WO2023005020A1 - 反光板定位方法、机器人及计算机可读存储介质 - Google Patents

反光板定位方法、机器人及计算机可读存储介质 Download PDF

Info

Publication number
WO2023005020A1
WO2023005020A1 PCT/CN2021/126717 CN2021126717W WO2023005020A1 WO 2023005020 A1 WO2023005020 A1 WO 2023005020A1 CN 2021126717 W CN2021126717 W CN 2021126717W WO 2023005020 A1 WO2023005020 A1 WO 2023005020A1
Authority
WO
WIPO (PCT)
Prior art keywords
data frame
reflector
frame
reflector points
coordinates
Prior art date
Application number
PCT/CN2021/126717
Other languages
English (en)
French (fr)
Inventor
赵勇胜
熊友军
Original Assignee
深圳市优必选科技股份有限公司
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 深圳市优必选科技股份有限公司 filed Critical 深圳市优必选科技股份有限公司
Publication of WO2023005020A1 publication Critical patent/WO2023005020A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/48Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/481Constructional features, e.g. arrangements of optical elements
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/48Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/481Constructional features, e.g. arrangements of optical elements
    • G01S7/4817Constructional features, e.g. arrangements of optical elements relating to scanning
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/48Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/497Means for monitoring or calibrating

Definitions

  • the present application belongs to the field of robots, and in particular relates to a reflector positioning method, a robot and a computer-readable storage medium.
  • lidar For the convenience of description, it is collectively referred to as the reflector
  • the lidar scans the reflector or the reflective column (for the convenience of description, it is collectively referred to as the reflector)
  • the reflector can obtain a strong reflective signal, which is easier to distinguish than the reflective signal of other objects.
  • the laser radar obtains the reflection signals of 3 or more reflectors at the same time, the plane coordinates of the laser radar in the reflector coordinate system can be accurately calculated by triangulation or the least square method, so as to determine the coordinates of the robot.
  • the position of the reflector can be obtained by measuring with a total station, but the measurement process is cumbersome, and manual registration of the position of the reflector and the map is required. The whole process requires a lot of labor and time costs.
  • the embodiment of the present application provides a reflector positioning method, a robot and a computer-readable storage medium to solve the problem of using a total station to measure the position of the reflector when positioning through the reflector in the prior art, and Manual registration is required, and the whole process will consume more labor costs and time costs.
  • the first aspect of the embodiments of the present application provides a reflector positioning method, the method comprising:
  • Collect the current data frame by synchronous positioning and mapping method, determine that the number of reflector points included in the current data frame is two or more, and determine that the reflector points included in the current data frame are within a preset Coordinates in the map plane coordinate system;
  • two or more reflector points included in the current data frame are determined according to the coordinates of the reflector points included in the data frame, Similarity to two or more reflector points included in the data frame being looked up, including:
  • the reference frame is the data frame being searched, and the reference frame is located before the current data frame and includes two or more data frames of reflector points;
  • the coordinates of the reflector points included in the current data frame and the reference frame determine the distance between the reflector points in the current data frame and the reflector points in the reference frame
  • the distance is compared with a preset first distance threshold, and the similarity of the reflector points is determined according to the comparison result.
  • searching for data frames within a preset range includes:
  • two or more reflector points included in the current data frame are determined according to the coordinates of the reflector points included in the data frame, Similarity to two or more reflector points included in the data frame being looked up, including:
  • a first distance matrix is determined, and the first distance matrix is determined by the distance between the reflector points in the current data frame constituted matrix;
  • the second distance matrix is between the reflector points in the searched data frame The matrix formed by the distance between;
  • the similarity is determined based on the first distance matrix and the second distance matrix.
  • determining the similarity according to the first distance matrix and the second distance matrix includes:
  • the degree of similarity is determined according to matching scores of the first point cloud and the second point cloud.
  • collecting the current data frame through the synchronous positioning and mapping method also includes:
  • the current data frame is determined according to the currently collected key frame.
  • determining the key frame in the data frame collected by the lidar includes:
  • the current frame is a key frame
  • the currently collected data frame is not the first frame, and the change of the collection time of the previous key frame is greater than the preset first time threshold, and the change of the collection position of the previous key frame is greater than the preset third distance threshold , the currently collected data frame is a key frame.
  • the coordinates of the reflector points are determined according to the optimized data frame, including:
  • the coordinates of the combined reflector points are determined according to the combined coordinates of the reflector points.
  • the second aspect of the embodiment of the present application provides a reflector positioning device, which includes:
  • the data frame acquisition unit is used to collect the current data frame by synchronous positioning and mapping method, determine that the number of reflector points included in the current data frame is two or more, and determine the number of reflector points included in the current data frame The coordinates of the reflector point in the preset map plane coordinate system;
  • the similarity determination unit is used to search the data frame within the preset range, and determine two or more reflector points included in the current data frame according to the coordinates of the reflector points included in the data frame, and Find the similarity of two or more reflector points included in the data frame;
  • the loopback optimization unit is used to optimize the pose of the data frame included in the loopback according to the loopback formed by the current data frame and the searched data frame when the similarity is greater than a preset similarity threshold ;
  • the reflector point coordinate determining unit is configured to determine the coordinates of the reflector point according to the optimized data frame.
  • the third aspect of the embodiments of the present application provides a robot, including a memory, a processor, and a computer program stored in the memory and operable on the processor.
  • the processor executes the computer program, the following steps are implemented: The steps of any one of the methods in one aspect.
  • the fourth aspect of the embodiments of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of the first aspect is implemented A step of.
  • the embodiment of the present application collects the current data frame including two or more reflector points through the laser radar, and compares it with the current data frame found within the preset range.
  • the data frames are used to compare the similarity of the reflector points.
  • the similarity of the reflector points is greater than the preset similarity threshold, according to the loop formed by the current data frame and the searched data frame, the position of the robot that collects the data frame is compared.
