WO2022257550A1 - 自主移动叉车的对接方法及自主移动叉车 - Google Patents

自主移动叉车的对接方法及自主移动叉车 Download PDF

Info

Publication number
WO2022257550A1
WO2022257550A1 PCT/CN2022/082727 CN2022082727W WO2022257550A1 WO 2022257550 A1 WO2022257550 A1 WO 2022257550A1 CN 2022082727 W CN2022082727 W CN 2022082727W WO 2022257550 A1 WO2022257550 A1 WO 2022257550A1
Authority
WO
WIPO (PCT)
Prior art keywords
target object
autonomous mobile
fork
image
docking
Prior art date
Application number
PCT/CN2022/082727
Other languages
English (en)
French (fr)
Inventor
成鹏
齐欧
张硕
Original Assignee
灵动科技（北京）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 灵动科技（北京）有限公司 filed Critical 灵动科技（北京）有限公司
Publication of WO2022257550A1 publication Critical patent/WO2022257550A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
    • B66F9/00—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes
    • B66F9/06—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes movable, with their loads, on wheels or the like, e.g. fork-lift trucks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
    • B66F9/00—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes
    • B66F9/06—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes movable, with their loads, on wheels or the like, e.g. fork-lift trucks
    • B66F9/075—Constructional features or details
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
    • B66F9/00—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes
    • B66F9/06—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes movable, with their loads, on wheels or the like, e.g. fork-lift trucks
    • B66F9/075—Constructional features or details
    • B66F9/0755—Position control; Position detectors
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B66—HOISTING; LIFTING; HAULING
    • B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
    • B66F9/00—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes
    • B66F9/06—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes movable, with their loads, on wheels or the like, e.g. fork-lift trucks
    • B66F9/075—Constructional features or details
    • B66F9/20—Means for actuating or controlling masts, platforms, or forks
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
    • G01S13/06—Systems determining position data of a target
    • G01S13/08—Systems for measuring distance only
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • 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
    • G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
    • G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
    • G01S15/06—Systems determining the position data of a target
    • G01S15/08—Systems for measuring distance only
    • 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
    • G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
    • G01S15/88—Sonar systems specially adapted for specific applications
    • G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
    • G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • 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
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G01S17/08—Systems determining position data of a target for measuring distance only
    • 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
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles

Definitions

  • the present application relates to the field of computer technology, and in particular to a docking method of an autonomous mobile forklift and the autonomous mobile forklift.
  • Automated Guided Vehicle is widely used in the field of automatic handling due to its high degree of automation and high level of intelligence.
  • the autonomous mobile forklift as a type of AGV, has the characteristics of fork teeth. It is mainly used to move empty shelves or shelves with objects in the factory site. There is usually a certain height gap between the bottom of the shelf and the ground, so that the fork can enter and Lifting the shelf involves the docking of the fork and the shelf before the fork enters the bottom of the shelf.
  • the present application provides a docking method of an autonomous mobile forklift and an autonomous mobile forklift that solve the above problems or at least partially solve the above problems.
  • a docking method of an autonomous mobile forklift includes a car body and an image acquisition unit arranged on the car body; the car body includes a car body and a fork part arranged on one side of the car body.
  • the method includes:
  • the autonomous mobile forklift is controlled to move towards the target object with its adjusted posture, so that the fork tine part docks with the docking part at the bottom of the target object.
  • an autonomous mobile forklift in another embodiment of the present application, includes:
  • a vehicle body which includes a vehicle body and a fork portion disposed on one side of the vehicle body;
  • an image acquisition unit arranged on the vehicle body, for acquiring the first image of the target object
  • a controller electrically connected to the image acquisition unit, configured to acquire the first image through the image acquisition device; determine target information related to the pose of the target object according to the first image; According to the target information, adjust the pose of the autonomous mobile forklift so that the fork is aligned with the docking part at the bottom of the target object; after the pose adjustment of the autonomous mobile forklift is completed, control the autonomous mobile forklift moving toward the target object in its adjusted posture such that the prongs abut against the docking portion on the bottom of the target object.
  • an image acquisition unit is provided on the body of the autonomous mobile forklift, and after acquiring the first image of the target object collected by the image acquisition unit, the target object can be determined according to the first image.
  • Target information related to the pose of the target object and adjust the pose of the autonomous mobile forklift according to the target information, so that the fork tines are aligned with the docking portion at the bottom of the target object; after that, the After the posture adjustment of the autonomous mobile forklift is completed, the autonomous mobile forklift can be controlled to move towards the target object with its adjusted posture, so that the fork tines dock with the docking portion at the bottom of the target object.
  • the autonomous mobile forklift includes a vehicle body, an image acquisition unit, and a controller; wherein, the vehicle body includes a vehicle body and a fork, and the image acquisition unit is arranged on the vehicle body for for acquiring the first image data of the target object; the controller is connected with the image acquisition unit, and is used to acquire the first image through the image acquisition device; according to the first image, determine the target object Target information related to the pose of the target object; according to the target information, adjust the pose of the autonomous mobile forklift so that the fork tines are aligned with the docking part at the bottom of the target object; the pose of the autonomous mobile forklift After the adjustment is completed, the autonomous mobile forklift is controlled to move towards the target object with its adjusted posture, so that the fork tines are docked with the docking portion at the bottom of the target object.
  • the autonomous mobile forklift in this solution can achieve precise docking with the target object, and has a simple structure and low cost.
  • FIG. 1 is a schematic flow diagram of a docking method for an autonomous mobile forklift provided by an embodiment of the present application
  • Figure 2a is a schematic diagram of the process of docking an autonomous mobile forklift with a target object provided by an embodiment of the present application
  • Fig. 2b is a schematic diagram of the process of docking an autonomous mobile forklift with a target object according to another embodiment of the present application
  • Fig. 3a is a schematic diagram of the process of docking an autonomous mobile forklift with a target object according to yet another embodiment of the present application;
  • Fig. 3b is a schematic diagram of the process of docking the autonomous mobile forklift with the target object provided by another embodiment of the present application;
  • FIG. 4 is a schematic diagram of the principle of adjusting the pose of an autonomous mobile forklift provided by an embodiment of the present application
  • FIG. 5 is a schematic flowchart of a docking method for an autonomous mobile forklift provided in another embodiment of the present application
  • FIG. 6 is a schematic diagram of an autonomous mobile forklift moving to a preset docking position in the docking portion at the bottom of the target object provided by an embodiment of the present application;
  • Fig. 7 is a bottom view corresponding to the tines of the autonomous mobile forklift entering the bottom of the target object according to an embodiment of the present application.
  • the AGV needs to move to the designated position to dock with the shelf.
  • the AGV with a manipulator is to obtain objects from the shelf; or, the submerged AGV is to dive into the bottom of the shelf and lift the shelf for handling;
  • the AGV of the structure is to haul the shelf through the connecting structure with the shelf; or, the AGV with the fork arm structure (that is, the autonomous mobile forklift) is to insert the fork into the docking part of the bottom of the shelf and lift the shelf for handling, etc.
  • the docking portion at the bottom of the shelf refers to a certain height space formed between the bottom of the shelf and the plane (such as the ground) on which the shelf is placed.
  • the proposal of the present application provides a docking method of an autonomous mobile forklift and an autonomous mobile forklift.
  • Fig. 1 shows a schematic flowchart of a docking method for an autonomous mobile forklift provided by an embodiment of the present application, which can be applied to the autonomous mobile forklift 1 shown in Fig. 2a, Fig. 2b, Fig. 3a, Fig. 3b and Fig. 6 , and is implemented by the controller in the autonomous mobile forklift 1.
  • the controller can be a central processing unit (Central Processing Unit, CPU), a single-chip microcomputer, etc., which is not limited here.
  • the autonomous mobile forklift 1 may include a vehicle body and an image acquisition unit 20 arranged on the vehicle body.
  • the image acquisition unit can be used to collect image data, and the vehicle body can include a vehicle body 11 and a fork portion 12 disposed on one side of the vehicle body.
  • the fork portion 12 can be used to dock with a target object (such as a shelf) for carrying the object.
  • the autonomous mobile forklift can also include memory, traveling parts, etc.; the memory can be RAM (Random Access Memory), Flash (flash memory), etc., which can be used to store received data (such as image data, radar data) , data required for processing, data generated during processing, etc.
  • received data such as image data, radar data
  • the method may include the following steps
  • the target information adjust the pose of the autonomous mobile forklift, so that the fork tine is aligned with the docking part at the bottom of the target object;
  • the target object may be a shelf for carrying objects, such as the shelf 2 shown in Fig. 2a, Fig. 2b, Fig. 3a, Fig. 3b and Fig. 6 .
  • the shelf has a load-bearing plane 21 and support legs 22, and the support legs 22 support the load-bearing plane, so that a certain height gap is formed between the bottom of the load-bearing plane and the working plane (such as the ground), and this certain height gap can be called
  • the fork tines of the autonomous mobile forklift can enter the docking part to dock with the shelf, so that the fork tines can be used to lift the shelf for easy transportation.
  • the autonomous mobile forklift automatically moves toward the shelf waiting for docking on the working plane according to a predetermined route.
  • the fork tines of the autonomous mobile forklift may not be able to dock with the shelf in a standard manner, which may easily cause the fork tines of the autonomous mobile forklift to enter the bottom of the shelf and cannot be located in the normal position of the docking part at the bottom of the shelf. in the middle.
  • the controller when the autonomous mobile forklift 1 is moving towards the target object (such as the shelf 2) waiting for docking, the controller can control the location of the autonomous mobile forklift 1
  • the image acquisition unit 20 on the main body 11 of the forklift 1 takes images in the direction of the shelf 2, and recognizes the images taken by the image acquisition unit 20 to determine whether the taken images contain the target object, and determine whether the taken images
  • the captured image can be determined as the first image of the shelf 2 .
  • the above step 101 "obtaining the first image of the target object collected by the image acquisition unit" may specifically include:
  • the existing image recognition technology can be used to identify and analyze the image collected by the image acquisition unit, and when it is determined that the collected image contains the target object according to the recognition result, the collected image will be used as the image of the target object.
  • the first image is used to determine the target information related to the pose of the shelf 2 based on the first image, so as to control the docking of the self-propelled forklift and the target object according to the target information.
  • the docking of the self-propelled forklift please refer to the following related content.
  • the above-mentioned image acquisition unit 20 may be arranged on the first side or the top of the vehicle body 11 .
  • the first side may refer to the side connected to the fork part 12, the fork part 12 may be the double-fork arm structure shown in Figure 2a and Figure 2b, of course it may also be the side shown in Figure 3a and Figure 3b
  • the single-fork arm structure is not limited in this embodiment.
  • the directions around the vehicle body 11 can be divided into: front side, rear side, left side, right side
  • the sides of the vehicle body 11 may include; the front side, the rear side, the left side and the right side.
  • the first side may specifically refer to the front side of the vehicle body, that is, the fork portion and the image acquisition unit may be disposed on the front side of the vehicle body 11 .
  • the image acquisition unit may also be arranged at other positions of the vehicle body 11 , such as the top of the vehicle body 11 , which is not limited in this embodiment.
  • the image acquisition unit 20 can be fixed at a preset position on the first side or top of the vehicle body, and swing at a preset pitch angle and yaw angle. put. Specifically, in order to facilitate subsequent calculations, the image acquisition unit 20 can be fixedly arranged at the intersection of the first side surface of the vehicle body 11 and the second vertical plane passing through the central axis of the fork portion 12; or, the image acquisition unit 20 can be It is fixedly arranged at the intersection of the top of the vehicle main body 11 and the second vertical plane passing through the central axis of the fork portion 12 . For example, as shown in Fig.
  • the intersection line between the front side of the vehicle body 11 and the second vertical plane S passing through the central axis of the fork portion 12 is l 1
  • an image acquisition device is arranged at position A on the intersection line l 1 unit 20
  • the acquisition direction of the image acquisition unit 20 at the position A is the front side direction of the vehicle body 11 .
  • the installation height of the image acquisition unit 20 is also fixed.
  • the top of the car body 11 is provided with a rotating mechanism, one end of which is connected to the top of the car body, and the other end is provided with an image acquisition unit 20; Rotate (eg, clockwise or counterclockwise) to rotate the image acquisition unit 20 to the side where the fork tines are located.
  • the above-mentioned image acquisition unit 20 can be a camera capable of outputting image information and depth information, such as RGBD (depth camera), and of course other types of cameras, such as a fisheye camera, for collecting video or image data Ordinary cameras, etc., are not limited here.
  • RGBD depth camera
  • other types of cameras such as a fisheye camera, for collecting video or image data Ordinary cameras, etc., are not limited here.
  • the target information may be pose information of the target object, such as the position and posture of the target object; or it may also be the position of the target object and the orientation of the insertion end surface.
  • the insertion end face refers to the end face corresponding to the entry port of the passage provided by the butt joint at the bottom of the target object for the prongs to enter. A certain height plane is formed.
  • the docking portion at the bottom of the target object 2 refers to a certain height gap formed between the bottom of the target object 2 and the working plane (such as the ground), and the docking portion at the bottom of the target object 2 is provided with
  • the entry port of the channel for the prongs 12 to enter can be a certain height plane formed between the rear edge of the bottom of the target object 2 and the ground.
  • the insertion end face of the target object refers to the rear side of the target object 2.
  • the entry port of the passage can also be a certain height plane formed between other edges of the bottom of the target object and the ground, and the corresponding insertion end face can also refer to other sides of the target object 2, for example, the entry port can also be the target object
  • the plane at a certain height formed between the front edge of 2 and the ground, at this time, the insertion end surface refers to the front side of the target object 2, which is not specifically limited in this embodiment. It can be seen that the plane where the inlet port of the channel and the insertion end face of the corresponding target object are located is the same plane. It should be noted that the above-mentioned side division method of the target object is the same as the side division method of the main body of the autonomous mobile forklift, and details will not be repeated here.
  • image recognition technology may be used to identify and analyze the first image to determine target information related to the pose of the target object.
  • the image recognition technology can be a machine learning model, wavelet moment algorithm, etc., which is not specifically limited in this embodiment; when using a machine learning model to recognize and analyze the first image, it is necessary to pre-train relevant machines based on a large number of training samples
  • a learning model such as a neural network model, that is, when using a trained neural network model to identify and analyze the first image, the first image can be used as an input to the trained neural network model, and the neural network model is executed to pass through the neural network model.
  • the corresponding recognition result can be obtained by analyzing and calculating the first image; and then according to the recognition result, the target information related to the pose of the target object can be determined.
  • the autonomous mobile forklift can also include sensors; the sensors can be arranged on the vehicle body, specifically the sensors can be arranged on the Data information related to the target object.
  • the above-mentioned step 102 of "determining the target information related to the pose of the target object according to the first image" may specifically include:
  • the senor can be a ranging sensor, and the ranging sensor can be a radar, and the radar can specifically be a laser radar, a millimeter-wave radar, an ultrasonic radar, etc.; or, the ranging sensor can also be other types that can realize Sensors for distance measurement, such as ultrasonic sensors, infrared sensors, etc., are not limited in this embodiment.
  • the above-mentioned sensor can also be an image acquisition unit in addition to a distance measuring sensor. Cooperate to form a binocular camera.
  • the sensor When setting up the sensor on the fork part, the sensor can be arranged at the far end of the fork part away from the vehicle body (hereinafter referred to as the far end of the fork), and the far end of the fork can refer to the fork
  • the tooth end of the tooth that is, the end not connected with the main body of the car.
  • the detection direction of the sensor arranged at the far end of the fork can be the front side direction, and the sensor can be connected with the controller of the autonomous mobile forklift.
  • the controller passes the image acquisition unit 20. While acquiring the first image of the target object, the first detection data about the target object detected by the sensor on the far end of the tines will also be acquired.
  • the fork part 12 of the autonomous mobile forklift 1 is a double-fork arm structure, that is, the fork part 12 includes a fork 121 and a fork 122 .
  • a sensor for detecting the front direction may be provided at the distal end of each corresponding fork tine 121 and fork tine 122 .
  • a sensor 30 for detecting the front direction may be provided at the central position B of the distal end of the fork 121 and the central position C of the distal end of the fork 122, respectively.
  • the first detection data obtained by the controller is jointly detected by the radar 30 arranged at the far end of the fork 121 and the sensor 30 arranged at the far end of the fork 122 .
  • the fork part 12 of the autonomous mobile forklift 1 is a single fork arm structure, that is, only one fork is included, and the far end of the fork as shown in Fig. 2a and Fig. 2b can be
  • the way of setting the sensor is to set a sensor 30 at the center position D of the far end of the fork, and at this time the first detection data acquired by the controller is collected by the sensor 30 on the end of the fork.
  • a sensor may also be provided on the distal end of only one of the fork, which is not limited in this embodiment.
  • sensors are preferably provided at the far ends of the two fork tines.
  • the first detection data and the first image may be integrated to determine the target information related to the pose of the target object, so as to improve the accuracy of the target information.
  • the sensor located at the far end of the fork is a radar
  • the first detection data is radar data as an example
  • image recognition technology can be used to identify and analyze the first image, and the target object can be obtained according to the identification result.
  • the contour information of the target object determines the target information related to the pose of the target object.
  • the sensor located at the far end of the fork is an image acquisition unit, and the image acquisition unit is a camera.
  • the camera at the far end of the fork and the camera on the vehicle body can be combined into a binocular camera.
  • the average value can be calculated Target information related to the pose of the target object is determined.
  • step 103 based on the content in step 102, it can be known that the docking part at the bottom of the target object may be provided with a channel for the tines to enter.
  • the position information of the first vertical plane passing through the central axis of the channel can be further determined according to the first image, so that according to the target information and the position of the first vertical plane information to adjust the pose of an autonomous mobile forklift.
  • the docking part at the bottom of the target object can be provided with a channel for the fork to enter; correspondingly, step 103 "according to the target information, adjust the pose of the autonomous mobile forklift so that the fork A possible technical solution for aligning the butt joint at the bottom of the target object" is:
  • the target information and the position information about the first vertical plane adjust the pose of the autonomous mobile forklift, so that the second vertical plane passing through the central axis of the tines part is in line with the first vertical plane.
  • the vertical planes lie on the same plane.
  • the first image can be used to analyze and determine the position information of the central axis of the entry port of the channel provided by the docking part of the bottom of the target object for the fork to enter; and then according to the position of the central axis of the entry port information to determine the location information about the first vertical plane. That is, during specific implementation, the position information about the first vertical plane may include: the position of the intersection line between the first vertical plane and the plane where the inlet port of the channel is located.
