponding movement strategy and control the robot to perform cleaning work according to the movement strategy when it is determined that there is an obstacle that satisfies the preset first type.
  • the above processing module 202 is specifically used to:
  • the above processing module 202 is also specifically used to:
  • the obstacle corresponding to the cross section constituting the rectangle or triangle of the preset size is determined as an obstacle that satisfies the preset first type.
  • the obstacle information also includes height information of the obstacle's bottom surface from the ground determined based on the obstacle's bottom surface point cloud data and the obstacle's bottom surface area;
  • the above processing module 202 is also used to:
  • the above control module 203 is also used for:
  • the corresponding cleaning mode is obtained and the robot is controlled to perform cleaning work according to the cleaning mode.
  • the above-mentioned processing module 202 is also used to:
  • the cleaning mode includes a normal cleaning mode and an enhanced cleaning mode
  • the values of the working parameters of the enhanced cleaning mode are greater than the values of the working parameters of the normal cleaning mode; the working parameters include suction power;
  • the above control module 203 is also used to obtain the enhanced cleaning mode and control the robot to perform cleaning work according to the enhanced cleaning mode.
  • control module 203 is also used to:
  • the edge of the obstacle in contact with the ground is determined, and the robot is controlled to clean the edge of the obstacle;
  • the cleaning edge is determined based on the point cloud data of the cross-section of the obstacle, and the robot is controlled to clean within the area determined by the cleaning edge.
  • the above device also includes an annotation module 204 for:
  • the obstacle is marked in the preset map model based on the determined location information of the obstacle.
  • Figure 3 discloses a schematic diagram of a robot provided by an embodiment of the present disclosure.
  • the robot includes: a memory 31, a processor 32, and a computer program 33 stored in the memory 31 and executable on the processor 32, such as a program for a robot control method.
  • the processor 32 executes the computer program 33, it implements the steps in the above-mentioned embodiment of the robot control method, such as steps 101 to 103 shown in FIG. 1 .
  • the processor 32 executes the computer program 33, it implements the functions of each module in the above-mentioned embodiment of the robot control device, such as the functions of the modules 201 to 204 shown in Figure 2.
  • the above-mentioned robot also includes a measuring element 34 and a movement unit 35 .
  • the measuring element 34 may be a radar, a sensor, etc.; the radar may be a lidar or an infrared radar, and the lidar may be a single-line radar or a multi-line radar.
  • the movement unit 35 is used to control robot movement.
  • the processor 32 can be a central processing unit (Central Processing Unit, CPU), or other general-purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), Ready-made field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • CPU Central Processing Unit
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Ready-made field-programmable gate array
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
  • the memory 31 may be an internal storage unit of the robot, such as a hard disk or memory of the robot.
  • the memory 31 can also be an external storage device of the robot, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SD) card, a flash memory card ( Flash Card) wait.
  • the memory 31 may also include both an internal storage unit of the robot and an external storage device.
  • the memory 31 is used to store the computer program and other programs and data required by the robot.
  • the memory 31 can also be used to temporarily store data that has been output or is to be output.
  • Figure 3 is only an example of a robot and does not constitute a limitation to a robot. It may include more or fewer components than shown in the figure, or some components may be combined, or different components may be used. , for example, the robot may also include input and output devices, network access devices, buses, etc.
  • Module completion means dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above.
  • Each functional unit and module in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.
  • the above-mentioned integrated unit can be hardware-based. It can also be implemented in the form of software functional units.
  • the specific names of each functional unit and module are only for the convenience of distinguishing each other and are not used to limit the scope of the present disclosure. For the specific working processes of the units and modules in the above system, please refer to the corresponding processes in the foregoing method embodiments, and will not be described again here.
  • Embodiments of the present disclosure also provide a computer-readable storage medium that stores a computer program.
  • the computer program is executed by a processor, the steps in each of the above method embodiments can be implemented.
  • the program part in the technology can be considered as a "product” or “artifact” in the form of executable code and/or related data, which is participated in or implemented through computer-readable media.
  • Tangible, permanent storage media may include the memory or storage used by any computer, processor, or similar device or related module. For example, various semiconductor memories, tape drives, disk drives, or similar devices that provide storage capabilities for software.
  • All or portions of the Software may from time to time communicate over a network, such as the Internet or other communications networks. Such communications may load software from one computer device or processor to another. Therefore, another medium that can transmit software elements can also be used as a physical connection between local devices, such as light waves, radio waves, electromagnetic waves, etc., propagated through cables, optical cables, or air.
  • the physical medium used to carry the waves, such as cables, wireless connections, or fiber optic cables and similar devices, can also be considered the medium that carries the software.
  • tangible “storage” media other terms referring to computer or machine "readable media” mean media that participates in the execution of any instructions by the processor.

