WO2021254369A1 - Procédé et appareil de repositionnement de robot, dispositif électronique et support d'enregistrement. - Google Patents

Procédé et appareil de repositionnement de robot, dispositif électronique et support d'enregistrement. Download PDF

Info

Publication number
WO2021254369A1
WO2021254369A1 PCT/CN2021/100284 CN2021100284W WO2021254369A1 WO 2021254369 A1 WO2021254369 A1 WO 2021254369A1 CN 2021100284 W CN2021100284 W CN 2021100284W WO 2021254369 A1 WO2021254369 A1 WO 2021254369A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
resolution
map
grid map
iterative search
Prior art date
Application number
PCT/CN2021/100284
Other languages
English (en)
Chinese (zh)
Inventor
马福强
王超
姚秀军
桂晨光
蔡禹丞
蔡小龙
李振
郭新然
崔丽华
Original Assignee
京东科技信息技术有限公司
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 京东科技信息技术有限公司 filed Critical 京东科技信息技术有限公司
Publication of WO2021254369A1 publication Critical patent/WO2021254369A1/fr

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
    • G01C21/005—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
    • G01C21/20—Instruments for performing navigational calculations
    • G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO 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
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications

Definitions

  • the present disclosure generally relates to the technical field of mobile robot positioning and navigation, and more specifically to robot repositioning methods, devices, electronic equipment, and storage media.
  • indoor robot technology based on multi-sensor fusion has gradually emerged, taking on more tasks such as indoor inspection, service, and transportation, and greatly reducing labor costs.
  • navigation and positioning technology is one of the key technologies of indoor robot technology, and it is the key to realize the autonomous movement of mobile robots.
  • Currently commonly used positioning technologies mainly include outside-in methods and inside-out methods.
  • typical outside-in methods include visual recognition methods based on April tag codes and indoor positioning methods based on visible light communication
  • typical inside-out methods include AMCL (Adaptive Monte Carlo Localization) based on lidar, and adaptive Monte Carlo localization. )method.
  • AMCL Adaptive Monte Carlo Localization
  • the outside-in method needs to set a priori information in the working environment in advance, and needs to modify the working environment, the usage scenarios are limited.
  • the inside-out method actively locates the position in the working environment, without pre-setting prior information in the working environment, and without modifying the working environment. Therefore, the AMCL method based on lidar is currently the mainstream positioning method for indoor robots.
  • the AMCL method based on lidar supports the relocation function in theory, but its computational complexity is large, and it takes a long time to converge, and relocation cannot be completed quickly. It is extremely easy when there are repeated scenes. A relocation error has occurred.
  • the present disclosure provides a robot relocation method, which includes:
  • the first position is determined to be the position of the robot relative to the origin and output.
  • the iterative search on the first multi-resolution grid map to determine the first position of the robot in the grid map includes:
  • an iterative search is performed on the first multi-resolution grid map to determine the first position of the robot in the grid map.
  • the iterative search on the first multi-resolution grid map based on the first iterative search order to determine the first position of the robot in the grid map includes :
  • an iterative search is performed on the search area in the first multi-resolution grid map to determine the first position of the robot in the grid map.
  • the determining and outputting the first position as the position of the robot relative to the origin includes:
  • the first position and the first target position both include X-axis coordinates, Y-axis coordinates, and angular offset.
  • the method further includes:
  • the second position is determined to be the position of the robot relative to the origin and output.
  • the iterative search on the second multi-resolution grid map based on the initial position to determine the second position of the robot in the grid map includes:
  • an iterative search is performed on the second multi-resolution grid map to determine the second position of the robot in the grid map.
  • the determining and outputting the second position as the position of the robot relative to the origin includes:
  • the second position and the second target position both include X-axis coordinates, Y-axis coordinates, and angular offset.
  • a robot relocation device which includes:
  • the map acquisition module is configured to acquire the grid map corresponding to the current area when it is determined that the robot is not located at the origin;
  • the map down-sampling module is configured to down-sample the raster map based on a preset first depth rule to generate a first multi-resolution raster map;
  • a position determining module configured to perform an iterative search on the first multi-resolution grid map to determine the first position of the robot in the grid map;
  • the position output module is configured to determine and output the first position as the position of the robot relative to the origin.
  • the present disclosure provides an electronic device, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;
  • Memory configured to store computer programs