  • the position information of the first vertical plane must also include: the position of the intersection line between the first vertical plane and the plane where the insertion end face of the target object is located .
  • the position information of the first vertical plane includes the position of the intersection line between the first vertical plane and the back side of the target object.
  • the first vertical plane and the target object can be A point on the intersecting line of the inserted end faces is taken as the position of the first vertical plane.
  • O1 is a point on the intersection line between the first vertical plane and the rear side of the target object 2 , then the coordinates of point O1 can be used as the position of the first vertical plane.
  • the determined target information related to the pose of the target object is set as the pose information of the target object, and the pose information includes the position and pose of the target object.
  • the pose information includes the position and pose of the target object.
  • the coordinates of point O1 are used as the position of the first vertical plane. Assuming that point A is on the intersection line between the front side of the main body of the autonomous mobile forklift 1 and the second vertical plane passing through the central axis of the tines, point A can be used as the position of the second vertical plane. Let the image acquisition unit be fixed at the position of point A, that is, point A can also be regarded as the origin of the camera coordinate system.
  • point A and point O 1 are at The projection coordinates on the horizontal coordinate plane (xoy plane shown in Figure 4) are respectively (x 2 , y 2 ), (x 1 , y 1 ), based on the projection coordinates of point A on the xoy plane (x 1 , y 1 ) and the projection coordinates (x 2 , y 2 ) of point O 1 on the xoy plane, the lateral deviation distance and deviation angle of point A relative to point O 1 can be determined. Specifically, referring to FIG.
  • , offset angle ⁇ arctan(x 1 -x 2 )/(y 1 -y 2 ).
  • the autonomous mobile forklift can be controlled to adjust its own posture, so that the adjusted posture of the autonomous mobile forklift is consistent with the posture of the target object.
  • the adjusted attitude of the autonomous mobile forklift 1 is the autonomous Move the attitude of the forklift 1'.
  • it can be further based on the lateral deviation distance and deviation angle of the second vertical plane calculated in the above example relative to the first vertical plane, to control the autonomous mobile forklift to adjust its own posture. Location.
  • the controller may control the autonomous mobile forklift to move in a direction that can shorten the lateral deviation distance and/or deviation angle, Until the lateral deviation distance and deviation angle of the second vertical plane relative to the first vertical plane are both zero.
  • the adjusted lateral deviation distance and deviation angle of the second vertical plane relative to the first vertical plane are both zero, it means that the second vertical plane is located on the same plane as the first vertical plane, and the location of the autonomous mobile forklift has been completed so far. posture adjustment.
  • the autonomous mobile forklift is subsequently controlled to move towards the target object with its adjusted posture, so that the fork tine part is docked with the docking part at the bottom of the target object, which can ensure the accuracy of the docking.
  • controlling the autonomous mobile forklift to move towards the target object with its adjusted attitude may specifically include:
  • the image acquisition unit installed on the autonomous mobile forklift body can be controlled to continue to take images in the direction of the target object, so as to A plurality of second images are collected and sent to the controller, so that the controller can determine whether the fork tines have moved to a preset docking position in the docking portion of the bottom of the target object according to the plurality of second images.
  • the controller receives the multiple second images sent by the image acquisition unit, it can identify and analyze the multiple second images, and when it is determined that the received second images do not contain the target object and the second
  • the resolution of the image is smaller than a preset threshold, it is determined that the tines of the fork move to a preset docking position in the docking portion of the bottom of the target object.
  • the prongs are not moved to the preset docking position in the docking portion on the bottom of the target object.
  • the aforementioned preset thresholds can be flexibly set according to actual conditions, and are not specifically limited here.
  • the posture of the autonomous mobile forklift is relatively different from the original adjustment Afterwards, the posture may change slightly, causing the tines to obstruct the direction of travel of the fork as it moves across the bottom of the target object.
  • the target object in this figure is a shelf 2 with a "Chuan" shape at the bottom, and the attitude of the autonomously moving forklift is relative to its adjusted The attitude tilts to the left.
  • the obstacle in the direction of travel of the fork tine 121 is the middle long leg l 1 at the bottom of the shelf 2. If the attitude of the autonomous mobile forklift is not modified at this time, the autonomous mobile forklift will be controlled In the process of continuing to move, it may cause the fork tine 121 to collide with the middle long leg 11 at the bottom of the shelf, thereby causing damage to the fork tine 121 or the shelf 2 .
  • the detection data of the butt joint at the bottom of the target object detected by the sensor provided on the fork tine can be used to determine whether there is an obstacle in the direction of travel of the fork tine, and When it is determined that there is an obstacle, the pose of the autonomous mobile forklift can be corrected further based on the detection data of the butt joint at the bottom of the target object detected by the sensor.
  • control the autonomous mobile forklift to move towards the target object with its adjusted posture, so that the fork tines and the Docking portion docking at the bottom of the target object may specifically include:
  • the second detection data detected by the radar on 122 determines that there is an obstacle in the direction of travel of the fork 122 (that is, the middle long leg l 1 at the bottom of the shelf 2 shown in the figure), it can be calculated according to the second detection data Analyze the offset angle ⁇ of the vertical plane l 2 passing through the central axis of the fork 122 relative to the middle long leg l 1 , adjust the posture of the autonomous mobile forklift based on the offset angle ⁇ until the offset angle ⁇ is 90 ° ,
  • the attitude of the autonomous mobile forklift 1 after adjustment is the attitude of the autonomous mobile forklift shown by the dotted line in FIG. 7 .
  • the second vertical plane passing through the central axis of the tines and the first vertical plane passing through the central axis of the butt joint at the bottom of the shelf 2 may appear (such as The middle long leg 11 shown in FIG. 7 can be regarded as the situation that the first vertical plane) is no longer on the same plane.
  • the detection data detected by the radar on the tooth end of the fork tine 121 can continue to be used to determine the vertical plane and the middle of the central axis of the fork tine 121.
  • the first distance d 1 between the long legs l 1 in the same way, the second distance d 2 (not shown) between the vertical plane of the central axis of the fork 122 and the middle long legs l 1 (not shown) can be obtained, and then the control The controller can correct the position of the autonomous mobile forklift according to the first distance d 1 and the second distance d 2 , so that the first distance d 1 is equal to the second distance d 2 .
  • the controller can judge whether the fork has moved to the docking part at the bottom of the shelf 2 according to the acquired detection data detected by the sensor. Preset docking position.
  • the fork tooth part moves to the preset docking position in the docking part of the bottom of the target object; on the contrary, if the sensor arranged on the tooth end of the fork part can still detect the data information related to the docking part of the bottom of the target object, it means that the fork tooth The portion has not moved to the preset docking position in the docking portion on the bottom of the target object.
  • the controller can control the autonomous mobile forklift to stop moving, and control the tines of the fork to lift to lift
  • the target object is easy to handle. How to control the fork tines to carry out jacking is the same as the prior art, and will not be described in detail here.
  • an image acquisition unit is provided on the body of the autonomous mobile forklift, and when the autonomous mobile forklift moves towards the target object (such as a shelf) waiting for docking, the first image of the target object collected by the image acquisition unit is acquired.
  • the target information related to the pose of the target object can be determined based on the first image; and according to the target information, the pose of the autonomous mobile forklift can be adjusted so that the fork tines are aligned with the The docking part at the bottom of the target object; and after the pose adjustment of the autonomous mobile forklift is completed, the autonomous mobile forklift can be controlled to move towards the target object with its adjusted posture, so that the fork tines are docked with the bottom of the target object Ministry docking. Because this solution can ensure that the fork of the autonomous mobile forklift is aligned with the docking part at the bottom of the target during the process of controlling the autonomous mobile forklift to move towards the target with its adjusted posture, this allows the fork to enter the target.
  • the docking part on the bottom of the object and can be located in the middle of the docking part when entering the docking part on the bottom of the target object. Therefore, this solution can enable the autonomous mobile forklift to achieve precise docking with the target object (such as a shelf), thereby helping to avoid the occurrence of deflection or dumping of the target object during the process of being transported due to the position deviation generated during the docking process.
  • the target object such as a shelf
  • FIG. 5 shows a schematic flowchart of a docking method for an autonomous mobile forklift provided by another embodiment of the present application.
  • the autonomous mobile forklift may specifically include a car body 11 and a radar 20 arranged on the car body.
  • the radar can be used to detect radar data related to the target object
  • the vehicle body can include a vehicle body 11 and a fork portion 12 disposed on one side of the vehicle body.
  • the tine part can be used to dock with a target object (such as a shelf) to carry the object.
  • a target object such as a shelf
  • the target information adjust the pose of the autonomous mobile forklift, so that the fork tine is aligned with the docking part at the bottom of the target object;
  • the radar may be laser radar, millimeter wave radar, ultrasonic radar, etc., which is not limited in this embodiment.
  • the radar can be arranged at the far end of the fork part far away from the vehicle body (hereinafter referred to as the fork distal end).
  • the fork distal end can refer to the tooth end of the fork, that is, the end not connected to the vehicle body.
  • the detection direction of the radar at the far end of the fork can be the front side of the vehicle body, and the radar can be connected with the controller of the autonomous mobile forklift.
  • the front side of the vehicle body is determined according to the traveling direction of the autonomous mobile forklift.
  • the specific setting of the radar and how to obtain the first radar data of the target object through the radar please refer to the corresponding parts in the above-mentioned embodiments, which will not be repeated here.
  • the docking part at the bottom of the target object is provided with a passage for the fork tines to enter; correspondingly, step 203 "according to the target information, adjust the pose of the autonomous mobile forklift so that the The tines are aligned with the docking portion at the bottom of the target object", which may specifically include:
  • the target information and the position information about the first vertical plane adjust the pose of the autonomous mobile forklift, so that the second vertical plane passing through the central axis of the fork part is in line with the first vertical plane.
  • the vertical planes lie on the same plane.
  • the "controlling the autonomous mobile forklift to move towards the target object with its adjusted attitude" in the above 204 may specifically include:
  • the second radar data determine whether the tine part moves to a preset docking position in the docking part on the bottom of the target object.
  • the radar 30 located at the tooth end of the fork 12 cannot collect radar data related to the target object, that is to say, when the autonomous mobile forklift moves towards the target object with its adjusted attitude, If it is determined that the radar 30 on the tooth end of the fork tine 12 cannot collect radar data related to the target object, it can be considered that the autonomous mobile forklift has moved to a preset docking position in the docking portion at the bottom of the target object.
  • the fork tines when determining whether the fork tines have moved to the preset docking position in the docking portion of the bottom of the target object according to the second radar data, specifically, it may be as follows: when it is determined that the second radar data has nothing to do with the target object In the case of , it can be considered that the tines of the fork have moved to the preset docking position in the docking part of the bottom of the target object; otherwise, the tines of the fork have not moved to the preset docking position of the docking part of the bottom of the target object.
  • the target information related to the pose of the target object can be determined based on the first radar data, and the target information can be determined according to the target information.
  • This solution can ensure that when the autonomous mobile forklift is moving towards the target object for docking, the tines of the autonomous mobile forklift are aligned with the docking portion at the bottom of the target object, so that the tines can enter the docking portion at the bottom of the target object , and when entering the docking part at the bottom of the target object, it can be located in the middle of the docking part. Therefore, this scheme can realize precise docking between autonomous mobile forklifts and target objects (such as shelves).
  • an autonomous mobile forklift such as the autonomous mobile forklift 1 shown in Figure 2a, Figure 2b, Figure 3a, Figure 3b and Figure 6, the autonomous mobile forklift 1 includes : car body 10, image acquisition unit 20 and controller (not shown in the accompanying drawings); wherein,
  • the vehicle body 10 includes a vehicle body 11 and a fork portion 12 disposed on one side of the vehicle body.
  • An image acquisition unit 20 arranged on the vehicle body, for acquiring a first image of the target object
  • a controller electrically connected to the image acquisition unit 20, configured to acquire the first image through the image acquisition unit; according to the first image, determine target information related to the pose of the target object; According to the target information, adjust the pose of the autonomous mobile forklift so that the fork is aligned with the docking part at the bottom of the target object; after the pose adjustment of the autonomous mobile forklift is completed, control the autonomous The mobile forklift moves towards the target object with its adjusted posture, so that the fork tine part docks with the docking part at the bottom of the target object.
  • the fork portion 12 is used to carry objects, and it can be a double-fork arm structure shown in Figure 2a and Figure 2b, or a single-fork arm structure shown in Figure 3a and Figure 3b. Examples are not limited to this.
  • the fork portion 12 can be arranged on the first side of the vehicle body 11, which side of the vehicle body 11 the first side specifically refers to can be determined according to the actual situation.
  • the directions around the vehicle body 10 can be divided into: Front side, rear side, left side, right side;
  • the sides of the vehicle body 11 include; front side, rear side, left side and right side.
  • the fork portion 12 can be arranged on the front side of the vehicle body, that is, the first side can refer to the front side of the vehicle body 11 , and the rear side of the vehicle body is the side facing away from the fork portion 12 .
  • the image acquisition unit 20 can also be arranged on the first side (ie front side) of the vehicle body 11; of course, or the image acquisition unit can also be arranged on the vehicle body 11
  • This embodiment does not specifically limit the specific setting position of the image acquisition unit.
  • For the specific setting of the image acquisition unit please refer to the relevant content above, and details will not be
  • the above-mentioned image acquisition unit 20 can be a camera capable of outputting image information and depth information, such as RGBD (depth camera), and of course it can also be an ordinary camera for collecting video or image data, which is not limited here.
  • the controller can be a central processing unit (Central Processing Unit, CPU) with data processing and computing capabilities, a single-chip microcomputer, etc., and the controller can be flexibly arranged at any position of the car body 10 according to actual conditions, such as inside the car body 10, It is also not limited here.
  • CPU Central Processing Unit
  • the autonomous mobile forklift includes a car body, an image acquisition unit and a controller; Acquiring first image data of the target object; a controller connected to the image acquisition unit for acquiring the first image through the image acquisition device; determining the distance between the target object and the target object according to the first image Pose-related target information; according to the target information, adjust the pose of the autonomous mobile forklift so that the fork tines are aligned with the docking part at the bottom of the target object; adjust the pose of the autonomous mobile forklift After completion, the autonomous mobile forklift is controlled to move towards the target object with its adjusted posture, so that the fork tines are docked with the docking portion at the bottom of the target object.
  • the autonomous mobile forklift in this solution can achieve precise docking with the target object, and has a simple structure and low cost.
  • the autonomous mobile forklift provided in this embodiment further includes: a radar 30; the radar 30 is arranged on the fork portion 12;
  • the controller can be electrically connected to the radar 30, and is used to obtain radar data about the target object detected by the radar; according to the first image and the radar data, determine pose-related target information.
  • the radar 30 may be a laser radar, a millimeter wave radar, an ultrasonic radar, etc., which is not limited in this embodiment.
  • the radar 30 can be arranged at the far end of the fork part away from the vehicle body (hereinafter referred to as the fork distal end), and the fork distal end can refer to the tooth end of the fork, that is, the end not connected to the vehicle body .
  • the detection direction of the radar disposed at the far end of the fork can be the front side of the vehicle body.
  • the controller can be electrically connected with the radar 30, so that when the self-moving forklift moves towards the target object waiting to be docked, when the first image of the target object is acquired by the image acquisition unit 20, the radar detected radar data about the target object, and then determine target information related to the pose of the target object according to the first image and the radar data.
  • the autonomous mobile forklift provided in this embodiment may include other functional structures, such as memory, audio components, traveling components, etc., in addition to the above-mentioned structural functions, which are not limited herein.
  • the embodiments of the present application also provide a computer-readable storage medium storing a computer program, and when the computer program is executed by a computer, the steps or functions in the methods for docking autonomous mobile forklifts provided in the above-mentioned embodiments can be realized.
  • the device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative efforts.
  • each embodiment can be realized by means of software plus a necessary general-purpose hardware platform, and of course also by hardware.
  • the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic discs, optical discs, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Transportation (AREA)
  • Structural Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mechanical Engineering (AREA)
  • Geology (AREA)
  • Civil Engineering (AREA)
  • Electromagnetism (AREA)
  • Acoustics & Sound (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Forklifts And Lifting Vehicles (AREA)

Abstract

一种自主移动叉车的对接方法及自主移动叉车。其中，自主移动叉车（1）包括车体以及设置于车体的图像采集单元（20）；车体包括车主体（11）以及设置于车主体（11）一侧的叉齿部（12）；方法包括：获取图像采集单元（20）采集的目标对象的第一图像（101）；根据第一图像，确定与目标对象的位姿相关的目标信息（102）；根据目标信息，调整自主移动叉车（1）的位姿，以使叉齿部（12）对准目标对象底部的对接部（103）；自主移动叉车（1）的位姿调整完成后，控制自主移动叉车（1）以其调整后的姿态朝目标对象移动，以使叉齿部（12）与目标对象底部的对接部对接（104），实现自主移动叉车（1）与目标对象精准对接，且自主移动叉车（1）结构简单，成本低。

Description

自主移动叉车的对接方法及自主移动叉车
交叉引用
本申请引用于2021年06月08日递交的名称为“自主移动叉车的对接方法及自主移动叉车”的第202110637439.5号中国专利申请，其通过引用被全部并入本申请。
技术领域
本申请涉及计算机技术领域，尤其涉及一种自主移动叉车的对接方法及自主移动叉车。
背景技术
目前，自动导引车(Automated Guided Vehicle，AGV)由于其自动化程度高以及智能化水平高的特点，被广泛应用于自动搬运领域。其中，自主移动叉车作为AGV的一种，具有叉齿特征，主要用作搬运工厂场地内的空货架或放有物体的货架，货架底部与地面通常存有一定高度空隙，以便于货叉进入并托举起货架，在叉齿进入货架底部前，涉及到叉齿与货架的对接问题。若对接不精确，可能会导致叉齿碰撞货架风险，或叉齿进入货架底部后走歪，致使货架在被搬运过程中发生偏斜或倾倒等问题。可见，如何提高自主移动叉车与货架对接的准确度尤为重要。
发明内容
本申请提供一种解决上述问题或至少部分地解决上述问题的自主移动叉车的对接方法及自主移动叉车。
在本申请的一个实施例中，提供了一种自主移动叉车的对接方法。所述自主移动叉车包括车体以及设置于所述车体的图像采集单元；所述车体包括车主体以及设置于所述车主体一侧的叉齿部。该方法包括：
获取所述图像采集单元采集的目标对象的第一图像；
根据所述第一图像，确定与所述目标对象的位姿相关的目标信息；
根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；
所述自主移动叉车的位姿调整完成后，控制所述自主移动叉车以其调整 后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。
在本申请的另一实施例中，提供了一种自主移动叉车。该自主移动叉车包括：
车体，其包括车主体及设置于所述车主体一侧的叉齿部；
图像采集单元，设置在所述车主体上，用于采集目标对象的第一图像；
控制器，与所述图像采集单元电连接，用于通过所述图像采集设备获取所述第一图像；根据所述第一图像，确定与所述目标对象的位姿相关的目标信息；根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；所述自主移动叉车的位姿调整完成后，控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。
本申请一实施例提供的技术方案中，自主移动叉车车体上设有图像采集单元，在获取到由图像采集单元采集到的目标对象的第一图像后，可根据所述第一图像确定出与目标对象的位姿相关的目标信息，并根据所述目标信息来调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；之后，在所述自主移动叉车的位姿调整完成后，可控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。该技术方案能够实现自主移动叉车与目标对象精准对接，从而利于避免因对接过程中产生的位置偏差导致目标对象在被搬运过程中发生偏斜或倾倒等现象的发生。
本申请又一实施例提供的技术方案中，自主移动叉车包括车体、图像采集单元和控制器；其中，车体包括车主体及叉齿部，图像采集单元设置在所述车主体上，用于采集目标对象的第一图像数据；控制器，与所述图像采集单元连接，用于通过所述图像采集设备获取所述第一图像；根据根据所述第一图像，确定与所述目标对象的位姿相关的目标信息；根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；所述自主移动叉车的位姿调整完成后，控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。该方案中的自主移动叉车能够实现与目标对象的精准对接，且结构简单、成本低。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请一实施例提供的自主移动叉车的对接方法的流程示意图；
图2a为本申请一实施例提供的自主移动叉车与目标对象进行对接的过程原理性示意图；
图2b为本申请另一实施例提供的自主移动叉车与目标对象进行对接的过程原理性示意图；
图3a为本申请又一实施例提供的自主移动叉车与目标对象进行对接的过程原理性示意图；
图3b为本申请又一实施例提供的自主移动叉车与目标对象进行对接的过程原理性示意图；
图4为本申请一实施例提供的调整自主移动叉车的位姿的原理示意图；
图5为本申请又一实施例提供的自主移动叉车的对接方法的流程示意图；
图6为本申请一实施例提供的自主移动叉车移动至目标对象底部的对接部中的预设对接位置的示意图；
图7为本申请一实施例提供的自主移动叉车的叉齿部进入目标对象底部对应的仰视图。
具体实施方式
目前，采用AGV搬运货架已成为一种主流趋势，但在AGV与货架对接过程中，AGV与货架之间的对接精度直接影响到对接的成功率；而且，由于可移动货架摆放具有较高的随意性，这就需要AGV对货架的摆放姿态做出判断，并矫正自己的位置与姿态从而进行精确的对接。
通常AGV在与货架完成对接之前，先需要AGV移动至指定位置与货架对接。根据AGV类型的不同，对接方式包括多种，例如，具有机械手的AGV，是从货架上获取物体；或者，潜入式的AGV，是潜入货架底部并将货架顶升进行搬运；再或者，具有衔接结构的AGV，是与货架通过衔接结构拖运货架；又或者，具有叉齿臂结构的AGV(即自主移动叉车)，是通过将叉齿插入货架底部的对接部并将货架顶升进行搬运等；其中，货架底部的对接部指的是货架底部与货架所放置平面(如地面)之间所形成的一定高度空间。针对自主移动叉车通过将叉齿插入货架底部的对接部并将货架顶升这一对接方式，为了实现自主移动叉车与货架的精准对接，常需要保证叉齿在进入货架底部的对接部时，能够位于对接部的正中间位置。如果叉齿在货架底部的位置相对于货架底部的对接部的正中间位置产生偏差，那么自主移动叉车在顶升搬运货架时可能会因重心不稳发生偏斜或倾倒。基于上述问题，本申请方案提供了一种自主移动叉车的对接方法及自主移动叉车。
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述。
在本申请的说明书、权利要求书及上述附图中描述的一些流程中，包含了按照特定顺序出现的多个操作，这些操作可以不按照其在本文中出现 的顺序来执行或并行执行。操作的序号如101、102等，仅仅是用于区分各个不同的操作，序号本身不代表任何的执行顺序。另外，这些流程可以包括更多或更少的操作，并且这些操作可以按顺序执行或并行执行。需要说明的是，本文中的“第一”、“第二”等描述，是用于区分不同的消息、设备、模块等，不代表先后顺序，也不限定“第一”和“第二”是不同的类型。而本申请中术语“或/和”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如：A或/和B，表示可以单独存在A，同时存在A和B，单独存在B这三种情况；本申请中字符“/”，一般表示前后关联对象是一种“或”关系。此外，下述的各实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
图1示出了本申请一实施例提供的自主移动叉车的对接方法的流程示意图，该方法可应用于如图2a、图2b、图3a、图3b及图6中示出的自主移动叉车1，并由自主移动叉车1中的控制器实现。控制器可以为中央处理器单元(Central Processing Unit，CPU)、单片机等，此处不作限定。自主移动叉车1可包括车体以及设置于所述车体上的图像采集单元20。图像采集单元可用来采集图像数据，车体可包括车主体11及设置于车主体一侧的叉齿部12。其中，叉齿部12可用于与目标对象(如货架)对接，以进行物体的搬运。此外，自主移动叉车还可包括存储器、行进部件等；存储器可以为RAM(Random Access Merory，随机存取存储器)、Flash(闪存)等，可用来存储接收到的数据(如图像数据、雷达数据)、处理过程所需的数据、处理过程所生成的数据等。有关自主移动叉车1的具体结构功能可参见下述相关内容，此处不作具体赘述。如图1所示，该方法可包括以下步骤
101、获取所述图像采集单元采集的目标对象的的第一图像；
102、基于所述第一图像，确定与所述目标对象的位姿相关的目标信息；
103、根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；
104、所述自主移动叉车的位姿调整完成后，控制所述自主移动叉车以调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象的对接部对接。
上述101中，所述目标对象可以是用于承载物体的货架，如图2a、图2b图3a、图3b及图6中示出的货架2。参见图2a所示，该货架具有承载平面21和支架腿22，支架腿22支撑起承载平面，使得承载平面底部与工作平面(如地面)形成一定的高度空隙，该一定的高度空隙可被称为对接空间(或对接部)，自主移动叉车的叉齿可以进入此对接部与货架进行对接，以利用叉齿将货架顶升方便搬运。在自主移动叉车的叉齿进入对接部 前，自主移动叉车是在工作平面上自动按照预定的路线朝向等待对接的货架移动，但由于在移动过程中存在多种影响其移动准确性的因素，因此当自主移动叉车行进至货架时，自主移动叉车的叉齿不一定能与货架标准地对接上，从而易造成自主移动叉车的叉齿在进入货架底部时，并不能位于货架底部的对接部的正中间位置。针对上述问题，参见图2a、图2b、图3a或图3b所示，本实施例在自主移动叉车1处于朝等待对接的目标对象(如货架2)移动时，控制器可以控制设在自主移动叉车1车主体11上的图像采集单元20向货架2方向拍摄图像，并对图像采集单元20所拍摄的图像进行识别，以确定所拍摄的图像中是否含有目标对象，并在确定所拍摄的图像中含有目标对象时，便可以将所拍摄的图像确定为货架2的第一图像。基于此，即在一种可实现的技术方案中，上述步骤101“获取所述图像采集单元采集的目标对象的的第一图像”，可具体包括：
获取所述图像采集单元的采集图像；
对所述采集图像进行图像识别，以确定所述采集图像中是否包含有所述目标对象；
所述采集图像中包含有所述目标对象时，将所述采集图像确定为所述第一图像。
具体实施时，可采用现有图像识别技术对图像采集单元所采集到的图像进行识别分析，并在根据识别结果确定出所采集的图像中含有目标对象时，便将所采集的图像作为目标对象的第一图像，以便于后续基于第一图像确定与货架2的位姿相关的目标信息，从而根据目标信息来控制自移动叉车与目标对象的对接，具体如何对接可参见下述相关内容。
在具体实施时，上述图像采集单元20可设置在所述车主体11的第一侧面或顶部上。第一侧面可指的是与叉齿部12相连接的侧面，叉齿部12可以是图2a和图2b中所示出的双叉齿臂结构，当然也可以是图3a和图3b中示出的单叉齿臂结构，本实施例对此不作限定。
沿自主移动叉车行进方向，如图2a、图2b、图3a或图3b中示出的横向箭头所指示方向，车主体11周围各方位可区分为：前侧、后侧、左侧、右侧；相应地，为了方便描述，按照上述方位，车主体11的侧面可包含有；前侧面、后侧面、左侧面和右侧面。基于此，第一侧面可具体指的是车主体的前侧面，即叉齿部和图像采集单元可设置于车主体11的前侧面。此外，或者图像采集单元也可以设置在车主体11的其它位置，比如车主体11的顶部，本实施例对此不作限定。
具体设置时，在一种可实现的技术方案中，图像采集单元20可被固定设置在车主体的第一侧面或顶部的预设位置处，并以预设的仰俯角、横摆角进行摆放。具体地，为了便于后续计算，图像采集单元20可被固定设置在车主体11的第一侧面与经过叉齿部12的中心轴的第二垂面的交线位置；或者，图像采集单元20可被固定设置在车主体11的顶部与经过叉齿部12的中心轴的第二垂面的交线位置。例如，参见图2a所示，车主体11的前侧面与经过叉齿部12的中心轴的第二垂面S的交线为l 1，在交线l 1上的位 置A处设置有一图像采集单元20，且该位置A处的图像采集单元20的采集朝向为车主体11的前侧方向。当图像采集单元20被固定安装好之后，图像采集单元20的安装高度也即是固定的。在上述图像采集单元20的安装参数固定之后，后续在基于图像采集单元20采集到与目标对象相关的图像来确定诸如目标对象的位姿相关的目标信息、自主移动叉车的叉齿部是否移动至目标对象底部的对接部中的预设对接位置等也就较为简单。有关如何确定目标对象的位姿相关的目标信息、自主移动叉车的叉齿部是否移动至目标对象底部的对接部中的预设对接位置的方法将在后面进行详细介绍，此处不作具体赘述。
在另一种可实现的技术方案中，车主体11的顶部设有旋转机构，其一端与所述车主体的顶部连接，另一端设有图像采集单元20；所述旋转机构可沿设定方向(如顺时针方向或逆时针方向)旋转，以旋转至使图像采集单元20朝向叉齿部所在侧。
需说明的是：上述图像采集单元20可以为能输出图像信息及深度信息的摄像机，比如RGBD(深度摄像机)，当然也可以是其它类型的摄像机，比如鱼眼摄像机、用于采集视频或图像数据的普通摄像机等，此处不作限定。
上述102中，目标信息可以是目标对象的位姿信息，比如目标对象的位置和姿态；或者也可以是目标对象的位置和插入端面的朝向。插入端面指的是目标对象底部的对接部所设有的供叉齿部进入的通道的进入端口对应的端面，进入端口可以是指目标对象底部的一边缘与工作平面(如地面)之间所形成的一定高度平面。例如，参见图2a所示，目标对象2底部的对接部指的是目标对象2底部与工作平面(如地面)之间所形成的一定高度空隙，该目标对象2底部的对接部所设有的供叉齿部12进入的通道的进入端口可以为目标对象2底部的后边缘与地面之间形成的一定高度平面，此时目标对象的插入端面即指目标对象2的后侧面。当然，上述通道的进入端口也可以为目标对象底部的其它边缘与地面之间所形成的一定高度平面，相应地插入端面也可以指目标对象2的其它侧面，比如，进入端口也可以为目标对象2的前边缘与地面之间所形成的一定高度平面，此时插入端面即指目标对象2的前侧面，本实施例对此不作具体限定。可见，通道的进入端口与其相应的目标对象的插入端面所在的平面为同一平面。需说明的是：上述目标对象的侧面划分方式同自主移动叉车的车主体的侧面划分方式，此处不再作具体赘述。
在具体实施时，可以利用图像识别技术对第一图像进行识别分析来确定出与目标对象的位姿相关的目标信息。其中，图像识别技术可以为机器学习模型，小波矩算法等，本实施例对此不作具体限定；在利用机器学习模型对第一图像识别分析时，需先基于大量训练样本预先训练好相关的机器学习模型，比如神经网络模型，即利用训练好的神经网络模型对第一图像识别分析时，可将第一图像作为训练好的神经网络模型的输入，执行该神经网络模型，经该神经网络模型对第一图像进行分析与计算，即可得到 相应的识别结果；然后根据识别结果，便能够确定出与目标对象的位姿相关的目标信息。
不过，考虑到仅依靠第一图像来确定与目标对象的位姿相关的目标信息时，可能存在精确性较低的问题。为了提高目标信息的精确性，可进一步地将第一图像与其它传感器(如测距传感器)所探测到的探测数据相结合，以此来得到与目标对象的位姿相关的目标信息。即，在一种可实现的技术方案中，自主移动叉车还可包括传感器；所述传感器可设置在车体上，具体地所述传感器可设置在所述叉齿部上，以用于探测与目标对象相关的数据信息。相应地，上述步骤102“根据所述第一图像，确定与所述目标对象的位姿相关的目标信息”，可具体包括：
1021、获取所述传感器探测到的有关所述目标对象的第一探测数据；
1022、根据所述第一图像及所述第一探测数据，确定与所述目标对象的位姿相关的目标信息。
上述1021中，所述传感器可以为测距传感器，所述测距传感器可以为雷达，雷达具体可以为激光雷达、毫米波雷达、超声波雷达等；或者，测距传感器也可以为其他类型的能够实现测距的传感器，比如超声波传感器、红外传感器等，本实施例对此不作限定。当然，上述传感器除了可以为测距传感器之外，也还可以是图像采集单元，在设在叉齿部上的传感器为图像采集单元的情况下，其可以与设在车主体上的图像采集单元相配合组成如双目摄像机。在对设在叉齿部上的传感器进行具体设置时，可以将该传感器设置在叉齿部的远离车主体的远端(以下简称为叉齿远端)，叉齿远端可以指的是叉齿的齿端，即不与车主体相连接的一端。设在叉齿远端的传感器的探测朝向可以为前侧方向，该传感器可与自主移动叉车的控制器连接，在自移动叉车朝向等待对接的目标对象移动过程中，控制器在通过图像采集单元20获取目标对象的第一图像的同时，将还可获取到叉齿部远端上的传感器探测到的有关目标对象的第一探测数据。
例如，参见图2a和图2b所示，自主移动叉车1的叉齿部12为双叉齿臂结构，即叉齿部12包括叉齿121和叉齿122。此种情况下，可以在叉齿121和叉齿122各自对应的叉齿远端均设置有向前侧方向探测的传感器。具体地，如图2a和图2b所示，可以在叉齿121远端的中心位置B处以及叉齿122远端的中心位置C处，分别设有向前侧方向探测的传感器30，此时控制器所获取到的第一探测数据是由设在叉齿121远端的雷达30和设在叉齿122远端的传感器30共同探测得到。又比如，参见图3a和图3b所示，自主移动叉车1的叉齿部12为单叉齿臂结构，即仅包含一个叉齿，可以如图2a和图2b中示出的叉齿远端设置传感器的方式，在叉齿远端的中心位置D处设置一个传感器30，此时控制器所获取到的第一探测数据即由叉齿齿端上的传感器30采集得到。需说明的是，在叉齿部12为双叉齿臂结构时，也可以仅在其中的一个叉齿远端上设有传感器，本实施例对此并不做限定。不过考虑到传感器探测范围的局限性，为了获取到比较全面的与目标对象相关的第一探测数据，本实施例优先在两个叉齿的远端均设置有传 感器。
上述1022中，在经由步骤1021获取到第一探测数据后，可以综合第一探测数据和第一图像来确定目标对象的位姿相关的目标信息，以提高目标信息的精确性。具体地：比如，以设在叉齿部远端的传感器为雷达，第一探测数据为雷达数据为例，可先利用图像识别技术对第一图像进行识别分析，并根据识别结果得到目标对象的初始轮廓信息；然后再利用所获取到的雷达数据来优化第一图像的识别结果(即利用雷达数据来优化目标对象的初始轮廓信息)，以进一步精确地确定出目标对象的轮廓信息；最后基于目标对象的轮廓信息确定出与目标对象的位姿相关的目标信息。再比如，设在叉齿部远端的传感器为图像采集单元，图像采集单元为摄像机，此时该叉齿部远端上的摄像机和设在车主体上的摄像机可以组合成双目摄像机。这种情况下，在根据分别叉齿部远端摄像机以及车主体上的摄像机各自所采集到的第一图像确定出有关目标对象的位姿相关的目标信息后，可以通过求取平均值的方式确定出与目标对象位姿相关的目标信息。
上述103中，基于步骤102中的内容可知，目标对象底部的对接部可设置有供叉齿部进入的通道。在确定出与目标对象的位姿相关的目标信息后，可进一步根据第一图像确定出经过通道的中心轴的第一垂面的位置信息，以根据所述目标信息和第一垂面的位置信息来调整自主移动叉车的位姿。据此，即目标对象底部的对接部可设置有供叉齿部进入的通道；相应地，步骤103“根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部”的一种可实现技术方案为：
1031、根据所述第一图像，确定有关第一垂面的位置信息；其中，所述第一垂面指的是经过所述通道的中心轴的垂面；
1032、根据所述目标信息及有关所述第一垂面的位置信息，调整所述自主移动叉车的位姿，以使经过所述叉齿部的中心轴的第二垂面与所述第一垂面位于同一平面。
上述1031中，可以先根据第一图像，分析确定出目标对象底部的对接部所设置的供叉齿部进入的通道的进入端口的中心轴的位置信息；然后根据该进入端口的中心轴的位置信息来确定有关第一垂面的位置信息。即，在具体实施时，有关所述第一垂面的位置信息可包括：第一垂面与通道的进入端口所在平面的交线的位置。由于通道的进入端口与其相应的目标对象的插入端面所在的平面为同一平面，则即第一垂面的位置信息也必然包括：第一垂面与目标对象的插入端面所在平面的交线的位置。例如，目标对象的插入端面为目标对象的后侧面，则第一垂面的位置信息包括第一垂面与目标对象后侧面的交线的位置。
在具体实施时，为了方便于后续根据所述目标对象及有关第一垂面的位置信息进行分析计算，以便根据分析计算结果来调整自主移动叉车的位姿，可以将第一垂面与目标对象的插入端面的交线上的一点作为第一垂面的位置。例如，参见图4所示，O1为第一垂面与目标对象2的后侧面的交线上的一点，则可以将点O1的坐标作为第一垂面的位置。
上述1032中，设定所确定出的与目标对象的位姿相关的目标信息为目标对象的位姿信息，所述位姿信息包含有目标对象的位置和姿态。在根据所述目标信息及有关所述第一垂面的位置信息，调整所述自主移动叉车的位姿时，具体可以先根据第一垂面的位置信息，计算分析出经过所述叉齿部的中心轴的第二垂面相对于第一垂面的横向偏离距离和偏离角度；然后根据目标对象的姿态以及第二垂面相对于第一垂面的横向偏离距离和偏离角度，来调整所述自主移动叉车的位姿。
下面列举一具体示例来介绍说明调整自主移动叉车的位姿过程。具体地：
计算第二垂面相对于第一垂面的横向偏离距离和偏离角度
参见图4并承接上述步骤1031中的示例，以点O 1的坐标作为第一垂面的位置。假设点A处在自主移动叉车1车主体的前侧面与经过叉齿部的中心轴的第二垂面的交线上，则可将点A作为第二垂面的位置。令图像采集单元被固定设置在点A的位置处，即点A也就可以看作相机坐标系的原点。由于后续在依据点A和点O 1在计算第二垂面相对于第一垂面的横向偏离距离和偏离方向时，是需要将点A和点O 1转换到同一坐标系(如世界坐标系)下的，上述将图像采集单元固定设置在点A的位置可有益于减少后续坐标转换的计算量。假设，在世界坐标系下，点A的坐标为(x 1，y 1，z 1)，点O 1的坐标为(x 2，y 2，z 2)，则点A和点O 1各自在水平坐标平面(如图4中示出的xoy平面)上的投影坐标为分别为(x 2，y 2)、(x 1，y 1)，基于点A在xoy平面上的投影坐标(x 1，y 1)及点O 1在xoy平面上的投影坐标(x 2，y 2)，即可确定出点A相对于点O 1的横向偏离距离和偏离角度。具体地，参见图4所示，上述点A相对于点O 1的横向偏离距离Dist为：Dist＝|x 1-x 2|，偏移角度α＝arctan(x 1-x 2)/(y 1-y 2)，也即第二垂面相对于第一垂面的横向偏离距离Dist为：Dist＝|x 1-x 2|，偏移角度α＝arctan(x 1-x 2)/(y 1-y 2)。
调整自主移动叉车的位姿
继续参见图4所示，可先基于目标对象的姿态，控制自主移动叉车对自身的姿态进行调整，以使调整后的自主移动叉车的姿态与目标对象的姿态一致。如图4中所示，基于目标对象2的姿态，在控制自主移动叉车1对自身的姿态进行调整后，调整后的自主移动叉车1的姿态即为图4中由虚线段所表示出的自主移动叉车1’的姿态。在控制自主移动叉车1对自身的姿态进行调整后，可进一步地基于上述示例中所计算出的第二垂面相对于第一垂面的横向偏离距离和偏离角度，来控制自主移动叉车调整自身的位置。具体地，当第二垂面相对于第一垂面的横向偏离距离和/或偏离角度不为零时，控制器可控制自主移动叉车沿可以缩短横向偏移距离和/或偏离角度的方向移动，直至第二垂面相对于第一垂面的横向偏离距离和偏离角度均为零。当调整后的第二垂面相对于第一垂面的横向偏离距离和偏离角度均为零时，即说明第二垂面与第一垂面位于同一平面，至此也就完成有自主移动叉车的位姿调整。自主移动叉车的位姿调整完成后，由于此时经过叉齿部的中心轴的第二垂面和经过对接部所设有供叉齿部进入的通道 的中心轴的第一垂面是保持在同一平面上的，为此后续在控制自主移动叉车以其调整后的姿态朝目标对象移动，以使叉齿部与目标对象底部的对接部对接，能够保证对接的精准性。
上述在控制自主移动叉车以其调整后的姿态朝目标对象继续移动过程中，还需要控制车主体上的图像采集设备继续采集图像，以基于图像采集设备继续采集到的图像对叉齿部是否移动到目标对象底部的对接部中的预设对接位置进行判断，以便在确定叉齿部移动到对接部中的预设对接位置时，控制自主移动叉车停止移动，进而控制叉齿部顶升以托举起目标对象方便搬运。基于此，在一种可实现的技术方案中，步骤104中的“控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动”，可具体包括：
S11、在所述自主移动叉车以其调整后的姿态朝所述目标对象移动的过程中，获取所述图像采集单元采集的多个第二图像；
S12、根据所述多个第二图像，确定所述叉齿部是否移动到所述目标对象底部的对接部中的预设对接位置。
上述S11中，自主移动叉车在以其调整后的姿态朝所述目标对象方向继续移动过程中，可控制设在在自主移动叉车车体上的图像采集单元继续向目标对象的方向拍摄图像，以采集得到多个第二图像并发送至控制器，以便于由控制器根据多个第二图像来确定叉齿部是否移动到目标对象底部的对接部中的预设对接位置。
上述S12中，考虑到在自主移动叉车以其调整后的姿态朝所述目标对象方向继续移动过程中，随着自主移动叉车逐渐向目标对象移动靠近，图像采集单元将会逐渐无法采集到目标对象的完整图像，且所采集到的图像的分辨率也将会逐渐减低。基于此，控制器在接收到图像采集单元发送过来的多个第二图像后，可以通过对多个第二图像进行识别分析，当确定出所接收到的第二图像不包含有目标对象且第二图像的分辨率小于一预设阈值时，便确定叉齿部移动到目标对象底部的对接部中的预设对接位置。反之，叉齿部则未移动到目标对象底部的对接部中的预设对接位置。上述预设阈值可根据实际情况灵活设定，此处不作具体限定。
不过在实际应用中，考虑到在控制自主移动叉车以其调整后的姿态朝目标对象移动，使得叉齿部进入目标对象底部后，由于各种因素的影响，自主移动叉车的姿态相对于原先调整后的姿态可能会发生稍微改变，致使叉齿部在目标对象底部移动过程中其行进方向上存在障碍。比如，参见图7所示出的叉齿部进入目标对象底部之后的仰视图，该图中目标对象为底部呈“川”字型形状的货架2，自主移动叉车的姿态相对于其调整后的姿态发生向左倾斜，这种情况下，叉齿121的行进方向上所存在的障碍为货架2底部的中间长脚l 1，若此时不对自主移动叉车的姿态进行修改，在控制自主移动叉车继续行进过程中，可能会导致叉齿121与货架底部的中间长脚l 1发生碰撞，从而造成叉齿121或货架2的损坏等。针对上述问题，在叉齿部进入目标对象底部后，可以利用叉齿部上设置的传感器所探测到的有关目标对象底部的对接部的探测数据来确定叉齿部行进方向上是否存 在障碍，并在确定存在障碍的情况下，还可以进一步地根据传感器所探测到的有关目标对象底部的对接部的探测数据，对自主移动叉车的位姿进行修正。基于此，即在另一种可实现的技术方案中，上述步骤104中的“控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接”，可具体包括：
S21、所述叉齿部进入所述目标对象底部后，根据所述调整后的姿态以及所述传感器探测到的有关所述对接部的第二探测数据，确定所述叉齿部的行进方向上是否存在障碍；
S22、若存在障碍，则根据所述第二探测数据，对所述自主移动叉车的姿态进行修正；
S23、控制所述自主移动叉车以其修正后的姿态继续行进，以使所述叉齿部移动至所述对接部中的预设对接位置。
对于上述步骤S21和S22，举例来说：承接上述示例继续参见图7所示，假设在叉齿121的中心位置C处以及叉齿122的中心位置D处所设的传感器为雷达，在根据叉齿122上的雷达所探测到的第二探测数据确定出叉齿122的行进方向上存在障碍(即图中所示的货架2底部的中间长脚l 1)时，可以根据该第二探测数据计算分析出经过叉齿122的中心轴的垂面l 2相对于中间长脚l 1的偏移角度θ，基于该偏移角度θ调整自主移动叉车的姿态，直至使偏移角度θ为90 °，调整后自主移动叉车1的姿态如图7中虚线所示出的自主移动叉车的姿态。
这里需说明的是，在对自主移动叉车的姿态进行修正后，可能会出现经过叉齿部的中心轴的第二垂面与经过货架2底部的对接部的中心轴的第一垂面(如可以将图7中示出的中间长脚l 1作为第一垂面)不再同一平面上的情况。为了避免这种情况的发生，在自主移动叉车的姿态修正完成后，还继续可以根据叉齿121齿端上的雷达所探测的探测数据，确定出经过叉齿121的中心轴的垂面与中间长脚l 1间的第一距离d 1，同理也可以得到经过叉齿122的中心轴的垂面与中间长脚l 1间的第二距离d 2(图中未示出)，之后控制器可以根据第一距离d 1和第二距离d 2对自主移动叉车的位置进行修正，使得第一距离d 1等于第二距离d 2。
上述S23中，对于控制自主移动叉车以其修改后的姿态继续行进，以使叉齿部移动至目标对象底部的对接部中的预设对接位置的具体实现过程中，这里考虑到叉齿部移动至目标对象底部的对接部中的预设对接位置时，叉齿部一般是会超出目标对象底部的，此时设在叉齿齿端上的传感器是无法探测到与目标对象底部的对接部相关的数据信息的。基于此，在控制自主移动叉车以其修正后的姿态继续行进过程中，控制器可以根据所获取到的传感器所探测到的探测数据，来判断叉齿部是否移动至货架2底部的对接部的预设对接位置。具体地，控制自主移动叉车以其修正后的姿态继续行进过程中，当确定出设在叉齿部齿端上的传感器无法探测到与目标对象底部的对接部相关的数据信息时，便确定叉齿部移动至目标对象底部的对接部中的预设对接位置；反之，若设在叉齿部齿端上的传感器仍能够探测 到与目标对象底部的对接部相关的数据信息，则说明叉齿部还未移动至目标对象底部的对接部中的预设对接位置。
进一步地，当自主移动叉车的叉齿部移动到目标对象底部的对接部中的预设对接位置后，控制器可控制自主移动叉车停止移动，并控制叉齿部进行顶升，以托举起所述目标对象方便搬运。有关如何控制叉齿部进行顶升同现有技术，此处就不再作具体赘述。
本实施例提供的技术方案，自主移动叉车车体上设有图像采集单元，在自主移动叉车朝向等待对接的目标对象(如货架)移动时，在获取到图像采集单元采集到的目标对象的第一图像后，可基于第一图像确定出与目标对象的位姿相关的目标信息；并根据该目标信息，可调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；且在自主移动叉车的位姿调整完成后，可控制自主移动叉车以其调整后的姿态朝目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。由于本方案能够确保在控制自主移动叉车以其调整后的姿态朝目标对象移动过程中，自主移动叉车的叉齿部是对准目标对象底部的对接部的，这样可使得叉齿部能够进入目标对象底部的对接部，且在进入目标对象底部的对接部时能位于对接部的正中间位置。因此，本方案可使自主移动叉车与目标对象(如货架)实现精准对接，从而利于避免因对接过程中产生的位置偏差导致目标对象在被搬运过程中发生偏斜或倾倒等现象的发生。
上述实施例主要是从图像采集单元所采集到的图像数据与其它传感器所探测的探测数据相结合的角度来说明如何使自主移动叉车与目标对象精确的完成对接的。除此之外，在其它传感器为雷达的情况下，当然也可仅基于所获取到的雷达数据实现自主移动叉车与目标对象的精确对接。下面一实施例为从仅基于获取到的雷达数据的角度实现自主移动叉车与目标对象的精准对接所对应的技术方案。具体地，图5示出了本申请另一实施例提供的自主移动叉车的对接方法的流程示意图，该方法可以应用于自主移动叉车，并由自主移动叉车中的控制器实现。控制器可以为中央处理器单元(Central Processing Unit，CPU)、单片机等，此处不作限定。参见图2a所示，自主移动叉车可具体包括车体11以及设置于所述车体上的雷达20。雷达可用来探测得到与目标对象相关的雷达数据，车体可包括车主体11及设置于车主体一侧的叉齿部12。其中，叉齿部可用于与目标对象(如货架)对接，以进行物体的搬运。有关自主移动叉车的具体结构功能可参见上述或下述相关内容，此处不作具体赘述。如图5所示，该方法包括如下步骤：
201、获取雷达探测到的有关目标对象的第一雷达数据；
202、基于所述第一雷达数据，确定与所述目标对象的位姿相关的目标信息；
203、根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；
204、所述自主移动叉车的位姿调整完成后，控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。
上述201和202中，雷达可以为激光雷达、毫米波雷达、超声波雷达等，本实施例对此不作限定。所述雷达可设置在叉齿部的远离车主体的远端(以下简称为叉齿远端)，叉齿远端可以指的是叉齿的齿端，即不与车主体相连接的一端。设在叉齿远端的雷达的探测朝向可以为车主体的前侧方向，该雷达可与自主移动叉车的控制器连接。其中，车主体的前侧是根据自主移动叉车行进方向确定的，具体可参见上述相关内容，此处不作具体赘述。此外有关雷达的具体设置以及具体如何通过雷达获取到有关目标对象的第一雷达数据，可参见上述各实施例中的相应的部分，此处不作赘述。
上述203中，所述目标对象底部的对接部设置有供所述叉齿部进入的通道；相应地，步骤203“根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部”，可具体包括：
2031、根据所述第一雷达数据，确定有关第一垂面的位置信息；其中，所述第一垂面指的是经过所述通道的中心轴的垂面；
2032、根据所述目标信息及有关所述第一垂面的位置信息，调整所述自主移动叉车的位姿，以使经过所述叉齿部的中心轴的第二垂面与所述第一垂面位于同一平面。
上述204中的“控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动”，可具体包括：
2041、在所述自主移动叉车以其调整后的姿态朝所述目标对象移动的过程中，获取所述雷达采集的第二雷达数据；
2042、根据所述第二雷达数据，确定所述叉齿部是否移动到所述目标对象底部的对接部中的预设对接位置。
具体实施时，考虑到当自主移动叉车的叉齿部移动至目标对象底部的对接部中的预设对接位置后，一般情况下，叉齿部的齿端会超出目标对象的底部，比如图6所示出的示例，叉齿12的齿端超出目标对象2的底部。此时，设在叉齿12齿端的雷达30是采集不到与目标对象相关的雷达数据的，即也就是说，当自主移动叉车以其调整后的姿态朝所述目标对象移动的过程中，若确定出设在叉齿12齿端上的雷达30无法采集到与目标对象相关的雷达数据，即可认为自主移动叉车移动至目标对象底部的对接部中的预设对接位置。基于此，即在根据第二雷达数据来确定叉齿部是否移动到所述目标对象底部的对接部中的预设对接位置时，具体地可以为：在确定出第二雷达数据与目标对象无关的情况下，即可认为叉齿部移动到目标对象底部的对接部中的预设对接位置；反之，叉齿部则未移动到目标对象底部的对接部中的预设对接位置。
本实施例提供的技术方案，在通过雷达获取到有关目标对象的第一雷达数据后，将可基于该第一雷达数据确定出与目标对象的位姿相关的目标 信息，并根据所述目标信息来调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；之后，在所述自主移动叉车的位姿调整完成后，控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。该方案能够保证自主移动叉车在向目标对象移动以进行对接过程中，自主移动叉车的叉齿部是对准目标对象底部的对接部的，这样可使得叉齿部能够进入目标对象底部的对接部，且在进入目标对象底部的对接部时能位于对接部的正中间位置。因此，本方案可使自主移动叉车与目标对象(如货架)实现精准对接。
这里需要说明的是：本实施例提供的所述方法中各步骤未尽详述的内容可参见上述各实施例中的相应内容，此处不再赘述。此外，本实施例提供的所述方法中除了上述各步骤以外，还可包括上述各实施例中其他部分或全部步骤，具体可参见上述各实施例相应内容，在此不再赘述。
基于上文内容，本申请又一实施例还提供了一种自主移动叉车，如图2a、图2b、图3a、图3b及图6中示出的自主移动叉车1，该自主移动叉车1包括：车体10、图像采集单元20以及控制器(附图中未示出)；其中，
车体10，包括车主体11及设置于所述车主体一侧的叉齿部12。
图像采集单元20，设置在所述车主体上，用于采集目标对象的第一图像；
控制器，与所述图像采集单元20电连接，用于通过所述图像采集单元获取所述第一图像；根据根据所述第一图像，确定与所述目标对象的位姿相关的目标信息；根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；所述自主移动叉车的位姿调整完成后，控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。
具体实施时，叉齿部12用于承载物体，其可以是图2a和图2b中所示的双叉齿臂结构，也可以是图3a和图3b示出的单叉齿臂结构，本实施例对此不作限定。叉齿部12可以设置于所述车主体11的第一侧面，第一侧面具体指的是车主体11的哪一侧面，可根据实际情况进行确定。
在实际应用中，沿自主移动叉车1行进的方向，如图2a、图2b、图3a、图3b及图6中示出的横向箭头所指示的方向，车主体10周围各方位可区分为：前侧、后侧、左侧、右侧；相应地，为了方便描述，按照上述方位，车主体11的侧面含有；前侧面、后侧面、左侧面和右侧面。叉齿部12可设置在车主体的前侧面，即第一侧面可指的是车主体11的前侧面，车主体的后侧面即为背向叉齿部12的侧面。
参见图2a、图2b、图3a及图3b所示，图像采集单元20也可设置在车主体11的第一侧面(即前侧面)；当然，或者图像采集单元也可以设置在车主体11的其它位置，比如车主体11的顶部，具体体：如在所述车主 体的顶部设有固定朝向于所述叉齿部所在侧(即车主体的前侧)的所述图像采集单元；或者，在所述车主体的顶部设有旋转机构，其一端与所述车主体的顶部连接，另一端上设有所述图像采集单元；相应地，所述控制器，还与所述旋转机构电连接，用于控制所述旋转机构沿设定方向旋转，以旋转至使所述图像采集单元朝向于所述叉齿部所在侧。本实施例对图像采集单元的具体设置位置不作具体限定，有关图像采集单元的具体设置可参见上述相关内容，此处不作具体赘述。此外，关于旋转机构的具体结构可参见现有技术。
在具体实施时，上述图像采集单元20可以为能输出图像信息及深度信息的摄像头，比如RGBD(深度摄像机)，当然也可以是用于采集视频或图像数据的普通摄像机，此处不作限定。控制器可以是具有数据处理、计算能力的中央处理单元(Central Processing Unit，CPU)、单片机等，且控制器可以根据实际情况灵活的设置在车体10的任何位置处，比如车主体10内部，此处同样不作限定。
本实施例提供的技术方案中，自主移动叉车包括车体，图像采集单元和控制器；车体包括车主体及设置于车主体叉齿部，图像采集单元设置在所述车主体上，用于采集目标对象的第一图像数据；控制器，与所述图像采集单元连接，用于通过所述图像采集设备获取所述第一图像；根据根据所述第一图像，确定与所述目标对象的位姿相关的目标信息；根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；所述自主移动叉车的位姿调整完成后，控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。该方案中的自主移动叉车能够实现与目标对象的精准对接，且结构简单、成本低。
进一步地，本实施例提供的所述自主移动叉车还包括：雷达30；所述雷达30设置在所述叉齿部12上；
所述控制器，可与所述雷达30电连接，用于获取所述雷达探测到的有关所述目标对象的雷达数据；根据所述第一图像和所述雷达数据，确定与所述目标对象的位姿相关的目标信息。
具体实施时，所述雷达30可以为激光雷达、毫米波雷达、超声波雷达等，本实施例对此不作限定。所述雷达30可设置在叉齿部的远离车主体的远端(以下简称为叉齿远端)，叉齿远端可以指的是叉齿的齿端，即不与车主体相连接的一端。设在叉齿远端的雷达的探测朝向可以为车主体的前侧方向。控制器可与雷达30电连接，以用于在自移动叉车朝向等待对接的目标对象移动过程中，在通过图像采集单元20获取目标对象的第一图像的同时，将还可获取到雷达探测到的有关目标对象的雷达数据，进而根据所述第一图像和所述雷达数据来确定出与所述目标对象的位姿相关的目标信息。
这里需要说明的是：本实施例提供的所述自主移动叉车的各结构功能中未尽详述的内容，可参见上述各实施例中的相应内容，此处不再作赘述。 此外，本实施例提供的所述自主移动叉车除了上述各结构功能以外，还可包括其它的功能结构，比如存储器，音频组件、行进部件等，此处并不作限定。
此外，本申请实施例还提供一种存储有计算机程序的计算机可读存储介质，所述计算机程序被计算机执行时能够实现上述各实施例提供的自主移动叉车对接方法中的步骤或功能。
以上所描述的装置实施例仅仅是示意性的，其中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模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，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)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (17)

  1. 一种自主移动叉车的对接方法，其特征在于，所述自主移动叉车包括车体以及设置于所述车体的图像采集单元；所述车体包括车主体以及设置于所述车主体一侧的叉齿部；
    所述方法，包括：
    获取所述图像采集单元采集的目标对象的第一图像；
    根据所述第一图像，确定与所述目标对象的位姿相关的目标信息；
    根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；
    所述自主移动叉车的位姿调整完成后，控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。
  2. 根据权利要求1所述的方法，其特征在于，所述目标对象底部的对接部设置有供所述叉齿部进入的通道；
    根据所述目标信息，调整所述自主移动叉车的位姿，包括：
    根据所述第一图像，确定有关第一垂面的位置信息；其中，所述第一垂面指的是经过所述通道的中心轴的垂面；
    根据所述目标信息及有关所述第一垂面的位置信息，调整所述自主移动叉车的位姿，以使经过所述叉齿部的中心轴的第二垂面与所述第一垂面位于同一平面。
  3. 根据权利要求2所述的方法，其特征在于，有关所述第一垂面的位置信息包括：所述第一垂面与所述通道的进入端口所在平面的交线的位置。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述叉齿部设置于所述车主体的第一侧面；
    所述图像采集单元设置于所述车主体的第一侧面。
  5. 根据权利要求1至3中任一项所述的方法，其特征在于，
    所述车主体的顶部设有固定朝向于所述叉齿部所在侧的所述图像采集单元；或者
    所述车主体的顶部设有旋转机构，其一端与所述车主体的顶部连接，另一端上设有所述图像采集单元；所述旋转机构可沿设定方向旋转，以旋转至使所述图像采集单元朝向所述叉齿部所在侧。
  6. 根据权利要求1至3中任一项所述的方法，其特征在于，控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，包括：
    在所述自主移动叉车以其调整后的姿态朝所述目标对象移动的过程中，获取所述图像采集单元采集的多个第二图像；
    根据所述多个第二图像，确定所述叉齿部是否移动到所述目标对象底部的对接部中的预设对接位置。
  7. 根据权利要求1至3中任一项所述的方法，其特征在于，所述自主移动叉车还包括传感器；所述传感器设置于所述叉齿部；
    根据所述第一图像，确定与所述目标对象的位姿相关的目标信息，包括：
    获取所述传感器探测到的有关所述目标对象的第一探测数据；
    根据所述第一图像及所述第一探测数据，确定与所述目标对象的位姿相关的目标信息。
  8. 根据权利要求7所述的方法，其特征在于，控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接，包括：
    所述叉齿部进入所述目标对象底部后，根据所述调整后的姿态以及所述传感器探测到的有关所述对接部的第二探测数据，确定所述叉齿部的行进方向上是否存在障碍；
    若存在障碍，则根据所述第二探测数据，对所述自主移动叉车的姿态进行修正；
    控制所述自主移动叉车以其修正后的姿态继续行进，以使所述叉齿部移动至所述对接部中的预设对接位置。
  9. 根据权利要求7所述的方法，其特征在于，
    所述传感器设置在所述叉齿部的远离所述车主体的远端。
  10. 根据权利要求7所述的方法，其特征在于，所述传感器为测距传感器。
  11. 根据权利要求1至3中任一项所述的方法，其特征在于，还包括：
    获取所述图像采集单元的采集图像；
    对所述采集图像进行图像识别，以确定所述采集图像中是否包含有所述目标对象；
    所述采集图像中包含有所述目标对象时，将所述采集图像确定为所述第一图像。
  12. 一种自主移动叉车，其特征在于，包括：
    车体，其包括车主体及设置于所述车主体一侧的叉齿部；
    图像采集单元，设置在所述车主体上，用于采集目标对象的第一图像；
    控制器，与所述图像采集单元电连接，用于获取所述图像采集单元采集的所述第一图像；根据所述第一图像，确定与所述目标对象的位姿相关的目标信息；根据所述目标信息，调整所述自主移动叉车的位姿，以使所述叉齿部对准所述目标对象底部的对接部；所述自主移动叉车的位姿调整完成后，控制所述自主移动叉车以其调整后的姿态朝所述目标对象移动，以使所述叉齿部与所述目标对象底部的对接部对接。
  13. 根据权利要求12所述的自主移动叉车，其特征在于，
    所述叉齿部设置于所述车主体的第一侧面；
    所述图像采集单元设置于所述车主体的第一侧面。
  14. 根据权利要求12所述的自主移动叉车，其特征在于，
    所述车主体的顶部设有固定朝向于所述叉齿部所在侧的所述图像采集单元；或者
    所述车主体的顶部设有旋转机构，其一端与所述车主体的顶部连接，另一端上设有所述图像采集单元；所述控制器，还与所述旋转机构电连接，用于控制所述旋转机构沿设定方向旋转，以旋转至使所述图像采集单元朝向所述叉齿部所在侧。
  15. 根据权利要求12至14中任一项所述的自主移动叉车，其特征在于，还包括：
    传感器，设置在所述叉齿部上；
    所述控制器，与所述传感器电连接，用于获取所述传感器探测到的有关所述目标对象的第一探测数据；根据所述第一图像和所述第一探测数据，确定与所述目标对象的位姿相关的目标信息。
  16. 根据权利要求15所述的自主移动叉车，其特征在于，
    所述传感器设置于所述叉齿部的远离所述车主体的远端。
  17. 根据权利要求15所述的自主移动叉车，其特征在于，所述传感器为测距传感器。
PCT/CN2022/082727 2021-06-08 2022-03-24 自主移动叉车的对接方法及自主移动叉车 WO2022257550A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110637439.5 2021-06-08
CN202110637439.5A CN115520808A (zh) 2021-06-08 2021-06-08 自主移动叉车的对接方法及自主移动叉车

