Method and apparatus for tracking object of mobile robot using 2d lidar-based marker

The use of 2D lidar sensors to detect high-intensity reflective markers on objects allows mobile robots to accurately track objects, addressing cost and accuracy issues in existing technologies, enhancing their tracking capabilities.

JP2024163035AInactive Publication Date: 2024-11-21CHUNGBUK NAT UNIV IND ACADEMIC COOP FOUNDATION
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2024068956
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-09
Filing Date
2024-04-22
Publication Date
2024-11-21
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Mobile robots face challenges in cost-effectively recognizing and tracking objects due to the high cost of deep learning-based methods and the accuracy issues of image sensors like cameras, while lidar sensors, though accurate, are expensive.

Method used

A method and apparatus using a 2D lidar sensor to detect markers with high-intensity reflective materials, processing point cloud data to estimate the pose of objects by clustering and analyzing changes in reflection intensity and point distribution.

Benefits of technology

This approach enables accurate and cost-effective object recognition and tracking, reducing computational costs and improving robustness in crowded environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024163035000001_ABST
    Figure 2024163035000001_ABST
Patent Text Reader

Abstract

To provide a method and an apparatus for tracking an object of a mobile robot using a 2D lidar-based marker.SOLUTION: According to one aspect of the present disclosure, a method for estimating the posture of a target object of a mobile robot using a 2D lidar-based marker performs the following processes of: acquiring first point cloud data including distance data and reflectance intensity using a 2D lidar sensor of the mobile robot; extracting second point cloud data corresponding to a highly luminous reflective material contained in a marker attached to the object from the first point cloud data; clustering the second point cloud data into at least one cluster; identifying a target cluster corresponding to the target object from the at least one cluster; and estimating the posture of the target object based on a change in the target cluster.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a method and apparatus for tracking an object of a mobile robot using 2D LIDAR-based markers, and more particularly, to a technology for a mobile robot to identify a target object and estimate its pose using 2D LIDAR-based markers. [Background technology]

[0002] The following description is merely intended to provide background information related to the present invention and may not constitute prior art.

[0003] The Mobility as a Service (MaaS) market is expected to grow in the future, and based on this prediction, mobile robots will mainly play the role of tracking people and helping and collaborating with them.

[0004] Mobile robots are used to load and move objects in various places, such as factories, logistics centers, museums, restaurants, commercial facilities, airports, or smart farms, or to provide people with information or services while moving. In particular, when a person loads objects onto a mobile robot and moves around in an airport, commercial facility, factory, or the like, the mobile robot can follow the person. The mobile robot's automatic recognition and tracking of a person has the advantage that the person does not need to directly control a transport device such as a cart to load objects onto the transport device and move the transport device.

[0005] For a mobile robot to perform this role, it must be able to recognize and track people while maintaining a safe distance, and it must be able to stably track people even in crowded environments.

[0006] Deep learning-based methods (e.g., Mask R-CNN, YOLO, SSD, etc.) are commonly used to perform object recognition and / or tracking. However, deep learning-based methods have the problem that they require high-performance hardware, which increases the price of mobile robots.

[0007] In the case of image sensors such as cameras, the accuracy of object recognition from captured images can be reduced due to factors such as lighting changes, low resolution, occlusion, etc. LIDAR (Light Detection And Ranging) sensors measure the distance to a reflector by capturing a laser pulse and measuring the time it takes for it to return, and are highly accurate but relatively expensive.

[0008] Therefore, there is a need for a technology that can configure a cost-effective and robust system for a mobile robot to recognize and track a target object. Summary of the Invention [Problem to be solved by the invention]

[0009] An object of the present disclosure is to provide a technology that enables a mobile robot to recognize and track an object using markers attached to the object and a 2D LIDAR sensor mounted on the mobile robot.

[0010] An object of the present disclosure is to provide a technique for detecting an object and estimating the posture of the object using a marker including a high-brightness reflective material.