  • the processor is configured to execute the program stored in the memory to implement the robot relocation method described in the present disclosure.
  • the present disclosure provides a storage medium in which instructions are stored, which when run on a computer, cause the computer to execute the robot relocation method described in the present disclosure.
  • the present disclosure provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the robot relocation method described in the present disclosure.
  • the robot relocation method, device, electronic device, and storage medium of the present disclosure achieve rapid completion of relocation and avoid relocation errors when there are repeated scenes.
  • the grid map corresponding to the current area is obtained, and the grid map is down-sampled based on the preset first depth rule to generate the first multi-resolution grid map , Perform iterative search on the first multi-resolution grid map, determine the first position of the robot in the grid map, and determine the first position as the position of the robot relative to the origin and output.
  • the raster map is down-sampled by the preset first depth rule to generate the first multi-resolution raster map, and the first multi-resolution raster map is iteratively searched to determine the first position of the robot in the raster map , You can quickly complete the relocation, and avoid relocation errors when there are repeated scenes.
  • Figure 1 shows a schematic diagram of the implementation process of a robot relocation method in an embodiment of the present disclosure
  • FIG. 2 shows a schematic diagram of the implementation process of another robot relocation method in an embodiment of the present disclosure
  • Fig. 3 shows a schematic diagram of grid map area division in an embodiment of the present disclosure
  • FIG. 4 shows a schematic diagram of an implementation process of a robot positioning method in an embodiment of the present disclosure
  • Figure 5 shows a schematic structural diagram of a robot relocation device in an embodiment of the present disclosure.
  • Fig. 6 shows a schematic structural diagram of an electronic device in an embodiment of the present disclosure.
  • FIG. 1 it is a schematic diagram of the implementation process of the robot relocation method provided by the embodiments of the present disclosure.
  • the method may include the following steps:
  • S103 Perform an iterative search on the first multi-resolution grid map to determine the first position of the robot in the grid map;
  • S104 Determine that the first position is the position of the robot relative to the origin and output.
  • the robot if the robot is located at the origin of (coordinates), subsequent positioning processing can be performed on the robot; if the robot is not located at the origin of (coordinates), the robot needs to be repositioned (that is, determining The position of the robot relative to the origin of the coordinate), and then the robot can be subjected to subsequent positioning processing.
  • the embodiment of the present disclosure needs to obtain the grid corresponding to the current area. map.
  • the current area may be an indoor working area or a designated outdoor area, which is not limited in the embodiment of the present disclosure.
  • the robot when it is determined that the robot is not located at the origin (coordinates), the robot needs to be repositioned, and the repositioning process can be performed once when the robot is turned on.
  • the embodiment of the present disclosure performs down-sampling on the raster map based on a preset first depth rule to generate a first multi-resolution raster map, where down-sampling refers to reducing The resolution of the raster map.
  • the first multi-resolution raster map it may include the first lowest resolution raster map, the first intermediate resolution raster map, and the first highest resolution raster map.
  • the first highest resolution raster map that is The grid map corresponding to the above current area.
  • the first intermediate resolution raster map includes at least one first intermediate resolution raster map, and raster maps of different resolutions can form a first multi-resolution raster map with a depth of D1 .
  • the raster map is down-sampled based on the preset first depth rule, and the resolution can be generated as The first multi-resolution raster map of 1000*1000, 500*500, 250*250;
  • the first lowest resolution raster map includes: a raster map with a resolution of 250*250
  • the first intermediate resolution raster map includes: a raster map with a resolution of 500*500
  • the first highest resolution raster map The grid map includes: a grid map with a resolution of 1000*1000.
  • the grid maps of different resolutions can form the first multi-resolution grid map with a depth of D1 (that is, 3).
  • the raster map is down-sampled based on the preset first depth rule, and the resolution can be generated as 10000*10000, 5000*5000, 2500*2500, 1250*1250, 625*625 grid map;
  • the first lowest resolution raster map includes: a raster map with a resolution of 625*625, and the first intermediate resolution raster map includes: a raster with a resolution of 5000*5000, 2500*2500, 1250*1250
  • the first highest resolution raster map includes: a raster map with a resolution of 10000*10000.
  • the raster maps of different resolutions can form the first multi-resolution raster map with a depth of D1 (that is, 5).
  • the raster map is down-sampled based on the preset first depth rule to generate the first multi-resolution raster map.