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种机器人控制方法，包括：获取机器人行进过程中的障碍物信息；其中，障碍物信息包括障碍物的横截面的点云数据；基于障碍物的横截面的点云数据确定是否存在满足预设第一类型的障碍物；在确定存在满足预设第一类型的障碍物的情况下，获取相应的移动策略并按照移动策略控制机器人进行清洁工作。该控制方法无需过多传感器进行协同工作，只需要使用某一种或者能实现相同功能的某一类传感器来采集障碍物的截面数据，通过分析截面数据确定障碍物的类型，尤其是能精确识别家具类物体，从而快速实现该类障碍物所在区域的清洁工作。还提供了一种机器人控制装置、机器人及存储介质。

Description

机器人控制方法、装置、机器人及存储介质
本公开要求如下专利申请的优先权：于2022年04月15日提交中国专利局、申请号为202210395433.6、发明名称为“机器人控制方法、装置、机器人及存储介质”的中国专利申请；上述专利申请的全部内容通过引用结合在本公开中。
技术领域
本公开属于机器人技术领域，尤其涉及一种机器人控制方法、装置、机器人及存储介质。
背景技术
近年来，随着科技的发展以及人们生活水平逐步提高，服务类机器人开始出现在市面上，提高了人们生活的便利性。扫地机器人作为一种服务类机器人，可以自动进行清扫工作，为人们解放了双手。
在家庭作业场景中，识别桌椅、沙发、床等这些常见的物体时，现有机器人会利用摄像头采集物体图像，使用机器学习算法(如模式识别等)对图像进行分析、得到物体类型，再根据测距传感器或者单目估计的方式计算物体的位置。上述处理方式需要多种传感器协同合作、算法复杂、处理过程过于单一，并且根据测距传感器或者单目估计的方法计算物体位置存在缺陷，对于一些较大的家具来说，由于摄像头等传感器的角度、安装位置等原因，无法获取物体的某些重要特征，从而可能导致无法准确识别类型并且位置估计也不再准确。
发明内容
为了解决现有技术的问题，本公开提出一种机器人控制方法、装置、机器人及存储介质。该方法无需过多传感器进行协同工作，只需要使用某一种或者能实现相同功能的某一类传感器来采集障碍物的截面数据，通过分析截面数据确定障碍物的类型，尤其是能精确识别家具类物体，从而快速实现该类障碍物所在区域的清洁工作。
本公开实施例提供的具体技术方案如下：
第一方面，提供一种机器人控制方法，所述方法包括：
获取机器人行进过程中的障碍物信息；其中，所述障碍物信息包括障碍物的横截面的点云数据；
基于所述障碍物的横截面的点云数据确定是否存在满足预设第一类型的障碍物；
在确定存在满足预设第一类型的障碍物的情况下，获取相应的移动策略并按照所述移动 策略控制所述机器人进行清洁工作。
在一些实施例中，所述基于所述障碍物的横截面的点云数据确定是否存在满足预设第一类型的障碍物具体包括：
基于所述障碍物的横截面的点云数据，提取出横截面宽度满足预设第一阈值范围的所有横截面；
获取所述横截面宽度满足预设第一阈值范围的所有横截面的分布位置并进行分析处理；
当判断横截面的分布满足预设分布情形时，则确定存在满足预设第一类型的障碍物。
在一些实施例中，所述判断横截面的分布满足预设分布情形具体包括：
确定障碍物的至少部分横截面的分布构成预设大小的矩形或三角形；
所述确定存在满足预设第一类型的障碍物，包括：
将构成预设大小的矩形或三角形的横截面所对应的障碍物确定为满足预设第一类型的障碍物。
在一些实施例中，所述障碍物信息还包括基于障碍物的底面点云数据确定的障碍物底面距地面的高度信息以及障碍物的底面面积；
所述方法还包括：
基于所述障碍物底面距地面的高度信息以及障碍物的底面面积，确定是否存在满足预设第二类型的障碍物；
在确定存在满足预设第二类型的障碍物的情况下，获取相应的清洁模式并按照所述清洁模式控制所述机器人进行清洁工作。
在一些实施例中，所述基于所述障碍物底面距地面的高度信息以及障碍物的底面面积，确定是否存在满足预设第二类型的障碍物具体包括：
获取所述障碍物底面距地面的高度信息与预设第二阈值范围的比较结果；
当所述障碍物底面距地面的高度信息在预设第二阈值范围内时，确定所述障碍物的底面面积是否在预设第三阈值范围内；
当所述障碍物的底面面积在预设第三阈值范围内时，则确定存在满足预设第二类型的障碍物。
在一些实施例中，所述清洁模式包括正常清洁模式、增强清洁模式；
所述增强清洁模式的工作参数的数值大于所述正常清洁模式的工作参数的数值；所述工作参数包括吸入功率；
所述获取相应的清洁模式并按照所述清洁模式控制所述机器人进行清洁工作具体包括：
获取增强清洁模式并按照所述增强清洁模式控制所述机器人进行清洁工作。
在一些实施例中，所述按照所述移动策略控制所述机器人进行清洁工作具体包括：
基于所述障碍物的横截面的点云数据确定与地面相接触的障碍物的边缘，控制机器人对障碍物的边缘进行清洁；
基于所述障碍物的横截面的点云数据确定清洁边沿，控制所述机器人在所述清洁边沿所确定的区域内进行清洁。