  • the coordinates of the reflector points can be determined more accurately and efficiently, and the reflector points can be established during synchronous positioning and mapping.
  • the matching of board points and map coordinates can reduce the positioning efficiency of reflector points.
  • FIG. 1 is a schematic diagram of a reflector positioning scene provided by an embodiment of the present application
  • Fig. 2 is a schematic diagram of the implementation flow of a reflector positioning method provided by the embodiment of the present application
  • FIG. 3 is a schematic diagram of a loopback optimization provided by an embodiment of the present application.
  • Fig. 4 is a schematic diagram of a reflector positioning device provided in an embodiment of the present application.
  • Fig. 5 is a schematic diagram of a robot provided by an embodiment of the present application.
  • FIG. 1 is a schematic diagram of an implementation scene of a reflector positioning method provided in an embodiment of the present application.
  • the board is installed according to the working scene information, including information such as walls and gate posts.
  • the installation height of each reflector relative to the moving plane of the robot is a constant value, which can be suitable for the height of the laser radar of the robot.
  • the size of the reflector can be pre-set to a uniform size, such as a rectangle with a width of 3 cm and a height of 10 cm.
  • FIG. 2 is a schematic flow diagram of a method for positioning a reflector provided in an embodiment of the present application. As shown in Figure 2, the process includes:
  • S201 collect the current data frame by synchronous positioning and mapping method, determine that the number of reflector points included in the current data frame is two or more, and determine the reflector points included in the current data frame The coordinates in the preset map plane coordinate system.
  • simultaneous localization and mapping English abbreviation for simultaneous localization and mapping, English abbreviation SLAM
  • SLAM simultaneous localization and mapping
  • the key frame may be the first frame of the data frame collected by the lidar. That is, no matter whether the collected data frame includes reflector points or not, the first frame may be called a key frame.
  • the currently collected data frame is a key frame. It can be based on the collection time of the previous key frame of the current time, and whether the time difference between the current time and the current time exceeds the first time threshold; or the collection position of the previous key frame of the current time , the distance between the acquisition position of the data frame at the current time is greater than the preset third distance threshold; or the acquisition angle of the previous key frame at the current time, and the change of the acquisition angle of the data frame at the current time is greater than the second angle threshold , the currently collected data frame is a key frame.
  • the reflector point that is, the robot detects the reflector by emitting a detection signal through the laser radar, and the detected position of the reflector represented by the point is the reflector point.
  • the number of reflector points included in the data frame it can be judged according to the intensity of the laser point.
  • the position of a point on the reflector can be determined according to the average value of the consecutive laser points. If the intensity of a single laser point exceeds the preset first intensity threshold, this point is used as a position point of a reflector, that is, a reflector point.
  • the distance and angle of the reflector relative to the lidar can be determined.
  • the data frame is searched within the preset range, and according to the coordinates of the reflector points included in the data frame, two or more reflector points included in the current data frame are determined, which are related to the searched data. The similarity of two or more reflector points included in the frame.
  • the data frame searched within the preset range may be the reference frame corresponding to the current data frame, that is, the previous reference frame of the current data frame, or the data within the predetermined range before the current data frame Any data frame in the frame, or any key frame within a predetermined range before the current data frame.
  • the reference frame may be obtained by filtering key frames.
  • the number of reflector points can be set to be greater than or equal to 2. Then, when the number of reflector points in a key frame is greater than or equal to 2 and is before the current data frame, the data frame can be called a reference frame.
  • the distance between the coordinates of the reflector points included in the data frame and the reference frame can be calculated. For example, the distances from each reflector point in the current data frame to all reflector points in the reference frame can be determined sequentially. The determined distance is compared with a preset first distance threshold.
  • the first distance threshold may be 10 cm. If the calculated distance is less than 10 cm, it is determined that the two reflector points are points corresponding to the same reflector, and the similarity is greater than a preset similarity threshold. Alternatively, when the distance between two or more groups of reflector points is less than a preset first distance threshold, it is determined that the similarity is greater than a predetermined similarity threshold.
  • the acquisition angle between the data frame to be compared and the current data frame may be greater than the first angle threshold, or the angle between the data frame to be compared and the current data frame If the distance from the robot's collection position is greater than the predetermined second distance threshold, the data frame to be compared meets the preset range requirement. After satisfying the preset range requirements, if the data frame to be compared is a key frame and includes two or more reflector points, the data frame to be compared is a reference frame that can be used for searching and comparing.
  • the first distance matrix may be determined according to the coordinates of two or more reflector points included in the current data frame.
  • the distance between any two reflector points may be calculated according to the coordinates of two or more reflector points included in the current data frame, and the calculated distance may be used as an element in the first distance matrix.
  • the distance matrix the distance between each reflector point is set up as a matrix with the serial number of the reflector point as the abscissa and ordinate, and the elements of the matrix are the distances between the points of two serial numbers.
  • the matrix is a diagonal matrix, and only the value of half of the oblique angle can be reserved, and the elements on the diagonal and the value of the other oblique angle are set to zero.
  • the current data frame includes n reflector points, the distance between the first reflector point and the second reflector point is d01, the distance between the first reflector point and the third reflector point is d02, and the first reflector point
  • the distance to the nth reflector point is d0(n-1)
  • the distance between the second reflector point and the third reflector point is d12
  • the distance between the second reflector point and the nth reflector point is d1(n- 1)
  • the distance between the n-1 reflector point and the n-th reflector point is d(n-2)(n-1).
  • the first distance matrix can be expressed as:
  • the distance between the reflector points can also be calculated according to the coordinates of each reflector point, and the second distance matrix can be determined according to the calculated distance.
  • the similarity between the current data frame and the searched data frame can be determined.
  • the threshold range where the searched data frame is located may include that the distance between the location where the searched data frame is collected and the location where the current data frame is collected is greater than the preset third distance threshold, and the current data frame and the searched data are collected
