WO2019183928A1 - 一种室内机器人定位的方法及机器人 - Google Patents

一种室内机器人定位的方法及机器人 Download PDF

Info

Publication number
WO2019183928A1
WO2019183928A1 PCT/CN2018/081363 CN2018081363W WO2019183928A1 WO 2019183928 A1 WO2019183928 A1 WO 2019183928A1 CN 2018081363 W CN2018081363 W CN 2018081363W WO 2019183928 A1 WO2019183928 A1 WO 2019183928A1
Authority
WO
WIPO (PCT)
Prior art keywords
pose
robot
coordinate system
preset
map
Prior art date
Application number
PCT/CN2018/081363
Other languages
English (en)
French (fr)
Inventor
周祖鸿
王加加
王可可
沈剑波
Original Assignee
深圳市神州云海智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市神州云海智能科技有限公司 filed Critical 深圳市神州云海智能科技有限公司
Priority to PCT/CN2018/081363 priority Critical patent/WO2019183928A1/zh
Publication of WO2019183928A1 publication Critical patent/WO2019183928A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00

Definitions

  • the invention belongs to the field of robot technology, and in particular relates to a method and a robot for positioning an indoor robot.
  • the prior art performs positioning assistance by artificial manual operation or by other positioning methods.
  • the operation is simple when the user initializes or relocates the positioning, but the positioning initialization operation needs to be manually performed before starting the positioning, and there is a certain error in the indoor positioning initialization or repositioning of the robot in this way, resulting in the robot not positioning. accurate.
  • the embodiment of the present invention provides a method and a robot for positioning an indoor robot, so as to solve the problem that the robot has a certain error in indoor positioning initialization or repositioning of the robot in the prior art, resulting in inaccurate positioning of the robot.
  • a first aspect of the embodiments of the present invention provides a method for positioning an indoor robot, including:
  • the second pose includes a pose of the two-dimensional code in a preset robot coordinate system or a preset of the robot Pose in the dimensional coordinate system;
  • a second aspect of the embodiments of the present invention provides a robot, including:
  • a first pose unit for acquiring a first pose of the two-dimensional code installed on the indoor surface in a preset map coordinate system
  • a second pose unit configured to determine a second pose according to the first pose and a preset first coordinate transformation strategy; the second pose includes the two-dimensional code in a preset robot coordinate system a pose or a pose of the robot in a preset two-dimensional code coordinate system;
  • the pose determining unit is configured to determine a pose of the robot in the map coordinate system according to the first pose, the second pose, and a preset second coordinate transformation strategy.
  • a third aspect of the embodiments of the present invention provides a robot, including: a processor, an input device, an output device, and a memory, wherein the processor, the input device, the output device, and the memory are connected to each other, wherein the memory is used for storing
  • a computer program supporting a device for performing the above method the computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of the first aspect above.
  • a fourth aspect of an embodiment of the present invention provides a computer readable storage medium storing a computer program, the computer program including program instructions, the program instructions causing the processing when executed by a processor The method of the first aspect described above is performed.
  • the beneficial effect of the embodiment of the present invention compared with the prior art is: obtaining a first pose in a preset map coordinate system by acquiring a two-dimensional code installed on the indoor surface; according to the first pose and the preset The first coordinate transformation strategy determines a second pose; the second pose includes a pose of the two-dimensional code in a preset robot coordinate system or a pose of the robot in a preset two-dimensional code coordinate system; The first pose, the second pose, and a preset second coordinate transformation strategy determine the pose of the robot in the map coordinate system.
  • the robot directly acquires the pose of the two-dimensional code installed on the indoor surface, and coordinates the pose to obtain the pose of the robot relative to the map coordinate system. With this pose, laser positioning initialization and weight can be performed without human intervention. The positioning speeds up the convergence of the laser positioning particles and improves the reliability and accuracy of the laser positioning of the indoor robot.
  • FIG. 1 is a flowchart of a method for positioning an indoor robot according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a method for positioning an indoor robot according to another embodiment of the present invention.
  • FIG. 3 is a schematic diagram of a robot according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a robot according to another embodiment of the present invention.
  • FIG. 5 is a schematic diagram of a robot according to still another embodiment of the present invention.
  • FIG. 1 is a flowchart of a method for positioning an indoor robot according to an embodiment of the present invention.
  • the execution body of the method for positioning the indoor robot in this embodiment is a robot.
  • the method for indoor robot positioning as shown in FIG. 1 may include the following steps:
  • S101 Acquire a first posture of the two-dimensional code installed on the indoor surface in a preset map coordinate system.
  • the laser positioning algorithm for positioning such as the Monte Carlo positioning algorithm based on the laser sensor
  • Perform robot positioning initialization When the robot is forced to move the robot, or if the current operating environment of the robot changes greatly compared to the environment when the initial mapping is made, for example, when the pedestrian suddenly becomes more and more, the robot will be disturbed, and the robot cannot perform autonomous positioning. Problem, at this time you need to reposition the robot to restore the normal positioning of the robot.
  • the common solution is manual manual operation or positioning assistance by other positioning methods. It is simple to manually initialize or relocate the positioning, but it needs to manually perform the positioning initialization operation before starting the positioning, and since it is not known when the robot needs to be relocated, it needs to be manually timed for observation, which is very inconvenient to use; There is a certain error when manually performing positioning initialization or relocation, which will increase the convergence time of the positioning particles, resulting in a longer positioning initialization or relocation time.
  • Another solution is to use other auxiliary equipment for positioning, such as using WIreless-FIdelity (WiFi) positioning for laser positioning assistance, and distributing particles around the robot by positioning it according to WiFi positioning.
  • WiFi WIreless-FIdelity
  • Particle convergence for positioning initialization or relocation When the amount of WiFi used in the environment satisfies the WiFi positioning requirement, the WiFi positioning error is about 1 meter. At this time, the particle convergence takes a certain time, causing the relocation speed to be too slow. When the amount of WiFi used is insufficient, the WiFi needs to be built artificially. The source improves the laser positioning assistance cost.
  • laser positioning in the robot room is performed by a two-dimensional code by mounting a two-dimensional code on the surface of the indoor wall.
  • the QR code can be installed on the wall around the room or on the ceiling of the room.
  • the number and pose of the two-dimensional code installation that is, the coordinates and orientation angle of the two-dimensional code in the Cartesian coordinate system, are determined according to the specific environment, user requirements, or configuration information of the robot. Since the two-dimensional code is installed on the indoor surface, only ordinary two-dimensional code paper is needed, so that the laser positioning assistance cost can be effectively reduced.
  • the robot acquires the posture of the two-dimensional code installed on the indoor surface through the sensor, and on the wall around the ordinary indoor, the two-dimensional code information is easily blocked by the obstacle when the sensor acquires the two-dimensional code information, thereby causing the two-dimensional code information.
  • the acquisition is inaccurate or incomplete. Therefore, the QR code is installed on the indoor ceiling, and the first posture of the two-dimensional code in the preset map coordinate system is obtained by a sensor disposed on the robot, such as a camera.
  • the preset map coordinate system is a coordinate system established by the robot according to the indoor information of the robot before acquiring the two-dimensional code information.
  • a map coordinate system information of indoor target points can be unified, and position information of some fixed reference targets can be determined by the map coordinate system.
  • the robot simultaneously performs the detection of the two-dimensional code when initially establishing the image of the external environment.
  • the pose in the map coordinate system calculates the pose of the two-dimensional code in the map coordinate system by the coordinate system conversion formula:
  • x 2 ', y 2 ' respectively represent the abscissa value and the ordinate value of the two-dimensional code in the map coordinate system
  • x' 0 , y' 0 respectively represent the abscissa value of the robot in the two-dimensional code coordinate system
  • the ordinate value, x 2 , y 2 respectively represent the abscissa value and the ordinate value of the robot in the map coordinate system
  • represents the angle between the x-axis of the map coordinate system and the x-axis of the two-dimensional code coordinate system.
  • S102 Determine a second pose according to the first pose and a preset first coordinate transformation strategy; the second pose includes a pose of the two-dimensional code in a preset robot coordinate system or the robot is in advance Set the pose in the two-dimensional code coordinate system.
  • the pose of the two-dimensional code in the preset robot coordinate system is calculated by the coordinate system conversion formula:
  • x 1 ', y 1 ' respectively represent the abscissa and ordinate values of the two-dimensional code in the robot coordinate system
  • x 0 and y 0 respectively represent the abscissa and ordinate values of the robot in the robot coordinate system
  • x 1 , y 1 respectively represent the abscissa value and the ordinate value of the robot in the map coordinate system
  • represents the angle between the x-axis of the map coordinate system and the x-axis of the robot coordinate system.
  • the pose of the robot in the preset two-dimensional code coordinate system is calculated by the coordinate system conversion formula:
  • x 2 ', y 2 ' respectively represent the abscissa and ordinate values of the robot in the two-dimensional code coordinate system
  • x 0 and y 0 respectively represent the abscissa value and the ordinate of the robot in the two-dimensional code coordinate system
  • the values, x 2 , y 2 represent the abscissa and ordinate values of the robot currently in the map coordinate system
  • represents the angle between the x-axis of the two-dimensional code coordinate system and the x-axis of the map coordinate system.
  • S103 Determine a pose of the robot in the map coordinate system according to the first pose, the second pose, and a preset second coordinate transformation strategy.
  • the conversion strategy determines the pose of the robot in the map coordinate system.
  • step S103 includes:
  • x 1 ', y 1 ' respectively represent the abscissa value and the ordinate value of the robot in the map coordinate system
  • x' 0 , y' 0 respectively represent the abscissa value of the two-dimensional code in the preset map coordinate system and The ordinate value, that is, the first pose
  • x 1 , y 1 respectively represent the abscissa value and the ordinate value of the two-dimensional code in the preset robot coordinate system, or the abscissa of the robot in the preset two-dimensional code coordinate system
  • represents the angle between the x-axis of the map coordinate system and the x-axis of the robot coordinate system.
  • the first pose in the preset map coordinate system is obtained by acquiring the two-dimensional code installed on the indoor surface; and the second pose is determined according to the first pose and the preset first coordinate conversion strategy;
  • the second pose includes a pose of the two-dimensional code in a preset robot coordinate system or a pose of the robot in a preset two-dimensional code coordinate system; according to the first pose, the second pose, and
  • the preset second coordinate transformation strategy determines the pose of the robot in the map coordinate system.
  • the robot directly acquires the pose of the two-dimensional code installed on the indoor surface, and coordinates the pose to obtain the pose of the robot relative to the map coordinate system.
  • laser positioning initialization and weight can be performed without human intervention. The positioning speeds up the convergence of the laser positioning particles and improves the reliability and accuracy of the laser positioning of the indoor robot.
  • FIG. 2 is a flowchart of a method for positioning an indoor robot according to another embodiment of the present invention.
  • the execution body of the method for positioning the indoor robot in this embodiment is a robot.
  • This embodiment differs from the previous embodiment in that S204 to S206 are further included after step S103 in the previous embodiment.
  • the method of indoor robot positioning as shown in FIG. 2 may include the following steps:
  • S201 Acquire a first posture of the two-dimensional code installed on the indoor surface in a preset map coordinate system.
  • S202 Determine a second pose according to the first pose and a preset first coordinate transformation strategy; the second pose includes a pose of the two-dimensional code in a preset robot coordinate system or the robot is in advance Set the pose in the two-dimensional code coordinate system.
  • S203 Determine a pose of the robot in the map coordinate system according to the first pose, the second pose, and a preset second coordinate transformation strategy.
  • FIG. 1 is a description of S101 to S103, and details are not described herein.
  • S204 Acquire a first distance between the robot and an obstacle by using a sensor disposed on the robot; the particle is a target point randomly selected within a preset range centered on the robot.
  • the first distance between the robot and the obstacle is acquired by a sensor disposed on the robot.
  • the pose initialization method of each particle is: randomly assigning values within a certain range according to the initial pose of the robot.
  • the limited range is the random distribution of the particles in a circle with a radius of 50cm in the center of the robot's current pose.
  • the horizontal and vertical values do not exceed the range of a circle with a radius of 50 cm in the center of the robot pose, and the angular range in the particle pose is 0 to 360 degrees.
  • the update of each particle pose is calculated according to the speed of the robot, wherein the speed of the robot includes the linear velocity and the angular velocity.
  • the distance between the robot and the obstacle is obtained by a sensor set on the robot.
  • the sensor can be a laser sensor.
  • the distance between each particle and the laser sensor can be directly obtained by the laser sensor.
  • the size of the first distance can be determined accurately and in real time for later calculation.
  • S205 Determine a confidence level of each of the particles according to the first distance and a pose of each of the particles in the preset map.
  • the distance between the indoor particle and the sensor is pre-acquired by the robot to use the distance data to establish a preset map.
  • the data is recorded.
  • the obstacle distance information measured by the laser sensor is map data, and a preset map is constructed by using the map data. .
  • step S205 specifically includes:
  • represents the variance of the difference between the first distance and the second distance
  • the preset map stores a distance between the pose and the sensor corresponding to the particle pose, and the pose of the particle is used to search for a pose of the particle corresponding to the sensor in the preset map.
  • Distance the second distance. Thereafter, the second distance is compared with the first distance, and the confidence of the particle is determined by comparing the similarity between the first distance and the second distance.
  • the robot measures the first distance of the obstacle at position C as d, and the posture C is the robot in the true pose, this bit The pose C robot cannot be directly obtained, and the laser positioning algorithm is to find the pose C.
  • the distance d 1 of the particle to the obstacle is calculated according to the pose of each particle in the map, and compared with the laser data d measured at the pose C, The similarity between d and d 1 , so that the confidence of particle A can be obtained, and particle B is similar.
  • the confidence calculation uses a normal distribution method.
  • the normal distribution is a bell curve. The closer to the center, the larger the value, the farther away from the center, the smaller the value.
  • the specific calculation formula is:
  • the first distance and the pose of each particle in the preset map are calculated by using the positive distribution to determine the confidence of each particle.
  • the accuracy and accuracy of the phase velocity between the distances is calculated.
  • S206 Perform relocation if the difference between the pose of the target particle with the highest confidence and the pose of the robot in the map coordinate system is greater than a preset threshold.
  • the particle with the highest confidence is identified as the target particle.
  • step S206 specifically includes:
  • the pose of the target particle is randomly assigned within a preset range, according to Determining the pose of the target particle to the pose of the robot in the map coordinate system;
  • the preset range is a circle whose center position in the map coordinate system is calculated by coordinate conversion, and a circle with a preset distance as a radius.
  • the pose of the target particle with the highest confidence is compared with the pose of the robot in the map coordinate system.
  • the preset threshold is used to determine the difference between the pose of the target particle and the pose of the robot in the map coordinate system. If the difference is less than or equal to the preset threshold, it indicates that the pose of the target particle and the pose of the robot in the map coordinate system are smaller, that is, the pose of the robot in the map coordinate system calculated by the coordinate conversion. More accurate, no relocation is required.
  • the difference is greater than the preset threshold, it indicates that the pose of the target particle and the pose of the robot in the map coordinate system are larger, that is, the accuracy of the pose of the robot in the map coordinate system calculated by the coordinate conversion. Lower, you need to relocate.
  • a confidence threshold can also be set to compare with the confidence of the target particle to determine if relocation is required. Exemplarily, if the confidence of the target particle is less than or equal to the confidence threshold, it is determined that relocation is required; if the confidence of the target particle is greater than the confidence threshold, no relocation is needed.
  • the pose of the robot in the map coordinate system calculated by the coordinate conversion is the center of the circle, and the preset radius is used to establish the preset range.
  • the pose of the target particle is randomly assigned, and the pose of the robot in the map coordinate system is initialized according to the pose of the target particle to realize the relocation of the pose of the robot in the map coordinate system.
  • the convergence speed of the laser positioning of the particles can be accelerated, and the speed of repositioning can be improved.
  • the first distance between the robot and the obstacle is acquired by a sensor disposed on the robot; the particle is a target point randomly selected within a preset range centered on the robot; according to the first distance And determining a confidence level of each of the particles in the preset map; if the position of the target particle with the highest confidence is different from the pose of the robot in the map coordinate system is greater than the pre-predetermined If the threshold is set, relocation is performed.
  • the accuracy of the confidence calculation is improved, and the confidence is determined according to the confidence.
  • FIG. 3 is a schematic diagram of a robot according to an embodiment of the present invention.
  • Each unit included in the robot 300 of the present embodiment is used to perform the steps in the embodiment corresponding to FIG. 1.
  • the robot 300 of the present embodiment includes a first pose unit 301, a second pose unit 302, and a pose determining unit 303.
  • a first pose unit 301 configured to acquire a first pose of the two-dimensional code installed on the indoor surface in a preset map coordinate system
  • a second pose unit 302 configured to determine a second pose according to the first pose and a preset first coordinate transformation strategy; the second pose includes the two-dimensional code in a preset robot coordinate system The pose or the pose of the robot in the preset two-dimensional code coordinate system;
  • the pose determining unit 303 is configured to determine a pose of the robot in the map coordinate system according to the first pose, the second pose, and a preset second coordinate transformation strategy.
  • the first pose in the preset map coordinate system is obtained by acquiring the two-dimensional code installed on the indoor surface; and the second pose is determined according to the first pose and the preset first coordinate conversion strategy;
  • the second pose includes a pose of the two-dimensional code in a preset robot coordinate system or a pose of the robot in a preset two-dimensional code coordinate system; according to the first pose, the second pose, and
  • the preset second coordinate transformation strategy determines the pose of the robot in the map coordinate system.
  • the robot directly acquires the pose of the two-dimensional code installed on the indoor surface, and coordinates the pose to obtain the pose of the robot relative to the map coordinate system.
  • laser positioning initialization and weight can be performed without human intervention. The positioning speeds up the convergence of the laser positioning particles and improves the reliability and accuracy of the laser positioning of the indoor robot.
  • FIG. 4 is a schematic diagram of a robot according to an embodiment of the present invention.
  • the units included in the robot 400 of the present embodiment are used to perform the steps in the embodiment corresponding to FIG. 2 .
  • the robot 400 of the present embodiment includes a first pose unit 401, a second pose unit 402, a pose determination unit 403, a distance acquisition unit 404, a confidence determination unit 405, and a positioning determination unit 406.
  • a first pose unit 401 configured to acquire a first pose of the two-dimensional code installed on the indoor surface in a preset map coordinate system
  • a second pose unit 402 configured to determine a second pose according to the first pose and a preset first coordinate transformation strategy; the second pose includes the two-dimensional code in a preset robot coordinate system The pose or the pose of the robot in the preset two-dimensional code coordinate system;
  • the pose determining unit 403 is configured to determine a pose of the robot in the map coordinate system according to the first pose, the second pose, and a preset second coordinate transformation strategy.
  • a distance obtaining unit 404 configured to acquire a first distance between the robot and the obstacle through a sensor disposed on the robot when the pose determining unit determines the pose of the robot in the map coordinate system; the particle a target point randomly selected within a robot-centric preset range;
  • a confidence determining unit 405 configured to determine a confidence level of each of the particles according to the first distance and a pose of each of the particles in the preset map;
  • the positioning determining unit 406 is configured to perform relocation if the difference between the pose of the target particle with the highest confidence and the pose of the robot in the map coordinate system is greater than a preset threshold.
  • the positioning determining unit includes:
  • a relocating unit configured to: if the difference between the pose of the target particle with the highest confidence and the pose of the robot in the map coordinate system is greater than a preset threshold, the pose of the target particle within a preset range Performing a random assignment to initialize the pose of the robot in the map coordinate system according to the pose of the target particle;
  • the preset range is a circle whose center position in the map coordinate system is calculated by coordinate conversion, and a circle with a preset distance as a radius.
  • the pose determining unit includes:
  • a pose calculation unit configured to convert a formula according to the first pose, the second pose, and a coordinate:
  • x 1 ', y 1 ' respectively represent the pose of the robot in the map coordinate system
  • x 0 , y 0 respectively represent the abscissa value and the ordinate value of the first pose
  • x 1 , y 1 The abscissa value and the ordinate value of the second pose are respectively indicated
  • represents an angle between the x-axis of the map coordinate system and the x-axis of the robot coordinate system.
  • the confidence determination unit includes:
  • a second distance unit configured to determine, according to the pose of the particle in the preset map, a second distance between the particle and the obstacle in the preset map
  • represents the variance of the difference between the first distance and the second distance
  • the first distance between the robot and the obstacle is acquired by a sensor disposed on the robot; the particle is a target point randomly selected within a preset range centered on the robot; according to the first distance And determining a confidence level of each of the particles in the preset map; if the position of the target particle with the highest confidence is different from the pose of the robot in the map coordinate system is greater than the pre-predetermined If the threshold is set, relocation is performed.
  • the accuracy of the confidence calculation is improved, and the confidence is determined according to the confidence.
  • FIG. 5 is a schematic diagram of a robot according to still another embodiment of the present invention.
  • the robot 500 in this embodiment as shown in FIG. 5 may include a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and operable on the processor 501.
  • the processor 501 when executing the computer program 503, implements the steps in the various method embodiments described above for indoor robot positioning.
  • Memory 502 is for storing a computer program, the program comprising program instructions.
  • the processor 501 is configured to execute program instructions stored by the memory 502.
  • the processor 501 is configured to invoke the program instruction to perform the following operations:
  • the processor 501 is configured to acquire a first pose of the two-dimensional code installed on the indoor surface in a preset map coordinate system
  • the processor 501 is further configured to determine a second pose according to the first pose and a preset first coordinate transformation strategy; the second pose includes a pose of the two-dimensional code in a preset robot coordinate system Or the pose of the robot in the preset two-dimensional code coordinate system;
  • the processor 501 is further configured to determine a pose of the robot in the map coordinate system according to the first pose, the second pose, and a preset second coordinate transformation strategy.
  • the processor 501 is specifically configured to acquire a first distance between the robot and an obstacle by using a sensor disposed on the robot; the particle is a target point randomly selected within a preset range centered on the robot;
  • the processor 501 is specifically configured to determine a confidence level of each of the particles according to the first distance and a pose of each of the particles in the preset map;
  • the processor 501 is specifically configured to perform relocation if the difference between the pose of the target particle with the highest confidence and the pose of the robot in the map coordinate system is greater than a preset threshold.
  • the processor 501 is specifically configured to: if the difference between the pose of the target particle with the highest confidence and the pose of the robot in the map coordinate system is greater than a preset threshold, the pose of the target particle within a preset range Performing a random assignment to initialize the pose of the robot in the map coordinate system according to the pose of the target particle;
  • the preset range is a circle whose center position in the map coordinate system is calculated by coordinate conversion, and a circle with a preset distance as a radius.
  • the processor 501 is specifically configured to convert a formula according to the first pose, the second pose, and a coordinate Calculating the pose of the robot in the map coordinate system;
  • x 1 ', y 1 ' respectively represent the pose of the robot in the map coordinate system
  • x 0 , y 0 respectively represent the abscissa value and the ordinate value of the first pose
  • x 1 , y 1 The abscissa value and the ordinate value of the second pose are respectively indicated
  • represents an angle between the x-axis of the map coordinate system and the x-axis of the robot coordinate system.
  • the processor 501 is specifically configured to determine, according to the pose of the particle in the preset map, a second distance between the particle and the obstacle in the preset map;
  • the processor 501 is specifically configured to Calculate the confidence of each particle
  • represents the variance of the difference between the first distance and the second distance
  • the first distance between the robot and the obstacle is acquired by a sensor disposed on the robot; the particle is a target point randomly selected within a preset range centered on the robot; according to the first distance And determining a confidence level of each of the particles in the preset map; if the position of the target particle with the highest confidence is different from the pose of the robot in the map coordinate system is greater than the pre-predetermined If the threshold is set, relocation is performed.
  • the accuracy of the confidence calculation is improved, and the confidence is determined according to the confidence.
  • the processor 501 may be a central processing unit (CPU), and the processor may also be another general-purpose processor, a digital signal processor (DSP). , Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the memory 502 can include read only memory and random access memory and provides instructions and data to the processor 501.
  • a portion of the memory 502 can also include a non-volatile random access memory.
  • the memory 502 can also store information of the device type.
  • the processor 501, the memory 502, and the computer program 503 described in the embodiments of the present invention may perform the implementation of the first embodiment and the second embodiment of the method for positioning an indoor robot provided by an embodiment of the present invention.
  • the implementation manner of the robot described in the embodiment of the present invention may also be implemented, and details are not described herein again.
  • a computer readable storage medium is stored, the computer readable storage medium storing a computer program comprising program instructions, the program instructions being implemented by a processor to:
  • the second pose includes a pose of the two-dimensional code in a preset robot coordinate system or a preset of the robot Pose in the dimensional coordinate system;
  • the particle is a target point randomly selected within a preset range centered on the robot;
  • the pose of the target particle is randomly assigned within a preset range, according to Determining the pose of the target particle to the pose of the robot in the map coordinate system;
  • the preset range is a circle whose center position in the map coordinate system is calculated by coordinate conversion, and a circle with a preset distance as a radius.
  • x 1 ', y 1 ' respectively represent the pose of the robot in the map coordinate system
  • x 0 , y 0 respectively represent the abscissa value and the ordinate value of the first pose
  • x 1 , y 1 The abscissa value and the ordinate value of the second pose are respectively indicated
  • represents an angle between the x-axis of the map coordinate system and the x-axis of the robot coordinate system.
  • represents the variance of the difference between the first distance and the second distance
  • the first distance between the robot and the obstacle is acquired by a sensor disposed on the robot; the particle is a target point randomly selected within a preset range centered on the robot; according to the first distance And determining a confidence level of each of the particles in the preset map; if the position of the target particle with the highest confidence is different from the pose of the robot in the map coordinate system is greater than the pre-predetermined If the threshold is set, relocation is performed.
  • the accuracy of the confidence calculation is improved, and the confidence is determined according to the confidence.
  • the computer readable storage medium may be an internal storage unit of the robot described in any of the foregoing embodiments, such as a hard disk or a memory of the robot.
  • the computer readable storage medium may also be an external storage device of the robot, such as a plug-in hard disk equipped on the robot, a smart memory card (SMC), and a Secure Digital (SD) card. , Flash Card, etc.
  • the computer readable storage medium may also include both an internal storage unit of the robot and an external storage device.
  • the computer readable storage medium is for storing the computer program and other programs and data required by the robot.
  • the computer readable storage medium can also be used to temporarily store data that has been output or is about to be output.
  • the disclosed robot and method can be implemented in other ways.
  • the robot embodiment described above is merely illustrative.
  • the division of the unit is only a logical function division, and the actual implementation may have another division manner, for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, or an electrical, mechanical or other form of connection.
  • the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention contributes in essence or to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

Landscapes

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

Abstract

适用于机器人技术领域,提供了一种室内机器人定位的方法及机器人,包括:通过获取安装在室内表面的二维码在地图坐标系中的第一位姿;根据第一位姿以及坐标转换策略确定第二位姿;根据第一位姿、第二位姿以及预设的坐标转换策略确定机器人在地图坐标系中的位姿。通过机器人直接获取安装在室内表面的二维码的位姿,并将该位姿进行坐标转换得到机器人相对地图坐标系位姿,利用该位姿即可无需人为干涉便可进行激光定位初始化和重定位,加快了激光定位粒子收敛的速度,提高了室内机器人激光定位的可靠性和精确性。

Description

一种室内机器人定位的方法及机器人 技术领域
本发明属于机器人技术领域,尤其涉及一种室内机器人定位的方法及机器人。
背景技术
目前,室内移动机器人在使用激光定位进行定位时,为了加快初始定位粒子的收敛,需要根据机器人在物理环境的位置对应在地图中选择一个位姿进行机器人定位初始化。当人为强制机器人移动,或者当机器人的实际运行环境与预设地图相比发生了很大变化时,比如在行人突然变多的情况下,此时就会发生无法实现机器人定位的情况,则需要对机器人进行重定位以恢复机器人正常定位和行进。
针对以上问题,现有技术通过人为的手动操作或者借助其他定位方式进行定位辅助。人为进行定位初始化或者重定位时操作简单,但每次开始定位前都需要人工进行定位初始化操作,并且,通过这种方式对机器人进行室内定位初始化或者重定位时会存在一定误差,导致机器人定位不准确。
技术问题
有鉴于此,本发明实施例提供了一种室内机器人定位的方法及机器人,以解决了现有技术中对机器人进行室内定位初始化或者重定位时会存在一定误差,导致机器人定位不准确的问题。
技术解决方案
本发明实施例的第一方面提供了一种室内机器人定位的方法,包括:
获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;
根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿;
根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。
本发明实施例的第二方面提供了一种机器人,包括:
第一位姿单元,用于获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;
第二位姿单元,用于根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标 系中的位姿;
位姿确定单元,用于根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。
本发明实施例的第三方面提供了一种机器人,包括:处理器、输入设备、输出设备和存储器,所述处理器、输入设备、输出设备和存储器相互连接,其中,所述存储器用于存储支持装置执行上述方法的计算机程序,所述计算机程序包括程序指令,所述处理器被配置用于调用所述程序指令,执行上述第一方面的方法。
本发明实施例的第四方面提供了一种计算机可读存储介质,所述计算机存储介质存储有计算机程序,所述计算机程序包括程序指令,所述程序指令当被处理器执行时使所述处理器执行上述第一方面的方法。
有益效果
本发明实施例与现有技术相比存在的有益效果是:通过获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿;根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。通过机器人直接获取安装在室内表面的二维码的位姿,并将该位姿进行坐标转换得到机器人相对地图坐标系位姿,利用该位姿即可无需人为干涉便可进行激光定位初始化和重定位,加快了激光定位粒子收敛的速度,提高了室内机器人激光定位的可靠性和精确性。
附图说明
为了更清楚地说明本发明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发明的一些实施例,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是本发明一实施例提供的室内机器人定位的方法的流程图;
图2是本发明另一实施例提供的室内机器人定位的方法的流程图;
图3是本发明一实施例提供的机器人的示意图;
图4是本发明另一实施例提供的机器人的示意图;
图5是本发明再一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,以便透彻理解本发明实施例。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发明。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发明的描述。
为了说明本发明所述的技术方案,下面通过具体实施例来进行说明。
实施例1
参见图1,图1是本发明一实施例提供的一种室内机器人定位的方法的流程图。本实施例中室内机器人定位的方法的执行主体为机器人。如图1所示的室内机器人定位的方法可以包括以下步骤:
S101:获取安装在室内表面的二维码在预设地图坐标系中的第一位姿。
目前,室内移动机器人在使用激光定位算法进行定位时,例如基于激光传感器的蒙特卡洛定位算法,为了加快初始定位粒子的收敛速度,需要根据机器人在物理环境的位置对应在地图中选择一个位姿进行机器人定位初始化。当人为强制移动机器人,或者若机器人当前运行环境比初始建图时的环境发生了很大的变化的情况下,例如在行人突然变多时,就会对机器人造成干扰,发生机器人不能进行自主定位的问题,此时则需要对机器人进行重定位以恢复机器人正常定位。
针对以上问题,常用的解决方法为人为的手动操作或者借助其他定位方式进行定位辅助。人为进行定位初始化或者重定位操作简单,但每次开始定位前都需要人工进行定位初始化操作,而且由于不知道机器人什么时候需要进行重定位,所以需要人工定时进行观察,使用非常不方便;同时,人为进行定位初始化或者重定位时会存在一定误差,这会增加定位粒子的收敛时间,导致定位初始化或者重定位时间变长。
另外一种解决方法则是借助其他辅助设备进行定位的方式,如利用无线保真(WIreless-FIdelity,WiFi)定位进行激光定位辅助,通过根据WiFi定位出来的机器人位姿在其周围分布粒子,利用粒子收敛来进行定位初始化或者重定位。当使用的环境WiFi数量满足WiFi定位需求时,WiFi定位误差在1米左右,此时粒子收敛则需要一定时间,造成重定位速度过慢;当使用的环境WiFi数量不足时,还需人为搭建WiFi源,提高了激光定位辅助成本。
因此本实施例通过在室内墙壁表面安装二维码,通过二维码进行机器人室内的激光定位。需要说明的是,二维码可以安装在室内四周的墙壁上,也可以安装在室内的天花板上。 二维码安装的数量和位姿,即二维码在直角坐标系中的坐标和朝向角,根据具体的环境、用户需求或者机器人的配置信息决定。由于在室内表面安装二维码时,只需要普通的二维码纸张,因此能有效的减少激光定位辅助成本。
优选的,由于机器人是通过传感器获取安装在室内表面的二维码的位姿,而在普通的室内四周墙壁上,通过传感器获取二维码信息时容易受到障碍物的遮挡,导致二维码信息获取不准确或者不全面,因此,将二维码安装在室内天花板上,通过设置于机器人身上的传感器,例如照相机,获取二维码在预设地图坐标系中的第一位姿。
预设地图坐标系为机器人在获取二维码信息之前,根据机器人当前所处的室内信息,所建立的坐标系。通过建立地图坐标系可以将室内目标点的信息统一起来,并能通过该地图坐标系确定某些固定参考目标的位置信息。
可选的,机器人在初始建立外界环境图像的时候,同时进行二维码的检测。根据检测到的二维码计算出二维码在预设的机器人坐标系中的位姿,或者机器人在预设的二维码坐标系中的位姿,利用计算出来的位姿,结合机器人当前在地图坐标系中的位姿,通过坐标系转换公式计算出二维码在地图坐标系中的位姿:
Figure PCTCN2018081363-appb-000001
其中,x 2',y 2'分别表示二维码在地图坐标系中的横坐标值和纵坐标值,x' 0,y' 0分别表示机器人在二维码坐标系中的横坐标值和纵坐标值,x 2,y 2分别表示机器人当前在地图坐标系中的横坐标值和纵坐标值;θ表示地图坐标系的x轴与二维码坐标系的x轴之间夹角。通过这种计算方式,可以准确的计算出二维码在地图坐标系中的横坐标值和纵坐标值,进而精确确定机器人在当前位置处所获取二维码的位姿。
S102:根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿。
在获取安装在室内表面的二维码在预设地图坐标系中的第一位姿之后,根据第一位姿和预设的坐标转换策略确定二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿。
具体的,通过坐标系转换公式计算出二维码在预设机器人坐标系中的位姿:
Figure PCTCN2018081363-appb-000002
其中,x 1',y 1'分别表示二维码在机器人坐标系中的横坐标值和纵坐标值,x 0,y 0分别表示机器人在机器人坐标系中的横坐标值和纵坐标值,x 1,y 1分别表示机器人当前在地图坐标系中的横坐标值和纵坐标值;θ表示地图坐标系的x轴与机器人坐标系的x轴之间夹角。
具体的,通过坐标系转换公式计算出机器人在预设二维码坐标系中的位姿:
Figure PCTCN2018081363-appb-000003
其中,x 2',y 2'分别表示机器人在二维码坐标系中的横坐标值和纵坐标值,x 0,y 0分别表示机器人在二维码坐标系中的横坐标值和纵坐标值,x 2,y 2分别表示机器人当前在地图坐标系中的横坐标值和纵坐标值;θ表示二维码坐标系的x轴与地图坐标系的x轴之间夹角。
S103:根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。
在计算出二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿,即第二位姿之后,根据第一位姿、第二位姿以及坐标转换策略确定机器人在地图坐标系中的位姿。
具体的,步骤S103包括:
根据所述第一位姿、所述第二位姿以及坐标转换公式:
Figure PCTCN2018081363-appb-000004
计算机器人在所述地图坐标系中的位姿。
其中,x 1',y 1'分别表示机器人在地图坐标系中的横坐标值和纵坐标值;x' 0,y' 0分别表示二维码在预设地图坐标系中的横坐标值和纵坐标值,即第一位姿;x 1,y 1分别表示二维码在预设机器人坐标系中的横坐标值和纵坐标值,或者机器人在预设二维码坐标系中的横坐标值和纵坐标值,即第二位姿;θ表示地图坐标系的x轴与机器人坐标系的x轴之间夹角。
上述方案,通过获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿;根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。 通过机器人直接获取安装在室内表面的二维码的位姿,并将该位姿进行坐标转换得到机器人相对地图坐标系位姿,利用该位姿即可无需人为干涉便可进行激光定位初始化和重定位,加快了激光定位粒子收敛的速度,提高了室内机器人激光定位的可靠性和精确性。
实施例2
参见图2,图2是本发明另一实施例提供的一种室内机器人定位的方法的流程图。本实施例中室内机器人定位的方法的执行主体为机器人。本实施与上一实施例的区别在于,在上一实施例中的步骤S103之后还包括S204~S206。如图2所示的室内机器人定位的方法可以包括以下步骤:
S201:获取安装在室内表面的二维码在预设地图坐标系中的第一位姿。
S202:根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿。
S203:根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。
其中,在本实施例中S201~S203详见图1中S101~S103的相关描述,在此不再赘述。
S204:通过设置于机器人上的传感器获取所述机器人与障碍物之间的第一距离;所述粒子为在以机器人为中心的预设范围内随机选择的目标点。
在确定机器人在地图坐标系中的位姿之后,通过设置于机器人上的传感器获取机器人与障碍物之间的第一距离。
需要说明的是,在激光定位算法中会维持一定数量的粒子,每个粒子的位姿初始化方法为:根据机器人初始位姿,在一定范围内进行随机赋值。示例性的,当机器人的位姿为(100m,100m,90度)时,限定范围为以机器人当前的位姿为圆心,半径为50cm的圆内进行粒子随机分布,则随机分布的粒子的位置的横坐标值和纵坐标值不会超过以机器人位姿为圆心,半径为50cm的圆的范围,粒子位姿中的角度随机范围则在0~360度。之后每个粒子位姿的更新则是根据机器人的运动速度来计算,其中,机器人的运动速度包括线速度和角速度。
通过设定于机器人上的传感器来获取机器人与障碍物之间的距离。其中,传感器可以为激光传感器,通过将激光传感器安装在机器人身上,便可以通过激光传感器直接获取到每个粒子与激光传感器之间的距离。通过激光传感器直接获取第一距离的方式,可以准确、实时地确定第一距离的大小,以备进行之后的计算。
S205:根据所述第一距离和预设地图中每个所述粒子的位姿确定每个所述粒子的置信 度。
在计算粒子的置信度之前,先通过机器人预先获取室内粒子与传感器之间的距离,以将这些距离数据用来建立预设地图。
示例性的,控制机器人在某个环境中移动,通过机器人上的激光传感器测量到新的障碍物距离时,就将这些数据记录下来,当机器人走遍这个环境中的每个地方之后,所有记录的激光传感器测量到的障碍物距离信息就是地图数据,通过这些地图数据构建出预设地图。.
进一步的,步骤S205具体包括:
根据所述预设地图中所述粒子的位姿确定所述预设地图中所述粒子与障碍物之间的第二距离;
根据
Figure PCTCN2018081363-appb-000005
计算每个粒子的置信度;
其中,m表示所述第一距离与所述第二距离之间的差值,σ表示所述第一距离与所述第二距离之间的差值的方差。
具体的,预设地图中存储有粒子位姿对应的该位姿与传感器之间的距离,通过该粒子的位姿,在预设地图中查找该粒子的位姿所对应的与传感器之间的距离,即第二距离。之后,将第二距离与第一距离进行对比,通过比较第一距离和第二距离之间的相似度,确定该粒子的置信度。
示例性的,假设激光定位算法维持了2个粒子(A和B),机器人在位姿C处测量到障碍物的第一距离为d,此时位姿C是机器人在真实位姿,这个位姿C机器人并不能直接获取到,而激光定位算法就是为了求出位姿C。通过机器人在构建预设地图时记录的激光数据,根据每个粒子在地图中的位姿,计算粒子到障碍物的距离d 1,并与在位姿C处测量到的激光数据d对比,比较d和d 1的相似度,这样就可以得到粒子A的置信度,粒子B同理。
具体的,置信度的计算采用了正态分布的方法。正态分布是一种钟形曲线,越接近中心,取值越大,越远离中心,取值越小。通过计算第一距离和第二距离之间的差值,当差值越小时,位于正态分布的位置越靠近中心,其置信度越大。具体的计算公式为:
Figure PCTCN2018081363-appb-000006
其中,m表示所述第一距离与所述第二距离之间的差值,σ表示所述第一距离与所述 第二距离之间的差值的方差;由于正太分布中的μ是x的均值,因为计算平均值的时候,中心点就是原点,所以正太分布中的μ等于0。
通过根据传感器测量到的距离和预先构建地图时的距离进行相似度的计算,利用正太分布的方式计算出第一距离和预设地图中每个粒子的位姿确定每个粒子的置信度,提高了距离之间相速度的计算精度和准确度。
S206:若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位。
在根据第一距离和预设地图中每个粒子的位姿确定每个粒子的置信度之后,识别置信度最高的粒子为目标粒子。
进一步的,步骤S206具体包括:
若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则在预设范围内对所述目标粒子的位姿进行随机赋值,根据所述目标粒子的位姿对机器人在所述地图坐标系中的位姿进行初始化;
所述预设范围为以通过坐标转换计算出的机器人在所述地图坐标系中的位姿为圆心,以预设距离为半径的圆。
在计算出置信度之后,将置信度最高的目标粒子的位姿与机器人在地图坐标系中的位姿进行比较。其中,预设阈值用于判断目标粒子的位姿与机器人在地图坐标系中的位姿的差值的大小。若该差值小于或者等于预设阈值,则说明目标粒子的位姿与机器人在地图坐标系中的位姿的出入较小,即通过坐标转换计算出来的机器人在地图坐标系中的位姿的比较准确,则不需要进行重定位。
若该差值大于预设阈值,则说明目标粒子的位姿与机器人在地图坐标系中的位姿的出入较大,即通过坐标转换计算出来的机器人在地图坐标系中的位姿的准确率较低,便需要进行重定位。
可选的,还可以通过设置置信度阈值,用于与目标粒子的置信度进行对比,以确定是否需要进行重定位。示例性的,若目标粒子的置信度小于或者等于该置信度阈值,则确定需要进行重定位;若目标粒子的置信度大于该置信度阈值,则就不需要进行重定位。
在对机器人在地图坐标系中的位姿进行重定位时,以通过坐标转换计算出的机器人在地图坐标系中的位姿为圆心,以预设距离为半径的圆,建立预设范围,在该预设范围之内,对目标粒子的位姿进行随机赋值,根据目标粒子的位姿对机器人在地图坐标系中的位姿进行初始化,实现对机器人在地图坐标系中的位姿的重定位。同时利用计算出的机器人在地 图坐标系中的位姿进行粒子的激光分布定位,能加快激光定位粒子过程中的收敛速度,提高了重定位的速度。
上述方案,通过设置于机器人上的传感器获取所述机器人与障碍物之间的第一距离;所述粒子为在以机器人为中心的预设范围内随机选择的目标点;根据所述第一距离和预设地图中每个所述粒子的位姿确定每个所述粒子的置信度;若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位。通过用正太分布的方式计算出预设地图中粒子与传感器之间的第二距离与机器人实时获取到的粒子与传感器之间第二距离的置信度,提高了置信度的计算精度,并根据置信度确定具有最优位姿的目标粒子,用于与通过坐标转换计算出来的机器人在地图坐标系中的位姿进行对比,以确定是否需要进行重定位,提高了重定位的精度,减小了机器人在室内定位过程中的误差。
实施例3
参见图3,图3是本发明一实施例提供的一种机器人的示意图。本实施例的机器人300包括的各单元用于执行图1对应的实施例中的各步骤,具体请参阅图1及图1对应的实施例中的相关描述,此处不赘述。本实施例的机器人300包括第一位姿单元301、第二位姿单元302以及位姿确定单元303。
第一位姿单元301,用于获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;
第二位姿单元302,用于根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿;
位姿确定单元303,用于根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。
上述方案,通过获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿;根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。通过机器人直接获取安装在室内表面的二维码的位姿,并将该位姿进行坐标转换得到机器人相对地图坐标系位姿,利用该位姿即可无需人为干涉便可进行激光定位初始化和重定位,加快了激光定位粒子收敛的速度,提高了室内机器人激光定位的可靠性和精确性。
实施例4
参见图4,图4是本发明实施例提供的一种机器人的示意图。本实施例的机器人400包括的各单元用于执行图2对应的实施例中的各步骤,具体请参阅图2及图2对应的实施例中的相关描述,此处不赘述。本实施例的机器人400包括第一位姿单元401、第二位姿单元402、位姿确定单元403、距离获取单元404、置信度确定单元405以及定位判断单元406。
第一位姿单元401,用于获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;
第二位姿单元402,用于根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿;
位姿确定单元403,用于根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。
距离获取单元404,用于在位姿确定单元确定机器人在所述地图坐标系中的位姿时,通过设置于机器人上的传感器获取所述机器人与障碍物之间的第一距离;所述粒子为在以机器人为中心的预设范围内随机选择的目标点;
置信度确定单元405,用于根据所述第一距离和预设地图中每个所述粒子的位姿确定每个所述粒子的置信度;
定位判断单元406,用于若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位。
可选的,所述定位判断单元包括:
重定位单元,用于若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则在预设范围内对所述目标粒子的位姿进行随机赋值,根据所述目标粒子的位姿对机器人在所述地图坐标系中的位姿进行初始化;
所述预设范围为以通过坐标转换计算出的机器人在所述地图坐标系中的位姿为圆心,以预设距离为半径的圆。
可选的,所述位姿确定单元包括:
位姿计算单元,用于根据所述第一位姿、所述第二位姿以及坐标转换公式:
Figure PCTCN2018081363-appb-000007
计算机器人在所述地图坐标系中的位姿;
其中,x 1',y 1'分别表示机器人在所述地图坐标系中的位姿;x 0,y 0分别表示所述第一位姿的横坐标值和纵坐标值;x 1,y 1分别表示所述第二位姿的横坐标值和纵坐标值;θ表示所述地图坐标系的x轴与机器人坐标系的x轴之间夹角。
可选的,所述置信度确定单元包括:
第二距离单元,用于根据所述预设地图中所述粒子的位姿确定所述预设地图中所述粒子与障碍物之间的第二距离;
置信度计算单元,用于根据
Figure PCTCN2018081363-appb-000008
计算每个粒子的置信度;
其中,m表示所述第一距离与所述第二距离之间的差值,σ表示所述第一距离与所述第二距离之间的差值的方差。
上述方案,通过设置于机器人上的传感器获取所述机器人与障碍物之间的第一距离;所述粒子为在以机器人为中心的预设范围内随机选择的目标点;根据所述第一距离和预设地图中每个所述粒子的位姿确定每个所述粒子的置信度;若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位。通过用正太分布的方式计算出预设地图中粒子与传感器之间的第二距离与机器人实时获取到的粒子与传感器之间第二距离的置信度,提高了置信度的计算精度,并根据置信度确定具有最优位姿的目标粒子,用于与通过坐标转换计算出来的机器人在地图坐标系中的位姿进行对比,以确定是否需要进行重定位,提高了重定位的精度,减小了机器人在室内定位过程中的误差。
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,而不应对本发明实施例的实施过程构成任何限定。
实施例5
参见图5,图5是本发明再一实施例提供的一种机器人的示意图。如图5所示的本实施例中的机器人500可以包括:处理器501、存储器502以及存储在存储器502中并可在处理器501上运行的计算机程序503。处理器501执行计算机程序503时实现上述各个用于室内机器人定位的方法实施例中的步骤。存储器502用于存储计算机程序,所述计算机程序包括程序指令。处理器501用于执行存储器502存储的程序指令。其中,处理器501 被配置用于调用所述程序指令执行以下操作:
处理器501用于获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;
处理器501还用于根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿;
处理器501还用于根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。
处理器501具体用于通过设置于机器人上的传感器获取所述机器人与障碍物之间的第一距离;所述粒子为在以机器人为中心的预设范围内随机选择的目标点;
处理器501具体用于根据所述第一距离和预设地图中每个所述粒子的位姿确定每个所述粒子的置信度;
处理器501具体用于若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位。
处理器501具体用于若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则在预设范围内对所述目标粒子的位姿进行随机赋值,根据所述目标粒子的位姿对机器人在所述地图坐标系中的位姿进行初始化;
所述预设范围为以通过坐标转换计算出的机器人在所述地图坐标系中的位姿为圆心,以预设距离为半径的圆。
处理器501具体用于根据所述第一位姿、所述第二位姿以及坐标转换公式
Figure PCTCN2018081363-appb-000009
计算机器人在所述地图坐标系中的位姿;
其中,x 1',y 1'分别表示机器人在所述地图坐标系中的位姿;x 0,y 0分别表示所述第一位姿的横坐标值和纵坐标值;x 1,y 1分别表示所述第二位姿的横坐标值和纵坐标值;θ表示所述地图坐标系的x轴与机器人坐标系的x轴之间夹角。
处理器501具体用于根据所述预设地图中所述粒子的位姿确定所述预设地图中所述粒子与障碍物之间的第二距离;
处理器501具体用于根据
Figure PCTCN2018081363-appb-000010
计算每个粒子的置信度;
其中,m表示所述第一距离与所述第二距离之间的差值,σ表示所述第一距离与所述第二距离之间的差值的方差。
上述方案,通过设置于机器人上的传感器获取所述机器人与障碍物之间的第一距离;所述粒子为在以机器人为中心的预设范围内随机选择的目标点;根据所述第一距离和预设地图中每个所述粒子的位姿确定每个所述粒子的置信度;若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位。通过用正太分布的方式计算出预设地图中粒子与传感器之间的第二距离与机器人实时获取到的粒子与传感器之间第二距离的置信度,提高了置信度的计算精度,并根据置信度确定具有最优位姿的目标粒子,用于与通过坐标转换计算出来的机器人在地图坐标系中的位姿进行对比,以确定是否需要进行重定位,提高了重定位的精度,减小了机器人在室内定位过程中的误差。
应当理解,在本发明实施例中,所称处理器501可以是中央处理单元(Central Processing Unit,CPU),该处理器还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现成可编程门阵列(Field-Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
该存储器502可以包括只读存储器和随机存取存储器,并向处理器501提供指令和数据。存储器502的一部分还可以包括非易失性随机存取存储器。例如,存储器502还可以存储设备类型的信息。
具体实现中,本发明实施例中所描述的处理器501、存储器502、计算机程序503可执行本发明实施例提供的室内机器人定位的方法的第一实施例和第二实施例中所描述的实现方式,也可执行本发明实施例所描述的机器人的实现方式,在此不再赘述。
在本发明的另一实施例中提供一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序包括程序指令,所述程序指令被处理器执行时实现:
获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;
根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿;
根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。
进一步的,所述计算机程序被处理器执行时还实现:
通过设置于机器人上的传感器获取所述机器人与障碍物之间的第一距离;所述粒子为在以机器人为中心的预设范围内随机选择的目标点;
根据所述第一距离和预设地图中每个所述粒子的位姿确定每个所述粒子的置信度;
若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位。
进一步的,所述计算机程序被处理器执行时还实现:
若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则在预设范围内对所述目标粒子的位姿进行随机赋值,根据所述目标粒子的位姿对机器人在所述地图坐标系中的位姿进行初始化;
所述预设范围为以通过坐标转换计算出的机器人在所述地图坐标系中的位姿为圆心,以预设距离为半径的圆。
进一步的,所述计算机程序被处理器执行时还实现:
根据所述第一位姿、所述第二位姿以及坐标转换公式
Figure PCTCN2018081363-appb-000011
计算机器人在所述地图坐标系中的位姿;
其中,x 1',y 1'分别表示机器人在所述地图坐标系中的位姿;x 0,y 0分别表示所述第一位姿的横坐标值和纵坐标值;x 1,y 1分别表示所述第二位姿的横坐标值和纵坐标值;θ表示所述地图坐标系的x轴与机器人坐标系的x轴之间夹角。
进一步的,所述计算机程序被处理器执行时还实现:
根据所述预设地图中所述粒子的位姿确定所述预设地图中所述粒子与障碍物之间的第二距离;
根据
Figure PCTCN2018081363-appb-000012
计算每个粒子的置信度;
其中,m表示所述第一距离与所述第二距离之间的差值,σ表示所述第一距离与所述第二距离之间的差值的方差。
上述方案,通过设置于机器人上的传感器获取所述机器人与障碍物之间的第一距离;所述粒子为在以机器人为中心的预设范围内随机选择的目标点;根据所述第一距离和预设地图中每个所述粒子的位姿确定每个所述粒子的置信度;若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位。通过用正太分布的方式计算出预设地图中粒子与传感器之间的第二距离与机器人实时获取到的粒子与传感器之间第二距离的置信度,提高了置信度的计算精度,并根据置信度确定具有最优位姿的目标粒子,用于与通过坐标转换计算出来的机器人在地图坐标系中的位姿进行对比,以确定是否需要进行重定位,提高了重定位的精度,减小了机器人在室内定位过程中的误差。
所述计算机可读存储介质可以是前述任一实施例所述的机器人的内部存储单元,例如机器人的硬盘或内存。所述计算机可读存储介质也可以是所述机器人的外部存储设备,例如所述机器人上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步地,所述计算机可读存储介质还可以既包括所述机器人的内部存储单元也包括外部存储设备。所述计算机可读存储介质用于存储所述计算机程序及所述机器人所需的其他程序和数据。所述计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的数据。
本领域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、计算机软件或者二者的结合来实现,为了清楚地说明硬件和软件的可互换性,在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。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发明的范围。
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,上述描述的机器人和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的机器人和方法,可以通过其它的方式实现。例如,以上所描述的机器人实施例仅仅是示意性的,例如,所述单元的划分,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。另外,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口、装置或单元的间接耦合或通信连接,也可以是电的,机械的或其它的形式连接。
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发明实施例方案的目的。
另外,在本发明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,也可以是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,本发明的技术方案本质上或者说对现有技术做出贡献的部分,或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,仅为本发明的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,可轻易想到各种等效的修改或替换,这些修改或替换都应涵盖在本发明的保护范围之内。因此,本发明的保护范围应以权利要求的保护范围为准。

