WO2022133697A1 - 移动机器人地图构建方法、装置、计算机设备和存储介质 - Google Patents

移动机器人地图构建方法、装置、计算机设备和存储介质 Download PDF

Info

Publication number
WO2022133697A1
WO2022133697A1 PCT/CN2020/138193 CN2020138193W WO2022133697A1 WO 2022133697 A1 WO2022133697 A1 WO 2022133697A1 CN 2020138193 W CN2020138193 W CN 2020138193W WO 2022133697 A1 WO2022133697 A1 WO 2022133697A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
elevator
floor
map
detected
Prior art date
Application number
PCT/CN2020/138193
Other languages
English (en)
French (fr)
Inventor
吴新开
霍向
宋涛
何山
么子瀛
Original Assignee
北京洛必德科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京洛必德科技有限公司 filed Critical 北京洛必德科技有限公司
Priority to US18/256,909 priority Critical patent/US20240094028A1/en
Priority to PCT/CN2020/138193 priority patent/WO2022133697A1/zh
Publication of WO2022133697A1 publication Critical patent/WO2022133697A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3833—Creation or updating of map data characterised by the source of data
    • G01C21/3841—Data obtained from two or more sources, e.g. probe vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3807—Creation or updating of map data characterised by the type of data
    • G01C21/383—Indoor data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3833—Creation or updating of map data characterised by the source of data
    • G01C21/3848—Data obtained from both position sensors and additional sensors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/05—Geographic models