Publications (1)

Publication Number Publication Date
WO2022257550A1 true WO2022257550A1 (zh) 2022-12-15

Family

ID=84424720

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/082727 WO2022257550A1 (zh) 2021-06-08 2022-03-24 自主移动叉车的对接方法及自主移动叉车

Country Status (2)

Country Link
CN (1) CN115520808A (zh)
WO (1) WO2022257550A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116674920A (zh) * 2023-04-25 2023-09-01 中国铁建电气化局集团有限公司 一种智能化运输方法、装置、设备和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150347840A1 (en) * 2014-05-27 2015-12-03 Murata Machinery, Ltd. Autonomous vehicle, and object recognizing method in autonomous vehicle
CN109081272A (zh) * 2018-10-23 2018-12-25 西安中科光电精密工程有限公司 一种基于激光与视觉混合引导的无人转运叉车及方法
WO2020199471A1 (zh) * 2019-04-02 2020-10-08 北京极智嘉科技有限公司 一种高位机器人、归还仓储容器的校准方法及存储介质
CN112830428A (zh) * 2020-06-18 2021-05-25 陈凤阳 用于修正叉车agv测量叉取托盘姿态的系统及其工作方法
CN112849898A (zh) * 2019-11-27 2021-05-28 北京极智嘉科技股份有限公司 一种自驱动机器人及自驱动机器人的搬运方法
CN215160705U (zh) * 2021-06-08 2021-12-14 灵动科技（北京）有限公司 自主移动叉车

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150347840A1 (en) * 2014-05-27 2015-12-03 Murata Machinery, Ltd. Autonomous vehicle, and object recognizing method in autonomous vehicle
CN109081272A (zh) * 2018-10-23 2018-12-25 西安中科光电精密工程有限公司 一种基于激光与视觉混合引导的无人转运叉车及方法
WO2020199471A1 (zh) * 2019-04-02 2020-10-08 北京极智嘉科技有限公司 一种高位机器人、归还仓储容器的校准方法及存储介质
CN112849898A (zh) * 2019-11-27 2021-05-28 北京极智嘉科技股份有限公司 一种自驱动机器人及自驱动机器人的搬运方法
CN112830428A (zh) * 2020-06-18 2021-05-25 陈凤阳 用于修正叉车agv测量叉取托盘姿态的系统及其工作方法
CN215160705U (zh) * 2021-06-08 2021-12-14 灵动科技（北京）有限公司 自主移动叉车

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116674920A (zh) * 2023-04-25 2023-09-01 中国铁建电气化局集团有限公司 一种智能化运输方法、装置、设备和存储介质
CN116674920B (zh) * 2023-04-25 2024-01-23 中国铁建电气化局集团有限公司 一种智能化运输方法、装置、设备和存储介质

Also Published As

Publication number Publication date
CN115520808A (zh) 2022-12-27

Similar Documents

Publication Publication Date Title
US11772267B2 (en) Robotic system control method and controller
CN109160452B (zh) 基于激光定位和立体视觉的无人转运叉车及导航方法
US10315865B2 (en) Conveying device, conveying system, and conveying method
US10850961B2 (en) Forklift
JP6507894B2 (ja) 無人フォークリフトにおける荷取り時の走行制御方法及び荷取り時の走行制御装置
CN109345593B (zh) 一种摄像机姿态的检测方法及装置
WO2020042426A1 (zh) 机器人检测直边的方法和清洁机器人筛选参考墙边的方法
CN113253737B (zh) 货架检测方法及装置、电子设备、存储介质
WO2022257550A1 (zh) 自主移动叉车的对接方法及自主移动叉车
US11554501B2 (en) Robot system and control method
TW202220915A (zh) 貨物取放方法、裝置、倉儲機器人和倉儲系統
JP7377627B2 (ja) 物体検出装置、物体把持システム、物体検出方法及び物体検出プログラム
CN110815202A (zh) 障碍物检测方法及装置
JP2017217726A (ja) ロボット
CN215160705U (zh) 自主移动叉车
JP2022177834A (ja) 物体サイズ検出のためのロボットシステム
JP5370122B2 (ja) 移動体位置推定装置及び移動体位置推定方法
TWM606382U (zh) 即時校正夾持座標之機械手臂系統
Iinuma et al. Pallet detection and estimation for fork insertion with rgb-d camera
US20220355474A1 (en) Method and computing system for performing robot motion planning and repository detection
CN113768420B (zh) 扫地机及其控制方法、装置
CN116309882A (zh) 一种面向无人叉车应用的托盘检测和定位方法及系统
CN112306061B (zh) 一种机器人控制方法以及机器人
WO2021082855A1 (zh) 自主机器人及其及移动控制方法、装置和存储介质
KR100335327B1 (ko) 크레인의무인자동화방법및그장치

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: 22819155

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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 1205 DATED 30.01.24