  • the change in time of the frame is at a first time threshold.
  • the time change can also be represented by the number of frames, that is, the number of frames between the collected current data frame and the searched data frame is greater than the first frame number threshold.
  • the distance matrix (the first distance matrix and the second distance matrix), whether the difference between the element values in the distance matrix is less than the predetermined fourth distance threshold, it is considered that there is a rough correspondence between the two frames , you can further determine the matching score of the frame by means of point cloud matching. Two data frames are considered similar if the matching score is greater than a predetermined matching threshold, and the reflector points in the data frames include the same reflector points.
  • the similarity between the two frames is greater than the preset similarity threshold, it means that the two frames contain the same reflector point, and the matching can be combined according to the collected poses of the current data frame and the reference frame (or the searched data frame).
  • the position of the reflector point in the image can determine the displacement of the robot when collecting the current data frame and collecting the reference frame.
  • the displacement determined according to the loop closure is the displacement of the robot changing from the pose of the collected data frame to the pose of the current data frame.
  • the displacement that constitutes the loop can be used as the actual displacement.
  • the inter-frame displacement that occurs between two adjacent frames is calculated.
  • an error between the calculated total displacement and the actual displacement can be obtained, and the data frame in the current data frame and the absolute data frame can be optimized according to the error.
  • the optimization method includes, but is not limited to, evenly distributing to each data frame according to the error between the robot's current pose and the actual pose.
  • the coordinates of the reflector points are determined according to the optimized data frame.
  • the data frame or key frame is optimized, including the optimization of the robot coordinates for collecting the key frame.
  • the coordinates of the reflector point in the data frame corresponding to the movement trajectory can be determined.
  • the coordinates of the reflector points in all the data frames can be recorded, and according to the distance between the coordinates of the reflector points, the reflector points whose distance is less than the predetermined merge distance threshold are merged into the same reflector point, and the combined
  • the average value of the coordinates of the reflector points is used as the coordinates of the merged reflector points.
  • the coordinates of the reflector points generated in this application are determined based on synchronous positioning and mapping, there is no need to manually match the coordinates of the reflector points with the map, and in the process of synchronous positioning and mapping , according to the similarity of two or more reflector points in the data frame, find the corresponding loop point of the data frame, and optimize the position of the data frame, so that the coordinates of the reflector points can be obtained automatically, and the The accuracy of the obtained coordinates can be improved.
  • Fig. 4 is a schematic diagram of a reflector positioning device provided in the embodiment of the present application, the device includes:
  • the data frame collection unit 401 is used to collect the current data frame by synchronous positioning and mapping method, determine that the number of reflector points included in the current data frame is two or more, and determine that the current data frame includes The coordinates of the reflector point in the preset map plane coordinate system;
  • the similarity determination unit 402 is configured to search for data frames within a preset range, determine two or more reflector points included in the current data frame according to the coordinates of the reflector points included in the data frame, and The similarity of two or more reflector points included in the searched data frame;
  • the loop-closing optimization unit 403 is used to perform the pose of the data frame included in the loop according to the loop formed by the current data frame and the searched data frame when the similarity is greater than the preset similarity threshold optimization;
  • the reflector point coordinate determining unit 404 is configured to determine the coordinates of the reflector point according to the optimized data frame.
  • the reflector positioning device shown in FIG. 4 corresponds to the reflector positioning method shown in FIG. 2 .
  • Fig. 5 is a schematic diagram of a robot provided by an embodiment of the present application.
  • the robot 5 of this embodiment includes: a processor 50 , a memory 51 , and a computer program 52 stored in the memory 51 and operable on the processor 50 , such as a reflector positioning program.
  • the processor 50 executes the computer program 52, the steps in the embodiments of the reflector positioning method described above are realized.
  • the processor 50 executes the computer program 52, the functions of the modules/units in the above-mentioned device embodiments are realized.
  • the computer program 52 can be divided into one or more modules/units, and the one or more modules/units are stored in the memory 51 and executed by the processor 50 to complete this application.
  • the one or more modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execution process of the computer program 52 in the robot 5 .
  • the robot may include, but not limited to, a processor 50 and a memory 51 .
  • a processor 50 and a memory 51 .
  • Fig. 5 is only an example of the robot 5, and does not constitute a limitation to the robot 5, and may include more or less components than shown in the illustration, or combine certain components, or different components, for example
  • the robot may also include input and output devices, network access devices, buses, and the like.
  • the so-called processor 50 can be a central processing unit (Central Processing Unit, CPU), and can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the memory 51 may be an internal storage unit of the robot 5 , such as a hard disk or memory of the robot 5 . Described memory 51 also can be the external storage device of described robot 5, for example the plug-in type hard disk that is equipped on described robot 5, smart memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, Flash card (Flash Card), etc. Further, the memory 51 may also include both an internal storage unit of the robot 5 and an external storage device. The memory 51 is used to store the computer program and other programs and data required by the robot. The memory 51 can also be used to temporarily store data that has been output or will be output.
  • the disclosed apparatus/terminal device and method may be implemented in other ways.
  • the device/terminal device embodiments described above are only illustrative.
  • the division of the modules or units is only a logical function division.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.
  • the integrated module/unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments in this application can also be completed by hardware related to computer program instructions.
  • the computer program can be stored in a computer-readable storage medium.
  • the computer program When executed by a processor, the steps in the above-mentioned various method embodiments can be realized.
  • the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form.
  • the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, computer-readable media Excluding electrical carrier signals and telecommunication signals.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种反光板定位方法、机器人及计算机可读存储介质,属于机器人领域。该方法包括:通过同步定位与建图方法采集当前数据帧(S201);在预设范围内查找数据帧,确定当前数据帧所包括的两个或两个以上的反光板点,与所查找的数据帧的反光板点的相似度(S202);当相似度大于预先设定的相似度阈值,则根据当前数据帧与所查找的数据帧所构成的回环,对回环中包括的数据帧的位姿进行优化(S203);根据优化后的数据帧确定反光板点的坐标(S204)。该方法通过同步定位与建图将反光板点的坐标与地图坐标系匹配,并根据两个或两个以上的反光板点的相似度对数据帧进行回环优化,从而能够更为精确的确定反光板点的坐标,并有利于提高反光板点的定位效率。