Definitions

  • the present invention relates to the technical field of robot map construction, in particular to a mobile robot map construction method, device, computer equipment and storage medium.
  • the current multi-floor environment map construction is usually to make the robot traverse the entire floor in a trial-and-error manner to realize the construction of the environment map of this floor; and then manually transfer the robot to the next floor to complete the construction of the environment map of the next floor. .
  • For traversing floors by trial and error it takes a long time and is inefficient; while the manual operation method to transfer the robot to the next floor relies on the intervention of the operator, and the automatic transfer of the robot between floors cannot be realized.
  • the prior art treats it as a common obstacle when constructing the floor environment map, ignoring the possible area behind the glass that needs to construct the environment map.
  • a method for constructing a map for a mobile robot includes:
  • Obtain the point cloud data of the surrounding environment of the current position through the lidar obtain the image data of the surrounding environment of the current position through the camera, construct an environment map and mark the glass position according to the point cloud data and the image data, and the environment map includes obstacles object area, passable area and to-be-detected area, wherein the glass position is located in the passable area;
  • an apparatus for constructing a map for a mobile robot includes:
  • Get module used to get the floor number and current floor information
  • the map building module is used to obtain the point cloud data of the surrounding environment of the current position through the lidar, obtain the image data of the surrounding environment of the current position through the camera, construct the environment map according to the point cloud data and the image data, and mark the glass position,
  • the environment map includes an obstacle area, a passable area and a to-be-detected area, wherein the glass position is located in the passable area;
  • a judgment module for judging whether there is an area to be detected in the environment map, and if there is an area to be detected, the area to be explored is detected according to a preset rule
  • the transfer model is used to avoid obstacles and move to the nearest elevator according to the elevator position marked on the environment map if there is no area to be detected, and take the elevator to the undetected floor until the environment map construction of all undetected floors is completed.
  • the present invention also provides a computer device including a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the computer program.
  • a computer device including a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the computer program.
  • the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the processor causes the processor to execute the above Steps of a mobile robot map construction method.
  • the mobile robot map construction method provided by the embodiment of the present invention uses point cloud data and image data to construct an environment map, and can identify glass features through comprehensive processing of the point cloud data and image data, overcoming the inaccurate identification of glass features in the prior art.
  • the mobile robot map construction method provided by the present invention enables the robot to take an elevator to realize automatic cross-floor detection without manual intervention, and can realize automatic cross-floor map construction with a high degree of intelligence.
  • Fig. 1 is the application environment diagram of the mobile robot map construction method provided in one embodiment
  • FIG. 2 is a flowchart of a method for constructing a map of a mobile robot in one embodiment
  • FIG. 3 is a specific flow chart of marking the glass position according to the point cloud data and the image data in FIG. 2;
  • Fig. 4 is the concrete flow chart of detecting the area to be explored according to the preset rule in Fig. 2;
  • Fig. 5 is the concrete flow chart of selecting new path candidate position point in Fig. 4;
  • Fig. 6 is a flow chart of the steps included after step S208 in Fig. 2;
  • Fig. 7 is a structural block diagram of a mobile robot map construction device in one embodiment
  • FIG. 8 is a block diagram of the internal structure of a computer device in one embodiment.
  • first, second and the like used in this application may be used herein to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish a first element from another element. For example, a first xx script could be referred to as a second xx script, and similarly, a second xx script could be referred to as a first xx script, without departing from the scope of this application.
  • FIG. 1 is an application environment diagram of the xx method provided in an embodiment. As shown in FIG. 1 , the application environment includes a mobile robot 100 and a control device 200 .
  • the mobile robot 100 includes mobile components that can be used for movement and devices for data collection, such as lidar, cameras, etc., and can also include infrared sensors, communication modules, voice recognition modules, etc., which are optional specific implementations. This embodiment of the present invention does not specifically limit this. It should be understood that the hardware structure of the mobile robot 100 can be various, and the method of the present invention mainly relates to the algorithm of the mobile robot 100 in the automatic map construction, and the specific hardware settings are not further limited.
  • control device 200 may also be included. Communication can be performed between the control device 200 and the mobile robot 100 , and the communication can be wired or wireless. Through the control device, the operator can operate the mobile robot 100 . It should be noted that, the operation of the operator may not involve the process of automatic map construction, but is only used for basic operations such as starting and stopping.
  • the mobile robot 100 can implement the map construction method provided by the embodiment of the present invention. Construct.
  • the composition and specific form of the control device 200 are not specifically limited in this embodiment of the present invention.
  • a method for constructing a map of a mobile robot is proposed, and this embodiment is mainly illustrated by applying the method to the mobile robot 100 in the above-mentioned FIG. 1 . Specifically, the following steps may be included:
  • Step S202 acquiring the floor number and current floor information.
  • the current floor information includes, but does not start with, the total number of floors, the purpose of the floor, the number and distribution of merchants and residents on the floor, and the like. Such information is mainly used to assist the construction of an environmental map.
  • the number of floors and the current floor information can be obtained by the operator input or by the mobile robot through wireless communication, and can also be obtained from the corresponding signs on the floor by means of image and square character recognition.
  • step S204 the point cloud data of the surrounding environment of the current position is obtained through the lidar, the image data of the surrounding environment of the current position is obtained through the camera, an environment map is constructed according to the point cloud data and the image data, and the glass position is marked.
  • the map includes an obstacle area, a passable area, and a to-be-detected area, wherein the glass position is located in the passable area.
  • the construction of the environment map needs to combine the point cloud data and the image data, and the recognition of the glass features also needs to combine the processing results of the point cloud data and the image data.
  • the environment map includes an obstacle area, a passable area, and a to-be-detected area. It should be noted that the three types of areas divided here do not necessarily exist in the constructed environment map at the same time.
  • the environment map may include one or more of the area types, and this is only the division of the area types in the environment map in the present invention.
  • Step S206 judging whether there is an area to be detected in the environment map, and if there is an area to be detected, the area to be explored is detected according to a preset rule.
  • the to-be-detected area may be detected according to a preset rule.
  • Step S208 if there is no area to be detected, move to the nearest elevator according to the elevator position marked on the environment map to avoid obstacles and take the elevator to the undetected floor until the environment map construction of all undetected floors is completed.
  • the elevator position on the map environment may be pre-calibrated or calibrated during the construction of the environment map.
  • the mobile robot map construction method provided by the embodiment of the present invention uses point cloud data and image data to construct an environment map, and can identify glass features through comprehensive processing of the point cloud data and image data, overcoming the inaccurate identification of glass features in the prior art.
  • the method for constructing a map of a mobile robot provided by the present invention enables the robot to take an elevator to realize automatic cross-floor detection, which requires no manual intervention, can realize automatic cross-floor map construction, and has a high degree of intelligence.
  • step S204 the glass position is marked according to the point cloud data and the image data, which may specifically include steps S302-S310:
  • Step S302 Input the point cloud data into the pre-trained first neural network model, and output the probability p(x, y, z) that the coordinate point (x, y, z) belongs to the glass.
  • the training method of the neural network module may refer to the prior art, which is not specifically limited in the embodiment of the present invention. It should be noted that the present invention utilizes the diffuse reflection of the laser light by the glass to make the reflection map appear in a specific shape, and judges whether the object is glass according to the similarity between the specific shape and the point cloud data collected on site.
  • Step S304 Input the image data into the pre-trained second neural network model, and output the probability f(x, y, z) that the coordinate point (x, y, z) belongs to the glass.
  • the image data is also processed through the neural network model, and the specific training process of the neural network model is not specifically limited in the embodiment of the present invention.
  • Step S306 if p(x, y, z) and f(x, y, z) are both greater than or less than the corresponding preset thresholds, determine whether the position is glass according to the comparison result.
  • the preset thresholds corresponding to the two probabilities may be the same or different, and there is no direct connection between the two. Determine whether the position is glass according to the comparison result. Specifically, if the two probabilities are both greater than or less than the corresponding preset thresholds, it means that the results of the two methods are the same and can be mutually confirmed, then the position can be determined to be glass. Or not for glass.
  • a comprehensive probability is determined by the above formula, and the difference between the comprehensive probability and its preset threshold is determined by the above formula.