Claims (10)

  1. 一种室内机器人定位的方法,其特征在于,包括:
    获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;
    根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿;
    根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。
  2. 如权利要求1所述的室内机器人定位的方法,其特征在于,所述根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿之后,还包括:
    通过设置于机器人上的传感器获取所述机器人与障碍物之间的第一距离;
    根据所述第一距离和预设地图中每个所述粒子的位姿确定每个所述粒子的置信度;所述粒子为在以机器人为中心的预设范围内随机选择的目标点;
    若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位。
  3. 如权利要求2所述的室内机器人定位的方法,其特征在于,所述若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位,包括:
    若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则在预设范围内对所述目标粒子的位姿进行随机赋值,根据所述目标粒子的位姿对机器人在所述地图坐标系中的位姿进行初始化;
    所述预设范围为以通过坐标转换计算出的机器人在所述地图坐标系中的位姿为圆心,以预设距离为半径的圆。
  4. 如权利要求1-3任一项所述的室内机器人定位的方法,其特征在于,所述根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿,包括:
    根据所述第一位姿、所述第二位姿以及坐标转换公式
    Figure PCTCN2018081363-appb-100001
    计算机器人在所述地图坐标系中的位姿;
    其中,x 1',y 1'分别表示机器人在所述地图坐标系中的位姿;x 0,y 0分别表示所述第一位姿的横坐标值和纵坐标值;x 1,y 1分别表示所述第二位姿的横坐标值和纵坐标值;θ表示所述地图坐标系的x轴与机器人坐标系的x轴之间夹角。
  5. 如权利要求2所述的室内机器人定位的方法,其特征在于,所述根据所述第一距离和预设地图中所述粒子的位姿确定每个所述粒子的置信度,包括:
    根据所述预设地图中所述粒子的位姿确定所述预设地图中所述粒子与障碍物之间的第二距离;
    根据
    Figure PCTCN2018081363-appb-100002
    计算每个粒子的置信度;
    其中,m表示所述第一距离与所述第二距离之间的差值,σ表示所述第一距离与所述第二距离之间的差值的方差。
  6. 一种机器人,其特征在于,包括:
    第一位姿单元,用于获取安装在室内表面的二维码在预设地图坐标系中的第一位姿;
    第二位姿单元,用于根据所述第一位姿以及预设的第一坐标转换策略确定第二位姿;所述第二位姿包括所述二维码在预设机器人坐标系中的位姿或者机器人在预设二维码坐标系中的位姿;
    位姿确定单元,用于根据所述第一位姿、所述第二位姿以及预设的第二坐标转换策略确定机器人在所述地图坐标系中的位姿。
  7. 如权利要求6所述的机器人,其特征在于,所述机器人还包括:
    距离获取单元,用于通过设置于机器人上的传感器获取所述机器人与障碍物之间的第一距离;
    置信度确定单元,用于根据所述第一距离和预设地图中每个所述粒子的位姿确定每个所述粒子的置信度;所述粒子为在以机器人为中心的预设范围内随机选择的目标点;
    定位判断单元,用于若置信度最高的目标粒子的位姿与机器人在所述地图坐标系中的位姿的差值大于预设阈值,则进行重定位。
  8. 如权利要求6或7所述的机器人,其特征在于,所述位姿确定单元包括:
    位姿计算单元,用于根据所述第一位姿、所述第二位姿以及坐标转换公式
    Figure PCTCN2018081363-appb-100003
    计算机器人在所述地图坐标系中的位姿;
    其中,x 1',y 1'分别表示机器人在所述地图坐标系中的位姿;x 0,y 0分别表示所述第一位 姿的横坐标值和纵坐标值;x 1,y 1分别表示所述第二位姿的横坐标值和纵坐标值;θ表示所述地图坐标系的x轴与机器人坐标系的x轴之间夹角。
  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5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5任一项所述方法的步骤。
PCT/CN2018/081363 2018-03-30 2018-03-30 一种室内机器人定位的方法及机器人 WO2019183928A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/081363 WO2019183928A1 (zh) 2018-03-30 2018-03-30 一种室内机器人定位的方法及机器人

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/081363 WO2019183928A1 (zh) 2018-03-30 2018-03-30 一种室内机器人定位的方法及机器人

Publications (1)

Publication Number Publication Date
WO2019183928A1 true WO2019183928A1 (zh) 2019-10-03

Family

ID=68059154

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/081363 WO2019183928A1 (zh) 2018-03-30 2018-03-30 一种室内机器人定位的方法及机器人

Country Status (1)

Country Link
WO (1) WO2019183928A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111637877A (zh) * 2020-05-29 2020-09-08 拉扎斯网络科技(上海)有限公司 机器人定位方法、装置、电子设备和非易失性存储介质
CN113124850A (zh) * 2019-12-30 2021-07-16 北京极智嘉科技股份有限公司 机器人、地图生成方法、电子设备及存储介质
CN113566827A (zh) * 2021-07-09 2021-10-29 中国能源建设集团安徽省电力设计院有限公司 一种基于信息融合的变电站巡检机器人室内定位方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102735235A (zh) * 2012-06-07 2012-10-17 无锡普智联科高新技术有限公司 基于二维码的室内移动机器人定位系统和方法
CN105953798A (zh) * 2016-04-19 2016-09-21 深圳市神州云海智能科技有限公司 移动机器人的位姿确定方法和设备
CN107689061A (zh) * 2017-07-11 2018-02-13 西北工业大学 用于室内移动机器人定位的规则图形码及定位方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102735235A (zh) * 2012-06-07 2012-10-17 无锡普智联科高新技术有限公司 基于二维码的室内移动机器人定位系统和方法
CN105953798A (zh) * 2016-04-19 2016-09-21 深圳市神州云海智能科技有限公司 移动机器人的位姿确定方法和设备
CN107689061A (zh) * 2017-07-11 2018-02-13 西北工业大学 用于室内移动机器人定位的规则图形码及定位方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113124850A (zh) * 2019-12-30 2021-07-16 北京极智嘉科技股份有限公司 机器人、地图生成方法、电子设备及存储介质
CN113124850B (zh) * 2019-12-30 2023-07-28 北京极智嘉科技股份有限公司 机器人、地图生成方法、电子设备及存储介质
CN111637877A (zh) * 2020-05-29 2020-09-08 拉扎斯网络科技(上海)有限公司 机器人定位方法、装置、电子设备和非易失性存储介质
CN113566827A (zh) * 2021-07-09 2021-10-29 中国能源建设集团安徽省电力设计院有限公司 一种基于信息融合的变电站巡检机器人室内定位方法

Similar Documents

Publication Publication Date Title
CN110319834B (zh) 一种室内机器人定位的方法及机器人
TWI662388B (zh) 機器人之避障控制系統及方法
CN109275093B (zh) 基于uwb定位与激光地图匹配的定位方法和移动终端
JP7278263B2 (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
JP6349418B2 (ja) 高精度単眼移動によるオブジェクト位置特定
US11788845B2 (en) Systems and methods for robust self-relocalization in a visual map
CN108638062B (zh) 机器人定位方法、装置、定位设备及存储介质
WO2019183928A1 (zh) 一种室内机器人定位的方法及机器人
WO2019062649A1 (zh) 一种自适应区域划分的方法及系统
JP2015127664A (ja) キャリブレーション装置、キャリブレーション方法およびキャリブレーションプログラム
JP2024509690A (ja) 三次元地図を構築する方法および装置
CN108332752B (zh) 机器人室内定位的方法及装置
WO2019136613A1 (zh) 机器人室内定位的方法及装置
US10902610B2 (en) Moving object controller, landmark, and moving object control method
JP6746050B2 (ja) キャリブレーション装置、キャリブレーション方法およびキャリブレーションプログラム
US20220230350A1 (en) Position recognition method and system based on visual information processing
JP6673504B2 (ja) 情報処理装置、データベース生成装置、方法、プログラム、及び記憶媒体
JP2018173882A (ja) 情報処理装置、方法、及びプログラム
CN111426316B (zh) 机器人定位方法、装置、机器人及可读存储介质
CN111474560B (zh) 一种障碍物定位方法、装置及设备
CN109489658B (zh) 一种运动目标定位方法、装置及终端设备
US10012729B2 (en) Tracking subjects using ranging sensors
CN109541541B (zh) 一种室内三角定位精度修正方法及装置
CN110853098A (zh) 机器人定位方法、装置、设备及存储介质
Cupec et al. Global localization based on 3d planar surface segments

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: 18911943

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 18911943

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 04/02/2021)