Description

反光板定位方法、机器人及计算机可读存储介质
本申请要求于2021年07月30日在中国专利局提交的、申请号为202110873994.8的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请属于机器人领域,尤其涉及一种反光板定位方法、机器人及计算机可读存储介质。
背景技术
室内轮式移动的机器人一般采用单线激光雷达进行定位。在一些要求高可靠性的场景中,通常会部署反光板或反光柱。激光雷达扫描到反光板或反光柱(为便于描述,统一称为反光板)上时,可以得到较强的反光信号,相对于其它物体的反光信号更容易分辨。当激光雷达同时获得3个或3个以上的反光板的反光信号,通过三角定位或最小二乘法即可准确的计算激光雷达在反光板坐标系下的平面坐标,从而确定机器人的坐标。
在通过反光板对机器人定位时,需要先确定反光板的位置。一般情况下,通过全站仪测量可得到反光板的位置,但测量过程较为麻烦,并且需要手动进行反光板位置与地图的配准,整个过程需要耗费较多的人力成本和时间成本。
技术问题
有鉴于此,本申请实施例提供了一种反光板定位方法、机器人及计算机可读存储介质,以解决现有技术中通过反光板进行定位时,需要通过全站仪测量反光板的位置,且需要人工进行配准,整个过程会耗费较多的人力成本和时间成本的问题。
技术解决方案
本申请实施例的第一方面提供了一种反光板定位方法,所述方法包括:
通过同步定位与建图方法采集当前数据帧,确定所述当前数据帧中包括的反光板点数量为两个或两个以上,以及确定所述当前数据帧中包括的反光板点在预设的地图平面坐标系下的坐标;
在预设范围内查找数据帧,根据数据帧中包括的反光板点的坐标,确定所述当前数据帧所包括的两个或两个以上的反光板点,与所查找的数据帧中包括的两个或两个以上的反光板点的相似度;
当所述相似度大于预先设定的相似度阈值,则根据所述当前数据帧与所查找的数据帧所构成的回环,对回环中包括的数据帧的位姿进行优化;
根据优化后的数据帧确定反光板点的坐标。
结合第一方面,在第一方面的第一种可能实现方式中,根据数据帧中包括的反光板点的坐标,确定所述当前数据帧所包括的两个或两个以上的反光板点,与所查找的数据帧中包括的两个或两个以上的反光板点的相似度,包括:
获取基准帧,所述基准帧为所查找的数据帧,且所述基准帧位于所述当前数据帧之前,并包括两个或两个以上的反光板点的数据帧;
根据所述当前数据帧和所述基准帧中包括的反光板点的坐标,确定所述当前数据帧中的反光板点,与所述基准帧中的反光板点的之间距离;
将所述距离与预先设定的第一距离阈值进行比较,根据所述比较结果确定反光板点的相似度。
结合第一方面的第一种可能实现方式,在第一方面的第二种可能实现方式中,在预设范围内查找数据帧,包括:
确定所述当前数据帧与所查找的所述基准帧的采集坐标的变化大于第二距离阈值,或 者所述当前数据帧与所查找的所述基准帧的采集角度的变化大于第一角度阈值。
结合第一方面,在第一方面的第三种可能实现方式中,根据数据帧中包括的反光板点的坐标,确定所述当前数据帧所包括的两个或两个以上的反光板点,与所查找的数据帧中包括的两个或两个以上的反光板点的相似度,包括:
根据所述当前数据帧所包括的两个或两个以上的反光板点的坐标,确定第一距离矩阵,所述第一距离矩阵为所述当前数据帧中的反光板点之间的距离所构成的矩阵;
根据预设范围内所查找的数据帧中包括的两个或两个以上的反光板点的坐标,确定第二距离矩阵,所述第二距离矩阵为所查找的数据帧中的反光板点之间的距离所构成的矩阵;
根据所述第一距离矩阵和所述第二距离矩阵确定所述相似度。
结合第一方面的第三种可能实现方式,在第一方面的第四种可能实现方式中,根据所述第一距离矩阵和所述第二距离矩阵确定所述相似度,包括:
如果第一距离矩阵与第二距离矩阵的元素的差值小于第三距离阈值,则获取所述当前数据帧的第一点云,以及所查找的数据帧的第二点云;
根据所述第一点云和所述第二点云的匹配分值,确定所述相似度。
结合第一方面,在第一方面的第五种可能实现方式中,通过同步定位与建图方法采集当前数据帧,还包括:
确定激光雷达所采集的数据帧中的关键帧;
根据当前所采集的关键帧确定所述当前数据帧。
结合第一方面的第五种可能实现方式,在第一方面的第六种可能实现方式中,确定激光雷达所采集的数据帧中的关键帧,包括:
如果当前所采集的数据帧为第一帧,则当前帧为关键帧;
如果当前所采集的数据帧不是第一帧,且前一个关键帧的采集时间的变化大于预先设定的第一时间阈值、前一关键帧的采集位置的变化大于预先设定的第三距离阈值,则当前所采集的数据帧为关键帧。
结合第一方面,在第一方面的第七种可能实现方式中,根据优化后的数据帧确定反光板点的坐标,包括:
获取位姿优化后的机器人轨迹,确定在该轨迹上所采集的数据帧中包括的反光板点的坐标;
根据所记录的反光板点的坐标之间的距离,对反光板点进行合并;
根据所合并的反光板点的坐标确定合并后的反光板点的坐标。
本申请实施例的第二方面提供了一种反光板定位装置,该装置包括:
数据帧采集单元,用于通过同步定位与建图方法采集当前数据帧,确定所述当前数据帧中包括的反光板点数量为两个或两个以上,以及确定所述当前数据帧中包括的反光板点在预设的地图平面坐标系下的坐标;
相似度确定单元,用于在预设范围内查找数据帧,根据数据帧中包括的反光板点的坐标,确定所述当前数据帧所包括的两个或两个以上的反光板点,与所查找的数据帧中包括的两个或两个以上的反光板点的相似度;
回环优化单元,用于当所述相似度大于预先设定的相似度阈值,则根据所述当前数据帧与所查找的数据帧所构成的回环,对回环中包括的数据帧的位姿进行优化;
反光板点坐标确定单元,用于根据优化后的数据帧确定反光板点的坐标。
本申请实施例的第三方面提供了机器人,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任一项所述方法的步骤。
本申请实施例的第四方面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如第一方面任一项所述方法的步骤。
有益效果
本申请实施例与现有技术相比存在的有益效果是:本申请实施例通过激光雷达采集到包括两个或两个以上的反光板点的当前数据帧,将其与预设范围内查找的数据帧进行反光板点的相似度比较,在反光板点的相似度大于预设的相似度阈值时,则根据当前数据帧和所查找的数据帧构成的回环,对采集数据帧的机器人的位姿进行优化,从而得到更为准确的机器人的位姿,根据优化了位姿后的数据帧,更为准确、高效的确定反光板点的坐标,且在同步定位和建图时即建立了反光板点与地图坐标的匹配,可减少反光板点的定位效率。
附图说明
为了更清楚地说明本申请实施例中的技术方案,下面将对实施例或现有技术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申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的反光板定位场景示意图;
图2是本申请实施例提供的一种反光板定位方法的实现流程示意图;