  • the relationship determines whether the target location belongs to glass. This method makes up for the inadequacy of individual judgment.
  • Step S310 if it is determined to be glass, mark the glass position in the environment map.
  • s(x, y, z) is the comprehensive probability of the coordinate point (x, y, z), a 1 , a 2 are preset coefficients, p(x, y, z) is calculated from the point cloud data The probability that the position is glass, and f(x, y, z) is the probability that the position is glass calculated from the image data.
  • the glass position is marked in the environment map
  • the marking method can be annotative, for example, it is explained by text, or the preset glass feature image, model, etc. can be called and displayed in the environment in the map.
  • the mobile robot map construction method provided by the embodiment of the present invention uses point cloud data and image data to identify glass, which can improve the accuracy of glass identification.
  • step S206 the area to be explored is detected according to a preset rule, which may specifically include steps S402-S408:
  • Step S402 select the position point with the lowest movement cost from the current position of the robot on the boundary of the to-be-detected area as the path candidate position point, and the movement cost includes the cost of turning, the cost of going straight, and the cost of danger warning.
  • the exercise cost is determined according to the following formula:
  • F(x) is the motion cost of the x-th boundary point of the area to be detected
  • ⁇ d is the distance weight parameter preset by the system
  • d(x, O) is the distance between the x-th boundary point of the area to be detected and the current robot
  • ⁇ ⁇ is the steering weight parameter preset by the system
  • ⁇ (x, O) is the steering angle between the xth boundary position point of the area to be detected and the current position of the robot
  • ⁇ g is the system preset danger warning weight parameter
  • g(x) is the closest distance between the boundary point of the xth region to be explored and the boundary of the detected obstacle.
  • Step S404 determine an accessible area, the accessible area covers the position point to be selected on the path and its center position is closest to the current position of the robot, the accessible area can accommodate the entire robot outline and has a safe distance.
  • the size of the safety distance can be set by itself.
  • Step S406 it is judged whether the robot can reach the reachable area from the current position without colliding with the obstacle and the glass, and if it can, move to the reachable area by avoiding obstacles.
  • the judgment process may be performed in conjunction with a pre-built environment map, for example, a path hypothesis planning is performed in the built environment map.
  • Step S408 otherwise, mark the path candidate position point as the boundary point in the area to be detected in the glass, and select a new path candidate position point.
  • a new path candidate location point is selected, which may specifically include steps S502-S504:
  • Step S502 judging whether a new path candidate position point and reachable area can be selected so that the robot can reach the reachable area from the current position without colliding with the glass and obstacles, and if possible, select a new path candidate position Point and reachable area and avoid obstacles to reach the reachable area.
  • Step S504 otherwise, select the position point on the glass boundary that is close to the robot side and has the lowest movement cost from the robot's current position as the new path candidate position point, and avoid obstacles and move to the path candidate position point.
  • steps S602 to S604 may be specifically included:
  • Step S602 start the elevator position sensing mode, identify the elevator position according to the point cloud data or the image data, or use an elevator sensor to sense the elevator position.
  • utilize elevator sensor to perceive elevator position specifically can be, elevator installs near-field signal transmitter, robot installs near-field signal receiver, can realize the perception of mobile robot to elevator by the sending and receiving of near-field signal.
  • Step S604 it is judged whether the elevator position can be calibrated within the detected passable area, and if so, the elevator position is calibrated within the passable area.
  • step S208 according to the elevator position demarcated on the environment map, avoid obstacles and move to the nearest elevator and take the elevator to the undetected floor, which may specifically include steps S702-S708:
  • Step S702 when there are multiple undetected floors, label the undetected floors ⁇ 1, 2, .
  • the layer difference is ⁇ e 1 ,e 2 ,K,e R ⁇ .
  • step S704 the undetected floor corresponding to the smallest floor difference is selected as the floor to be reached.
  • Step S706 set the current position as (x o , y o ), the label of the elevator in the current floor is set as ⁇ 1, 2, ..., N ⁇ , N is the total number of elevators on the current floor, the current position to the current floor
  • the path distance of each elevator is ⁇ d 1 , d 2 , K, d N ⁇
  • the time for the car of each elevator in the current floor to reach the floor is ⁇ t 1 , t 2 , K, t N ⁇ .
  • step S708 the priority decision value of the robot to take the elevator is calculated according to the following formula to determine the preferred elevator:
  • Q n is the priority decision value of the robot taking the nth elevator of the current floor, where n ⁇ 1,2,K,N ⁇ , dn is the path from the robot's current position to the nth elevator in the current floor Distance, v is the speed set by the robot, t n is the time when the car of the nth elevator in the current floor arrives at the floor.
  • the above formula is used to determine the optimal decision to take the elevator, which can shorten the time to reach the undetected floor and reduce the movement cost of the mobile robot.
  • a mobile robot map construction device is provided, and the mobile robot map construction device can be integrated into the above-mentioned mobile robot 100 , and may specifically include:
  • an acquisition module 701 used for acquiring the floor number and current floor information
  • the map construction module 702 is used to obtain the point cloud data of the surrounding environment of the current position through the lidar, obtain the image data of the surrounding environment of the current position through the camera, construct an environment map according to the point cloud data and the image data, and mark the glass position , the environment map includes an obstacle area, a passable area and a to-be-detected area, wherein the glass position is located in the passable area;
  • the judgment module 703 is used for judging whether there is an area to be detected in the environment map, and if there is an area to be detected, the area to be explored is detected according to a preset rule;
  • the transfer model 704 is used to avoid obstacles and move to the nearest elevator according to the elevator position marked on the environment map if there is no area to be detected, and take the elevator to the undetected floor until the environment map construction of all the undetected floors is completed.
  • the mobile robot map construction device uses point cloud data and image data to construct an environment map, and can identify glass features through comprehensive processing of the point cloud data and image data, overcoming the inaccurate identification of glass features in the prior art.
  • the method for constructing a map of a mobile robot provided by the present invention enables the robot to take an elevator to realize automatic cross-floor detection, which requires no manual intervention, can realize automatic cross-floor map construction, and has a high degree of intelligence.
  • Figure 8 shows an internal structure diagram of a computer device in one embodiment.
  • the computer device may be the mobile robot 100 in FIG. 1 .
  • the computer device includes a processor, a memory, a network interface, an input device, and a display screen connected through a system bus.
  • the memory includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium of the computer device stores an operating system, and also stores a computer program, which, when executed by the processor, enables the processor to implement the method for constructing a map for a mobile robot provided by the embodiment of the present invention.
  • a computer program may also be stored in the internal memory, and when the computer program is executed by the processor, the processor may execute the method for constructing a map of a mobile robot provided by the embodiment of the present invention.
  • the display screen of the computer equipment may be a liquid crystal display screen or an electronic ink display screen
  • the input device of the computer equipment may be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the shell of the computer equipment, or It can be an external keyboard, trackpad or mouse, etc.
  • FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.
  • the mobile robot map construction apparatus may be implemented in the form of a computer program, and the computer program may be executed on the computer device as shown in FIG. 8 .
  • the memory of the computer device can store various program modules that constitute the mobile robot map construction device, for example, the acquisition module, the map construction module, the judgment module and the transfer module shown in FIG. 7 .
  • the computer program constituted by each program module enables the processor to execute the steps in the method for constructing a map for a mobile robot according to the various embodiments of the present application described in this specification.
  • the computer equipment shown in FIG. 8 can execute step S202 through the acquisition module in the mobile robot map construction device shown in FIG. 7 ; the computer equipment can execute step S204 through the map building module; the computer equipment can execute step S206 through the judgment module ; The computer device may execute step S208 through the transfer module.
  • a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the computer
  • the program implements the following steps:
  • Obtain the point cloud data of the surrounding environment of the current position through the lidar obtain the image data of the surrounding environment of the current position through the camera, construct an environment map and mark the glass position according to the point cloud data and the image data, and the environment map includes obstacles object area, passable area and to-be-detected area, wherein the glass position is located in the passable area;
  • a computer-readable storage medium is provided, and a computer program is stored on the computer-readable storage medium.
  • the processor executes the following steps:
  • Obtain the point cloud data of the surrounding environment of the current position through the lidar obtain the image data of the surrounding environment of the current position through the camera, construct an environment map and mark the glass position according to the point cloud data and the image data, and the environment map includes obstacles object area, passable area and to-be-detected area, wherein the glass position is located in the passable area;
  • Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDRSDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • SLDRAM synchronous chain Road (Synchlink) DRAM
  • SLDRAM synchronous chain Road (Synchlink) DRAM
  • Rambus direct RAM
  • DRAM direct memory bus dynamic RAM
  • RDRAM memory bus dynamic RAM