在一些实施例中，所述方法还包括：
当识别得到障碍物的所属类型时，基于确定的障碍物的位置信息，将所述障碍物在预设地图模型中进行标注。
第二方面，提供一种机器人控制装置，所述装置包括：
获取模块，用于获取机器人行进过程中的障碍物信息；其中，所述障碍物信息包括障碍物的横截面的点云数据；
处理模块，用于基于所述障碍物的横截面的点云数据确定是否存在满足预设第一类型的障碍物；
控制模块，用于在确定存在满足预设第一类型的障碍物的情况下，获取相应的移动策略并按照所述移动策略控制所述机器人进行清洁工作。
第三方面，提供一种机器人，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如第一方面所述的方法。
第四方面，提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现如第一方面所述的方法。
本公开实施例具有如下有益效果：
1、本公开通过障碍物横截面的点云数据来判断当前遇到的障碍物的类型，确定类型后控制机器人实现相应移动，相比于现有技术来说，无需过多传感器进行协同工作，也无需使用复杂的识别算法，只需要使用某一种或者能实现相同功能的某一类传感器来采集上述障碍物的横截面数据，通过分析横截面数据便可实现桌椅类家具的识别，整个识别过程高效、快速，同时还能依据该类障碍物的特性，基于相应的移动策略控制机器人执行清洁工作；
2、本公开通过分析横截面的宽度、分布情形判断障碍物是否为桌椅等家具，算法简单同时可以实现精准识别；
3、本公开还可以基于障碍物底面距地面的高度信息、障碍物的底面面积来判断障碍物的类型，从而实现床、沙发类家具的有效识别，同时也能较快实现该类障碍物所在区域的清洁工作；
4、由于沙发、床等家具底面通常距地面较近，因此本公开首先对障碍物底面距地面的高度信息进行初步判断，当高度满足条件时对障碍物的底面面积进行再次判断，只有当底面面积满足预设条件时才将当前障碍物确定为床、沙发类家具，整个判断过程保证了障碍物识别的精确性；
5、在判断得到当前障碍物为沙发、床等类型时，考虑到此类障碍物底部属于平时不易触及的区域，因此更换清洁模式，采用增强清洁模式控制机器人进行清洁，使得区域更干净；
6、在判断得到当前障碍物为桌椅等类型时，首先将容易被忽略、容易堆积污垢的障碍物的边缘(即桌椅的腿部与地面的接触边缘)清洁干净，随后再清洁整个地面区域，保证了区域的清洁效果；
本公开还实现了对障碍物的位置标注，由此后续再遇到该障碍物时可以根据预存信息快速判断类型从而实现清洁工作。
附图说明
为了更清楚地说明本公开实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本公开的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是根据本公开实施例的机器人控制方法的示例性流程图；
图2是根据本公开实施例的机器人控制装置的结构示意图；
图3是根据本公开实施例的机器人的结构示意图。
具体实施方式
为使本公开的目的、技术方案和优点更加清楚，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案行进清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。
如背景技术所述，在识别桌椅、沙发、床等这些常见的物体时，现有机器人通常会利用两种不同的传感器来分别获取物体的类型、距离等信息。在获取距离信息时，通常采用测距传感器或者用单目估计的方法计算物体位置，该方法存在一定缺陷。对于较大的家具来说，由于摄像头等传感器的角度、安装位置等原因，可能无法获取物体的某些重要特征，从而可能导致无法准确识别类型并且位置估计也不再准确。
基于此，本公开发明人创造性想到利用深度相机获取障碍物的点云数据从而进行分析识 别。由于不同家具的主要特征不同，因此对于桌椅类家具，利用其腿部横截面的点云数据进行识别判断，对于床、沙发类家具，利用其边缘距底面的高度、底面面积等点云数据进行识别判断，由此可以实现不同类型的家具所在区域的清洁工作。
图1示出了根据本公开实施例的机器人控制方法的示例性流程图，该机器人控制方法的详述如下：
步骤101、获取机器人行进过程中的障碍物信息；其中，障碍物信息包括障碍物的横截面的点云数据。
其中，上述障碍物信息可由安装在机器人本体上的传感元件采集得到。本实施例中，采用深度相机作为上述传感元件，具体包括结构光相机、TOF相机等。应该理解的是，本领域的技术人员可以根据实际需求选择相应的深度相机，并不局限于结构光相机、TOF相机这两种。本实施例中，深度相机安装在机器人正前方，用于获取机器人行驶前方的信息。
另外，本实施例所述的横截面，是指在传感元件可达范围内获取到的由障碍物的外表面构成的图形。示例性的，若障碍物为一较高的立柱(如，2米)，那么由于在传感元件可达范围内无法获取到立柱的全貌，只能采集部分区域的信息，因此其获取到的部分立柱的横截面为一矩形；若障碍物为一扇门，那么传感在可达范围内获取到的横截面同样为一矩形，与上述立柱的区别在于两个横截面的大小有所不同。