  • the resolution of the grid map is relatively high, and the grid map can be down-sampled in more levels based on the preset first depth rule to generate the first multi-resolution grid map (for example, the above-mentioned resolution of 10000*10000 Processing process of raster map), if the resolution of the raster map is low, the raster map can be down-sampled at a lower level based on the preset first depth rule to generate the first multi-resolution raster map (Such as the above processing process for the raster map with a resolution of 1000*1000).
  • an iterative search is performed on the first multi-resolution raster map to determine the robot's position in the raster map. One location.
  • the iterative search from coarse to fine on the first multi-resolution grid map can determine the first position of the robot in the grid map.
  • the first position includes X-axis coordinates, Y-axis coordinates, and angular offset.
  • the angular offset can be understood as the angular offset relative to the preset direction of the robot. For example, suppose that the initial direction of the robot (ie, the preset direction) is true north, and the robot direction is true south during the subsequent movement of the robot, and the angle offset of the robot at this time is 180 degrees.
  • the first position of the robot in the grid map it can be understood as the position of the robot relative to the origin, and the first position can be output. So far, the relocation of the robot is completed.
  • the robot For the first position of the robot in the grid map, it can be used as the particle with the highest weight in the AMCL to perform filter calculation in the next positioning calculation, so that the loop of the technology chain is realized.
  • the grid map corresponding to the current area is obtained, and the grid map is down-sampled based on the preset first depth rule to generate the first Multi-resolution raster map, iterative search is performed on the first multi-resolution raster map, the first position of the robot in the raster map is determined, and the first position is determined as the position of the robot relative to the origin and output.
  • the raster map is down-sampled by the preset first depth rule to generate the first multi-resolution raster map, and the first multi-resolution raster map is iteratively searched to determine the first position of the robot in the raster map , You can quickly complete the relocation, and avoid relocation errors when there are repeated scenes.
  • FIG. 2 it is a schematic diagram of the implementation process of another robot relocation method provided by an embodiment of the present disclosure.
  • the method may include the following steps:
  • S203 Determine a first iterative search order of the first multi-resolution raster map based on the resolution, where the iterative order includes an iterative search from low resolution to high resolution;
  • S204 Perform an iterative search on the first multi-resolution grid map based on the first iterative search order, and determine the first position of the robot in the grid map;
  • S205 Determine that the first position is the position of the robot relative to the origin and output.
  • step S201 is similar to the foregoing step S101, which is not limited in the embodiment of the present disclosure.
  • step S202 is similar to the foregoing step S102, which is not limited in the embodiment of the present disclosure.
  • the first multi-resolution raster map may include the first lowest resolution raster map, the first intermediate resolution raster map, and the first highest resolution raster map. Due to the difference in resolution, it can be determined based on the resolution
  • the first iterative search order of the first multi-resolution raster map where the first iterative order includes an iterative search from low resolution to high resolution.
  • the first multi-resolution raster map may include the first lowest resolution raster map, the first intermediate resolution raster map, and the first highest resolution raster map, the first lowest resolution raster map
  • the rate raster map includes: a raster map with a resolution of 250*250
  • the first intermediate resolution raster map includes: a raster map with a resolution of 500*500
  • the first highest resolution raster map includes: resolution
  • the first iterative search order of the first multi-resolution raster map is determined based on the resolution, as shown in Table 1 below.
  • Raster maps of different resolutions 1 Raster map with a resolution of 250*250 2 Raster map with a resolution of 500*500 3 Raster map with a resolution of 1000*1000
  • the first multi-resolution raster map is searched from coarse to fine, and the first position of the robot in the raster map can be determined, as shown below, so that the robot can be quickly completed reset:
  • the first lowest resolution raster map preset the first search box area (to avoid multiple similar scenes in the environment, if there are no similar scenes, you can perform a real global search) to search, confirm The optimal position of the robot in the first lowest resolution grid map, and the optimal position as the initial position for searching in the first search box area preset in the first intermediate resolution grid map next time;
  • the optimal position of the robot in the first intermediate resolution grid map as the initial position, search in the first search box area preset in the first highest resolution grid map to determine that the robot is at the first highest resolution
  • the first position in the rate grid map that is, the grid map corresponding to the above-mentioned current area.
  • each search can calculate the matching score between the current laser point cloud and the current resolution raster map, where the largest matching score in the first search box area is selected and the matching score score is greater than score_th (preset threshold).