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Computer Graphics (AREA)
  • Theoretical Computer Science (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种移动机器人地图构建方法、装置、计算机设备和存储介质，所述移动机器人地图构建方法包括：获取楼层层数和当前楼层信息（S202）；通过激光雷达获取当前位置周围环境的点云数据，通过摄像头获取当前位置周围环境的图像数据，根据所述点云数据以及所述图像数据构建环境地图并标注出玻璃位置（S204）；判断所述环境地图中是否存在待探测区域，若存在待探测区域则根据预设规则对待探索区域进行探测（S206）；若不存在待探测区域，则根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层直至完成所有未探测楼层的环境地图构建（S208）。通过点云数据以及图像数据对玻璃进行识别，提高了识别准确率。

Description

移动机器人地图构建方法、装置、计算机设备和存储介质 技术领域
本发明涉及机器人地图构建技术领域，特别是涉及一种移动机器人地图构建方法、装置、计算机设备和存储介质。
背景技术
目前，智能移动机器人在各行各业中的应用越来越广泛，随着智能时代的到来，急需机器人能够在没有人工干预的前提下高效准确的构建出涉及多楼层复杂场景的环境地图。
目前的多楼层环境地图构建通常是使机器人采用试错的方式遍历整个楼层以实现本楼层环境地图的构建；而后通过人工操作的方式将机器人转移到下一楼层以完成下一楼层环境地图的构建。对于采用试错的方式遍历楼层，花费时间长，效率低；而采用人工操作的方式将机器人转移到下一楼层则依赖于操作人员的干预，无法实现机器人在楼层之间的自动转移。此外，对于楼层内存在玻璃的位置，现有技术在楼层环境地图构建时将其当作普通阻碍物处理，忽略了玻璃后方可能存在的需要构建环境地图的区域。
可见，现有技术对于多楼层场景且楼层内存在玻璃干扰的环境地图构建没有一套完整的解决方案，需要进行改进。
发明内容
基于此，有必要针对上述的问题，提供一种移动机器人地图构建方法、装置、计算机设备和存储介质。
本发明实施例是这样实现的，一种移动机器人地图构建方法，所述移动机器人地图构建方法包括：
获取楼层层数和当前楼层信息；
通过激光雷达获取当前位置周围环境的点云数据，通过摄像头获取当前位置周围环境的图像数据，根据所述点云数据以及所述图像数据构建环境地图并 标注出玻璃位置，所述环境地图包括障碍物区域、可通行区域以及待探测区域，其中，所述玻璃位置位于所述可通行区域；
判断所述环境地图中是否存在待探测区域，若存在待探测区域则根据预设规则对待探索区域进行探测；
若不存在待探测区域，则根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层直至完成所有未探测楼层的环境地图构建。
在其中一个实施例中，还提供了一种移动机器人地图构建装置，所述移动机器人地图构建装置包括：
获取模块，用于获取楼层层数和当前楼层信息；
地图构建模块，用于通过激光雷达获取当前位置周围环境的点云数据，通过摄像头获取当前位置周围环境的图像数据，根据所述点云数据以及所述图像数据构建环境地图并标注出玻璃位置，所述环境地图包括障碍物区域、可通行区域以及待探测区域，其中，所述玻璃位置位于所述可通行区域；
判断模块，用于判断所述环境地图中是否存在待探测区域，若存在待探测区域则根据预设规则对待探索区域进行探测；
转移模型，用于若不存在待探测区域，则根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层直至完成所有未探测楼层的环境地图构建。
在其中一个实施例中，本发明还提供了一种计算机设备，包括存储器和处理器，所述存储器中存储有计算机程序，所述计算机程序被所述处理器执行时，使得所述处理器执行上述移动机器人地图构建方法的步骤。
在其中一个实施例中，本发明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上存储有计算机程序，所述计算机程序被处理器执行时，使得所述处理器执行上述移动机器人地图构建方法的步骤。
本发明实施例提供的移动机器人地图构建方法利用点云数据以及图像数据建构环境地图，并且通过点云数据以及图像数据的综合处理可以识别玻璃特征，克服了现有中对于玻璃特征识别不准确的问题；此外，本发明提供的移动机器人地图构建方法使机器人乘坐电梯实现自动跨楼层探测，此过程无需人工干预， 可以实现自动化的跨楼层地图构建，智能化程度高。
附图说明
图1为一个实施例中提供的移动机器人地图构建方法的应用环境图；
图2为一个实施例中移动机器人地图构建方法的流程图；
图3为图2中根据所述点云数据以及所述图像数据标注出玻璃位置的具体流程图；
图4为图2中根据预设规则对待探索区域进行探测的具体流程图；
图5为图4中选择新的路径待选位置点的具体流程图；
图6为图2中步骤S208之后还包括的步骤流程图；
图7为一个实施例中移动机器人地图构建装置的结构框图；
图8为一个实施例中计算机设备的内部结构框图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。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。
可以理解，本申请所使用的术语“第一”、“第二”等可在本文中用于描述各种元件，但除非特别说明，这些元件不受这些术语限制。这些术语仅用于将第一个元件与另一个元件区分。举例来说，在不脱离本申请的范围的情况下，可以将第一xx脚本称为第二xx脚本，且类似地，可将第二xx脚本称为第一xx脚本。
图1为一个实施例中提供的xx方法的应用环境图，如图1所示，在该应用环境中，包括移动机器人100以及控制设备200。
移动机器人100包括可以用于移动的移动组件以及用于数据采集的装置，例如激光雷达、摄像头等，此外还可以包括红外传感器、通讯模块、语音识别模块等，此为可选的具体实现方式，本发明实施例对此不作具体限定。需要理解的是，移动机器人100的硬件结构可以多种多样，本发明的方法主要涉及移 动机器人100在自动地图构建中的算法，对于具体的硬件设置不作进一步限定。
此外，还可以包括控制设备200。控制设备200与移动机器人100之间可以进行通信，通信可以是有线的也可以是无线的，通过控制设备，操作人员可以对移动机器人100进行操作。需要说明的是，操作人员的操作可以不涉及地图自动构建的过程，而仅用于例如启动、停止等基本操作，移动机器人100通过执行本发明实施例提供的地图构建方法可以实现跨楼层地图的构建。对于控制设备200的组成以及具体形式本发明实施例对此不作具体限定。
如图2所示，在一个实施例中，提出了一种移动机器人地图构建方法，本实施例主要以该方法应用于上述图1中的移动机器人100来举例说明。具体可以包括以下步骤：
步骤S202，获取楼层层数和当前楼层信息。