图3是本申请实施例提供的一种回环优化示意图;
图4是本申请实施例提供的一种反光板定位装置的示意图;
图5是本申请实施例提供的机器人的示意图。
本发明的实施方式
以下描述中,为了说明而不是为了限定,提出了诸如特定系统结构、技术之类的具体细节,以便透彻理解本申请实施例。然而,本领域的技术人员应当清楚,在没有这些具体细节的其它实施例中也可以实现本申请。在其它情况中,省略对众所周知的系统、装置、电路以及方法的详细说明,以免不必要的细节妨碍本申请的描述。
为了说明本申请所述的技术方案,下面通过具体实施例来进行说明。
图1为本申请实施例提供的一种反光板定位方法的实施场景示意图。如图1所示,在机器人工作场景中包括若干个反光板(图1示例包括反光板1、反光板2、反光板3、反光板4,其它实际场景中也可能包括反光柱等),反光板根据工作场景信息,包括墙壁、门柱等信息进行安装。每个反光板相对于机器人移动平面的安装高度为恒定值,可以与机器人的激光雷达的高度相适。反光板的尺寸可以预先设定为统一大小,比如可以设置为宽度3厘米,高度10厘米的长方形。
在安装完成后,为了能够根据反光板的位置对机器人进行定位,需要准确的确定反光板在地图坐标系中的坐标。
图2为本申请实施例提供的一种反光板定位方法的实现流程示意图。如图2所示,该流程包括:
在S201中,通过同步定位与建图方法采集当前数据帧,确定所述当前数据帧中包括的反光板点数量为两个或两个以上,以及确定所述当前数据帧中包括的反光板点在预设的地图平面坐标系下的坐标。
具体的,同步定位与建图(英文全称为simultaneous localization and mapping,英文简称为SLAM)方法,即机器人在未知环境中从一个未知位置开始移动,在移动过程中根据位置和地图进行自身定位,同时在自身定位的基础上建造增量式地图,实现机器人的自主定位和导航的方法。
通过同步定位与建图方法采集当前数据帧时,可以仅对当前采集的关键帧进行筛选,获得满足要求的当前数据帧。
其中,关键帧可以为激光雷达所采集的数据帧的第一帧。即不管所采集的数据帧是否包括反光板点,该第一帧可以称为关键帧。
随着采集时间的变化,激光雷达所采集的数据帧中包括的关键帧可以越来越多。确定 当前所采集的数据帧是否为关键帧,可以根据当前时间的前一个关键帧的采集时间,与当前时间之间的时间差是否超过第一时间阈值;或者当前时间的前一个关键帧的采集位置,与当前时间的数据帧的采集位置之间距离大于预设的第三距离阈值;或者当前时间的前一个关键帧的采集角度,与当前时间的数据帧的采集角度的变化大于第二角度阈值,则当前采集的数据帧为关键帧。
所述反光板点,即机器人通过激光雷达发射检测信号来探测反光板,所探测到的、通过点来表示的反光板的位置,即为反光板点。
在确定数据帧中包括的反光板点数量时,可以根据激光点的强度来判断。当机器人所接收到多个连续的激光点的强度大于预先设定的第一强度阈值,则可以根据连续的激光点的平均值确定一个反光板点的位置。如果单个激光点的强度超过预设的第一强度阈值,则以该点作为一个反光板的位置点,即一个反光板点。
在进行同步定位与建图时,根据激光雷达在地图坐标系上的位姿,反光板相对于激光雷达的距离和角度,即可确定反光板点在地图坐标系上的坐标。
在S202中,在预设范围内查找数据帧,根据数据帧中包括的反光板点的坐标,确定所述当前数据帧所包括的两个或两个以上的反光板点,与所查找的数据帧中包括的两个或两个以上的反光板点的相似度。
在本申请实施例中,在预设范围内所查找的数据帧,可以为当前数据帧对应的基准帧,即当前数据帧的前一基准帧,也可以为当前数据帧之前预定范围内的数据帧中的任意数据帧,或者当前数据帧之前的预定范围内的任意关键帧。
其中,所述基准帧,可以通过对关键帧进行过滤筛选得到。比如,可以设定反光板点的数量大于或等于2,那么,当关键帧中的反光板点的数量大于或等于2,且在当前数据帧之前,则该数据帧可称为基准帧。
由于机器人建图时即确定了数据帧中包括的反光板点的坐标,因此,可以计算当前数据帧和基准帧中的反光板点的坐标之间的距离。比如,可以依次确定当前数据帧中的每一个反光板点,到基准帧中的所有反光板点的距离。将所确定的距离与预先设定的第一距离阈值进行比较。比如,第一距离阈值可以为10厘米,如果所计算的距离小于10厘米,则确定这两个反光板点为同一个反光板所对应的点,相似度大于预先设定的相似度阈值。或者,在包括两组或两组以上的反光板点的距离小于预设的第一距离阈值时,则确定相似度大于预定的相似度阈值。
其中,在预设的范围内确定与当前数据帧进行比较的基准帧时,可以待比较的数据帧与当前数据帧的采集角度大于第一角度阈值,或者待比较的数据帧与当前数据帧的机器人采集位置的距离大于预定的第二距离阈值,则该待比较的数据帧符合预设的范围要求。在满足预设的范围要求后,如果待比较的数据帧为关键帧,且包括两个或两个以上的反光板点,则该待比较的数据帧为可用于查找和比较的基准帧。
在可能的实现方式中,可以根据当前数据帧中所包括的两个或两个以上的反光板点的坐标,确定第一距离矩阵。比如,可以根据当前数据帧中所包括的两个或两个以上的反光板点的坐标,计算任意两个反光板点的距离,将所计算的距离作为第一距离矩阵中的元素。为了便于比较,在该距离矩阵中,各个反光板点之间的距离,以反光板点的序号为横坐标和纵坐标,建立矩阵,矩阵的元素是两个序号的点之间的距离。该矩阵是对角矩阵,可以只保留半个斜角的值,对角线上的元素和另外一个斜角的值置为零。
比如,当前数据帧中包括n个反光板点,第一反光板点与第二反光板点的距离为d01,第一反光板点与第三反光板点的距离为d02,第一反光板点与第n反光板点的距离为d0(n-1),第二反光板点与第三反光板点的距离为d12,第二反光板点与第n反光板点的距离为d1(n-1),第n-1反光板点与第n反光板点的距离为d(n-2)(n-1)。第一距离矩阵可以 表示为:
Figure PCTCN2021126717-appb-000001
同样,对于预设范围内所查找的数据帧,也可以按照各个反光板点的坐标计算反光板点之间的距离,根据所计算的距离确定第二距离矩阵。
将第一距离矩阵和第二距离矩阵进行比较,即可确定当前数据帧与所查找的数据帧之间的相似度。
其中,所查找的数据帧所在的阈值范围,可以包括采集所查找的数据帧的位置和采集当前数据帧的位置的距离大于预设的第三距离阈值,并且采集当前数据帧和所查找的数据帧的时间的变化在于第一时间阈值。其中,时间的变化也可以通过帧数来表示,即采集当前数据帧和所查找的数据帧之间的帧数大于第一帧数阈值。
在进行距离矩阵(第一距离矩阵和第二距离矩阵)的比较时,可以将距离矩阵中的元素值的差值是否小于预定的第四距离阈值,则认为两帧之间存在粗糙的对应关系,可以进一步通过点云匹配的方式,确定帧的匹配分值。如果匹配分值大于预定的匹配阈值,则认为两个数据帧相似,数据帧中的反光板点包括相同的反光板点。
在S203中,当所述相似度大于预先设定的相似度阈值,则根据所述当前数据帧与所查找的数据帧所构成的回环,对回环中包括的数据帧的位姿进行优化。