  • score_th preset threshold
  • N represents the number of points contained in the laser point cloud
  • ⁇ represents the weight parameter, which is usually calculated according to the distance of the laser point cloud
  • the cell(x) function represents the rental table of x in the current resolution raster map
  • T(x) represents the transformation of point x to the specified coordinate system
  • i represents the coordinates of the i-th laser point. It should be noted that in the above expression, i and x are both two-dimensional coordinates.
  • the search area of the robot in the grid map can be determined, so as to search based on the first iteration.
  • an iterative search is performed in the search area in the first multi-resolution grid map to determine the first position of the robot in the grid map.
  • the grid map can be divided into four areas A, B, C, and D. As shown in Figure 3, based on the prior information, it can be determined that the robot is in the area A of the grid map, thus Based on the first iterative search order, first search in area A of the first lowest resolution raster map, then search in area A of the first intermediate resolution raster map, and finally search in the first highest resolution raster map. Search in area A of the grid map to determine the first position of the robot in the grid map. Such a pre-determined approximate range of the robot can further accelerate the search and further speed up the completion of the relocation of the robot.
  • the embodiments of the present disclosure may optimize the first position, that is, optimize the first position by using a preset first target optimization algorithm.
  • the first target position is obtained, and the first target position is determined to be the position of the robot relative to the origin and output.
  • the first target position includes X-axis coordinates, Y-axis coordinates, and angular offset.
  • the embodiment of the present disclosure completes the optimization of the first position on the first highest resolution raster map (ie, the raster map corresponding to the current area described above), where the first target optimization algorithm is as follows.
  • ⁇ * arg min ⁇ [1-cell(S i ( ⁇ ))] 2 ;
  • ⁇ represents the combination of rotation and translation, namely (p x , p y , ⁇ ).
  • bilinear interpolation or trilinear interpolation is used to calculate the probability value of the grid at any point when calculating the derivative.
  • the optimized result is directly used as the final relocation result and output, which can be used as the highest weighted particle in AMCL to perform filtering calculation during the next positioning calculation to realize the technology The loop of the chain.
  • FIG. 4 it is a schematic diagram of the implementation process of the robot positioning method provided by the embodiments of the present disclosure.
  • the method may include the following steps:
  • S403 Perform an iterative search on the second multi-resolution grid map based on the initial position, and determine the second position of the robot in the grid map;
  • S404 Determine that the second position is the position of the robot relative to the origin and output.
  • subsequent positioning processing can be performed on the robot, that is, the initial position output by the AMCL method can be obtained, and the result output by the AMCL method can be corrected and optimized, which can improve the positioning accuracy;
  • subsequent positioning processing can also be performed on the robot, that is, the initial position output by the AMCL method can be obtained, and the results output by the AMCL method can be corrected and optimized, which can improve the positioning accuracy.
  • the raster map may be down-sampled based on a preset second depth rule to generate a second multi-resolution raster map.
  • the second multi-resolution raster map may include the second lowest resolution raster map, the second intermediate resolution raster map, and the second highest resolution raster map.
  • the second highest resolution raster map that is The grid map corresponding to the above current area.
  • the second intermediate-resolution raster map includes at least one second intermediate-resolution raster map
  • a second multi-resolution raster map with a depth of D2 can be composed of raster maps of different resolutions. , For D2, it is not greater than D1 in the above relocation process.
  • the second multi-resolution raster map may include the second lowest resolution raster map, the second intermediate resolution raster map, and the second highest resolution raster map. Due to the difference in resolution, it can be determined based on the resolution
  • the second multi-resolution raster map may include the second lowest resolution raster map, the second intermediate resolution raster map, and the second highest resolution raster map, the second lowest resolution raster map
  • the rate raster map includes: a raster map with a resolution of 250*250
  • the second intermediate resolution raster map includes: a raster map with a resolution of 500*500
  • the second highest resolution raster map includes: resolution
  • the second iterative search order of the second multi-resolution raster map is determined based on the resolution, as shown in Table 2 below.
  • Raster maps of different resolutions 1 Raster map with a resolution of 250*250 2 Raster map with a resolution of 500*500 3 Raster map with a resolution of 1000*1000