在本发明实施例中，当前楼层信息包括但不始于楼层总数、楼层的用途、楼层内商户、住户等数量、分布情况等，此类信息主要用于辅助环境地图构建。在本发明中，楼层层数以及当前楼层信息的获取可以由操作人员输入或者由移动机器人通过无线通信的方式获取，此外还可以通过图像、方字识别的方式从楼层内相应的标识上获取。
步骤S204，通过激光雷达获取当前位置周围环境的点云数据，通过摄像头获取当前位置周围环境的图像数据，根据所述点云数据以及所述图像数据构建环境地图并标注出玻璃位置，所述环境地图包括障碍物区域、可通行区域以及待探测区域，其中，所述玻璃位置位于所述可通行区域。
在本发明实施例中，环境地图的构建需要结合点云数据以及图像数据，且对于玻璃特征的识别也需要结合点云数据以及图像数据的处理结果。在本发明实施例中，环境地图包括障碍物区域、可通行区域以及待探测区域，需要说明的是，这里的划分出的三种类型的区域并不一定同时存在于构建出的环境地图中，环境地图中可以包括其中的一种或者多种区域类型，此仅仅是本发明对于环境地图内区域类型的划分。
步骤S206，判断所述环境地图中是否存在待探测区域，若存在待探测区域则根据预设规则对待探索区域进行探测。
在本发明实施例中，当前位置的探测完成之间，可能存在待探测区域，时此需要根据预设规则对待探测区域进行探测。
步骤S208，若不存在待探测区域，则根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层直至完成所有未探测楼层的环境地图构建。
在本发明实施例中，地图环境上的电梯位置可以是预告标定的也可以是在环境地图的构建过程中进行标定的。
本发明实施例提供的移动机器人地图构建方法利用点云数据以及图像数据建构环境地图，并且通过点云数据以及图像数据的综合处理可以识别玻璃特征，克服了现有中对于玻璃特征识别不准确的问题；此外，本发明提供的移动机器人地图构建方法使机器人乘坐电梯实现自动跨楼层探测，此过程无需人工干预，可以实现自动化的跨楼层地图构建，智能化程度高。
在一个实施例中，如图3所示，步骤S204中根据所述点云数据以及所述图像数据标注出玻璃位置，具体可以包括步骤S302～S310：
步骤S302，将所述点云数据输入预训练的第一神经网络模型，输出坐标点(x，y，z)属于玻璃的概率p(x，y，z)。
在本发明实施例中，神经网络模块的训练方法可以参考现有技术，本发明实施例对此不作具体限定。需要说明的是，本发明是利用玻璃对激光的漫反射使得反射图谱出现特定形态，根据该特定形状与现场采集到的点云数据的相近性判断对象是否为玻璃。
步骤S304，将所述图像数据输入预训练的第二神经网络模型，输出坐标点(x，y，z)属于玻璃的概率f(x，y，z)。
在本发明实施例中，对于图像数据同样是通过神经网络模型进行处理的，对于该神经网络模型的具体训练过程本发明实施例不作具体限定。
步骤S306，若p(x，y，z)、f(x，y，z)同时大于或者小于对应的预设阈值，则根据比较结果判断该位置是否为玻璃。
在本发明实施例中，需要说明的是，两个概率对应的预设阈值可以相同也可以不同，两者之间并没有直接联系。根据比较结果判断该位置是否为玻璃， 具体地，若两个概率均大于或者小于对应的预设阈值，则说明通过两种方式进行判断的结果相同，可以相互确认，则可以判断该位置为玻璃或者不为玻璃。
步骤S308，否则比较综合概率s(x,y,z)＝a 1·p(x,y,z)+a 2·f(x,y,z)是否大于预设阈值，根据比较结果确定该位置是否为玻璃。
在本发明实施例中，与上一步骤不同，若通过两个概率进行判断的结果不同，两种判断方式不能相互确认，则通过上式确定一个综合概率，通过该综合概率与其预设阈值的关系判定目标位置是否属于玻璃。此方法弥补了单独评判的不足。
步骤S310，若判断为玻璃则在所述环境地图中标注出玻璃位置。
其中，s(x，y，z)是坐标点(x，y，z)的综合概率，a 1,a 2是预设的系数，p(x，y，z)是由点云数据推算出该位置是玻璃的概率，f(x，y，z)是由图像数据推算出该位置是玻璃的概率。
在本发明实施例中，在环境地图中标注出玻璃位置，其标注方法可以是注释性的，例如通过文字进行说明，也可以调用预设的玻璃特征的图像、模型等并将之显示于环境地图中。
本发明实施例提供的移动机器人地图构建方法利用点云数据以及图像数据对玻璃进行识别，可以提高对玻璃识别的准确性。
在一个实施例中，如图4所示，步骤S206中根据预设规则对待探索区域进行探测，具体可以包括步骤S402～S408：
步骤S402，选择所述待探测区域的边界上距离机器人当前位置运动成本最低的位置点作为路径待选位置点，所述运动成本包括转向成本、直行成本以及危险预警成本。
在本发明实施例中，运动成本根据以下公式确定：
F(x)＝α d·d(x，O)+α ω·ω(x，O)+α g·g(x)
其中，F(x)为第x个待探测区域边界位置点的运动成本，α d为系统预设的距离权重参数，d(x，O)为第x个待探测区域边界位置点距离机器人当前位置的直线距离，α ω为系统预设的转向权重参数，ω(x，O)为第x个待探测区域边界位置点距 离机器人当前位置的转向角度，α g为系统预设的危险预警权重参数，g(x)为第x个待探索区域边界位置点距离已探测的障碍物边界最近的距离。
步骤S404，确定一个可达区域，所述可达区域覆盖所述路径待选位置点且其中心位置距离机器人当前位置最近，所述可达区域可以容纳整个机器人外轮廓且留有安全距离。
在本发明实施例中，安全距离的大小可以自行设定。
步骤S406，判断机器人从当前位置是否能够在不碰撞障碍物和玻璃的前提下到达所述可达区域，若能够则避障运动到所述可达区域。
在本发明实施例中，判断过程可以结合预构建的环境地图进行，例如在构建的环境地图中进行路径的假设规划等。
步骤S408，否则将该路径待选位置点标记为玻璃内待探测区域内边界点，并选择新的路径待选位置点。
在一个实施例中，如图5所示，步骤S408中选择新的路径待选位置点，具体可以包括步骤S502～S504：
步骤S502，判断是否可以选择新的路径待选位置点以及可达区域以使机器人从当前位置可以在不碰撞玻璃和障碍物的前提下到达可达区域，若可以则选择新的路径待选位置点以及可达区域并避障运动到可达区域。
步骤S504，否则选择玻璃边界上靠近机器人一侧且距离机器人当前位置运动成本最低的位置点作为新的路径待选位置点，并避障运动到该路径待选位置点。
在本发明实施例中，对于运动成本的确定参考前述实施例，对于避障运动的方式，可以参考现有技术实现，本发明实施例对此不作具体限定。
在一个实施例中，如图6所示，步骤S208之前具体还可以包括步骤S602～S604：
步骤S602，启动电梯位置感应模式，根据所述点云数据识或者所述图像数据识别出电梯位置，或者利用电梯传感器感知电梯位置。
在本发明实施例中，利用电梯传感器感知电梯位置具体可以是，电梯安装近场信号发射器，机器人安装近场信号接收器，通过近场信号的发送以及接收 可以实现移动机器人对电梯的感知。
步骤S604，判断所述电梯位置是否可以标定在已探测到的可通行区域内，若是则将电梯位置标定在所述可通行区域内。