下面以结构光相机为例，说明获取障碍物信息的具体过程：
当机器人正前方安装结构光相机时，若机器人前方有桌子这一障碍物，首先，结构光相机的投射器主动发射结构信息到障碍物表面(结构信息可以为激光条纹、格雷码、正弦条纹等)，由于桌子的腿部通常较长，因此结构光相机无法投射到桌面，只能投射到桌腿表面；随后，通过其摄像机拍摄桌腿的表面，得到桌腿的结构光图像；最后，对得到的桌腿的结构光图像进行处理，得到桌腿的横截面的点云数据。
当采用TOF相机时，由于TOF技术同结构光技术不同，其发射的是持续不断的“面光源”，因此光线遇到不可穿透的物体会发生反射。利用这一原理，通过记录反射光达到接收器的时间，已知的光速和光波长，便能快速计算出当前机器人距桌腿的距离，由此得到一张桌腿的3D图像，随后将桌腿的3D图像转换成桌腿的横截面的点云数据。
由此可见，不管是利用结构光相机还是TOF相机，都可以实现桌腿的深度图像采集，经过坐标变化便可将深度图像转换成桌腿的横截面的点云数据，便于后续利用横截面的点云数据进行分析与处理。
步骤102、基于障碍物的横截面的点云数据确定是否存在满足预设第一类型的障碍物。
在一些实施例中，上述基于障碍物的横截面的点云数据确定是否存在满足预设第一类型 的障碍物具体包括：
基于障碍物的横截面的点云数据，提取出横截面宽度满足预设第一阈值范围的所有横截面；
获取横截面宽度满足预设第一阈值范围的所有横截面的分布位置并进行分析处理；
当判断横截面的分布满足预设分布情形时，则确定存在满足预设第一类型的障碍物。
本实施例中，第一类型为桌椅类家具类型。具体的，机器人在进行清扫时，前方可能存在多种障碍物，为了实现精准识别，在获取到不同障碍物的横截面的点云数据时，可以首先对这些数据进行初筛，提取得到横截面宽度满足预设第一阈值范围的所有横截面。示例性的，为了识别桌椅类家具，可以将第一阈值范围设为0～10cm，当障碍物的横截面的宽度在此范围内时，可初步认为当前障碍物属于要识别的对象。
在初筛出障碍物后，为了进行精准识别，对初筛后的障碍物的横截面的分布位置进行分析处理。如，有可能障碍物的横截面只有一个，那么，其明显不属于待识别的桌椅类家具，便将其排除。只有判断横截面的分布满足预设分布情形时，才能确定存在满足预设第一类型的障碍物，即，确定当前障碍物属于桌椅类家具。
上述判断横截面的分布满足预设分布情形具体包括：
确定障碍物的至少部分横截面的分布构成预设大小的矩形或三角形；
上述确定存在满足预设第一类型的障碍物，包括：
将构成预设大小的矩形或三角形的横截面所对应的障碍物确定为满足预设第一类型的障碍物。
在家庭场景中，桌椅通常是由四条腿或者三条腿构成的，那么其对应的横截面的分布必然也构成矩形或三角形，并且，矩形或三角形的大小是需要满足一定条件的，如，矩形或三角形的边长(横截面之间的直线距离)在40～80cm范围内。当障碍物的至少部分横截面的分布构成预设大小的矩形或三角形，那么便可将构成预设大小的矩形或三角形的横截面所对应的障碍物确定为满足预设第一类型的障碍物，即桌椅类家具。
需要说明的是，在初筛出障碍物后，还可以基于横截面宽度对障碍物进行分类处理，当确定存在不同类型的障碍物时，判断不同类型的障碍物的横截面的分布是否满足预设分布情形。
示例性的，当机器人前方存在满足第一阈值范围但是横截面宽度不同的障碍物时，便可根据横截面宽度进行进一步分类，分类后再分别判断分布情况。这样做带来的效果是：相比于所有数据都杂糅再一起进行分布情况的分析，分类后可以加快处理过程；另外，实现了障碍物的进一步区分，对于一些位置容易变化的家具(如椅子等)，可能就不需要对其当前位 置进行标记，以免影响后续判断。
本公开通过分析横截面的宽度、分布情形判断障碍物是否为桌椅等家具，算法简单同时可以实现精确识别。
步骤103、在确定存在满足预设第一类型的障碍物的情况下，获取相应的移动策略并按照移动策略控制机器人进行清洁工作。
在一些实施例中，上述按照移动策略控制机器人进行清洁工作具体包括：
基于障碍物的横截面的点云数据确定与地面相接触的障碍物的边缘，控制机器人对障碍物的边缘进行清洁；
基于障碍物的横截面的点云数据确定清洁边沿，控制机器人在清洁边沿所确定的区域内进行清洁。
示例性的，若障碍物为桌子，机器人在清扫时，首先清扫桌腿与地面相接触的边缘，优选的，可控制机器人基于旋转的方式来执行上述区域的清扫，随后，确定由桌腿构成的清洁边沿，控制机器人在清洁边沿所确定的区域内进行清洁。
在判断得到当前障碍物为桌椅等家具类型时，首先将不被注意到的、容易堆积污垢的障碍物的边缘(即：桌椅的腿部与地面的接触边缘)清洁干净，随后再清洁整个地面区域，保证了区域的清洁效果。
在一些实施例中，上述障碍物信息还包括基于障碍物的底面点云数据确定的障碍物底面距地面的高度信息以及障碍物的底面面积；
本公开实施例的机器人控制方法还包括：