如果两帧的相似度大于预先设定的相似度阈值,则表示两帧中包括相同的反光板点,可以根据当前数据帧和基准帧(或所查找的数据帧)的采集位姿,结合匹配的反光板点在图像中的位置,可以确定机器人在采集当前数据帧与采集基准帧时发生的位移。
如图3所示,依据回环所确定的位移,即为机器人由采集所查找的数据帧的位姿变换为采集当前数据帧的位姿所发生变化的位移。构成该回环的位移可作为实际位移,根据当前数据帧与所查找的数据帧之间的数据帧(或关键帧)的点云,计算相邻两帧之间所发生的帧间位移,通过累计计算帧间位移,可以得到计算的总位移与实际位移的误差,根据该误差可以对所述当前数据帧和绝对数据帧中的数据帧进行优化。优化方法包括但不限于根据机器人当前位姿与实际位姿的误差,均匀分配至各个数据帧中。
在S204中,根据优化后的数据帧确定反光板点的坐标。
根据机器人移动过程中所检测到的回环,对数据帧或关键帧进行优化,包括对采集关键帧的机器人坐标的优化。根据优化后的数据帧所生成的机器人移动轨迹,可以确定移动轨迹相应的数据帧的反光板点的坐标。可以记录所有的数据帧中的反光板点的坐标,并根据反光板点的坐标之间的距离,将距离小于预定的合并距离阈值的反光板点合并为同一反光板点,并以所合并的反光板点的坐标的平均值,作为合并后的反光板点的坐标。
由于本申请所生成的反光板点的坐标是以同步定位和建图为基础所确定的坐标,因此,不需要额外进行人工将反光板点的坐标与地图匹配,并且在同步定位与建图过程中,根据数据帧中两个或两个以上的反光板点的相似性,查找数据帧对应的回环点,对数据帧的位置进行优化处理,从而能够自动得到反光板点的坐标的同时,还能提高所得到的坐标的精度。
应理解,上述实施例中各步骤的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本申请实施例的实施过程构成任何限定。
图4为本申请实施例提供的一种反光板定位装置示意图,该装置包括:
数据帧采集单元401,用于通过同步定位与建图方法采集当前数据帧,确定所述当前数据帧中包括的反光板点数量为两个或两个以上,以及确定所述当前数据帧中包括的反光板点在预设的地图平面坐标系下的坐标;
相似度确定单元402,用于在预设范围内查找数据帧,根据数据帧中包括的反光板点的坐标,确定所述当前数据帧所包括的两个或两个以上的反光板点,与所查找的数据帧中包括的两个或两个以上的反光板点的相似度;
回环优化单元403,用于当所述相似度大于预先设定的相似度阈值,则根据所述当前数据帧与所查找的数据帧所构成的回环,对回环中包括的数据帧的位姿进行优化;
反光板点坐标确定单元404,用于根据优化后的数据帧确定反光板点的坐标。
图4所示的反光板定位装置,与图2所示的反光板定位方法对应。
图5是本申请一实施例提供的机器人的示意图。如图5所示,该实施例的机器人5包括:处理器50、存储器51以及存储在所述存储器51中并可在所述处理器50上运行的计算机程序52,例如反光板定位程序。所述处理器50执行所述计算机程序52时实现上述各个反光板定位方法实施例中的步骤。或者,所述处理器50执行所述计算机程序52时实现上述各装置实施例中各模块/单元的功能。
示例性的,所述计算机程序52可以被分割成一个或多个模块/单元,所述一个或者多个模块/单元被存储在所述存储器51中,并由所述处理器50执行,以完成本申请。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段,该指令段用于描述所述计算机程序52在所述机器人5中的执行过程。
所述机器人可包括,但不仅限于,处理器50、存储器51。本领域技术人员可以理解,图5仅仅是机器人5的示例,并不构成对机器人5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,例如所述机器人还可以包括输入输出设备、网络接入设备、总线等。
所称处理器50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)、现场可编程门阵列(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51可以是所述机器人5的内部存储单元,例如机器人5的硬盘或内存。所述存储器51也可以是所述机器人5的外部存储设备,例如所述机器人5上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步地,所述存储器51还可以既包括所述机器人5的内部存储单元也包括外部存储设备。所述存储器51用于存储所述计算机程序以及所述机器人所需的其他程序和数据。所述存储器51还可以用于暂时地存储已经输出或者将要输出的数据。
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,并不用于限制本申请的保护范围。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。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述或记载的部分,可以参见其它实施例的相关描述。
本领域普通技术人员可以意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可 以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本申请的范围。
在本申请所提供的实施例中,应该理解到,所揭露的装置/终端设备和方法,可以通过其它的方式实现。例如,以上所描述的装置/终端设备实施例仅仅是示意性的,例如,所述模块或单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口,装置或单元的间接耦合或通讯连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元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。
所述集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请实现上述实施例方法中的全部或部分流程,也可以通过计算机程序指令相关的硬件来完成,所述的计算机程序可存储于一计算机可读存储介质中,该计算机程序在被处理器执行时,可实现上述各个方法实施例的步骤。其中,所述计算机程序包括计算机程序代码,所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、电载波信号、电信信号以及软件分发介质等。需要说明的是,所述计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减,例如在某些司法管辖区,根据立法和专利实践,计算机可读介质不包括是电载波信号和电信信号。
以上所述实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围,均应包含在本申请的保护范围之内。