在一个实施例中，步骤S208中根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层，之前具体还可以包括步骤S702～S708：
步骤S702，当存在多个未探测楼层时，对未探测楼层进行标号{1，2，...，R}，R是当前还未探测楼层的数量，各个未探测楼层距离机器人当前所在楼层的层数差为{e 1,e 2,K,e R}。
步骤S704，选择最小的层数差对应的未探测楼层作为要达到的楼层。
步骤S706，设置当前位置为(x o,y o)，当前楼层中电梯的标号设置为{1，2，...，N}，N是当前楼层电梯的总个数，当前位置到当前楼层中各电梯的路径距离{d 1,d 2,K,d N}，当前楼层中各个电梯的梯厢到达该楼层的时间{t 1,t 2,K,t N}。
步骤S708，按照以下公式计算机器人乘坐电梯的优先决策值以确定优选乘坐的电梯：
Figure PCTCN2020138193-appb-000001
式中，Q n是机器人乘坐当前楼层的第n个电梯的优先决策值，其中n∈{1,2,K,N}，d n是机器人的当前位置到当前楼层中第n个电梯的路径距离，v是机器人设定的速度，t n是当前楼层中第n个电梯的的梯厢到达该楼层的时间。
在本发明实施例中，通过上式确定乘坐电梯的优选决策，可以缩短到达未探测楼层的时间，同时减少移动机器人的运动成本。
如图7所示，在一个实施例中，提供了一种移动机器人地图构建装置，该移动机器人地图构建装置可以集成于上述的移动机器人100中，具体可以包括：
获取模块701，用于获取楼层层数和当前楼层信息；
地图构建模块702，用于通过激光雷达获取当前位置周围环境的点云数据，通过摄像头获取当前位置周围环境的图像数据，根据所述点云数据以及所述图 像数据构建环境地图并标注出玻璃位置，所述环境地图包括障碍物区域、可通行区域以及待探测区域，其中，所述玻璃位置位于所述可通行区域；
判断模块703，用于判断所述环境地图中是否存在待探测区域，若存在待探测区域则根据预设规则对待探索区域进行探测；
转移模型704，用于若不存在待探测区域，则根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层直至完成所有未探测楼层的环境地图构建。
在本发明实施例中，对于上述各模块的所执行的步骤的解释说明请参考前述任意一个或者多个实施例的组合，本发明实施例对此不再赘述。
本发明实施例提供的移动机器人地图构建装置利用点云数据以及图像数据建构环境地图，并且通过点云数据以及图像数据的综合处理可以识别玻璃特征，克服了现有中对于玻璃特征识别不准确的问题；此外，本发明提供的移动机器人地图构建方法使机器人乘坐电梯实现自动跨楼层探测，此过程无需人工干预，可以实现自动化的跨楼层地图构建，智能化程度高。
图8示出了一个实施例中计算机设备的内部结构图。该计算机设备具体可以是图1中的移动机器人100。如图8所示，该计算机设备包括该计算机设备包括通过系统总线连接的处理器、存储器、网络接口、输入装置和显示屏。其中，存储器包括非易失性存储介质和内存储器。该计算机设备的非易失性存储介质存储有操作系统，还可存储有计算机程序，该计算机程序被处理器执行时，可使得处理器实现本发明实施例提供的移动机器人地图构建方法。该内存储器中也可储存有计算机程序，该计算机程序被处理器执行时，可使得处理器执行本发明实施例提供的移动机器人地图构建方法。计算机设备的显示屏可以是液晶显示屏或者电子墨水显示屏，计算机设备的输入装置可以是显示屏上覆盖的触摸层，也可以是计算机设备外壳上设置的按键、轨迹球或触控板，还可以是外接的键盘、触控板或鼠标等。
本领域技术人员可以理解，图8中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件， 或者具有不同的部件布置。
在一个实施例中，本申请提供的移动机器人地图构建装置可以实现为一种计算机程序的形式，计算机程序可在如图8所示的计算机设备上运行。计算机设备的存储器中可存储组成该移动机器人地图构建装置的各个程序模块，比如，图7所示的获取模块、地图构建模块、判断模块和转移模块。各个程序模块构成的计算机程序使得处理器执行本说明书中描述的本申请各个实施例的移动机器人地图构建方法中的步骤。
例如，图8所示的计算机设备可以通过如图7所示的移动机器人地图构建装置中的获取模块执行步骤S202；计算机设备可通过地图构建模块执行步骤S204；计算机设备可通过判断模块执行步骤S206；计算机设备可通过转移模块执行步骤S208。
在一个实施例中，提出了一种计算机设备，所述计算机设备包括存储器、处理器及存储在所述存储器上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以下步骤：
获取楼层层数和当前楼层信息；
通过激光雷达获取当前位置周围环境的点云数据，通过摄像头获取当前位置周围环境的图像数据，根据所述点云数据以及所述图像数据构建环境地图并标注出玻璃位置，所述环境地图包括障碍物区域、可通行区域以及待探测区域，其中，所述玻璃位置位于所述可通行区域；
判断所述环境地图中是否存在待探测区域，若存在待探测区域则根据预设规则对待探索区域进行探测；
若不存在待探测区域，则根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层直至完成所有未探测楼层的环境地图构建。
在一个实施例中，提供一种计算机可读存储介质，计算机可读存储介质上存储有计算机程序，计算机程序被处理器执行时，使得处理器执行以下步骤：
获取楼层层数和当前楼层信息；
通过激光雷达获取当前位置周围环境的点云数据，通过摄像头获取当前位置周围环境的图像数据，根据所述点云数据以及所述图像数据构建环境地图并 标注出玻璃位置，所述环境地图包括障碍物区域、可通行区域以及待探测区域，其中，所述玻璃位置位于所述可通行区域；
判断所述环境地图中是否存在待探测区域，若存在待探测区域则根据预设规则对待探索区域进行探测；
若不存在待探测区域，则根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层直至完成所有未探测楼层的环境地图构建。
应该理解的是，虽然本发明各实施例的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，各实施例中的至少一部分步骤可以包括多个子步骤或者多个阶段，这些子步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些子步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一非易失性计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
以上所述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。
以上所述实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。