基于障碍物底面距地面的高度信息以及障碍物的底面面积，确定是否存在满足预设第二类型的障碍物；
在确定存在满足预设第二类型的障碍物的情况下，获取相应的清洁模式并按照清洁模式控制机器人进行清洁工作。
本实施例中，第二类型为床、沙发类家具类型。同样的，上述障碍物信息可以由安装在机器人本体上的深度相机采集得到。具体可以为激光雷达、结构光相机、TOF相机等任意一种。
需要说明的是，考虑到一些非封闭式大型家具，如床、沙发类家具相比于桌椅类家具较矮、面积更大，对于机器人来说，当其位于床、沙发类家具底部时，其可以比较容易获取到床、沙发类家具的边缘距地面的高度以及获取到家具的底面面积，因此利用此特征设计与桌椅类家具完全不同的识别算法，从而完成不同物体的识别，同时也能提高识别效果。
在一些实施例中，上述基于障碍物底面距地面的高度信息以及障碍物的底面面积，确定 是否存在满足预设第二类型的障碍物具体包括：
获取障碍物底面距地面的高度信息与预设第二阈值范围的比较结果；
当障碍物底面距地面的高度信息在预设第二阈值范围内时，确定障碍物的底面面积是否在预设第三阈值范围内；
当障碍物的底面面积在预设第三阈值范围内时，则确定存在满足预设第二类型的障碍物。
在上述实施方式中，首先对障碍物底面距地面的高度信息进行初步判断，完成障碍物的初筛。示例性的，若第二阈值范围为15～30cm，那么，当获取到的障碍物底面距地面的高度为25cm时，则可以确定当前障碍物初步满足预设条件。随后对其进行进一步分析，判断其底面面积。示例性的，若第三阈值范围为1平米～2平米，当获取到的障碍物的底面面积为1平米时，则可以确定当前障碍物的具体类型为床、沙发等家具，整个处理过程保证了障碍物判断的精确性。
在一些实施例中，清洁模式包括正常清洁模式、增强清洁模式；
增强清洁模式的工作参数的数值大于正常清洁模式的工作参数的数值；工作参数包括吸入功率；
获取相应的清洁模式并按照清洁模式控制机器人进行清洁工作具体包括：
获取增强清洁模式并按照增强清洁模式控制机器人进行清洁工作。
其中，吸入功率是大部分清洁机器人的一项非常重要的工作参数，当吸入功率较大时，清洁机器人的实际使用效果才能好。在判断得到当前障碍物为沙发、床等类型时，考虑到此类障碍物底部属于平时不易触及的区域，因此更换清洁模式，采用增强清洁模式控制机器人进行此类障碍物底面区域的深度清洁，使得区域更干净。
在一些实施例中，本公开实施例的机器人控制方法还包括：
当识别得到障碍物的所属类型时，基于确定的障碍物的位置信息，将障碍物在预设地图模型中进行标注。
本公开还实现了对障碍物的标注，由此后续再遇到该障碍物时可以根据预存信息快速判断类型从而实现清洁工作。
本公开通过障碍物横截面的点云数据来判断当前遇到的障碍物的类型，确定类型后控制机器人实现相应移动，相比于现有技术来说，无需过多传感器进行协同工作，也无需使用复杂的识别算法，只需要使用某一种或者能实现相同功能的某一类传感器来采集上述障碍物的横截面数据，通过分析横截面数据便可实现桌椅类家具的识别，整个识别过程高效、快速，同时还能依据该类障碍物的特性，基于相应的移动策略控制机器人执行清洁工作；本公开还可以基于障碍物底面距地面的高度信息以及障碍物的底面面积来判断障碍物的类型，从而实 现床、沙发类家具的有效识别，同时也能较快实现该类障碍物所在区域的清洁工作。
参见图2，作为对上述图1所示方法的实现，提供了一种机器人控制装置的一个实施例，该装置实施例与图1所示的方法实施例相对应，如图2所示，本实施例的机器人控制装置包括：
获取模块201，用于获取机器人行进过程中的障碍物信息；其中，障碍物信息包括障碍物的横截面的点云数据；
处理模块202，用于基于障碍物的横截面的点云数据确定是否存在满足预设第一类型的障碍物；
控制模块203，用于在确定存在满足预设第一类型的障碍物的情况下，获取相应的移动策略并按照移动策略控制机器人进行清洁工作。
在一些实施例中，上述处理模块202具体用于：
基于障碍物的横截面的点云数据，提取出横截面宽度满足预设第一阈值范围的所有横截面；
获取横截面宽度满足预设第一阈值范围的所有横截面的分布位置并进行分析处理；
当判断横截面的分布满足预设分布情形时，则确定存在满足预设第一类型的障碍物。
在一些实施例中，上述处理模块202具体还用于：
确定障碍物的至少部分横截面的分布构成预设大小的矩形或三角形；
将构成预设大小的矩形或三角形的横截面所对应的障碍物确定为满足预设第一类型的障碍物。
在一些实施例中，障碍物信息还包括基于障碍物的底面点云数据确定的障碍物底面距地面的高度信息以及障碍物的底面面积；
上述处理模块202还用于：
基于障碍物底面距地面的高度信息以及障碍物的底面面积，确定是否存在满足预设第二类型的障碍物；
上述控制模块203还用于：
在确定存在满足预设第二类型的障碍物的情况下，获取相应的清洁模式并按照清洁模式控制机器人进行清洁工作。
在一些实施例中，上述处理模块202还用于：
获取障碍物底面距地面的高度信息与预设第二阈值范围的比较结果；