  • the search area of the robot in the grid map can be determined based on the initial position, so that based on the second iterative search order, iterative search is performed on the search area in the second multi-resolution grid map .
  • the specific processing flow can refer to the above step S204, the embodiment of the present disclosure will not be repeated here.
  • the search area of the robot in the grid map can be roughly determined.
  • the difference between the positioning process in the embodiment of the present disclosure and the above-mentioned relocation process is reflected in the search box
  • the size is different, and the depth of the multi-resolution raster map is different.
  • the embodiment of the present disclosure may optimize the second position, that is, optimize the second position by using the preset second objective optimization function to obtain the first position.
  • Two target positions determining that the second target position is the position of the robot relative to the origin and outputting it.
  • the second position and the second target position both include X-axis coordinates, Y-axis coordinates, and angular offset.
  • the embodiment of the present disclosure completes the optimization of the second location on the second highest resolution raster map (ie, the raster map corresponding to the current area described above), where the second target optimization algorithm is as follows.
  • ⁇ * arg min ⁇ [ ⁇ (1-cell(S i ( ⁇ )))+ ⁇ ( ⁇ * - ⁇ )] 2 ;
  • ⁇ and ⁇ are the weight parameters of the two residuals, and other parameters can refer to the above-mentioned first objective optimization algorithm.
  • the optimized result is directly used as the final positioning result and output, which can be inserted into the particle swarm as the particle with the highest weight in the AMCL during the next positioning calculation. Calculate to realize the loop of the technology chain.
  • the embodiment of the present disclosure also provides a robot relocation device.
  • the device may include: a map acquisition module 510, a map down-sampling module 520, a position determination module 530, and a position output module 540.
  • the map obtaining module 510 is configured to obtain a grid map corresponding to the current area when it is determined that the robot is not located at the origin;
  • the map down-sampling module 520 is configured to down-sample the raster map based on a preset first depth rule to generate a first multi-resolution raster map;
  • a position determining module 530 configured to perform an iterative search on the first multi-resolution grid map, and determine the first position of the robot in the grid map;
  • the position output module 540 is configured to determine and output the first position as the position of the robot relative to the origin.
  • the embodiment of the present disclosure also provides an electronic device, as shown in FIG. 6, including a processor 61, a communication interface 62, a memory 63, and a communication bus 64.
  • the processor 61, the communication interface 62, and the memory 63 complete each other through the communication bus 64.
  • the memory 63 is configured to store computer programs
  • the robot When it is determined that the robot is not located at the origin, obtain the grid map corresponding to the current area; down-sample the grid map based on the preset first depth rule to generate a first multi-resolution grid map; An iterative search is performed on a multi-resolution grid map to determine the first position of the robot in the grid map; and the first position is determined to be the position of the robot relative to the origin and output.
  • the communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the communication bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used to indicate in the figure, but it does not mean that there is only one bus or one type of bus.
  • the communication interface is used for communication between the above-mentioned electronic device and other devices.
  • the memory may include random access memory (Random Access Memory, RAM for short), and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
  • non-volatile memory such as at least one disk memory.
  • the memory may also be at least one storage device located far away from the foregoing processor.
  • the aforementioned processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP), etc.; it may also be a digital signal processor (Digital Signal Processing, DSP for short) , Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • CPU Central Processing Unit
  • NP Network Processor
  • DSP Digital Signal Processing
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • the present disclosure also provides a storage medium in which instructions are stored, which when run on a computer, cause the computer to execute the robot relocation method described in the present disclosure.
  • the present disclosure also provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the robot relocation method described in the present disclosure.
  • the computer may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software it can be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instructions can be stored in a storage medium, or transmitted from one storage medium to another storage medium.
  • the computer instructions can be transmitted from a website, computer, server, or data center through a wired (such as coaxial cable, optical fiber) , Digital Subscriber Line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) to transmit to another website, computer, server or data center.
  • the storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center integrated with one or more available media.
  • the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)).