Claims (10)

  1. 一种移动机器人地图构建方法，其特征在于，所述移动机器人地图构建方法包括：
    获取楼层层数和当前楼层信息；
    通过激光雷达获取当前位置周围环境的点云数据，通过摄像头获取当前位置周围环境的图像数据，根据所述点云数据以及所述图像数据构建环境地图并标注出玻璃位置，所述环境地图包括障碍物区域、可通行区域以及待探测区域，其中，所述玻璃位置位于所述可通行区域；
    判断所述环境地图中是否存在待探测区域，若存在待探测区域则根据预设规则对待探索区域进行探测；
    若不存在待探测区域，则根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层直至完成所有未探测楼层的环境地图构建。
  2. 根据权利要求1所述的移动机器人地图构建方法，其特征在于，根据所述点云数据以及所述图像数据标注出玻璃位置，具体包括以下步骤：
    将所述点云数据输入预训练的第一神经网络模型，输出坐标点(x，y，z)属于玻璃的概率p(x，y，z)；
    将所述图像数据输入预训练的第二神经网络模型，输出坐标点(x，y，z)属于玻璃的概率f(x，y，z)；
    若p(x，y，z)、f(x，y，z)同时大于或者小于对应的预设阈值，则根据比较结果判断该位置是否为玻璃；
    否则比较综合概率s(x,y,z)＝a 1·p(x,y,z)+a 2·f(x,y,z)是否大于预设阈值，根据比较结果确定该位置是否为玻璃；
    若判断为玻璃则在所述环境地图中标注出玻璃位置；
    其中，s(x，y，z)是坐标点(x，y，z)的综合概率，a 1,a 2是预设的系数，p(x，y，z)是由点云数据推算出该位置是玻璃的概率，f(x，y，z)是由图像数据推算出该位置是玻璃的概率。
  3. 根据权利要求1所述的移动机器人地图构建方法，其特征在于，所述根据预设规则对待探索区域进行探测，具体包括以下步骤：
    选择所述待探测区域的边界上距离机器人当前位置运动成本最低的位置点作为路径待选位置点，所述运动成本包括转向成本、直行成本以及危险预警成本；
    确定一个可达区域，所述可达区域覆盖所述路径待选位置点且其中心位置距离机器人当前位置最近，所述可达区域可以容纳整个机器人外轮廓且留有安全距离；
    判断机器人从当前位置是否能够在不碰撞障碍物和玻璃的前提下到达所述可达区域，若能够则避障运动到所述可达区域；
    否则将该路径待选位置点标记为玻璃内待探测区域内边界点，并选择新的路径待选位置点。
  4. 根据权利要求3所述的移动机器人地图构建方法，其特征在于，所述选择新的路径待选位置点，具体包括以下步骤：
    判断是否可以选择新的路径待选位置点以及可达区域以使机器人从当前位置可以在不碰撞玻璃和障碍物的前提下到达可达区域，若可以则选择新的路径待选位置点以及可达区域并避障运动到可达区域；
    否则选择玻璃边界上靠近机器人一侧且距离机器人当前位置运动成本最低的位置点作为新的路径待选位置点，并避障运动到该路径待选位置点。
  5. 根据权利要求3所述的移动机器人地图构建方法，其特征在于，所述运动成本根据以下公式确定：
    F(x)＝α d·d(x，O)+α ω·ω(x，O)+α g·g(x)
    其中，F(x)为第x个待探测区域边界位置点的运动成本，α d为系统预设的距离权重参数，d(x，O)为第x个待探测区域边界位置点距离机器人当前位置的直线距离，α ω为系统预设的转向权重参数，ω(x，O)为第x个待探测区域边界位置点距离机器人当前位置的转向角度，α g为系统预设的危险预警权重参数，g(x)为第x个待探索区域边界位置点距离已探测的障碍物边界最近的距离。
  6. 根据权利要求1所述的移动机器人地图构建方法，其特征在于，所述若 不存在待探测区域则根据所述环境地图上标定的电梯位置，避障运动到最近的电梯并乘电梯到未探测楼层直至完成所有未探测楼层的环境地图构建，之前还包括以下步骤：
    启动电梯位置感应模式，根据所述点云数据识或者所述图像数据识别出电梯位置，或者利用电梯传感器感知电梯位置；
    判断所述电梯位置是否可以标定在已探测到的可通行区域内，若是则将电梯位置标定在所述可通行区域内。
  7. 根据权利要求6所述的移动机器人地图构建方法，其特征在于，所述根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层，之前还包括以下步骤：
    当存在多个未探测楼层时，对未探测楼层进行标号{1，2，...，R}，R是当前还未探测楼层的数量，各个未探测楼层距离机器人当前所在楼层的层数差为{e 1,e 2,K,e R}；
    选择最小的层数差对应的未探测楼层作为要达到的楼层；
    设置当前位置为(x o,y o)，当前楼层中电梯的标号设置为{1，2，...，N}，N是当前楼层电梯的总个数，当前位置到当前楼层中各电梯的路径距离{d 1,d 2,K,d N}，当前楼层中各个电梯的梯厢到达该楼层的时间{t 1,t 2,K,t N}；
    按照以下公式计算机器人乘坐电梯的优先决策值以确定优选乘坐的电梯：
    Figure PCTCN2020138193-appb-100001
    式中，Q n是机器人乘坐当前楼层的第n个电梯的优先决策值，其中n∈{1,2,K,N}，d n是机器人的当前位置到当前楼层中第n个电梯的路径距离，v是机器人设定的速度，t n是当前楼层中第n个电梯的的梯厢到达该楼层的时间。
  8. 一种移动机器人地图构建装置，其特征在于，所述移动机器人地图构建装置包括：
    获取模块，用于获取楼层层数和当前楼层信息；
    地图构建模块，用于通过激光雷达获取当前位置周围环境的点云数据，通过摄像头获取当前位置周围环境的图像数据，根据所述点云数据以及所述图像数据构建环境地图并标注出玻璃位置，所述环境地图包括障碍物区域、可通行区域以及待探测区域，其中，所述玻璃位置位于所述可通行区域；
    判断模块，用于判断所述环境地图中是否存在待探测区域，若存在待探测区域则根据预设规则对待探索区域进行探测；
    转移模型，用于若不存在待探测区域，则根据所述环境地图上标定的电梯位置避障运动到最近的电梯并乘电梯到未探测楼层直至完成所有未探测楼层的环境地图构建。
  9. 一种计算机设备，其特征在于，包括存储器和处理器，所述存储器中存储有计算机程序，所述计算机程序被所述处理器执行时，使得所述处理器执行权利要求1至7中任一项权利要求所述移动机器人地图构建方法的步骤。
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时，使得所述处理器执行权利要求1至7中任一项权利要求所述移动机器人地图构建方法的步骤。
PCT/CN2020/138193 2020-12-22 2020-12-22 移动机器人地图构建方法、装置、计算机设备和存储介质 WO2022133697A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US18/256,909 US20240094028A1 (en) 2020-12-22 2020-12-22 Mobile robot map construction method and apparatus, and computer device and storage medium
PCT/CN2020/138193 WO2022133697A1 (zh) 2020-12-22 2020-12-22 移动机器人地图构建方法、装置、计算机设备和存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/138193 WO2022133697A1 (zh) 2020-12-22 2020-12-22 移动机器人地图构建方法、装置、计算机设备和存储介质

Publications (1)

Publication Number Publication Date
WO2022133697A1 true WO2022133697A1 (zh) 2022-06-30

Family

ID=82156919

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/138193 WO2022133697A1 (zh) 2020-12-22 2020-12-22 移动机器人地图构建方法、装置、计算机设备和存储介质

Country Status (2)

Country Link
US (1) US20240094028A1 (zh)
WO (1) WO2022133697A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116394235A (zh) * 2023-03-16 2023-07-07 中国长江电力股份有限公司 一种基于三维测量的大型零部件机器人干冰清洗轨迹规划系统及方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108665541A (zh) * 2018-04-09 2018-10-16 北京三快在线科技有限公司 一种基于激光传感器的地图生成方法及装置和机器人
CN109425352A (zh) * 2017-08-25 2019-03-05 科沃斯机器人股份有限公司 自移动机器人路径规划方法
CN110704140A (zh) * 2018-07-09 2020-01-17 科沃斯机器人股份有限公司 地图处理方法、装置、终端设备和存储介质
CN111728533A (zh) * 2020-06-01 2020-10-02 珠海市一微半导体有限公司 一种机器人进出电梯的移动控制方法、激光机器人及芯片
CN112033410A (zh) * 2020-09-03 2020-12-04 中南大学 移动机器人环境地图构建方法、系统及存储介质
CN112051847A (zh) * 2020-08-26 2020-12-08 苏州三六零机器人科技有限公司 扫地机器人、扫地机器人的控制方法、装置及可读介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109425352A (zh) * 2017-08-25 2019-03-05 科沃斯机器人股份有限公司 自移动机器人路径规划方法
CN108665541A (zh) * 2018-04-09 2018-10-16 北京三快在线科技有限公司 一种基于激光传感器的地图生成方法及装置和机器人
CN110704140A (zh) * 2018-07-09 2020-01-17 科沃斯机器人股份有限公司 地图处理方法、装置、终端设备和存储介质
CN111728533A (zh) * 2020-06-01 2020-10-02 珠海市一微半导体有限公司 一种机器人进出电梯的移动控制方法、激光机器人及芯片
CN112051847A (zh) * 2020-08-26 2020-12-08 苏州三六零机器人科技有限公司 扫地机器人、扫地机器人的控制方法、装置及可读介质
CN112033410A (zh) * 2020-09-03 2020-12-04 中南大学 移动机器人环境地图构建方法、系统及存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116394235A (zh) * 2023-03-16 2023-07-07 中国长江电力股份有限公司 一种基于三维测量的大型零部件机器人干冰清洗轨迹规划系统及方法
CN116394235B (zh) * 2023-03-16 2023-11-21 中国长江电力股份有限公司 一种基于三维测量的大型零部件机器人干冰清洗轨迹规划系统及方法

Also Published As

Publication number Publication date
US20240094028A1 (en) 2024-03-21

Similar Documents

Publication Publication Date Title
US11530924B2 (en) Apparatus and method for updating high definition map for autonomous driving
JP6672212B2 (ja) 情報処理装置、車両、情報処理方法およびプログラム
CN107272710B (zh) 一种基于视觉定位的医用物流机器人系统及其控制方法
CN109901138B (zh) 激光雷达标定方法、装置、设备和存储介质
KR102499398B1 (ko) 차선 검출 방법 및 장치
US20180174038A1 (en) Simultaneous localization and mapping with reinforcement learning
KR101470240B1 (ko) 주차 영역 검출 장치 및 그 방법
CN107843267A (zh) 施工路段无人驾驶车辆的路径生成方法及装置
WO2020173188A1 (zh) 语义地图中障碍物定位方法、装置、计算机设备和存储介质
US10210411B2 (en) Method and apparatus for establishing feature prediction accuracy
CN111630460A (zh) 自主移动装置的路径规划
US10210403B2 (en) Method and apparatus for pixel based lane prediction
CN110807350A (zh) 用于面向扫描匹配的视觉slam的系统和方法
JP2022538535A (ja) 画像からの奥行の精緻化
CN113330279A (zh) 用于确定车辆的位置的方法和系统
US11755917B2 (en) Generating depth from camera images and known depth data using neural networks
US20220144265A1 (en) Moving Track Prediction Method and Apparatus
KR102441054B1 (ko) 차량의 경로 제어 장치 및 방법
WO2020168464A1 (en) Local sensing based autonomous navigation, and associated systems and methods
US11482007B2 (en) Event-based vehicle pose estimation using monochromatic imaging
CN114089330B (zh) 一种基于深度图像修复的室内移动机器人玻璃检测与地图更新方法
JP2017181476A (ja) 車両位置検出装置、車両位置検出方法及び車両位置検出用コンピュータプログラム
WO2022133697A1 (zh) 移动机器人地图构建方法、装置、计算机设备和存储介质
JP7464616B2 (ja) 速度および位置情報を使用するレーダ反射の認識
US20190094025A1 (en) Apparatus and method for localising a vehicle

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: 20966278

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: 20966278

Country of ref document: EP

Kind code of ref document: A1