当障碍物底面距地面的高度信息在预设第二阈值范围内时，确定障碍物的底面面积是否在预设第三阈值范围内；
当障碍物的底面面积在预设第三阈值范围内时，则确定存在满足预设第二类型的障碍物。
在一些实施例中，清洁模式包括正常清洁模式、增强清洁模式；
增强清洁模式的工作参数的数值大于正常清洁模式的工作参数的数值；工作参数包括吸入功率；
上述控制模块203还用于：获取增强清洁模式并按照增强清洁模式控制机器人进行清洁工作。
在一些实施例中，上述控制模块203还用于：
基于障碍物的横截面的点云数据确定与地面相接触的障碍物的边缘，控制机器人对障碍物的边缘进行清洁；
基于障碍物的横截面的点云数据确定清洁边沿，控制机器人在清洁边沿所确定的区域内进行清洁。
在一些实施例中，上述装置还包括标注模块204，用于：
当识别得到障碍物的所属类型时，基于确定的障碍物的位置信息，将障碍物在预设地图模型中进行标注。
图3公开了本公开一实施例提供的一种机器人的示意图。如图3所示，机器人包括：存储器31、处理器32以及存储在存储器31中并可在处理器32上运行的计算机程序33，例如一种机器人控制方法的程序。处理器32执行计算机程序33时实现上述一种机器人控制方法实施例中的步骤，例如图1所示的步骤101至步骤103。或者，处理器32执行计算机程序33时实现上述一种机器人控制装置实施例中各模块的功能，例如图2所示模块201至204的功能。此外，上述机器人还包括测量元件34、运动单元35。
测量元件34可以是雷达、传感器等；其中雷达可以为激光雷达或红外雷达，激光雷达可以是单线雷达或多线雷达。
运动单元35用于控制机器人运动。
所述处理器32可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
所述存储器31可以是一种机器人的内部存储单元，例如一种机器人的硬盘或内存。所述存储器31也可以是一种机器人的外部存储设备，例如一种机器人上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(SecureDigital，SD)卡，闪存卡(Flash Card) 等。进一步地，所述存储器31还可以既包括所述一种机器人的内部存储单元也包括外部存储设备。所述存储器31用于存储所述计算机程序以及所述一种机器人所需的其他程序和数据。所述存储器31还可以用于暂时地存储已经输出或者将要输出的数据。
本领域技术人员可以理解，图3仅仅是一种机器人的示例，并不构成对一种机器人的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述一种机器人还可以包括输入输出设备、网络接入设备、总线等。
需要说明的是，上述装置/单元之间的信息交互、执行过程等内容，由于与本公开方法实施例基于同一构思，其具体功能及带来的技术效果，具体可参见方法实施例部分，此处不再赘述。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将所述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本公开的保护范围。上述系统中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
本公开实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现可实现上述各个方法实施例中的步骤。
技术中的程序部分可以被认为是以可执行的代码和/或相关数据的形式而存在的“产品”或“制品”，通过计算机可读的介质所参与或实现的。有形的、永久的储存介质可以包括任何计算机、处理器、或类似设备或相关的模块所用到的内存或存储器。例如，各种半导体存储器、磁带驱动器、磁盘驱动器或者类似任何能够为软件提供存储功能的设备。
所有软件或其中的一部分有时可能会通过网络进行通信，如互联网或其他通信网络。此类通信可以将软件从一个计算机设备或处理器加载到另一个。因此，另一种能够传递软件元素的介质也可以被用作局部设备之间的物理连接，例如光波、电波、电磁波等，通过电缆、光缆或者空气等实现传播。用来载波的物理介质如电缆、无线连接或光缆等类似设备，也可以被认为是承载软件的介质。在这里的用法除非限制了有形的“储存”介质，其他表示计算机或机器“可读介质”的术语都表示在处理器执行任何指令的过程中参与的介质。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应 当认为是本说明书记载的范围。
以上实施例仅表达了本公开的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对公开专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本公开构思的前提下，还可以做出若干变形和改进，这些都属于本公开的保护范围。因此，本公开专利的保护范围应以所附权利要求为准。