Abstract

L'invention concerne un procédé et un appareil de repositionnement de robot, un dispositif électronique et un support d'enregistrement. Le procédé consiste : lors de la détermination qu'un robot n'est pas situé au niveau d'une origine, à obtenir une carte quadrillée correspondant à la région en cours (S101) ; à réaliser un sous-échantillonnage sur la carte quadrillée en fonction d'une première règle de profondeur prédéfinie afin de générer une première carte quadrillée multi-résolution (S102) ; à effectuer une recherche itérative sur la première carte quadrillée multi-résolution afin de déterminer une première position du robot dans la carte quadrillée (S103) ; et à déterminer la première position en tant que position du robot par rapport à l'origine et à émettre en sortie la première position (S104). Le procédé peut rapidement effectuer un repositionnement et éviter l'apparition d'erreurs de repositionnement en présence de scénarios répétés.
PCT/CN2021/100284 2020-06-18 2021-06-16 Procédé et appareil de repositionnement de robot, dispositif électronique et support d'enregistrement. WO2021254369A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010561916.X 2020-06-18
CN202010561916.XA CN111765884B (zh) 2020-06-18 2020-06-18 机器人重定位方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2021254369A1 true WO2021254369A1 (fr) 2021-12-23

Family

ID=72721036

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/100284 WO2021254369A1 (fr) 2020-06-18 2021-06-16 Procédé et appareil de repositionnement de robot, dispositif électronique et support d'enregistrement.

Country Status (2)

Country Link
CN (1) CN111765884B (fr)
WO (1) WO2021254369A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116817903A (zh) * 2023-08-24 2023-09-29 湖南大学 一种基于先验视觉引导的智能机器人全局定位方法及系统
CN117739993A (zh) * 2024-02-19 2024-03-22 福勤智能科技（昆山）有限公司 一种机器人定位方法、装置、机器人及存储介质

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111765884B (zh) * 2020-06-18 2023-06-23 京东科技信息技术有限公司 机器人重定位方法、装置、电子设备及存储介质
CN114443264B (zh) * 2020-11-05 2023-06-09 珠海一微半导体股份有限公司 一种基于硬件加速的激光重定位系统及芯片
CN112904367B (zh) * 2021-03-19 2023-03-14 北京小狗吸尘器集团股份有限公司 应用于扫地机重定位时的位置打分方法、装置和电子设备
CN113129379A (zh) * 2021-06-17 2021-07-16 同方威视技术股份有限公司 自动移动设备的全局重定位方法以及装置
CN113551677A (zh) * 2021-08-16 2021-10-26 河南牧原智能科技有限公司 对机器人进行重定位的方法和相关产品
CN114485662B (zh) * 2021-12-28 2024-03-08 深圳优地科技有限公司 机器人重定位方法、装置、机器人及存储介质
CN117031481A (zh) * 2023-08-14 2023-11-10 北京数字绿土科技股份有限公司 一种基于投影3d激光点云的移动机器人重定位方法及系统

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8594860B2 (en) * 2010-11-01 2013-11-26 Samsung Electronics Co., Ltd. Apparatus and method with mobile relocation
CN107831765A (zh) * 2017-10-23 2018-03-23 广州视源电子科技股份有限公司 定位方法、装置、设备及存储介质
CN107991683A (zh) * 2017-11-08 2018-05-04 华中科技大学 一种基于激光雷达的机器人自主定位方法
CN109978925A (zh) * 2017-12-27 2019-07-05 深圳市优必选科技有限公司 一种机器人位姿的识别方法及其机器人
CN110515382A (zh) * 2019-08-28 2019-11-29 锐捷网络股份有限公司 一种智能设备及其定位方法
CN111765884A (zh) * 2020-06-18 2020-10-13 北京海益同展信息科技有限公司 机器人重定位方法、装置、电子设备及存储介质
CN112179330A (zh) * 2020-09-14 2021-01-05 浙江大华技术股份有限公司 移动设备的位姿确定方法及装置
CN112362059A (zh) * 2019-10-23 2021-02-12 北京京东乾石科技有限公司 移动载体的定位方法、装置、计算机设备和介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6559535B2 (ja) * 2015-10-22 2019-08-14 株式会社東芝 障害物マップ生成装置、その方法、及び、そのプログラム
CN106940704B (zh) * 2016-11-25 2019-12-20 北京儒博科技有限公司 一种基于栅格地图的定位方法及装置
CN108319655B (zh) * 2017-12-29 2021-05-07 百度在线网络技术（北京）有限公司 用于生成栅格地图的方法和装置
CN110007670B (zh) * 2019-02-14 2021-11-23 四川阿泰因机器人智能装备有限公司 移动机器人定位建图方法
CN110132284B (zh) * 2019-05-30 2022-12-09 东北大学 一种基于深度信息的全局定位方法
CN110686676A (zh) * 2019-09-12 2020-01-14 深圳市银星智能科技股份有限公司 机器人重定位方法、装置及机器人