[0011] The problems to be solved by the present invention are not limited to those mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0012] According to one aspect of the present disclosure, there is provided a method for estimating a posture of a target object of a mobile robot using a 2D LIDAR-based marker, the method including: acquiring first point cloud data including distance data and reflection intensity using a 2D LIDAR sensor of the mobile robot; extracting second point cloud data corresponding to a high-brightness reflective material contained in a marker attached to an object from the first point cloud data; clustering the second point cloud data into at least one cluster; identifying a target cluster corresponding to a target object from the at least one cluster; and estimating a posture of the target object based on a change in the object cluster.

[0013] According to another aspect of the present disclosure, there is provided an apparatus for estimating a posture of a target object of a mobile robot using a 2D LIDAR based marker, the apparatus including: an acquisition unit that acquires first point cloud data including distance data and reflection intensity using a 2D LIDAR sensor of the mobile robot; a pre-processing unit that extracts second point cloud data corresponding to a high-brightness reflective material included in a marker attached to an object from the first point cloud data; a clustering unit that clusters the second point cloud data into at least one cluster; an identification unit that identifies a target cluster corresponding to a target object from the at least one cluster; and a posture estimation unit that estimates a posture of the target object based on a change in the object cluster. Effect of the Invention

[0014] According to the embodiments of the present disclosure, it is possible to configure a cost-effective system for object recognition and tracking of a mobile robot.

[0015] According to the embodiments of the present disclosure, it is possible to improve the accuracy of object recognition and tracking of a mobile robot and reduce the computational cost.

[0016] The effects of the present disclosure are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 is a configuration diagram of an apparatus for target object pose estimation for a mobile robot using 2D lidar-based markers according to one embodiment of the present disclosure. [Diagram 2] FIG. 2 is an exemplary diagram showing a marker in which a plurality of high brightness reflective materials having different sizes are arranged, according to one embodiment of the present disclosure. [Diagram 3] FIG. 3 is an example diagram illustrating a change in the number of points of point cloud data corresponding to high brightness reflective materials according to a change in the posture of an object. [Figure 4] 11 is an illustrative diagram illustrating a ratio between the number of points corresponding to a left high brightness reflective material and the number of points corresponding to a right high brightness reflective material when a 2D LIDAR sensor and an object are positioned perpendicularly to each other; FIG. [Diagram 5] FIG. 5 is an exemplary diagram illustrating that when the 2D LIDAR sensor and the object are positioned perpendicular to each other and the distance between the 2D LIDAR sensor and the object changes, the number of points changes but the ratio remains the same. [Figure 6] 6a and 6b are exemplary diagrams illustrating a change in ratio as the number of points corresponding to left / right high brightness reflective materials changes according to a change in the posture of an object. [Figure 7] FIG. 7 is a flowchart of a method for target object pose estimation for a mobile robot using 2D lidar-based markers according to one embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Some embodiments of the present disclosure will be described in detail below with reference to the drawings. When referring to components in each drawing, it should be noted that the same components are assigned the same reference numerals as much as possible even if they are displayed in different drawings. In describing the present disclosure, if a detailed description of a related publicly known configuration or function is deemed to obscure the gist of the present disclosure, the detailed description will be omitted.

[0019] In describing components of the embodiments of the present disclosure, reference numerals such as 1, 2, i), ii), a), and b) may be used. Such reference numerals are used to distinguish the components from other components, and do not limit the essence or order or sequence of the components. When a part of the specification "includes" or "has" a certain component, this does not mean that other components are excluded, but that other components may be further included, unless explicitly stated to the contrary. Furthermore, the terms "unit", "module", and the like described in this specification refer to a unit that processes at least one function or operation, and are embodied in hardware, software, or a combination of hardware and software.

[0020] The description of the invention disclosed below in conjunction with the accompanying drawings is intended to describe exemplary embodiments of the invention and is not intended to represent the only embodiments in which the invention may be practiced.