Claims (11)

  1. 一种机器人控制方法，其特征在于，所述方法包括：
    获取机器人行进过程中的障碍物信息；其中，所述障碍物信息包括障碍物的横截面的点云数据；
    基于所述障碍物的横截面的点云数据确定是否存在满足预设第一类型的障碍物；
    在确定存在满足预设第一类型的障碍物的情况下，获取相应的移动策略并按照所述移动策略控制所述机器人进行清洁工作。
  2. 根据权利要求1所述的方法，其中，所述基于所述障碍物的横截面的点云数据确定是否存在满足预设第一类型的障碍物具体包括：
    基于所述障碍物的横截面的点云数据，提取出横截面宽度满足预设第一阈值范围的所有横截面；
    获取所述横截面宽度满足预设第一阈值范围的所有横截面的分布位置并进行分析处理；
    当判断横截面的分布满足预设分布情形时，则确定存在满足预设第一类型的障碍物。
  3. 根据权利要求2所述的方法，其中，所述判断横截面的分布满足预设分布情形具体包括：
    确定障碍物的至少部分横截面的分布构成预设大小的矩形或三角形；
    所述确定存在满足预设第一类型的障碍物，包括：
    将构成预设大小的矩形或三角形的横截面所对应的障碍物确定为满足预设第一类型的障碍物。
  4. 根据权利要求1所述的方法，所述障碍物信息还包括基于障碍物的底面点云数据确定的障碍物底面距地面的高度信息以及障碍物的底面面积；
    所述方法还包括：
    基于所述障碍物底面距地面的高度信息以及障碍物的底面面积，确定是否存在满足预设第二类型的障碍物；
    在确定存在满足预设第二类型的障碍物的情况下，获取相应的清洁模式并按照所述清洁模式控制所述机器人进行清洁工作。
  5. 根据权利要求4所述的方法，所述基于所述障碍物底面距地面的高度信息以及障碍物的底面面积，确定是否存在满足预设第二类型的障碍物具体包括：
    获取所述障碍物底面距地面的高度信息与预设第二阈值范围的比较结果；
    当所述障碍物底面距地面的高度信息在预设第二阈值范围内时，确定所述障碍物的底面面积是否在预设第三阈值范围内；
    当所述障碍物的底面面积在预设第三阈值范围内时，则确定存在满足预设第二类型的障 碍物。
  6. 根据权利要求4或5所述的方法，其中，所述清洁模式包括正常清洁模式、增强清洁模式；
    所述增强清洁模式的工作参数的数值大于所述正常清洁模式的工作参数的数值；所述工作参数包括吸入功率；
    所述获取相应的清洁模式并按照所述清洁模式控制所述机器人进行清洁工作具体包括：
    获取增强清洁模式并按照所述增强清洁模式控制所述机器人进行清洁工作。
  7. 根据权利要求1～5任意一项所述的方法，其中，所述按照所述移动策略控制所述机器人进行清洁工作具体包括：
    基于所述障碍物的横截面的点云数据确定与地面相接触的障碍物的边缘，控制机器人对障碍物的边缘进行清洁；
    基于所述障碍物的横截面的点云数据确定清洁边沿，控制所述机器人在所述清洁边沿所确定的区域内进行清洁。
  8. 根据权利要求1～5任意一项所述的方法，其中，所述方法还包括：
    当识别得到障碍物的所属类型时，基于确定的障碍物的位置信息，将所述障碍物在预设地图模型中进行标注。
  9. 一种机器人控制装置，其特征在于，所述装置包括：
    获取模块，用于获取机器人行进过程中的障碍物信息；其中，所述障碍物信息包括障碍物的横截面的点云数据；
    处理模块，用于基于所述障碍物的横截面的点云数据确定是否存在满足预设第一类型的障碍物；
    控制模块，用于在确定存在满足预设第一类型的障碍物的情况下，获取相应的移动策略并按照所述移动策略控制所述机器人进行清洁工作。
  10. 一种机器人，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1～8任意一项所述的方法。
  11. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1～8任意一项所述的方法。
PCT/CN2023/082092 2022-04-15 2023-03-17 机器人控制方法、装置、机器人及存储介质 Ceased WO2023197822A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210395433.6 2022-04-15
CN202210395433.6A CN116945148B (zh) 2022-04-15 2022-04-15 机器人控制方法、装置、机器人及存储介质