Claims (10)

  1. 一种反光板定位方法,其特征在于,所述方法包括:
    通过同步定位与建图方法采集当前数据帧,确定所述当前数据帧中包括的反光板点数量为两个或两个以上,以及确定所述当前数据帧中包括的反光板点在预设的地图平面坐标系下的坐标;
    在预设范围内查找数据帧,根据数据帧中包括的反光板点的坐标,确定所述当前数据帧所包括的两个或两个以上的反光板点,与所查找的数据帧中包括的两个或两个以上的反光板点的相似度;
    当所述相似度大于预先设定的相似度阈值,则根据所述当前数据帧与所查找的数据帧所构成的回环,对回环中包括的数据帧的位姿进行优化;
    根据优化后的数据帧确定反光板点的坐标。
  2. 根据权利要求1所述的方法,其特征在于,根据数据帧中包括的反光板点的坐标,确定所述当前数据帧所包括的两个或两个以上的反光板点,与所查找的数据帧中包括的两个或两个以上的反光板点的相似度,包括:
    获取基准帧,所述基准帧为所查找的数据帧,且所述基准帧位于所述当前数据帧之前,并包括两个或两个以上的反光板点的数据帧;
    根据所述当前数据帧和所述基准帧中包括的反光板点的坐标,确定所述当前数据帧中的反光板点,与所述基准帧中的反光板点的之间距离;
    将所述距离与预先设定的第一距离阈值进行比较,根据所述比较结果确定反光板点的相似度。
  3. 根据权利要求2所述的方法,其特征在于,在预设范围内查找数据帧,包括:
    确定所述当前数据帧与所查找的所述基准帧的采集坐标的变化大于第二距离阈值,或者所述当前数据帧与所查找的所述基准帧的采集角度的变化大于第一角度阈值。
  4. 根据权利要求1所述的方法,其特征在于,根据数据帧中包括的反光板点的坐标,确定所述当前数据帧所包括的两个或两个以上的反光板点,与所查找的数据帧中包括的两个或两个以上的反光板点的相似度,包括:
    根据所述当前数据帧所包括的两个或两个以上的反光板点的坐标,确定第一距离矩阵,所述第一距离矩阵为所述当前数据帧中的反光板点之间的距离所构成的矩阵;
    根据预设范围内所查找的数据帧中包括的两个或两个以上的反光板点的坐标,确定第二距离矩阵,所述第二距离矩阵为所查找的数据帧中的反光板点之间的距离所构成的矩阵;
    根据所述第一距离矩阵和所述第二距离矩阵确定所述相似度。
  5. 根据权利要求4所述的方法,其特征在于,根据所述第一距离矩阵和所述第二距离矩阵确定所述相似度,包括:
    如果第一距离矩阵与第二距离矩阵的元素的差值小于第三距离阈值,则获取所述当前数据帧的第一点云,以及所查找的数据帧的第二点云;
    根据所述第一点云和所述第二点云的匹配分值,确定所述相似度。
  6. 根据权利要求1所述的方法,其特征在于,通过同步定位与建图方法采集当前数据帧,还包括:
    确定激光雷达所采集的数据帧中的关键帧;
    根据当前所采集的关键帧确定所述当前数据帧。
  7. 根据权利要求6所述的方法,其特征在于,确定激光雷达所采集的数据帧中的关键帧,包括:
    如果当前所采集的数据帧为第一帧,则当前帧为关键帧;
    如果当前所采集的数据帧不是第一帧,且前一个关键帧的采集时间的变化大于预先设定的第一时间阈值、前一关键帧的采集位置的变化大于预先设定的第三距离阈值,则当前 所采集的数据帧为关键帧。
  8. 根据权利要求1所述的方法,其特征在于,根据优化后的数据帧确定反光板点的坐标,包括:
    获取位姿优化后的机器人轨迹,确定在该轨迹上所采集的数据帧中包括的反光板点的坐标;
    根据所记录的反光板点的坐标之间的距离,对反光板点进行合并;
    根据所合并的反光板点的坐标确定合并后的反光板点的坐标。
  9. 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至8任一项所述方法的步骤。
  10. 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至8任一项所述方法的步骤。
PCT/CN2021/126717 2021-07-30 2021-10-27 反光板定位方法、机器人及计算机可读存储介质 WO2023005020A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110873994.8A CN113625249A (zh) 2021-07-30 2021-07-30 反光板定位方法、机器人及计算机可读存储介质
CN202110873994.8 2021-07-30