[0021] The present disclosure provides a cost-effective and robust object tracking technology by estimating the posture and predicting the behavior of a tracked object using a sensor-based method, i.e., a 2D lidar sensor and markers attached to the tracked object, where the tracked object may include, but is not limited to, a human being as well as other mobile robots.

[0022] The marker referred to in this specification includes a plurality of high brightness reflective materials having different sizes attached to an object. The marker includes a plurality of high brightness reflective materials aligned in a certain direction. The marker is attached to a specific position (e.g., back or elbow) of the object within the sensing range of the 2D lidar sensor. In order to increase the accuracy of marker recognition, it is preferable to attach the marker at a position having the same or similar height as the 2D lidar sensor of the mobile robot.

[0023] Furthermore, a marker having a different shape may be used for each object to identify the object, for example, but not limited to, each marker having a shape such as a barcode.

[0024] FIG. 1 is a configuration diagram of an apparatus for target object pose estimation for a mobile robot using 2D lidar-based markers (hereinafter referred to as a "target object pose estimation apparatus") according to one embodiment of the present disclosure.

[0025] Referring to FIG. 1, a target object pose estimation apparatus (10) includes all or part of an acquisition unit (110), a preprocessing unit (120), a clustering unit (130), an identification unit (140), and a pose estimation unit (150).

[0026] 1 is an embodiment of the present disclosure, and some components may be added, changed, or removed in other embodiments. For example, in other embodiments, the target object posture estimation device 10 may further include a control unit (not shown) that controls the behavior of a mobile robot based on the estimated posture of the target object.

[0027] 1 illustrates the target object posture estimation apparatus 10 as a device for convenience of explanation, and in other embodiments, the target object posture estimation apparatus 10 and each of its components may be implemented in hardware or software, or a combination of hardware and software. Furthermore, the functions of each component may be implemented in software, and one or more processors may execute the software functions corresponding to each component.

[0028] The acquisition unit 110 acquires point cloud data using a 2D lidar sensor of a mobile robot. The point cloud data includes distance data and reflection intensity. The reflection intensity means the intensity of a signal reflected back to the 2D lidar sensor. The point cloud data includes 2D coordinate information of detected points.

[0029] The pre-processing unit 120 extracts point cloud data corresponding to high-brightness reflective materials included in markers attached to the object from the point cloud data acquired by the acquiring unit 110. This is to use only point cloud data reflected by high-brightness reflective materials included in markers attached to the object for identifying and estimating the posture of the target object.

[0030] The pre-processing unit 120 extracts point cloud data having a reflection intensity value higher than a threshold from the acquired point cloud data as point cloud data corresponding to a high-brightness reflective material included in a marker attached to the object. This is because point cloud data having a reflection intensity value higher than the threshold can be determined to have been reflected from a high-brightness reflective material on a marker attached to the object. The threshold is, for example, a minimum value assumed as a reflection intensity corresponding to a high-brightness reflective material.

[0031] FIG. 2 is an exemplary diagram showing a marker in which a plurality of high brightness reflective materials having different sizes are arranged, according to one embodiment of the present disclosure.

[0032] 2, there is illustrated a marker 20, a plurality of high brightness reflective materials 21a and 21b, and point cloud data 31. A pre-processing unit 120 extracts only points reflected by the high brightness reflective materials 21a and 21b from the point cloud data 31.

[0033] The pre-processing unit 120 may further perform noise removal, downsampling, etc. on the point cloud data.

[0034] The clustering unit 130 clusters the pre-processed point cloud data into at least one cluster, i.e., divides the pre-processed point cloud data into groups of points corresponding to markers for each object.

[0035] The clustering unit 130 performs distance-based clustering on the pre-processed point cloud data. For example, the similarity measure may be Euclidean distance, Manhattan distance, Minkowski distance, Chebyshev distance, density, etc., and the clustering algorithm may be, but is not limited to, K-Means algorithm.

[0036] The identification unit 140 identifies a target cluster corresponding to a target object from among at least one cluster. The target object refers to an object to be tracked by a mobile robot, and the target object is identified by an attached marker. The target cluster refers to a cluster of points that detect a marker attached to the target object.

[0037] The identification unit 140 compares the shape of at least one cluster with a preset shape to identify a target cluster corresponding to a target object. Even if multiple clusters exist, markers with different shapes are used for each object, so that the identification unit 140 identifies the cluster that is most similar to the shape preset for the mobile robot from among the multiple clusters as the target cluster.

[0038] The pose estimation unit 150 estimates a pose of the target object based on the object cluster.

[0039] It is also possible to calculate a normal vector for a line passing through points of the point cloud data included in the target cluster, and estimate the posture of the target object based on the calculated normal vector. However, although posture estimation using the normal vector can predict the direction in which a person intends to move, there are difficulties in estimating the posture.

[0040] The posture estimation unit 150 divides the points of the point cloud data included in the target cluster into groups corresponding to a plurality of high brightness reflective materials of different sizes, and estimates the posture of the target object using the change in the ratio between the number of points included in each group.

[0041] First, a change in points of point cloud data corresponding to high brightness reflective materials included in markers attached to an object according to the position and / or orientation of the object is observed.

[0042] When an object rotates clockwise or counterclockwise to change its posture, the number of points in the point cloud data corresponding to the high brightness reflective material included in the marker may change because the distance between the 2D LIDAR sensor and the high brightness reflective material changes. Therefore, the posture change of the object is estimated based on the change in the number of points in the point cloud data corresponding to the high brightness reflective material included in the marker.

[0043] 3, it can be seen that the number of points in the point cloud data corresponding to the left high-brightness reflective material included in the left marker, which indicates that the object is rotated clockwise, is reduced, and the number of points in the point cloud data corresponding to the right high-brightness reflective material included in the right marker, which indicates that the object is rotated counterclockwise, is reduced.

[0044] 4, the number of points corresponding to each of the high-brightness reflective materials, the average position of the points corresponding to the high-brightness reflective materials, and the distance between the average position and each of the high-brightness reflective materials are illustrated when the 2D LIDAR sensor and the object are positioned perpendicular to each other. The ratio n of the number of points corresponding to the left high-brightness reflective material to the number of points corresponding to the right high-brightness reflective material is r :n l It can be confirmed that the ratio is 3:6. r :n l The ratio between the distances is calculated using Equation 1.

[0045] [Formula 1] JPEG2024163035000002.jpg15170

[0046] where n l is the number of points corresponding to the high-brightness reflective material on the left side, and n r is the number of points corresponding to the right-side high-brightness reflective material, and d init(l) is the distance between the average position of the points corresponding to the left and right high-brightness reflective materials and the left high-brightness reflective material, and d init(r) is the distance between the average position of the points corresponding to the left and right highly reflective materials and the right highly reflective material.

[0047] As long as the 2D lidar sensor and the object are positioned perpendicular to each other, r :n l is maintained constant regardless of the distance between the object and the 2D LIDAR sensor. In other words, as shown in FIG. 5, the number of points corresponding to each high-intensity reflective material changes depending on the distance between the object and the 2D LIDAR sensor, but the ratio nr :n l is kept constant at 6:3 or 4:2.

[0048] The posture estimation unit 150 detects a change in the target cluster by detecting the number n of points corresponding to the right-side high-brightness reflective material. r and the number of points corresponding to the high-brightness reflective material on the left side, n l Ratio to (n r :n l If the ratio changes, the posture estimation unit 150 estimates whether the posture of the target object has changed due to a clockwise rotation or a counterclockwise rotation. If the posture of the object has changed due to a clockwise or counterclockwise rotation, the ratio n r :n l will change.

[0049] Referring to FIG. 6a, when the object rotates clockwise and changes its pose, r :n l It can be seen that the ratio is 6:1, which is different from the 6:3 ratio in Figure 4 when the object is positioned perpendicular to the 2D lidar sensor.

[0050] Referring to FIG. 6b, when the object rotates counterclockwise and changes its pose, r :n l It can be seen that the ratio is 3:3, which is different from the 6:3 ratio in Figure 4 when the object is positioned perpendicular to the 2D lidar sensor.

[0051] Therefore, the ratio n r :n l If the rotation direction and rotation angle of the object are calculated as shown in Equations (2) and (3), the orientation estimation unit 150 estimates that the orientation of the object has changed. r and the number of points in the point cloud data corresponding to the high-brightness reflective material on the left side, n l Ratio to (n r :n l) changes, the rotation angle θ of the target object based on the orientation of the object perpendicular to the 2D LIDAR sensor is calculated by solving the following equation (3), and the orientation of the target object is estimated.

[0052] [Formula 2] JPEG2024163035000003.jpg36170

[0053] Here, rot is the rotation direction of the object based on the object's orientation perpendicular to the 2D lidar sensor, and d init(l) and d init(r) is the distance calculated by Equation 1 when the object is positioned perpendicular to the 2D lidar sensor, and d l and d r Each of these is the distance calculated by Equation 1 when the object is rotated and not positioned perpendicular to the 2D LIDAR sensor.

[0054] [Formula 3] JPEG2024163035000004.jpg36170

[0055] Here, θ is the rotation angle of the object based on the orientation in which the object is positioned perpendicular to the 2D LIDAR sensor.

[0056] As mentioned above, even if the distance between the object and the 2D lidar sensor is not constant, r :n l Since is constant, the pose of the object can be appropriately estimated regardless of the distance between the object and the 2D lidar sensor.

[0057] The posture estimation unit 150 divides the target cluster into a first group and a second group based on the position information of the points of the point cloud data included in the target cluster. For example, the points corresponding to the left high brightness reflective material 21a are divided into the first group, and the points corresponding to the right high brightness reflective material 21b are divided into the second group.

[0058] Pose estimation unit 150 obtains a ratio between the number of points of the point cloud data included in the first group and the number of points of the point cloud data included in the second group.

[0059] The posture estimation unit 150 estimates the posture of the target object based on a change in the ratio between the previous time point and the current time point. The posture estimation unit 150 calculates the rotation direction and rotation angle of the target object using the above-mentioned equations (1) to (3) to estimate the posture.

[0060] The posture of the target object estimated by the posture estimation unit 150 is used to predict and estimate the next state of the target object using a Kalman filter.

[0061] A control unit (not shown) controls the behavior of the mobile robot based on the estimated posture of the target object. The control unit predicts the behavior of the target object based on the estimated posture and controls the behavior of the mobile robot to track the target object.

[0062] FIG. 7 is a flowchart of a method for target object pose estimation for a mobile robot using 2D lidar-based markers according to one embodiment of the present disclosure.

[0063] 7, the target object pose estimation apparatus 10 acquires first point cloud data including distance data and reflection intensity using a 2D LIDAR sensor of a mobile robot (S710). The point cloud data includes 2D coordinate information of detected points.

[0064] The target object posture estimation apparatus 10 extracts second point cloud data corresponding to high brightness reflective materials included in the markers attached to the object from the first point cloud data (S720). Point cloud data having a reflection intensity value higher than a threshold is extracted as the second point cloud data from the first point cloud data.

[0065] The target object pose estimation apparatus 10 clusters the second point cloud data into at least one cluster (S730), and performs distance-based clustering on the second point cloud data.

[0066] The target object pose estimation apparatus 10 identifies an object cluster corresponding to the target object from among the at least one cluster (S740). The object cluster corresponding to the target object is identified by comparing a shape of the at least one cluster with a predefined shape.

[0067] The target object posture estimation device 10 estimates the posture of the target object based on the change in the target cluster (S750). Points of the point cloud data included in the target cluster are divided into groups corresponding to a plurality of high brightness reflective materials of different sizes, and the posture of the target object is estimated using the change in the ratio between the number of points included in each group.

[0068] The target object posture estimation device 10 controls the behavior of the mobile robot based on the estimated posture of the target object (S760).

[0069] At least some of the components described in the exemplary embodiments of the present disclosure may be implemented as hardware elements including at least one of a digital signal processor (DSP), a processor, a controller, an application-specific integrated circuit (ASIC), a programmable logic device (such as an FPGA), and other electronic devices, or a combination thereof. Furthermore, at least some of the functions or processes described in the exemplary embodiments may be implemented in software, and the software may be stored in a recording medium. At least some of the components, functions, and processes described in the exemplary embodiments of the present disclosure may be implemented as a combination of hardware and software.

[0070] Methods according to exemplary embodiments of the present disclosure may be implemented in a computer-executable program and may be embodied in a variety of recording media, such as magnetic storage media, optically readable media, and digital storage media.

[0071] Implementations of the various techniques described herein may be embodied in digital electronic circuitry, or in computer hardware, firmware, software, or in combinations thereof. Implementations may be embodied as a computer program product, i.e., a computer program tangibly embodied in an information carrier, e.g., a machine-readable storage device (computer-readable medium) or a radio signal, for processing by or controlling the operation of a data processing device, e.g., a programmable processor, a computer, or a plurality of computers. Computer programs, such as those described above, may be recorded in any form of programming language, including compiled or interpreted languages, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. Computer programs may be deployed to be processed on one computer or multiple computers at one site, or distributed across multiple sites and interconnected by a communications network.

[0072] Processors suitable for processing a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Typically, a processor receives instructions and data from a read-only memory or a random access memory, or both. Elements of a computer include at least one processor for executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices, such as magnetic, magnetic-optical, or optical disks, for storing data, or be coupled to receive data from, transmit data to, or both. Information carriers suitable for embodying computer program instructions and data include, by way of example, semiconductor memory devices, magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as compact disk read only memories (CD-ROMs) and digital video disks (DVDs), magneto-optical media such as floptical disks, read only memories (ROMs), random access memories (RAMs), flash memories, erasable programmable ROMs (EPROMs), electrically erasable programmable ROMs (EEPROMs), etc. The processor and memory may be supplemented by or included in special purpose logic circuitry.

[0073] The processor executes an operating system and software applications that run on the operating system. Additionally, the processor device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processor device may be described, but those skilled in the art will appreciate that a processor device may include multiple processing elements and / or multiple types of processing elements. For example, a processor device may include multiple processors, or a processor and a controller. Additionally, other processing configurations, such as parallel processors, are possible.

[0074] Additionally, non-transitory computer-readable media refers to any available media that can be accessed by a computer and includes both computer storage media and transmission media.

[0075] Although the specification includes many specific implementation details, these should not be construed as limitations on the scope of any invention or claimable subject matter, but rather as descriptions of features that are specific to particular embodiments of a particular invention. Certain features described herein in the context of a separate embodiment may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented in multiple embodiments either individually or in any suitable subcombination. Furthermore, although features may operate in a particular combination and be initially depicted as being so claimed, one or more features from a claimed combination may in some cases be excluded from that combination, or the claimed combination may be modified into a subcombination or a variation of the subcombination.

[0076] Similarly, although acts are depicted in the figures in a particular order, this should not be understood as requiring such acts to be performed in the particular order or sequential order shown in order to achieve desired results, or that all of the acts shown must be performed. In certain cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various apparatus components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the program components and apparatus described are typically integrated together in a single software product or packaged in multiple software products.

[0077] Meanwhile, the embodiments of the present invention disclosed in the specification and drawings are merely specific examples presented to facilitate understanding, and are not intended to limit the scope of the present invention. It is obvious to a person having ordinary skill in the art to which the present invention pertains that other modifications based on the technical concept of the present invention can be implemented in addition to the embodiments disclosed herein.

[0078] The scope of protection of the present embodiment should be interpreted according to the claims, and all technical ideas within the scope equivalent thereto should be interpreted as being included in the scope of rights of the present embodiment. [Explanation of symbols]

[0079] 110 Acquisition section 120 Pre-processing section 130 Clustering section 140 Identification section 150 Posture estimation section

Claims

1. A method for target object pose estimation for a mobile robot using 2D lidar based markers, comprising: acquiring first point cloud data including distance data and reflection intensity using a 2D lidar sensor of a mobile robot; extracting second point cloud data corresponding to a high brightness reflective material included in a marker attached to the object from the first point cloud data; clustering the second point cloud data into at least one cluster; identifying a target cluster corresponding to a target object from the at least one cluster; and estimating a pose of the target object based on the change in the object cluster; The method includes:

2. The marker attached to the object is The method of claim 1 including a plurality of high brightness reflective materials having at least one different size.

3. The extracting step includes: The method according to claim 1 , further comprising extracting, from the first point cloud data, point cloud data having a reflection intensity value higher than a threshold as the second point cloud data.

4. The clustering step includes: The method of claim 1 , further comprising performing distance-based clustering on the second point cloud data.

5. The identifying step includes: The method of claim 1 , further comprising comparing a morphology of the at least one cluster with a predefined morphology to identify a target cluster corresponding to the target object.

6. The estimating step includes: Dividing the object cluster into a first group and a second group based on position information of points of the point cloud data included in the object cluster; obtaining a ratio between the number of points of the point cloud data included in the first group and the number of points of the point cloud data included in the second group; and and estimating a pose of the target object based on the change in ratio.

7. The method of claim 1 , further comprising controlling a behavior of the mobile robot based on the estimated pose of the target object.

8. An apparatus for target object pose estimation for a mobile robot using 2D lidar-based markers, comprising: An acquisition unit that acquires first point cloud data including distance data and reflection intensity using a 2D lidar sensor of the mobile robot; a pre-processing unit for extracting second point cloud data corresponding to a high brightness reflective material included in a marker attached to an object from the first point cloud data; a clustering unit for clustering the second point cloud data into at least one cluster; an identification unit for identifying a target cluster corresponding to a target object from the at least one cluster; and a posture estimation unit that estimates a posture of the target object based on the change in the object cluster; An apparatus comprising:

9. The marker attached to the object is 10. The apparatus of claim 8, comprising a plurality of high brightness reflective materials having at least one different size.

10. The pre-treatment unit includes: The apparatus according to claim 8 , wherein point cloud data having a reflection intensity value higher than a threshold value is extracted as the second point cloud data from the first point cloud data.

11. The clustering unit includes: The apparatus of claim 8 , further comprising: performing distance-based clustering on the second point cloud data.

12. The identification unit is The apparatus of claim 8 , further comprising: comparing a morphology of the at least one cluster with a pre-defined morphology to identify an object cluster corresponding to the target object.

13. The posture estimation unit is 9. The apparatus of claim 8, further comprising: dividing the object cluster into a first group and a second group based on position information of points of point cloud data included in the object cluster; obtaining a ratio between a number of points of point cloud data included in the first group and a number of points of point cloud data included in the second group; and estimating a posture of the object based on a change in the ratio.

14. The apparatus of claim 8 , further comprising a controller configured to control a behavior of the mobile robot based on the estimated posture of the target object.

15. A computer-readable recording medium having stored thereon instructions, the instructions causing the computer to: acquiring first point cloud data including distance data and reflectance intensity using a 2D lidar sensor of a mobile robot; extracting second point cloud data corresponding to a high brightness reflective material included in a marker attached to the object from the first point cloud data; clustering the second point cloud data into at least one cluster; identifying a target cluster corresponding to a target object from the at least one cluster; and estimating a pose of the target object based on the change in the object cluster; A computer-readable recording medium for executing the above-mentioned.

Citation Information

Patent Citations

  • Vehicle utilizing spatial information acquired using sensors, sensing device utilizing spatial information acquired using sensors, and server

    JP2022518369A

  • Piece-wise network structure for long range environment perception

    US20210072391A1

  • Autonomous traveling robot system

    WO2019053798A1