Publications (1)

Publication Number Publication Date
WO2023197822A1 true WO2023197822A1 (zh) 2023-10-19

Family

ID=88328859

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/082092 Ceased WO2023197822A1 (zh) 2022-04-15 2023-03-17 机器人控制方法、装置、机器人及存储介质

Country Status (2)

Country Link
CN (1) CN116945148B (zh)
WO (1) WO2023197822A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025218028A1 (zh) * 2024-04-18 2025-10-23 追觅创新科技(苏州)有限公司 一种清洁机器人的控制方法、清洁机器人及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190370691A1 (en) * 2019-07-12 2019-12-05 Lg Electronics Inc. Artificial intelligence robot for determining cleaning route using sensor data and method for the same
US10571926B1 (en) * 2016-08-29 2020-02-25 Trifo, Inc. Autonomous platform guidance systems with auxiliary sensors and obstacle avoidance
CN110989631A (zh) * 2019-12-30 2020-04-10 科沃斯机器人股份有限公司 自移动机器人控制方法、装置、自移动机器人和存储介质
CN112000093A (zh) * 2020-07-15 2020-11-27 珊口（深圳）智能科技有限公司 移动机器人的控制方法、控制系统及存储介质
CN113907663A (zh) * 2021-09-22 2022-01-11 追觅创新科技(苏州)有限公司 障碍物地图构建方法、清洁机器人及存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9630319B2 (en) * 2015-03-18 2017-04-25 Irobot Corporation Localization and mapping using physical features
US11927965B2 (en) * 2016-02-29 2024-03-12 AI Incorporated Obstacle recognition method for autonomous robots
CN110216664B (zh) * 2019-04-30 2020-12-22 北京云迹科技有限公司 基于点云数据的障碍物识别方法及装置
CN114521836B (zh) * 2020-08-26 2023-11-28 北京石头创新科技有限公司 一种自动清洁设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10571926B1 (en) * 2016-08-29 2020-02-25 Trifo, Inc. Autonomous platform guidance systems with auxiliary sensors and obstacle avoidance
US20190370691A1 (en) * 2019-07-12 2019-12-05 Lg Electronics Inc. Artificial intelligence robot for determining cleaning route using sensor data and method for the same
CN110989631A (zh) * 2019-12-30 2020-04-10 科沃斯机器人股份有限公司 自移动机器人控制方法、装置、自移动机器人和存储介质
CN112000093A (zh) * 2020-07-15 2020-11-27 珊口（深圳）智能科技有限公司 移动机器人的控制方法、控制系统及存储介质
CN113907663A (zh) * 2021-09-22 2022-01-11 追觅创新科技(苏州)有限公司 障碍物地图构建方法、清洁机器人及存储介质

Also Published As

Publication number Publication date
CN116945148A (zh) 2023-10-27
CN116945148B (zh) 2025-09-09

Similar Documents

Publication Publication Date Title
CN108763606B (zh) 一种基于机器视觉的户型图元素自动提取方法与系统
US9412040B2 (en) Method for extracting planes from 3D point cloud sensor data
CN111104933A (zh) 地图处理方法、移动机器人及计算机可读存储介质
WO2023066078A1 (zh) 栅格地图的修正方法及装置、存储介质及电子装置
CN112369982B (zh) 门槛识别方法、装置、扫地机器人及存储介质
WO2019242174A1 (zh) 基于激光雷达的建筑结构自动测量及3d模型生成方法
CN107636680A (zh) 一种障碍物检测方法及装置
CN112741555B (zh) 一种清扫方法、系统及清扫设备
CN114365974B (zh) 一种室内清洁分区方法、装置和扫地机器人
Friedman et al. Online detection of repeated structures in point clouds of urban scenes for compression and registration
CN111862133B (zh) 封闭空间的区域分割方法、装置和可移动设备
CN112990098B (zh) 区域划分方法和装置、存储介质、电子装置
CN113962000A (zh) 一种cad图纸中感烟探测器动态排布的方法
WO2023197822A1 (zh) 机器人控制方法、装置、机器人及存储介质
CN104851127A (zh) 一种基于交互的建筑物点云模型纹理映射方法及装置
WO2025139902A1 (zh) 脏污检测装置、脏污检测方法、联合标定方法及机器人
US12426758B2 (en) Method and apparatus for controlling robot, electronic device, and computer-readable storage medium
CN114489058A (zh) 扫地机器人及其路径规划方法、装置和存储介质
CN112927278B (zh) 控制方法、装置、机器人及计算机可读存储介质
WO2023142710A1 (zh) 机器人导航方法、装置、机器人及存储介质
WO2023045798A1 (zh) 一种过道区域识别方法及装置
CN115357014A (zh) 一种清洁机器人的沿墙方法及清洁机器人
Wiemann et al. Optimizing triangle mesh reconstructions of planar environments
CN118806166A (zh) 移动机器人自动清扫方法和装置、移动机器人
CN116468876A (zh) 障碍物的三维重建方法、装置、移动机器人及介质

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: 23787470

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: 23787470

Country of ref document: EP

Kind code of ref document: A1