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8594860B2 (en) * 2010-11-01 2013-11-26 Samsung Electronics Co., Ltd. Apparatus and method with mobile relocation
CN107831765A (zh) * 2017-10-23 2018-03-23 广州视源电子科技股份有限公司 定位方法、装置、设备及存储介质
CN107991683A (zh) * 2017-11-08 2018-05-04 华中科技大学 一种基于激光雷达的机器人自主定位方法
CN109978925A (zh) * 2017-12-27 2019-07-05 深圳市优必选科技有限公司 一种机器人位姿的识别方法及其机器人
CN110515382A (zh) * 2019-08-28 2019-11-29 锐捷网络股份有限公司 一种智能设备及其定位方法
CN112362059A (zh) * 2019-10-23 2021-02-12 北京京东乾石科技有限公司 移动载体的定位方法、装置、计算机设备和介质
CN111765884A (zh) * 2020-06-18 2020-10-13 北京海益同展信息科技有限公司 机器人重定位方法、装置、电子设备及存储介质
CN112179330A (zh) * 2020-09-14 2021-01-05 浙江大华技术股份有限公司 移动设备的位姿确定方法及装置

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116817903A (zh) * 2023-08-24 2023-09-29 湖南大学 一种基于先验视觉引导的智能机器人全局定位方法及系统
CN116817903B (zh) * 2023-08-24 2023-11-21 湖南大学 一种基于先验视觉引导的智能机器人全局定位方法及系统
CN117739993A (zh) * 2024-02-19 2024-03-22 福勤智能科技（昆山）有限公司 一种机器人定位方法、装置、机器人及存储介质
CN117739993B (zh) * 2024-02-19 2024-04-30 福勤智能科技（昆山）有限公司 一种机器人定位方法、装置、机器人及存储介质

Also Published As

Publication number Publication date
CN111765884B (zh) 2023-06-23
CN111765884A (zh) 2020-10-13

Similar Documents

Publication Publication Date Title
WO2021254369A1 (fr) Procédé et appareil de repositionnement de robot, dispositif électronique et support d'enregistrement.
CN110927740B (zh) 一种移动机器人定位方法
CN110307838B (zh) 机器人重定位方法、装置、计算机可读存储介质及机器人
CN110561423B (zh) 位姿变换的方法、机器人及存储介质
KR102068419B1 (ko) 포인트 클라우드 데이터 수집 궤적을 조정하기 위한 방법, 장치 및 컴퓨터 판독 가능한 매체
CN111257909B (zh) 一种多2d激光雷达融合建图与定位方法及系统
JP2020532734A (ja) 位置特定を実施する際に使用するための方法およびシステム
JP2024509690A (ja) 三次元地図を構築する方法および装置
CN113251919A (zh) 一种基于坐标变换的圆柱体点云数据拟合方法及装置
CN112987724A (zh) 路径优化方法、装置、机器人及存储介质
JP2021121970A (ja) 障害物検出方法、装置、設備、記憶媒体、及びプログラム
CN116559928B (zh) 激光雷达的位姿信息确定方法、装置、设备及存储介质
CN108520543B (zh) 一种对相对精度地图进行优化的方法、设备及存储介质
CN111400830A (zh) 一种三维毛坯工件的加工校准方法及装置
CN111813984B (zh) 一种利用单应矩阵实现室内定位的方法、装置及电子设备
WO2022062355A1 (fr) Procédé et appareil de positionnement avec fusion
CN112085759A (zh) 一种基于大数据的直线拟合方法及装置
WO2023124233A1 (fr) Procédé et appareil de recherche de cercle, dispositif électronique et support de stockage
US9852542B1 (en) Methods and apparatus related to georeferenced pose of 3D models
CN110940994A (zh) 定位初始化方法及其系统
CN115453549A (zh) 一种基于二维激光雷达的环境直角点坐标角度的提取方法
CN113015117B (zh) 一种用户定位方法、装置、电子设备和存储介质
CN114998755A (zh) 在遥感图像中地标匹配的方法及装置
Wang et al. Graphics-assisted cutter orientation correction for collision-free five-axis machining
CN114430524A (zh) 一种超宽带基站的标定方法、装置及电子设备

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: 21826959

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: 21826959

Country of ref document: EP

Kind code of ref document: A1