Publications (1)

Publication Number Publication Date
WO2023005020A1 true WO2023005020A1 (zh) 2023-02-02

Family

ID=78381852

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/126717 WO2023005020A1 (zh) 2021-07-30 2021-10-27 反光板定位方法、机器人及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN113625249A (zh)
WO (1) WO2023005020A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114777757A (zh) * 2022-03-14 2022-07-22 深圳市优必选科技股份有限公司 信标地图构建方法、装置、设备及存储介质
CN115842875B (zh) * 2023-02-21 2023-06-02 德力西集团仪器仪表有限公司 相似数据帧的确定方法、装置、计算机设备和介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018119606A1 (en) * 2016-12-26 2018-07-05 Bayerische Motoren Werke Aktiengesellschaft Method and apparatus for representing a map element and method and apparatus for locating vehicle/robot
CN109613550A (zh) * 2018-12-28 2019-04-12 芜湖哈特机器人产业技术研究院有限公司 一种基于反光板的激光雷达地图构建及定位方法
CN110031817A (zh) * 2018-12-28 2019-07-19 芜湖哈特机器人产业技术研究院有限公司 一种激光雷达反光板的快速匹配方法
CN110471072A (zh) * 2019-08-19 2019-11-19 华晟(青岛)智能装备科技有限公司 一种反光柱位置辨识方法及系统
CN111596299A (zh) * 2020-05-19 2020-08-28 三一机器人科技有限公司 反光柱跟踪定位方法、装置及电子设备
CN111694013A (zh) * 2020-06-11 2020-09-22 三一机器人科技有限公司 一种反光柱建图方法、装置、设备及存储介质
CN112285725A (zh) * 2020-10-10 2021-01-29 杭州电子科技大学 一种基于激光雷达的单移动机器人室内定位方法
CN113160130A (zh) * 2021-03-09 2021-07-23 北京航空航天大学 一种回环检测方法、装置及计算机设备

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2008132251A (ru) * 2008-08-04 2010-02-10 Владимир Николаевич Арнаутов (RU) Устройство автоматической коррекции потока света от источника параллельных лучей
CN109613548B (zh) * 2018-12-28 2022-12-23 芜湖哈特机器人产业技术研究院有限公司 一种基于图优化的激光雷达路标地图构建方法
CN112629522B (zh) * 2020-12-31 2023-04-11 山东大学 一种反光板与激光slam融合的agv定位方法及系统

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018119606A1 (en) * 2016-12-26 2018-07-05 Bayerische Motoren Werke Aktiengesellschaft Method and apparatus for representing a map element and method and apparatus for locating vehicle/robot
CN109613550A (zh) * 2018-12-28 2019-04-12 芜湖哈特机器人产业技术研究院有限公司 一种基于反光板的激光雷达地图构建及定位方法
CN110031817A (zh) * 2018-12-28 2019-07-19 芜湖哈特机器人产业技术研究院有限公司 一种激光雷达反光板的快速匹配方法
CN110471072A (zh) * 2019-08-19 2019-11-19 华晟(青岛)智能装备科技有限公司 一种反光柱位置辨识方法及系统
CN111596299A (zh) * 2020-05-19 2020-08-28 三一机器人科技有限公司 反光柱跟踪定位方法、装置及电子设备
CN111694013A (zh) * 2020-06-11 2020-09-22 三一机器人科技有限公司 一种反光柱建图方法、装置、设备及存储介质
CN112285725A (zh) * 2020-10-10 2021-01-29 杭州电子科技大学 一种基于激光雷达的单移动机器人室内定位方法
CN113160130A (zh) * 2021-03-09 2021-07-23 北京航空航天大学 一种回环检测方法、装置及计算机设备

Also Published As

Publication number Publication date
CN113625249A (zh) 2021-11-09

Similar Documents

Publication Publication Date Title
US20210063577A1 (en) Robot relocalization method and apparatus and robot using the same
CN110561423B (zh) 位姿变换的方法、机器人及存储介质
WO2023005020A1 (zh) 反光板定位方法、机器人及计算机可读存储介质
WO2022121018A1 (zh) 机器人及其建图方法和装置
CN112667837A (zh) 图像数据自动标注方法及装置
CN111028277A (zh) 基于伪孪生卷积神经网络的sar和光学遥感图像配准方法
JP5385105B2 (ja) 画像検索方法およびシステム
CN110910389B (zh) 一种基于图描述子的激光slam回环检测系统及方法
CN112991459A (zh) 一种相机标定方法、装置、设备以及存储介质
CN115346183A (zh) 一种车道线检测方法、终端及存储介质
CN111383246A (zh) 条幅检测方法、装置及设备
CN113807293A (zh) 减速带的检测方法、系统、设备及计算机可读存储介质
EP3580690B1 (en) Bayesian methodology for geospatial object/characteristic detection
CN116912517A (zh) 相机视野边界的检测方法及装置
WO2022252482A1 (zh) 机器人及其环境地图构建方法和装置
CN116817887A (zh) 语义视觉slam地图构建方法、电子设备及存储介质
CN111179218A (zh) 传送带物料检测方法、装置、存储介质及终端设备
CN110930455B (zh) 定位方法、装置、终端设备及存储介质
CN114581890A (zh) 确定车道线的方法、装置、电子设备和存储介质
CN113112551A (zh) 相机参数的确定方法、装置、路侧设备和云控平台
CN109831737B (zh) 一种基于置信度的蓝牙定位方法、装置、设备和系统
CN113487634A (zh) 关联建筑物高度与面积的方法及装置
CN116977677B (zh) 基于聚类的图像特征点匹配筛选方法、装置、设备及介质
CN117419732B (zh) 一种基于路网的感知目标定位纠偏方法、设备及存储介质
CN112686246B (zh) 一种车牌字符分割方法、装置、存储介质及终端设备

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: 21951592

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE