WO2019148441A1 - 拣货方法、系统及其应用的获持与放置系统、机器人 - Google Patents

拣货方法、系统及其应用的获持与放置系统、机器人 Download PDF

Info

Publication number
WO2019148441A1
WO2019148441A1 PCT/CN2018/075036 CN2018075036W WO2019148441A1 WO 2019148441 A1 WO2019148441 A1 WO 2019148441A1 CN 2018075036 W CN2018075036 W CN 2018075036W WO 2019148441 A1 WO2019148441 A1 WO 2019148441A1
Authority
WO
WIPO (PCT)
Prior art keywords
state
end effector
robot
operated
controlling
Prior art date
Application number
PCT/CN2018/075036
Other languages
English (en)
French (fr)
Inventor
张�浩
Original Assignee
深圳蓝胖子机器人有限公司
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 深圳蓝胖子机器人有限公司 filed Critical 深圳蓝胖子机器人有限公司
Priority to CN201880002481.6A priority Critical patent/CN109641706B/zh
Priority to PCT/CN2018/075036 priority patent/WO2019148441A1/zh
Publication of WO2019148441A1 publication Critical patent/WO2019148441A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/0093—Programme-controlled manipulators co-operating with conveyor means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
    • B65G47/74—Feeding, transfer, or discharging devices of particular kinds or types
    • B65G47/90—Devices for picking-up and depositing articles or materials
    • B65G47/902—Devices for picking-up and depositing articles or materials provided with drive systems incorporating rotary and rectilinear movements
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
    • B25J9/1697—Vision controlled systems
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/41815—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by the cooperation between machine tools, manipulators and conveyor or other workpiece supply system, workcell
    • G05B19/4182—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by the cooperation between machine tools, manipulators and conveyor or other workpiece supply system, workcell manipulators and conveyor only
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/39—Robotics, robotics to robotics hand
    • G05B2219/39106—Conveyor, pick up article, object from conveyor, bring to test unit, place it
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/40—Robotics, robotics mapping to robotics vision
    • G05B2219/40022—Snatching, dynamic pick, effector contacts object, moves with object
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/40—Robotics, robotics mapping to robotics vision
    • G05B2219/40554—Object recognition to track object on conveyor
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • the invention relates to the field of robot control, in particular to a picking method and system, and a holding and placing system and a robot thereof.
  • the concept of Industry 4.0 is to transform manufacturing into intelligence.
  • the automation of the logistics and warehousing industry mainly uses a complex conveyor belt system to realize the automatic transportation of goods in the warehouse.
  • this method has greatly improved the efficiency of warehousing, there are still a lot of manual links, and the picking is carried out to place the goods on one operating end on the other.
  • the unloaded goods are picked and placed in the input area of the conveyor system to allow the goods to enter the automated operation of the conveyor system.
  • the intermediate link involves the need to transfer the goods from one conveyor subsystem output to another conveyor subsystem and so on.
  • the existing conveyor system automation system has the following problems:
  • a picking system including:
  • a sensing device for sensing an object to be operated
  • An operating robot comprising a free end provided with an end effector
  • At least one processor for:
  • the second state Included that the object to be operated has a target speed V G along a conveying direction of the conveying mechanism, wherein the target speed V G corresponds to the conveying speed V C ;
  • Embodiments of the present invention also provide a method of picking, implemented in one or more computer systems, including performing steps:
  • the second state including a conveying direction of the object to be conveyed along the conveying mechanism Having a target speed V G , wherein the target speed V G corresponds to the transport speed V C of the transport mechanism;
  • Embodiments of the present invention also provide a holding and placing system, including:
  • a sensing device for sensing an object to be operated
  • An operating robot comprising a free end provided with an end effector
  • At least one processor for:
  • the first state and the second state include a position, Attitude, velocity, acceleration, angular velocity, angular acceleration, geometry and/or weight distribution;
  • the end effector is controlled to place the object to be manipulated.
  • the embodiment of the invention also provides a robot, comprising:
  • a sensing device for sensing an object to be operated
  • An operating robot comprising a free end provided with an end effector
  • At least one processor for:
  • the first state and the second state include a position, Attitude, velocity, acceleration, angular velocity, angular acceleration, geometry and/or weight distribution;
  • the picking system and the picking method provided by the embodiments of the present invention realize that the goods placed on the transport mechanism match the transport state of the transport mechanism.
  • the method of manually picking and placing on the transmission mechanism solves the problem that the manual operation is difficult to match the high-speed operation of the transmission mechanism, and it is difficult to accurately store the goods under high-speed operation and maintain the stability after the object is placed.
  • the picking system and method provided by the embodiments of the present invention ensure the stability of the object placed on the transport mechanism, and the orderly and efficient operation of the system.
  • the embodiment of the present invention further provides a holding and placing system and a robot applied to the picking system and method, and implements a universal and flexible holding and placing solution, which can cope with different application scenarios for the first state. Independent planning and implementation to the different needs of the second state.
  • FIG. 1 is a schematic structural diagram of a picking system according to an embodiment of the present invention.
  • FIG. 2 is a schematic diagram of a picking scene according to an embodiment of the present invention.
  • FIG. 3 is a schematic flow chart of a picking method according to a first embodiment of the present invention.
  • FIG. 4 is a schematic flow chart of a picking method according to a second embodiment of the present invention.
  • FIG. 5 is a schematic flow chart of a picking method according to a third embodiment of the present invention.
  • FIG. 6 is a schematic flow chart of a picking method according to a fourth embodiment of the present invention.
  • FIG. 7 is a schematic flow chart of a picking method according to a fifth embodiment of the present invention.
  • FIG. 8 is a schematic structural diagram of a holding and placing system according to an embodiment of the present invention.
  • FIG. 9 is a schematic structural diagram of a robot according to an embodiment of the present invention.
  • the embodiment of the present invention provides a holding and placing system 20, as shown in FIG. 8, including a sensing device 12, an operating robot 13, and at least one processor 14.
  • the sensing device 12 is configured to sense an object to be operated.
  • the operating robot 13 includes a free end provided with an end effector 15.
  • the operation robot 13 includes a series robot, a parallel robot, and various options in combination with the mobile robot, and the operation of the end effector 15 on the object to be operated can be realized.
  • the tandem robot can be a robotic arm with 6 degrees of freedom.
  • At least one processor 14 is configured to execute the holding and placing method, including: obtaining a first state of the operating robot 13 and/or the end effector 15 according to the object to be operated, and performing the placing of the object to be operated Two states, get exercise planning.
  • first state and the second state comprise position, attitude, velocity, acceleration, angular velocity, angular acceleration, geometric shape and/or weight distribution.
  • the method further includes: controlling the operating robot 13 and/or the end effector 15 to move to the first state, and controlling the end effector 15 to hold the operated object, and controlling the operating robot 13 and/or according to the motion planning control.
  • the end effector 15 is moved to the second state, and the end effector 15 is controlled to place the object to be manipulated.
  • the above-mentioned holding and placing system provided by the embodiment of the present invention can flexibly cope with the operation of the object to be operated from the first state to the second state according to the scene requirement, including any position, posture, speed, acceleration, angular velocity, angular acceleration, The application requirements of any feature or combination of features of geometric shape and weight distribution.
  • some embodiments are exemplified below.
  • the sensing device 12 includes a visual sensor.
  • the at least one processor 14 is further configured to perform segmentation processing according to data acquired by the vision sensor to obtain information of the object to be manipulated, or to obtain information of the object to be manipulated according to the three-dimensional model of the object to be manipulated.
  • the at least one processor 14 is further configured to obtain, according to the information of the object to be operated, an execution parameter of the end effector contacting the object to be operated.
  • the control operation robot 13 is moved to the first state in accordance with the execution parameter, and the end effector 15 is controlled to hold the object to be operated.
  • a method of obtaining an execution parameter according to different variation parameters of the first state to the second state will be specifically exemplified.
  • Embodiment 1 The first state and the second state include positions.
  • the object to be operated includes goods, and the goods are moved from the source area to the destination area.
  • the operating robot 13 performs the transfer of the goods from the output O of one conveyor subsystem to the input I of the other conveyor subsystem.
  • the sensing device 12 senses the object of the output O.
  • the at least one processor 14 obtains an operation parameter of the object to be operated according to the object sensed by the sensing device 12, and the operation parameter includes the position of the object to be operated.
  • the first state in which the end effector 15 reaches the position of the operated object is obtained.
  • the motion plan of the position of the operated object to the target position is acquired.
  • the end effector 15 when the end effector 15 is used as the follower chuck, regardless of the posture, the end effector 15 can be adaptively grasped as long as the end effector 15 approaches the object to be manipulated.
  • Embodiment 2 The first state and the second state include a posture.
  • the processor 14 is configured to obtain a first state of the operated object according to the operating robot 13, in this example, the first state includes the current posture of the held object, and the end effector when the object label is oriented toward the target.
  • the target pose the second state in this example, acquires the motion plan. Including the rotation of the joint angles of the control robot 13, the end effector 15 is brought to the target pose, thereby realizing the target orientation of the workpiece label.
  • This example can also be combined with multi-operating robot collaboration.
  • the executed area of the object to be manipulated is opposite to the face on which the label is located, and the target orientation requires the area to be executed and placed.
  • the bearing surface contact of the area cannot be achieved due to mechanical constraints.
  • a second operational robot for performing the aforementioned inversion can be combined to realize a posture change of the operated object.
  • the first operation robot transfers the object to be operated to the second operation robot with the non-executed area, and the second operation robot can realize the target posture through motion planning, and perform placement so that the object to be operated The label is oriented towards the desired orientation.
  • Embodiment 3 The first state and the second state include speed.
  • the processor 14 is configured to acquire a first state of the object to be operated according to the operation robot 13, in this example, the first state is the current speed, and the target speed of the object to be operated in the second state, the motion plan is acquired. After the end effector 15 holds the object to be manipulated, the operation robot 13 performs the motion according to the motion plan so that the end effector 15 places the object to be manipulated after the motion speed reaches the target speed.
  • the target object is made to have a target speed when it is placed.
  • Embodiment 4 The first state and the second state include acceleration.
  • the processor 14 is configured to obtain a first state of the object to be operated according to the operation robot 13, in which the first state is the current or initial acceleration; and the target acceleration of the object in the second state; and the motion plan is acquired. After the operation robot 13 reaches the target acceleration according to the motion plan, the end effector 15 places the object to be manipulated. For some scenes, after the operation is performed by the robot 13, the object to be operated falls on the conveyor belt having the acceleration, so that the belt acceleration is better matched when the workpiece is placed. Thereby ensuring the relative stability of the object to be placed.
  • Embodiment 5 The first state and the second state include angular velocities.
  • the processor 14 is configured to obtain a first state of the operated object according to the operating robot 13 and/or the end effector 15, in which the first state is the current or initial angular velocity; and the target of the operated object in the second state Angular velocity; get motion planning.
  • the operating robot 13 and/or the end effector 15 according to the motion plan reaches the target angular velocity, and the end effector 15 places the object to be manipulated.
  • it is necessary to have an angular velocity limitation requirement such that the object to be manipulated has a target angular velocity when placed, thereby entering a certain placement area or space, Excellent match to the characteristics of the placement area or placement space.
  • Embodiment 6 The first state and the second state include angular acceleration.
  • the processor 14 is configured to acquire a first state of the object to be operated according to the operating robot 13 and/or the end effector 15, in this example, the first state is the current or initial angular acceleration, and the second state is the object to be operated Target angular acceleration, get motion planning.
  • the operating robot 13 and/or the end effector 15 according to the motion plan reaches the target angular velocity, and the end effector 15 places the object to be manipulated.
  • Embodiment 7 The first state and the second state include geometric shapes.
  • the processor 14 is configured to obtain a first state of the operated object according to the operating robot 13 and/or the end effector 15, in this example, the first state corresponds to an execution state of the current geometric shape of the operated object; and the second The state corresponds to the execution state of the manipulated object target geometry; the motion plan is acquired.
  • the execution state may include a position and/or a posture.
  • the operation robot 13 and/or the end effector 15 according to the motion plan after reaching the target execution, the end effector 15 places the object to be manipulated.
  • the operating robot 13 and/or the end effector 15 perform other tasks of holding and placing the object to be further used for combining the object being manipulated, such as when the object being opened is an open box, the other Tasks can be packaged.
  • the operating robot 13 closes the cover that the case is open. It is also possible to close the cover of the operation robot 13 by the end effector 15 to open the case.
  • the first state may be a position where the end effector 15 contacts the outside of the cover plate, or the end effector 15 is in a specific posture, for example, according to the posture of the cover plate when the case is opened, the first state is the end effector 15 being vertical
  • the outer side of the cover plate contacts the first position and/or attitude of the center of the cover plate
  • the second state is the position and/or the specific posture when the end effector is moved to the closed state of the cover plate.
  • the position and/or posture may include a position and/or a posture corresponding to the operating robot 13 when the end effector 15 reaches the corresponding position and/or posture.
  • the operating robot 13 is not required to move to the corresponding position and/or posture to cause the end effector 15 to reach the desired position.
  • Position and / or posture After the operating robot 13 reaches the second state according to the motion plan, if the box has a locking device, the locking device can be activated after the cover is closed, and the end effector 15 can be placed to restore the initial position and/or posture to complete the packaging.
  • the cover plate may also be sealed by a packaging device such as a tape packaging device or a nailing device, and the package is completed.
  • Embodiment 8 The first state and the second state include a weight distribution.
  • the processor 14 acquires the first state of the object to be operated according to the operation robot 13 and/or the end effector 15, in this example, the first state is operated corresponding to the operation robot 13 and/or the end effector 15 being held.
  • the execution state under the current weight distribution; and the second state corresponds to the execution state of the target object distributed by the operation robot 13 and/or the end effector 15; the motion plan is acquired.
  • the execution state may include a position and/or a posture.
  • the operating robot 13 and/or the end effector 15 can adjust the state of the held object to be in the second state, for example, the weight of the object to be manipulated in the end effector 15 when the object is held.
  • the distribution is unsuitable for stable holding, and therefore, the end effector 15 is adjusted to hold the posture of the workpiece to the posture conforming to the second state, so that the end effector 15 performs the holding better based on the weight distribution of the workpiece. Further, the stabilization of the held state in the second state is ensured to perform the subsequent motion, and the placement is performed when the position and/or posture corresponding to the placement task is reached. In another example, if the task is performed to adjust the object to be in the state of conforming to the second state, the placement task is performed. Further, in other examples, it is also possible to provide a requirement for further operation of other robots or devices after being placed according to the second state.
  • Embodiment 9 The first state and the second state include a position and a posture, that is, a posture.
  • the processor 14 is configured to obtain a first state of the object to be operated according to the operating robot 13, in the example, the first state is a current or initial pose; and the target pose of the operated object in the second state; acquiring a motion plan .
  • the operation robot 13 and/or the end effector 15 according to the motion plan after reaching the target pose, the end effector 15 places the object to be manipulated.
  • the operating robot 13 and/or the end effector 15 perform the holding and placing of the object to be manipulated, it is necessary to avoid obstacles in the execution environment or to meet the task requirements performed in a specific position and posture, so that more accurate Operating the object to be manipulated, more preferably meeting complex constraints.
  • the operating robot 13 is used for holding and placing the operating object, including direct operation, for example, the holding includes touching the object to be operated, and the placing includes moving to the untouched operation.
  • the state of the object also includes indirect operations, including completion of holding and placement by the end effector 15 coupled thereto.
  • Embodiment 10 The first state and the second state include a position, an attitude, and a speed.
  • the following example is combined with the picking system, which can be applied to the application scenario of the tally and sorting links in the express transfer field.
  • the bulk goods are placed on the conveyor system for sorting.
  • automation The automation of the transfer center of the shipment is not limited to only partial automation of the conveyor system.
  • this example provides a picking system 10 including a transport mechanism 11, a sensing device 12, an operating robot 13, and at least one processor 14.
  • the transport mechanism 11 has a transport speed V C .
  • the sensing device 12 is configured to sense the object A.
  • the sensing result may include acquiring description data or an image of the object A.
  • the operating robot 13 includes at least one free end provided with an end effector 15.
  • the at least one processor 14 is configured to: obtain a first state of the robot arm 13 according to the object A sensed by the sensing device 12, and place the object A in the second state of the transport mechanism 11 to acquire a motion plan.
  • the first state of the robot arm 13 is obtained based on the object A sensed by the sensing device 12, and may be description data or an image of the object A sensed according to the sensing device 12.
  • the object A can be one or more objects.
  • the second state includes the object A having a target speed V G in the conveying direction of the conveying mechanism 11, wherein the target speed V G corresponds to the conveying speed V C .
  • At least one processor 14 is further configured to control the operation robot 13 to move to the first state, and control the end effector 15 to hold the object A, and control the movement of the robot arm 13 to the second state according to the motion plan, and control the end The actuator 15 places the object A to be transported to the transport mechanism 11.
  • the principles of the present invention are exemplified in the context of the specific application.
  • the picking task is to pick up the goods in the pick-up area S one by one and arrange them on the transport mechanism 11 to facilitate the transport of the transport mechanism 11. It is assumed that the conveying mechanism 11 conveys the goods in the x-axis direction and has a conveying speed V C .
  • the system moves the control operation robot 13 to the pickup area S to hold the object A by the end effector 15, and conveys the object A to the conveyance mechanism 11, and when the goods A are placed on the conveyance mechanism 11,
  • the speed of the conveying mechanism 11 in the x-axis direction is equal to the conveying speed V C , and the speed in the y-axis direction of the conveying mechanism 11 is zero.
  • the operating robot 13 is a tandem robot having a DOF (Degree of Freedom) (hereinafter indicated by the same reference numeral 13).
  • DOF Degree of Freedom
  • the end effector 15 uses a suction cup
  • the sensing device 12 uses a visual sensor to exemplify the operation principle of the system. Therefore, the same reference numerals will be used in the following text. It is to be understood that the examples are not intended to limit the scope of the invention, and the illustrations are not intended to limit the form of the object.
  • the visual sensor 12 can be disposed on the robot arm 13 or at a site location where the global view of the system can be acquired, wherein the global scene includes the pickup area S and the transport mechanism 11. It can be understood that when the transport mechanism 11 is a fixed spatial position relative to the reference frame, the global scene may only include the pickup area S. It will be appreciated that the transport mechanism 11 of the system may be a moveable mechanism, for example, may have wheels.
  • the robot arm 13 can also be a movable mechanism, for example, the robot arm 13 is disposed on the movable base.
  • the above movable mechanism may be a passive moving mechanism with wheels or an active moving mechanism that also has a driving assembly.
  • the visual sensor 12 may include a plurality of, which constitute a visual input system, wherein the global scene acquisition visual sensor 12 including a specific position setting in the scene, and the follow-up visual sensor 12 disposed on the mechanical arm 13, specifically, may be disposed on the machine
  • the free end of the arm can also be placed at the end effector 15.
  • the at least one processor 14 is disposed on the mechanical arm 13 or is a separate control device, and further includes a physical form separately disposed on the mechanical arm 13, the control device, the transport mechanism 11, and the like, the at least one processor 14 and the sensing device 12,
  • the robot arm 13 and/or the end effector communication connection includes wired communication and wireless communication.
  • the processor 14 may also be referred to as a CPU (Central Processing Unit).
  • Processor 14 may be an integrated circuit chip with signal processing capabilities.
  • the processor 14 can also be a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA off-the-shelf programmable gate array
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the transport mechanism 11 is the transport portal of the conveyor system. That is, the example scenario may be the initial step of placing the cargo into the warehouse into the conveyor system, or when the conveyor system has a separate mechanism or subsystem, placing the cargo from one mechanism to another, or from a conveyor subsystem Another conveyor subsystem.
  • the vision sensor 12 acquires information of the pickup area S (S3021) to sense the object to be operated.
  • the providing processor 14 acquires the information providing robot 13 of the operated object A to perform the holding task.
  • the system includes a storage device 16 that includes instructions executable by the at least one processor 14, such that the processor 14 executable functions include: a segmentation processing module 21, a proximity vector acquisition module 22, a path planning module 23, an execution module 25.
  • the second state matching module 26 places the module 27.
  • the segmentation processing module 21 performs segmentation processing based on the image data acquired by the visual sensor 12 to obtain information of the object A (S3023).
  • the object to be operated A is a unit of goods that can be independently executed. It can be understood that it can be a single cargo or a cargo that is packaged together but processed uniformly.
  • the information of the object A includes the face information of the object A. Based on the surface information obtained from the image data, the face that conforms to the hold is selected, and the executed region T where the end effector 15 contacts the face is obtained.
  • the executed region T can be selected as the executed region T by using image data to determine whether the surface information includes a near plane and an area corresponding to the coverage of the end effector 15.
  • the pickup area S has a plurality of goods placed in a mixed manner, and the image information of the pickup area S acquired by the visual sensor 14 obtains at least one segmentation target according to the segmentation algorithm, wherein the segmentation target corresponds to A cargo.
  • the information obtained by the visual sensor 12 is an image having a depth, wherein the visual sensor 12 may be one or more, including a 3D camera, a 2D camera, a laser radar, an RGB-D sensor, and the like.
  • the segmentation algorithm includes a segmentation algorithm based on threshold, edge, and region. It can be flexibly applied according to the characteristics and needs of specific scenarios.
  • a segmentation target corresponds to a cargo.
  • the object A that is suitable for the end effector 15 to perform the holding task is selected. Specifically, an unobstructed segmentation target, a segmentation target close to the end effector 15, and the like can be selected. Further, the vision system needs to reconstruct a three-dimensional model of the target object for subsequent execution.
  • the end effector 15 is brought into contact with the executed region T of the object A based on the information of the object A (S3035).
  • the selected consideration factors may include an area in which the object A has a near-plane feature.
  • the end effector 15 may also include an area that meets the proximity and contact of the end effector 15, such as the end effector performing the hold task with a collision free path.
  • the end effector 15 being a suction cup, may include a region in which the suction cup can cover the object to be manipulated, the larger the coverage area, the better the quality of the grip, for the end effector 15
  • the parameter selection of the gripping tool for example, for the two-finger gripping tool, a pair of faces having a relatively parallel shape are selected according to the dividing target, and the like.
  • It may also include conditions after the hold, the face with the label meets a particular orientation, and the like. It can be understood that the conditions and factors of the selection reference can be flexibly set according to specific application scenarios.
  • the approach vector acquisition module 22 is configured to calculate the proximity vector of the end effector 15 approaching the executed region T according to the executed region T selected by the segmentation processing module 21 or according to the three-dimensional model of the object A (S3037).
  • This example uses a normal vector as the proximity vector.
  • the proximity vector can be calculated from the executed region T and the parameters of the end effector 15.
  • the parameters of the end effector 15 include a reference point, i.e., defined consistent reference information representative of the position of the end effector 15, including relative position information with the robot arm 13 at the reference coordinates of the defined end effector 15.
  • the joint of the end effector 15 to the robot arm 13 may be used, or when the end effector 15 is a complicated robot, the angle value of each joint of the robot may be included, and the like. Specifically, it can be flexibly set according to the specific application scenario and the end effector 15 used.
  • the path planning module 23 obtains the first execution path of the end effector 15 to the first state based on the proximity vector obtained by the proximity vector acquisition module 22 and the current pose of the end effector 15 (S3039).
  • the first state includes a pose when the end effector 15 holds the object A according to the proximity vector. For convenience of explanation, it is referred to herein as the first pose. In one embodiment, it is assumed that when the reference point of the end effector 15 uses the joint of the end effector 15 and the robot arm 13, the end effector 15 is obtained in the executed area T according to the position of the executed region T in the world coordinate system.
  • the end position of the robot arm 13 is obtained, and the joint angle of the robot arm 13 at the end position is obtained according to the inverse kinematics algorithm.
  • the first state of the robot arm 13 is obtained based on the first pose. According to the first pose and the current pose, the motion plan of the current pose to reach the first pose is performed.
  • the execution module 25 controls the robot arm 13 to move to the first state according to the first execution path, and controls the end effector 15 to hold the object A (S3041).
  • the end effector 15 is controlled to hold the object A.
  • control initiates adsorption.
  • the control initiates the gripping. It is feasible that each of the execution units to be driven may be separately provided with a drive or may be controlled by a unified drive system.
  • controlling the movement of the robot arm 13 to the second state according to the motion planning may include the following embodiments.
  • the path planning module 23 is further configured to obtain a second execution path in which the end effector 15 reaches the second state according to the current pose of the end effector 15 and the target position of the transport mechanism 11 included in the second state (S3043). It can be understood that the target location includes a specific location as well as a location area.
  • the second state matching module 26 is configured to obtain a trajectory plan according to the second execution path and the target speed V G of the second state (S3045).
  • the target speed V G corresponds to the conveying speed V C of the conveying mechanism 11, including the target speed V G being equal to the conveying speed V C , or the target speed V G falling within a threshold range of the conveying speed V C .
  • the execution module 25 is further configured to control the robot arm 13 to execute according to the trajectory planning of the second state matching module 26 after the object A is acquired (S3047).
  • control end effector 15 places the operated object A on the transport mechanism 11, and may include the following embodiments.
  • the module 27 is placed, and when the end effector 15 reaches the second state under the control of the execution module 25, the end effector 15 is controlled to place the object A to be operated (S3049).
  • the end effector 15 is a suction cup, control closes the suction.
  • the control closes the grip.
  • the object A is placed in operation transmitting mechanism 11 has a uniform conveying speed of the conveying mechanism V 11 C-motion state.
  • the operated object A has a stable and ordered state on the transport mechanism 11. Good, efficient and automated operating conditions are provided for subsequent operations performed on the transport mechanism 11.
  • the system further includes a default state, the default state including a default location and a default speed V D .
  • the at least one processor 14 acquires the motion plan, and further includes: the at least one processor 14 acquires the first motion plan according to the first state and the default state, and acquires the second motion plan according to the default state and the second state (S402).
  • the default state and the second state are known information, and therefore, the second motion plan is a relatively fixed execution process.
  • the second motion plan may be stored in the storage device 16.
  • the known second motion plan may be directly acquired to complete the second state.
  • the first motion planning can be performed with the known default state (S402), and the control robot arm can be moved to the first state, and the end effector of the robot arm 13 can be controlled.
  • 15 holds the object A (S404).
  • the robot arm movement to the default state according to the first motion plan can be performed (S406).
  • acquiring the second motion plan according to the default state and the second state includes: the second motion plan is a pre-stored control command.
  • the control end effector 15 places the operated object A on the transport mechanism 11 (S410).
  • the movement of the robot arm 13 to the second state (S408) according to the motion planning may include the following embodiments.
  • the path planning module 23 is further configured to obtain a third execution path in which the end effector 15 reaches the default state according to the current pose of the end effector 15 and the default position included in the default state (S4043).
  • the default state can also include the default speed V D .
  • the system further includes a default state matching module 24 for performing trajectory planning according to the third execution path and the default speed V D of the default state (S4045).
  • the default state includes the default speed V D
  • the second motion plan includes a fourth execution path from the default position to the target position, and a trajectory plan of the target speed V G when the default speed V D of the default position reaches the target position (S4049).
  • the execution module 25 is further configured to control the robot arm 13 to execute according to the trajectory planning of the default state matching module 24 after the object A is acquired (S4047). And after reaching the default state, the trajectory planning control robot 13 according to the second motion plan is executed (S4051).
  • the second state may further include the position at which the object A is placed at the transport mechanism 11 and the distance from the previous cargo is greater than or equal to the first threshold.
  • the distance between the target location and the previous shipment is greater than or equal to the first threshold, and may include an implementation manner.
  • the execution time T is obtained according to the first threshold and the transmission speed V C. After the system completes the task according to the placement module 27, The next round of the loop is performed, and the time for obtaining the task and placing the task is planned and executed using the execution time T.
  • the loop includes at least one processor 14 according to the data acquired by the vision sensor 12, and according to the segmentation processing module 21, the proximity vector acquisition module 22, the path planning module 23, and the execution module 25, according to the first state.
  • the placement task is performed according to the second state according to the path planning module 23, the second state matching module 26, and the execution module 26. It can be understood that the execution process of the foregoing modules may be performed in sequence, or may be performed in parallel.
  • at least one processor 14 includes the segmentation processing module 21 and the proximity vector acquisition module 22 acquiring synchronously when the other modules operate the current object A1. After the next object A2 is completed, after the current task of the object A1 is completed, the acquisition task can be directly executed according to the acquired acquired A2. Improve system execution efficiency.
  • the path planning module 23 can also perform the path planning according to the first state synchronously before the completion of the placement task of the current object A1, so that the system completes the placement of the current execution A1.
  • the execution module 25 can directly execute the path plan of the next object A2 according to the first state. It is to be understood that the foregoing is illustrative only and is not intended to limit the scope of the invention. In the synchronous execution mode, not only the acquisition of the acquired task information of the next object A2 is acquired synchronously, but also the holding task of acquiring a plurality of goods to be executed may be included.
  • the placement task adopts the mode with the default state
  • the acquisition task of the next object or the next plurality of objects and the placement task can be obtained synchronously.
  • the second state may also include that the location of the tag is at a predetermined orientation.
  • the at least one processor 14 is further configured to obtain the location of the tag of the object A according to the data acquired by the sensing device 12.
  • the goods are tagged with tags that are used to identify the cargo information and provide the information needed to convey the delivery system, such as the cargo identification, origin, destination, weight, size, and the like. After entering the conveyor system, the requirements for label identification will be involved. Therefore, in the system holding task and the placement task, the location of the label on the goods is also known, and the task is planned and placed according to the position of the label, so that the goods are placed on the label.
  • the orientation of the label conforms to the orientation of the demand.
  • the orientation of the demand is such that the label is not at the bottom (the surface in contact with the transport mechanism 11).
  • the orientation of the demand is such that the label faces any direction in which the scanning device is provided.
  • the tag on the goods is identified based on the image information of the pickup area S obtained by the sensing device 12. Specifically, it can be matched and identified according to the special identification and shape of the label.
  • the location is in a preset orientation according to the location of the tag and the location of the tag defined by the second state is selected.
  • the surface on which the execution region T is located is such that the label of the goods can be placed in the preset orientation when the end effector 15 is held and can be placed on the transport mechanism 11. That is, the orientation of the label corresponds to the orientation with the scanning device.
  • the following is an exemplary illustration of a typical scenario. When the scanning device is above the transport mechanism 11, that is, the position where the label is located is at the top surface (the surface opposite the contact surface of the transport mechanism).
  • the division processing module 21 divides a plurality of division targets based on the image data of the pickup area S, selects a division target having no occlusion and has a label, and selects the executed region T on the surface having the label. In this manner, the posture of the end effector 15 can be placed vertically with respect to the transporting mechanism 11 when the placement task is performed.
  • the unidentified segment identifies the tag on the target, but the location of the tag causes the end effector 15 to contact the face where the tag is located, and the executed region T can be selected on the face without the collision problem.
  • the posture of the end effector 15 in the second state is obtained, so that the position at which the end effector 15 is placed according to the posture conforms to the preset orientation.
  • the scanning device is the aforementioned five-way device
  • the executed region T on the collision-free surface can be arbitrarily selected, and in the general placement posture, that is, the second state end
  • the posture of the actuator 15 is all lowered by the direction of the vertical conveying mechanism 11.
  • the orientation of the label can be met to scan the device in either direction, not the bottom surface. It can be understood that the planning restriction can be reduced when the general placement posture is adopted.
  • the target speed V G may be less than the transmission speed V C .
  • At least one processor 14 further includes an acceleration module 28, according to a second state for controlling the robot arm 13 is moved to the target position, and controlling the robot arm 13 in the conveying direction of the conveying mechanism 11 is accelerated to the conveying speed V C.
  • the acceleration module 28 according to accelerate to the conveying speed V C, the placement module 27 to complete the placing operation.
  • the picking system of the various embodiments provided by the above embodiments of the present invention provides an automatic picking system in combination with the conveying mechanism, which realizes that the conveying speed of the goods placed on the conveying mechanism matches the conveying mechanism.
  • the method of manually picking and placing on the transmission mechanism solves the problem that the manual operation is difficult to match the high-speed operation of the transmission mechanism, and it is difficult to accurately ensure the high-speed operation of the goods, and maintain the stability after the object is placed.
  • the picking system provided by the embodiment of the invention ensures the stability of the object placed on the transport mechanism, and the orderly and high efficiency of the system operation.
  • the embodiment of the present invention further provides a picking method 200A. As shown in FIG. 3, the method is implemented in one or more computer systems, including performing steps:
  • S202 Obtain a motion plan according to the first state of the robot for operation and the second state of the object to be placed in the transport mechanism.
  • the second state includes the object to be operated having a target speed V G in the conveying direction of the conveying mechanism.
  • the target speed V G corresponds to the transmission speed V C of the transport mechanism.
  • S204 The control operation moves the robot to the first state, and controls the end effector to obtain the object to be operated.
  • step S202 may be processed in parallel with step S204. It is also included that steps S202 and S204 are alternately or interleaved, and S206 can be executed after both are completed.
  • the first state of the operating robot according to the object to be operated in step S202, as shown in FIG. 5, may include:
  • S3023 Perform segmentation processing according to the acquired data to obtain information of the object to be operated.
  • the method further includes:
  • S3035 Obtain an executed area where the end effector contacts the object to be manipulated based on the information of the object to be manipulated.
  • step S204 includes:
  • S3039 Obtain a first execution path of the end effector to the first state according to the obtained proximity vector and the current pose of the end effector.
  • control operation robot moves to the first state according to the first execution path, and controls the end effector to obtain the executed object.
  • the first state includes an end effector for grasping the pose of the operated object.
  • the second state may include the object being placed at a target location of the transport mechanism. It may also include that the position at which the object to be placed is placed at the transport mechanism is greater than or equal to the first threshold from the previous cargo.
  • the second state may further include the position where the label is located at a preset orientation.
  • step S206 controls the operation robot to move to the second state according to the motion planning, and may include the steps of:
  • S3043 Obtain a second execution path of the end effector reaching the second state according to the current pose of the end effector and the target position of the transport mechanism included in the second state.
  • step S208 controlling the end effector to place the operated object on the transport mechanism comprises:
  • controlling the operation robot to move to the second state according to the motion planning in step S206 further comprising: controlling the operation robot to move to the target position included in the second state according to the second state, and controlling the operation robot along the transport mechanism The conveying direction is accelerated to reach the conveying speed V C .
  • the following steps may be included:
  • the picking method further includes a default state, including a default position and a default speed V D .
  • Obtaining the motion plan in step S202 further includes: S402: acquiring the first motion plan according to the first state and the default state, and acquiring the second motion plan according to the default state and the second state.
  • the picking method may further include steps S3021 to S3041 of the method 300, performing the holding task, and the method 500 performing the placing task.
  • method 500 includes:
  • S5043 Obtain a third execution path that the end effector reaches the default state according to the current pose of the end effector and the default position included in the default state.
  • S5045 Perform trajectory planning according to the third execution path and the default speed V D of the default state.
  • S5047 The control operation is performed by the robot according to the trajectory planning.
  • S5049 The fourth execution path according to the default position to the target position, and the trajectory plan of the target speed V G of the target position by the default speed V D of the default position.
  • S5051 The control operation is performed by the robot according to the trajectory planning.
  • the picking method of the various embodiments provided by the above embodiments of the present invention provides an automatic picking method in combination with the conveying mechanism, which realizes that the conveying speed of the goods placed on the conveying mechanism matches the conveying mechanism.
  • the method of manually picking and placing on the transmission mechanism solves the problem that the manual operation is difficult to match the high-speed operation of the transmission mechanism, and it is difficult to accurately store the goods under high-speed operation and maintain the stability after the object is placed.
  • the picking method provided by the embodiment of the present invention ensures the stability of the object placed on the transport mechanism, and the orderly and efficient operation of the overall operation.
  • the holding and placement system 20 provided by the embodiment of the present invention can also be integrated into the robot.
  • the robot 30 includes a sensing device 12, an operating robot 13, and at least one processor 14.
  • the sensing device 12 is configured to sense an object to be operated.
  • the operating robot 13 includes a free end provided with an end effector 15.
  • the operation robot 13 includes a series robot, a parallel robot, and various options in combination with the mobile robot, and the operation of the end effector 15 on the object to be operated can be realized.
  • the tandem robot can be a robotic arm with 6 degrees of freedom.
  • At least one processor 14 is configured to execute the holding and placing method, including: obtaining a first state of the operating robot 13 and/or the end effector 15 according to the object to be operated, and performing the placing of the object to be operated Two states, get exercise planning.
  • the first state and the second state comprise position, attitude, velocity, acceleration, angular velocity, angular acceleration, geometric shape and/or weight distribution.
  • the method further includes: controlling the operating robot 13 and/or the end effector 15 to move to the first state, and controlling the end effector 15 to hold the operated object, and controlling the operating robot 13 and/or according to the motion planning control.
  • the end effector 15 is moved to the second state, and the end effector 15 is controlled to place the object to be manipulated.

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Robotics (AREA)
  • General Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Manipulator (AREA)

Abstract

一种拣货系统(10)，包括传送机构(11)；感知装置(12)，用于感测被操作物；操作用机器人(13)，其自由端设置有末端执行器(15)，至少一个处理器(14)，用于根据被操作物得到操作用机器人的第一状态，以及将该被操作物放置于传送机构(11)的第二状态，获取运动规划；第二状态包括该被操作物沿传送机构(11)的传送方向具有目标速度，其中，目标速度对应传送速度；控制操作用机器人(13)运动到第一状态并控制末端执行器(15)获持被操作物；控制操作用机器人(13)运动到第二状态；控制末端执行器(15)放置被操作物于传送机构(11)。系统使得被操作物放置于传送机构(11)时具有与传送机构(11)一致的运动状态。

Description

拣货方法、系统及其应用的获持与放置系统、机器人 技术领域
本发明涉及机器人控制领域，尤其涉及一种拣货方法及系统，以及其应用的一种获持与放置系统、机器人。
背景技术
工业4.0的概念是将制造业向智能化转型。目前，物流仓储业的自动化主要采用复杂的传送带系统，实现仓储中的货物自动化输送。该方式虽已大幅提升了仓储的运作效率，但是，目前仍存在大量人工环节，执行拣货，将货物于一个运作端放置于另一个运作端。例如，货物进入仓储的初始环节，将卸载的货物一一拣取放置于传送系统的输入区域，以使货物进入传送系统的自动化运作。以及中间环节，涉及到需要将货物由一个传送带子系统输出转至另一个传送带子系统等需要拣货的环节。据此，现有传送带系统的自动化体系，存在以下问题：
1、自动化仅限于传送带系统，拣货环节仍为人工操作。
2、人工操作为重复性体力劳动，执行效率会依据个人体能以及劳动时间产生不同影响，因此，系统运作受限于人工执行力。
3、对于高速运转的传送带系统，人工操作拣货放置于传送带的速度难以匹配，则会导致传送带系统的效率未能真正得以实施。
因此，改进人工拣货环节，是充分实现仓储自动化、提升运作效率的一个重要环节，是有待解决的问题。
发明内容
有鉴于背景技术存在的问题，本发明的实施方式提供了一种拣货系统，包括：
传送机构，所述传送机构具有传送速度V C；
感知装置，用于感测被操作物；
操作用机器人，包括自由端，该自由端设置有末端执行器，
至少一个处理器，用于：
根据所述感知装置感测的所述被操作物得到所述操作用机器人的第一状态，以及将该被操作物放置于所述传送机构的第二状态，获取运动规划；所述第二状态包括该被操作物沿所述传送机构的传送方向具有目标速度V G，其中，目标速度V G对应所述传送速度V C；
控制所述机械臂运动到所述第一状态，并控制所述末端执行器获持所述被操作物；
根据所述运动规划控制所述操作用机器人运动到所述第二状态；
控制所述末端执行器放置所述被操作物于所述传送机构。
本发明实施方式还提供了一种拣货方法，实施于一个或多个计算机系统，包括执行步骤：
根据被操作物得到操作用机器人的第一状态，以及将该被操作物放置于传送机构的第二状态，获取运动规划；所述第二状态包括该被操作物沿所述传送机构的传送方向具有目标速度V G，其中，目标速度V G对应所述传送机构的传送速度V C；
控制所述操作用机器人运动到所述第一状态，并控制所述末端执行器获持所述被操作物；
根据所述运动规划控制所述操作用机器人运动到所述第二状态；
控制所述末端执行器放置所述被操作物于所述传送机构。
本发明实施方式还提供了一种获持与放置系统，包括：
感知装置，用于感测被操作物；
操作用机器人，包括自由端，该自由端设置有末端执行器，
至少一个处理器，用于：
根据所述被操作物得到所述末端执行器的第一状态，以及将该被操作物执行放置所处的第二状态，获取运动规划；所述第一状态与所述第二状态包括位置、姿态、速度、加速度、角速度、角加速度、几何外形和/或重量分布；
控制所述操作用机器人运动到所述第一状态，并控制所述末端执行器获持所述被操作物；
根据所述运动规划控制所述操作用机器人运动到所述第二状态；
控制所述末端执行器放置所述被操作物。
本发明实施方式还提供了一种机器人，包括：
感知装置，用于感测被操作物；
操作用机器人，包括自由端，该自由端设置有末端执行器，
至少一个处理器，用于：
根据所述被操作物得到所述末端执行器的第一状态，以及将该被操作物执行放置所处的第二状态，获取运动规划；所述第一状态与所述第二状态包括位置、姿态、速度、加速度、角速度、角加速度、几何外形和/或重量分布；
控制所述操作用机器人运动到所述第一状态，并控制所述末端执行器获持所述被操作物；
根据所述运动规划控制所述操作用机器人运动到所述第二状态；
[根据细则91更正 27.02.2018]　
控制所述末端执行器放置所述被操作物。
[根据细则91更正 27.02.2018]　
[根据细则91更正 27.02.2018]　
[根据细则91更正 27.02.2018]　
本发明实施方式提供的拣货系统及拣货方法，实现了放置于传送机构的货物与传送机构的传送状态相匹配。相比现有技术由人工完成拣货并放置于传动机构的方式，解决了人工操作难以匹配高速运行的传送机构，以及难以满足高速运行状态下准确放置货物，并保持物体放置后的稳定性。就该问题而言，本发明实施方式提供的拣货系统及方法，保证了物体放置于传送机构的稳定性，以及系统运作的有序性及高效性。同时，本发明实施方式还提供了一种应用于拣货系统与方法的获持与放置系统及机器人，实现了一种通用、灵活的获持、放置方案，可以应对不同应用场景对于第一状态至第二状态的不同需求，进行自主规划及实现。
附图说明
下列附图用于结合具体实施方式详细说明本发明的各个实施方式。应当理解，附图中示意出的各元件并不代表实际的大小及比例关系，仅是为了清楚说明而示意出来的示意图，不应理解成对本发明的限制。
图1为本发明实施例提供的拣货系统结构示意图。
图2为本发明实施例提供的拣货场景示意图。
图3为本发明第一实施例提供的拣货方法流程示意图。
图4为本发明第二实施例提供的拣货方法流程示意图。
图5为本发明第三实施例提供的拣货方法流程示意图。
图6为本发明第四实施例提供的拣货方法流程示意图。
图7为本发明第五实施例提供的拣货方法流程示意图。
图8为本发明实施例提供的获持与放置系统结构示意图。
图9为本发明实施例提供的机器人结构示意图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合多个实施方式及附图，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施方式仅仅用以解释本发明，并不用于限定本发明。
本发明实施例提供一种获持与放置系统20，如图8，包括感知装置12，操作用机器人13，以及至少一个处理器14。其中，感知装置12用于感测被操作物。操作用机器人13，包括自由端，该自由端设置有末端执行器15。该操作用机器人13包括串联机器人，并联机器人，以及结合移动机器人的多种选择，可以实现末端执行器15对被操作物的操作即可。例如，串联机器人可以为具有6自由度的机械臂。至少一个处理器14用以执行获持与放置方法，包括：根据被操作物得到操作用机器人13和/或末端执行器15的第一状态，以及欲将该被操作物执行放置所处的第二状态，获取运动规划。其中，第一状态与第二状态包括位置、姿态、速度、加速度、角速度、角加速度、几何外形和/或重量分布。该方法还包括：控制操作用机器人13和/或末端执行器15运动到所述第一状态，并控制末端执行器15获持被操作物，以及根据运动规划控制控制操作用机器人13和/或末端执行器15运动到第二状态，以及控制末端执行器15放置被操作物。
本发明实施方式提供的上述获持与放置系统，可以根据场景需求，灵 活应对将被操作物由第一状态操作至第二状态，包括任意由位置、姿态、速度、加速度、角速度、角加速度、几何外形、重量分布任一特征或特征组合构建的应用需求。为了充分理解本发明原理，以下例举部分实施例。
感知装置12包括视觉传感器。至少一个处理器14，还用于根据视觉传感器获取的数据进行分割处理，得到被操作物的信息；或，用于根据被操作物的三维模型，得到被操作物的信息。
至少一个处理器14，还用于根据被操作物的信息得到末端执行器接触该被操作物的执行参数。根据该执行参数执行控制操作用机器人13运动到所述第一状态，并控制末端执行器15获持被操作物。以下将根据第一状态到第二状态的不同变化参数，获得执行参数的方法加以具体示例性说明。
为了便于理解本发明方案，以下结合一些应用场景阐述本发明包括的多种实施方式的示例。需要说明的是，以下实施例仅用于示例性说明，并不用于限定本发明范围。
实施例一：第一状态及第二状态包括位置。
该实施例，结合物流仓储应用场景而言，被操作物包括货物，将货物由货源区域移动到目的区域。例如，操作用机器人13执行将货物由一个传送带子系统的输出端O转移至另一个传送带子系统的输入端I。感知装置12感测输出端O的被操作物。至少一个处理器14根据感知装置12感测到的被操作物，得到该被操作物的操作参数，操作参数包括被操作物的位置。则得到末端执行器15到达该被操作物的位置的第一状态。根据该第一状态包括的被操作物的位置，以及输入端I的目标位置，获取被操作物的位置到目标位置的运动规划。例如，一种场景下，当采用末端执行器15为随动吸盘，不论以何种姿态，只要末端执行器15趋近被操作物，即 可自适应获持被操作物。
实施例二：第一状态及第二状态包括姿态。
该实施例中，当某一场景需要将货物翻转实现某操作需求，例如，需要将货物具有信息的一面朝向特定方位。最常见的场景包括将货物带有标签的一面翻转至具有扫码装置的目标朝向。处理器14根据操作用机器人13用于获持被操作物的第一状态，该示例中，第一状态包括获持被操作物的当前姿态，以及被操作物标签朝向目标朝向时末端执行器的目标姿态，即该示例中的第二状态，获取运动规划。包括控制操作用机器人13各关节角的转动，实现末端执行器15达到目标位姿，从而实现被操作物标签对应目标朝向。该示例还可以结合到多操作用机器人协作。例如，当获持被操作物的第一操作用机器人，在某些情形下，获持被操作物的被执行区域，与标签所在的面为相对面，而目标朝向需要将被执行区域与放置区域的承载面接触，由于机械限制，无法实现。则可以结合一用于执行前述翻转的第二操作用机器人，实现被操作物的姿态变化。例如，第一操作用机器人将被操作物以非被执行区域所在面交给第二操作用机器人获持，第二操作用机器人即可通过运动规划实现目标姿态，执行放置，使得被操作物的标签朝向所需的方位。
实施例三：第一状态及第二状态包括速度。
处理器14根据操作用机器人13用于获持被操作物的第一状态，该示例中，第一状态为当前速度，以及第二状态下被操作物的目标速度，获取运动规划。当末端执行器15获持被操作物后，操作用机器人13根据运动规划，执行运动使得运动速度达到目标速度后，末端执行器15放置被操作物。使得被操作物被放置时具有目标速度。
实施例四：第一状态及第二状态包括加速度。
处理器14根据操作用机器人13用于获持被操作物的第一状态，该示例中，第一状态为当前或初始加速度；以及第二状态下被操作物的目标加速度；获取运动规划。操作用机器人13根据运动规划，达到目标加速度后，末端执行器15放置被操作物。对于某些场景，操作用机器人13执行放置后，被操作物落于具有加速度的传送带时，使得被操作物被放置时更优地匹配传送带加速度。从而保证被操作物放置后的相对稳定性。
实施例五：第一状态及第二状态包括角速度。
处理器14根据操作用机器人13和/或末端执行器15用于获持被操作物的第一状态，该示例中，第一状态为当前或初始角速度；以及第二状态下被操作物的目标角速度；获取运动规划。操作用机器人13和/或末端执行器15根据运动规划，达到目标角速度后，末端执行器15放置被操作物。对于某些场景，操作用机器人13和/或末端执行器15执行放置被操作物时，需要具有角速度限制需求，使得被操作物被放置时具有目标角速度，从而进入某放置区域或空间时，更优地匹配放置区域或放置空间的特性。
实施例六：第一状态及第二状态包括角加速度。
处理器14根据操作用机器人13和/或末端执行器15用于获持被操作物的第一状态，该示例中，第一状态为当前或初始角加速度，以及第二状态下被操作物的目标角加速度，获取运动规划。操作用机器人13和/或末端执行器15根据运动规划，达到目标角速度后，末端执行器15放置被操作物。对于某些场景，操作用机器人13和/或末端执行器15执行放置被操作物时，需要具有角加速度限制需求，使得被操作物被放置时具有目标角加速度，从而进入某放置区域或空间时，更优地匹配放置区域或放置空间以及放置的运动特性。
实施例七：第一状态及第二状态包括几何外形。
处理器14根据操作用机器人13和/或末端执行器15用于获持被操作物的第一状态，该示例中，第一状态对应于操作被操作物当前几何外形的执行状态；以及第二状态对应于操作被操作物目标几何外形的执行状态；获取运动规划。其中，执行状态可以包括位置和/或姿态。操作用机器人13和/或末端执行器15根据运动规划，达到目标执行后，末端执行器15放置被操作物。对于某些应用场景，操作用机器人13和/或末端执行器15执行获持与放置被操作物，以进一步用于结合被操作物的其他任务，例如被操作物为打开的箱子时，该其他任务可以为打包。该实施示例下，若该打包任务具体为，操作用机器人13将箱子敞开的盖板合上。也可以为操作用机器人13通过末端执行器15将箱子敞开的盖板合上。例如，第一状态可以为末端执行器15接触到盖板外侧的位置，或末端执行器15以特定姿态，例如，根据盒子敞开时盖板的位姿，第一状态为末端执行器15以垂直盖板外侧接触盖板中心的第一位置和/或姿态，第二状态，为末端执行器运动至盖板合上状态时的位置和/或特定姿态。其中，位置和/或姿态，可以包括使得末端执行器15到达对应该位置和/或姿态时，操作用机器人13对应的位置和/或姿态。当然，若末端执行器15对应到达所需的位置和/或姿态，属于末端执行器15的运动范围内，则无需操作用机器人13运动到相应位置和/姿态以使末端执行器15到达所需的位置和/或姿态。当操作用机器人13根据运动规划达到第二状态后，若箱子具有锁扣装置，盖板合上后即可启动锁扣，末端执行器15放置可以为恢复初始位置和/或姿态，完成打包。其他实施例中，例如箱子为纸箱时，也可以通过打包设备，如胶带封装设备、钉固设备将盖板封固，配合完成打包。可以理解的是，上述实施例仅用于阐述原理，并不用于限定本方法的保护范围。
实施例八：第一状态及第二状态包括重量分布。
处理器14根据操作用机器人13和/或末端执行器15获持被操作物的第一状态，该示例中，第一状态对应于操作用机器人13和/或末端执行器15获持的被操作物当前重量分布下的执行状态；以及第二状态对应于操作用机器人13和/或末端执行器15获持的被操作物处于目标重量分布的执行状态；获取运动规划。其中，执行状态可以包括位置和/或姿态。该示例中，操作用机器人13和/或末端执行器15可以调整获持的被操作物的状态达到第二状态，例如，获持被操作物时，被操作物于末端执行器15中的重量分布，不适宜稳固获持，因此，调整末端执行器15获持被操作物的姿态至符合第二状态的姿态，使得末端执行器15根据被操作物的重量分布，更优的执行获持。进一步的，保证第二状态下获持状态的稳定以执行后续运动，达到放置任务对应的位置和/或姿态时，执行放置。另一示例中，如执行任务即为将被操作物调整至符合第二状态的状态时，即执行放置任务。进一步的，其他示例中，也可以为依据第二状态放置后，提供符合其他机器人或装置进一步操作的要求。
实施例九：第一状态及第二状态包括位置以及姿态，即位姿。
处理器14根据操作用机器人13用于获持被操作物的第一状态，该示例中，第一状态为当前或初始位姿；以及第二状态下被操作物的目标位姿；获取运动规划。操作用机器人13和/或末端执行器15根据运动规划，达到目标位姿后，末端执行器15放置被操作物。对于某些场景，操作用机器人13和/或末端执行器15执行获持以及放置被操作物时，需要避免执行环境中的障碍，或符合以特定位置和姿态执行的任务需求，使得更准确的操作被操作物，更优地满足复杂限定条件。
可以理解的是，对于简单的操作，操作用机器人13用于获持与放置备操作物，包括直接操作，例如，获持包括触碰到被操作物，放置包括运 动至未触碰到被操作物的状态；还包括间接操作，包括通过与其连接的末端执行器15完成获持与放置。
实施例十：第一状态及第二状态包括位置，姿态以及速度。
以下结合拣货系统加以示例说明，可应用于快件中转场中理货、分拣环节的应用场景，例如，对于进入快件中转场的批量货物，一一获持放置于传送带系统，实现分拣的自动化。使得快件中转场的自动化不仅仅限于传送带系统的部分自动化。
如图1所示，该示例提供一种拣货系统10，包括传送机构11，感知装置12，操作用机器人13，以及至少一个处理器14。其中，传送机构11具有传送速度V C。感知装置12，用于感测被操作物A。感测结果可以包括获取被操作物A的描述数据或图像。操作用机器人13包括至少一自由端，该自由端设置有末端执行器15。至少一个处理器14，用于：根据感知装置12感测的被操作物A得到机械臂13的第一状态，以及将该被操作物A放置于传送机构11的第二状态，获取运动规划。根据感知装置12感测的被操作物A得到机械臂13的第一状态，可以为根据感知装置12感测的被操作物A的描述数据或图像。被操作物A可以是一个或多个物体。其中，第二状态包括该被操作物A沿传送机构11的传送方向具有目标速度V G，其中，目标速度V G对应传送速度V C。至少一个处理器14还用于，控制操作用机器人13运动到第一状态，并控制末端执行器15获持被操作物A，以及根据运动规划控制机械臂13运动到第二状态，以及控制末端执行器15放置被操作物A于传送机构11。
为便于理解本发明包括的方案，以下将结合到具体应用场景加以示例性阐述本发明原理。如图2场景示意图所示，拣货任务为，将取货区域S的货物，一一独立拣放至传送机构11上，便于传送机构11的输送。假设 传送机构11沿x轴方向传送货物，并具有传送速度V C。则该系统将控制操作用机器人13运动到取货区域S通过末端执行器15获持被操作物A，并将被操作物A运送到传送机构11上，且货物A放置传送机构11时，沿传送机构11的x轴方向的速度等于传送速度V C，沿传送机构11的y轴方向的速度为0。
具体的，该示例中，操作用机器人13以具有6自由度(DOF，Degree of Freedom)的串联机械臂(以下采用相同标识13示意)。其中，末端执行器15以吸盘，感知装置12以视觉传感器，进行示例性说明该系统的运作原理。因此，下述文本中将采用相同的标识表示。可以理解的是，示例并不用于限定本发明保护范围，图示也并不用于限定物体形态。
视觉传感器12可以设置于机械臂13，或者设置于可获取系统全局景象的场地位置，其中，全局景象包括取货区域S、传送机构11。可以理解的是，当传送机构11为相对参考系固定不变的空间位置时，全局景象可以仅包括取货区域S。可以理解的是，该系统的传送机构11可以为可移动的机构，例如，可以具有轮子。机械臂13也可以为可移动的机构，例如，机械臂13设置于可移动底座。以上可移动机构均可以为具有轮子的被动移动机构，也可以为还具有驱动组件的主动移动机构。机械臂13视觉传感器12设置于机械臂13时，可以通过机械臂运动到视觉传感器12可以获取取货区域S的空间范围。视觉传感器12可以包括多个，构成视觉输入系统，其中，包括场景中特定位置设定的全局景象获取视觉传感器12，以及设置于机械臂13的随动视觉传感器12，具体的，可以设置于机械臂的自由端，也可以设置于末端执行器15。
至少一个处理器14包括设置于机械臂13，或者为独立的控制装置，还包括分离地设置于机械臂13、控制装置、传送机构11等物理形式，该 至少一个处理器14与感知装置12、机械臂13和/或末端执行器通信连接，包括有线通信、无线通信方式。当处理器14为多个时，彼此通信连接。处理器14还可以称为CPU(Central Processing Unit，中央处理单元)。处理器14可能是一种集成电路芯片，具有信号的处理能力。处理器14还可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(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。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。
此示例中，传送机构11为传送带系统的传送入口。即，该示例场景可以为货物进入仓库的置入传送带系统的初始环节，或者传送带系统具有分离的机构或子系统时，将货物从一个机构置入另一个机构，或从一个传送带子系统置入另一个传送带子系统。
以下可结合图3提供的拣货方法300进行示例性阐述。
视觉传感器12，获取取货区域S的信息(S3021)，以感测被操作物。作为视觉输入信息，提供处理器14获取被操作物A的信息提供机械臂13执行获持任务。
具体的，系统包括存储装置16，数据存储包括由至少一个处理器14可执行的指令，使得处理器14可执行功能包括：分割处理模块21，接近向量获取模块22，路径规划模块23，执行模块25，第二状态匹配模块26，放置模块27。
分割处理模块21，根据视觉传感器12获取的图像数据，进行分割处理，以得到被操作物A的信息(S3023)。其中，被操作物A为独立可被执行获持的货物单位。可以理解的是，可以为单独的货物，也可以为打包在一起的多个货物但被统一处理的货物。
具体的，被操作物A的信息包括被操作物A的面信息。根据图像数据得到的面信息，选择符合获持的面，并得到末端执行器15接触该面的 被执行区域T。其中，被执行区域T可通过图像数据，判断面信息是否包括近平面、对应末端执行器15覆盖范围的区域，则选择为被执行区域T。
例如，图像示例如图1所示，取货区域S具有混杂放置的多个货物，视觉传感器14获取的取货区域S的图像信息，根据分割算法得到至少一个分割目标，其中，分割目标对应于一个货物。具体的，视觉传感器12获得的信息为具有深度的图像，其中，视觉传感器12可以为一个，也可以为多个，包括3D相机、2D相机、激光雷达以及RGB-D传感器等。例如，分割算法包括基于阈值、边缘、区域的分割算法。可以依据具体场景的特征、需求而灵活应用。根据获得的至少一个分割目标，其中，一分割目标对应一货物。根据该分割目标包括的区域，选择适合末端执行器15执行获持任务的被操作物A。具体的，可以选择无遮挡的分割目标，接近末端执行器15的分割目标，等。进一步的，视觉系统需要重建目标对象的三维模型，用于后续的执行。选择被操作物A后，根据被操作物A的信息得到末端执行器15接触该被操作物A的被执行区域T(S3035)。具体的，选择的考量因素可以包括，被操作物A具有近平面特征的区域。也可以包括，符合末端执行器15接近并接触的区域，如，末端执行器执行获持任务具有无碰撞路径。还以包括末端执行器15的特征，例如，对于末端执行器15为吸盘的方案，可以包括吸盘可覆盖被操作物的区域面积，覆盖面积越大，获持质量越好，对于末端执行器15为夹持工具的方案，根据夹持工具的参数选择，例如，对于两指夹持工具，根据分割目标选择具有相对平行的一对面，等。还可以包括获持后，具有标签的面符合特定朝向的条件，等等。可以理解的是，该选择参考的条件及因素可以依据具体应用场景而灵活设定。
接近向量获取模块22，用于根据分割处理模块21选择的被执行区域 T，或者根据被操作物A的三维模型，计算获取末端执行器15接近该被执行区域T的接近向量(S3037)。该示例以法向量作为接近向量。以提供第一状态，包括符合末端执行器15通过被执行区域T获持被操作物A的位置及姿态。一实施方式下，接近向量可以根据被执行区域T以及末端执行器15的参数计算得到。末端执行器15的参数包括基准点，即定义的可代表末端执行器15位置的一致参考信息，包括在定义的末端执行器15的参考坐标下，与机械臂13的相对位置信息。例如，可以为末端执行器15与机械臂13连接的关节，或者当末端执行器15为复杂的机械手时，还可以包括机械手各个关节的角度值，等等。具体可以根据具体应用场景以及采用的末端执行器15而灵活设定。
路径规划模块23，根据接近向量获取模块22得到的接近向量，以及末端执行器15当前的位姿，获得末端执行器15到达第一状态的第一执行路径(S3039)。其中，第一状态包括末端执行器15根据接近向量获持被操作物A时的位姿。为便于说明，此处称为第一位姿。一实施方式下，假设当末端执行器15的基准点采用末端执行器15与机械臂13连接的关节，则根据被执行区域T于世界坐标系的位置，获得末端执行器15于被执行区域T对应世界坐标系下基准点的位置，即得到机械臂13的末端位置，进而根据逆运动学算法，得到机械臂13于该末端位置的关节角。根据该第一位姿得到机械臂13的第一状态。根据该第一位姿以及当前位姿，进行当前位姿到达第一位姿的运动规划。
执行模块25，控制机械臂13根据第一执行路径运动到第一状态，并控制末端执行器15获持被操作物A(S3041)。当末端执行器15到达第一位姿，控制末端执行器15获持被操作物A。当末端执行器15为吸盘时，控制启动吸附。当末端执行器15为夹持工具时，控制启动夹持。可行的， 各需驱动的执行单元可以分别设有驱动，也可以为统一的驱动系统控制执行。
具体的，根据运动规划控制机械臂13运动到第二状态，可以包括以下实施方式。
路径规划模块23，还用于根据末端执行器15当前位姿以及第二状态包括的于传送机构11的目标位置，获得末端执行器15到达第二状态的第二执行路径(S3043)。可以理解的是，该目标位置包括具体的位置，也包括位置区域。
第二状态匹配模块26，用于根据第二执行路径以及第二状态的目标速度V G，获得轨迹规划(S3045)。其中，目标速度V G对应传送机构11的传送速度V C，包括目标速度V G等于传送速度V C，或者目标速度V G落入传送速度V C的一个阈值范围内。
执行模块25，还用于获持被操作物A后，根据第二状态匹配模块26的轨迹规划控制机械臂13执行(S3047)。
具体的，控制末端执行器15放置被操作物A于传送机构11，可以包括以下实施方式。
放置模块27，当末端执行器15在执行模块25的控制下，到达第二状态，控制末端执行器15放置被操作物A(S3049)。当末端执行器15为吸盘时，控制关闭吸附。当末端执行器15为夹持工具时，控制关闭夹持。
由此，被操作物A放置于传送机构11时具有与传送机构11的传送速度V C一致的运动状态。由此，被操作物A于传送机构11上具有稳定有序的状态。对于后续于传送机构11上执行的其他工序，提供良好、高效自动化的运作条件。
另一实施例中，系统还包括默认状态，默认状态包括默认位置及默认 速度V D。为了便于理解，以下结合图6、图7提供的拣货方法400、500进行示例性说明。至少一个处理器14获取运动规划，还包括：至少一个处理器14根据第一状态以及默认状态获取第一运动规划，根据默认状态以及第二状态获取第二运动规划(S402)。其中，默认状态与第二状态为已知信息，因此，第二运动规划为相对固定的执行过程。具体的，该第二运动规划可以存储于存储装置16，当根据实时规划的第一运动规划到达默认状态，即可直接获取已知的第二运动规划，完成第二状态。该实施方式中，根据获得的第一状态，即可与已知的默认状态执行第一运动规划(S402)，并可执行控制机械臂运动到第一状态，并控制机械臂13的末端执行器15获持被操作物A(S404)。完成后即可执行根据第一运动规划控制机械臂运动到默认状态(S406)。由于默认状态及第二状态已知，根据默认状态以及第二状态获取第二运动规划(S402)包括：第二运动规划为预存的控制指令。当达到默认状态，即可执行根据第二运动规划控制机械臂运动到第二状态(S408)。到达第二状态，控制末端执行器15放置被操作物A于传送机构11(S410)。可以理解的是，本发明实施例提供的系统、方法的执行步骤并不限定于一一串行执行，包括可以并行处理、预处理的执行顺序。
具体的，根据运动规划控制机械臂13运动到第二状态(S408)，可以包括以下实施方式。
路径规划模块23，还用于根据末端执行器15当前位姿以及默认状态包括的默认位置，获得末端执行器15到达默认状态的第三执行路径(S4043)。
默认状态还可以包括默认速度V D。相应的，系统还包括默认状态匹配模块24，用于根据第三执行路径以及默认状态的默认速度V D，执行轨 迹规划(S4045)。相应的，当默认状态包括默认速度V D，第二运动规划包括由默认位置到目标位置的第四执行路径，以及由默认位置的默认速度V D达到目标位置时的目标速度V G的轨迹规划(S4049)。
执行模块25，还用于获持被操作物A后，根据默认状态匹配模块24的轨迹规划控制机械臂13执行(S4047)。以及达到默认状态后，根据第二运动规划的轨迹规划控制机械臂13执行(S4051)。
第二状态还可以包括被操作物A放置于传送机构11的位置与前一货物的距离大于或等于第一阈值。一实施方式下，目标位置与前一货物的距离大于或等于第一阈值，可以包括下述实现方式，根据第一阈值以及传送速度V C得到执行时间T，系统根据放置模块27完成任务后，进行下一轮循环，获持任务及放置任务的时间采用执行时间T进行规划并执行。其中，结合前述系统实施例，循环包括至少一个处理器14根据视觉传感器12获取的数据，以及根据分割处理模块21、接近向量获取模块22、路径规划模块23、执行模块25根据第一状态执行获持任务，以及获持后，根据路径规划模块23、第二状态匹配模块26、执行模块26根据第二状态执行放置任务。可以理解的是，上述模块的执行过程可以为依次执行，也可以包括并行执行。另一可行方式下，当具有专门获取取货区域S信息的感知装置12时，至少一个处理器14包括在其他模块运作当前被操作物A1时，分割处理模块21及接近向量获取模块22同步获取下一个被操作物A2，完成当前被操作物A1的放置任务后，即可直接根据已获得的下一个被执行获取A2执行获持任务。提高系统执行效率。当放置任务采用上述具有默认状态的方式时，在完成当前被操作物A1的放置任务前，路径规划模块23还可以同步执行根据第一状态的路径规划，使得系统完成当前被执行获取A1的放置任务后，执行模块25即可直接执行下一被操作物A2根 据第一状态的路径规划。可以理解的是，以上仅为示例性作用，并不用于限定本发明保护范围。同步执行的方式下，不仅限于同步获取下一被操作物A2的获持任务信息，还可以包括获持多个待执行货物的获持任务。当放置任务采用具有默认状态的方式时，在机械臂13执行当前任务的过程中，可以同步获得下一被操作物或下多个被操作物的获持任务以及放置任务。本领域技术人员基于该示例性原理，在不付出创造性劳动进行的变化方式仍属于本发明保护范围。
第二状态还可以包括标签所在的位置处于预设的方位。至少一个处理器14还用于，根据感知装置12获取的数据，得到被操作物A的标签所在的位置。一些应用场景下，货物上附有标签，标签用于识别货物信息，提供输送系统获取输送所需的信息，例如，货物标识，始发地，目的地，重量，尺寸，等。进入传送带系统以后会涉及标签识别的需求，因此，在系统获持任务以及放置任务中还包括获知货物上具有标签的所在位置，并根据该标签的位置规划获持、放置任务，使得货物放置于传送机构11时标签的朝向符合需求的朝向。例如，对于除了与传送机构11接触的面不具备扫描装置的五面扫描装置的应用场景而言，需求的朝向为标签不处于底部(与传送机构11接触的面)即可。对于设定了一向、两向等其他有特定限制的场景而言，需求的朝向为标签朝向设有扫描装置的任一向即可。于获持任务中，根据感知装置12获得的取货区域S的图像信息，识别货物上具有的标签。具体的，可以根据标签的特殊标识、形态等特征，予以匹配识别。在当根据分割处理模块21分割出至少一个分割目标，并于分割目标上识别到标签后，根据该标签处于货物的位置，以及第二状态限定的标签所在的位置处于预设的方位，选择被执行区域T所在的面为末端执行器15获持后可执行放置于传送机构11时货物的标签处于预设的方位。 即标签的朝向对应于具有扫描装置的朝向。为了便于理解，以下针对典型场景示例性说明。当扫描装置处于传送机构11的上方，即标签所在的位置处于顶面(与传送机构接触面相对的面)。分割处理模块21根据取货区域S的图像数据，分割出多个分割目标，选择无遮挡且具有标签的分割目标，并于具有标签的面选择被执行区域T。该方式下，在执行放置任务时，末端执行器15的姿态，以获持面相对传送机构11垂直放置即可。一些情况下，无遮挡的分割目标上识别的标签，但标签所在的位置，使得末端执行器15接触标签所在的面会存在碰撞，则可于无碰撞问题的面上选择被执行区域T。通过该被执行区域T以及标签所在位置处于预设的方位，获得末端执行器15于第二状态时的姿态，使得末端执行器15根据该姿态进行放置时标签所在的位置符合预设的方位。当扫描装置为前述五向装置时，当识别到无遮挡的分割目标具有设置标签的面时，可以任意选取无碰撞的面上的被执行区域T，当以通用放置姿态，即第二状态末端执行器15的姿态均为由垂直传送机构11的方向下放。均可以满足标签的方位是朝向任一方向扫描装置，而不在底面。可以理解的是，当采用通用放置姿态时，可以减少规划限制。
一实施方式，目标速度V G可以小于传送速度V C。至少一个处理器14还包括加速模块28，用于根据第二状态控制机械臂13运动到目标位置，以及，控制机械臂13沿传送机构11的传送方向加速达到传送速度V C。当根据加速模块28加速达到传送速度V C，放置模块27完成放置操作。
本发明上述实施例提供的多种实施方式的拣货系统，提供了结合传送机构的自动拣货系统，实现了放置于传送机构的货物与传送机构的传送速度匹配。相比现有技术由人工完成拣货并放置于传动机构的方式，解决了人工操作难以匹配高速运行的传送机构，以及难以满足高速运行状态下准 确放置货物，并保持物体放置后的稳定性。就该问题而言，本发明实施例提供的拣货系统，保证了物体放置于传送机构的稳定性，以及系统运作的有序性及高效性。
本发明实施例还提供一种拣货方法200A，如图3所示，该方法实施于一个或多个计算机系统，包括执行步骤：
S202：根据被操作物得到操作用机器人的第一状态，以及将该被操作物放置于传送机构的第二状态，获取运动规划。第二状态包括该被操作物沿传送机构的传送方向具有目标速度V G。其中，目标速度V G对应所述传送机构的传送速度V C。
S204：控制操作用机器人运动到第一状态，并控制末端执行器获持被操作物。
S206：根据运动规划控制操作用机器人运动到第二状态。
S208：控制末端执行器放置被操作物于传送机构。
需要说明的是，上述实施例并不用于限定执行步骤的顺序，另一实施方式中，拣货方法200B，如图4所示，获取到第一状态后，步骤S202可以与步骤S204并行处理。还包括，步骤S202、S204交替或交错执行，在二者均完成后即可执行S206。
其中，步骤S202中根据被操作物得到操作用机器人的第一状态，结合图5所示，可以包括：
S3021：获取取货区域的信息。
S3023：根据获取的数据进行分割处理，得到被操作物的信息。
其中，步骤S202中根据被操作物得到操作用机器人的第一状态，结合图5所示，还包括：
S3035：根据被操作物的信息得到末端执行器接触该被操作物的被执 行区域。
S3037：获取末端执行器接近该被执行区域的接近向量。
相应的，步骤S204包括：
S3039：根据得到的接近向量，以及末端执行器当前的位姿，获得末端执行器到达第一状态的第一执行路径。
S3041：控制操作用机器人根据第一执行路径运动到第一状态，并控制末端执行器获持被执行物体。
具体的，第一状态包括末端执行器用于获持被操作物的位姿。第二状态可以包括被操作物放置于传送机构的目标位置。还可以包括被操作物放置于传送机构的位置与前一货物的距离大于或等于第一阈值。当被操作物包括标签，且对标签方位有限定需求的应用场景而言，第二状态还可以包括标签所在的位置处于预设的方位。
一些实施方式下，目标速度V G等于传送速度V C。具体的，结合图5示例，步骤S206根据运动规划控制操作用机器人运动到第二状态，可以包括步骤：
S3043：根据末端执行器当前位姿以及第二状态包括的于传送机构的目标位置，获得末端执行器到达第二状态的第二执行路径。
S3045：根据第二执行路径以及第二状态的目标速度V G，获得轨迹规划。
S3047：根据轨迹规划控制操作用机器人执行。
相应的，步骤S208控制末端执行器放置被操作物于传送机构包括：
S3049：当末端执行器到达第二状态，控制末端执行器放置被执行物体。
还可以设置目标速度V G小于传送速度V C。相应的，步骤S206中根 据运动规划控制操作用机器人运动到第二状态，还包括：根据第二状态控制操作用机器人运动到第二状态包括的目标位置，以及，控制操作用机器人沿传送机构的传送方向加速达到传送速度V C。具体的，可以包括以下执行步骤：
一些实施方式下，结合图6所示的示例，拣货方法还包括默认状态，包括默认位置及默认速度V D。步骤S202中获取运动规划还包括：S402：根据第一状态及默认状态获取第一运动规划，以及根据默认状态及第二状态获取第二运动规划。
其他实施方式，结合图5、图7所示的示例，拣货方法还可以包括方法300的步骤S3021至S3041，执行获持任务，以及方法500执行放置任务。其中方法500包括：
S5043：根据末端执行器当前位姿以及默认状态包括的默认位置，获得末端执行器到达默认状态的第三执行路径。
S5045：根据第三执行路径以及默认状态的默认速度V D，执行轨迹规划。
S5047：根据轨迹规划控制操作用机器人执行。
S5049：根据默认位置到目标位置的第四执行路径，以及由默认位置的默认速度V D达到目标位置的目标速度V G的轨迹规划。
S5051：根据轨迹规划控制操作用机器人执行。
由于上述实施方式提供的拣货方法包括的步骤，在前述拣货系统中有对应的原理阐述，可结合参看，在此不再赘述。
本发明上述实施例提供的多种实施方式的拣货方法，提供了结合传送机构的自动拣货方法，实现了放置于传送机构的货物与传送机构的传送速度匹配。相比现有技术由人工完成拣货并放置于传动机构的方式，解决 了人工操作难以匹配高速运行的传送机构，以及难以满足高速运行状态下准确放置货物，并保持物体放置后的稳定性。就该问题而言，本发明实施例提供的拣货方法，保证了物体放置于传送机构的稳定性，以及整体运作的有序性及高效性。
本发明实施例提供的获持与放置系统20还可以集成于机器人。如图9，机器人30包括：包括感知装置12，操作用机器人13，以及至少一个处理器14。其中，感知装置12用于感测被操作物。操作用机器人13，包括自由端，该自由端设置有末端执行器15。该操作用机器人13包括串联机器人，并联机器人，以及结合移动机器人的多种选择，可以实现末端执行器15对被操作物的操作即可。例如，串联机器人可以为具有6自由度的机械臂。至少一个处理器14用以执行获持与放置方法，包括：根据被操作物得到操作用机器人13和/或末端执行器15的第一状态，以及欲将该被操作物执行放置所处的第二状态，获取运动规划。其中，第一状态与第二状态包括位置、姿态、速度、加速度、角速度、角加速度、几何外形和/或重量分布。该方法还包括：控制操作用机器人13和/或末端执行器15运动到所述第一状态，并控制末端执行器15获持被操作物，以及根据运动规划控制控制操作用机器人13和/或末端执行器15运动到第二状态，以及控制末端执行器15放置被操作物。具体原理及有益效果可参看前述获持与放置系统20的详细阐述。
以上所述仅为本发明的较佳实施方式而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。

Claims (22)

  1. 一种拣货系统，其特征在于，包括：
    传送机构，所述传送机构具有传送速度V C；
    感知装置，用于感测被操作物；
    操作用机器人，包括自由端，该自由端设置有末端执行器，
    至少一个处理器，用于：
    根据所述感知装置感测的所述被操作物得到所述操作用机器人的第一状态，以及将该被操作物放置于所述传送机构的第二状态，获取运动规划；所述第二状态包括该被操作物沿所述传送机构的传送方向具有目标速度V G，其中，目标速度V G对应所述传送速度V C；
    控制所述机械臂运动到所述第一状态，并控制所述末端执行器获持所述被操作物；
    根据所述运动规划控制所述操作用机器人运动到所述第二状态；
    控制所述末端执行器放置所述被操作物于所述传送机构。
  2. 如权利要求1所述的系统，其特征在于，所述感知装置包括视觉传感器，所述至少一个处理器，还用于根据所述视觉传感器获取的数据进行分割处理，得到所述被操作物的信息。
  3. 如权利要求2所述的系统，其特征在于，所述至少一个处理器，还用于根据所述被操作物的信息得到所述末端执行器接触该被操作物的被执行区域，得到所述被执行区域的法向量。
  4. 如权利要求1至3任一项所述的系统，其特征在于，所述第一状态包括所述末端执行器用于获持所述被操作物的位姿。
  5. 如权利要求1所述的系统，其特征在于，所述第二状态还包括所述被操作物放置于所述传送机构的位置与前一货物的距离大于或等于第一阈值。
  6. 如权利要求1所述的系统，其特征在于，所述至少一个处理器还用于，根据所述感知装置获取的数据，得到所述被操作物的标签所在的位置；所述第二状态还包括所述标签所在的位置处于预设的方位。
  7. 如权利要求1所述的系统，其特征在于，所述第二状态还包括所述被操作物放置于所述传送机构的目标位置。
  8. 如权利要求7所述的系统，其特征在于，所述目标速度V G小于所述传送速度V C；所述至少一个处理器还用于，根据所述第二状态控制所述操作用机器人运动到所述目标位置，以及，控制操作用机器人沿所述传送机构的传送方向加速达到所述传送速度V C。
  9. 如权利要求1所述的系统，其特征在于，还包括默认状态，所述默认状态包括默认位置及默认速度V D；所述至少一个处理器获取所述运动规划，还包括：所述至少一个处理器根据所述第一状态以及默认状态获取第一运动规划，以及根据所述默认状态以及第二状态获取第二运动规划。
  10. 如权利要求1所述的系统，其特征在于，所述目标速度V G等于所述传送速度V C。
  11. 一种拣货方法，其特征在于，所述方法实施于一个或多个计算机系统，包括执行步骤：
    根据被操作物得到操作用机器人的第一状态，以及将该被操作物放置于传送机构的第二状态，获取运动规划；所述第二状态包括该被操作物沿 所述传送机构的传送方向具有目标速度V G，其中，目标速度V G对应所述传送机构的传送速度V C；
    控制所述操作用机器人运动到所述第一状态，并控制所述末端执行器获持所述被操作物；
    根据所述运动规划控制所述操作用机器人运动到所述第二状态；
    控制所述末端执行器放置所述被操作物于所述传送机构。
  12. 如权利要求11所述的方法，其特征在于，所述根据所述被操作物得到所述操作用机器人的第一状态，包括：
    获取取货区域的信息；
    根据获取的信息进行分割处理，得到所述被操作物的信息。
  13. 如权利要求12所述的方法，其特征在于，所述根据所述被操作物得到所述操作用机器人的第一状态，还包括：
    根据所述被操作物的信息得到所述末端执行器接触该被操作物的被执行区域；
    获取末端执行器接近所述被执行区域的接近向量。
  14. 如权利要求11至13任一项所述的方法，其特征在于，所述第一状态包括所述末端执行器用于获持所述被操作物的位姿。
  15. 如权利要求11所述的方法，其特征在于，所述第二状态还包括所述被操作物放置于所述传送机构的位置与前一货物的距离大于或等于第一阈值。
  16. 如权利要求11所述的方法，其特征在于，所述被操作物包括标签，所述第二状态还包括所述标签所在的位置处于预设的方位。
  17. 如权利要求11所述的方法，其特征在于，所述第二状态还包括所述被操作物放置于所述传送机构的目标位置。
  18. 如权利要求17所述的方法，其特征在于，所述目标速度V G小于所述传送速度V C；所述根据所述运动规划控制所述操作用机器人运动到所述第二状态，还包括：根据所述第二状态控制所述操作用机器人运动到所述目标位置，以及，控制操作用机器人沿所述传送机构的传送方向加速达到所述传送速度V C。
  19. 如权利要求11所述的方法，其特征在于，还包括默认状态，所述默认状态包括默认位置及默认速度V D；所述获取所述运动规划，还包括：根据所述第一状态以及默认状态获取第一运动规划，以及根据所述默认状态以及第二状态获取第二运动规划。
  20. 如权利要求11所述的方法，其特征在于，所述目标速度V G等于所述传送速度V C。
  21. 一种获持与放置系统，其特征在于，包括：
    感知装置，用于感测被操作物；
    操作用机器人，包括自由端，该自由端设置有末端执行器，
    至少一个处理器，用于：
    根据所述被操作物得到所述末端执行器的第一状态，以及将该被操作物执行放置所处的第二状态，获取运动规划；所述第一状态与所述第二状态包括位置、姿态、速度、加速度、角速度、角加速度、几何外形和/或重量分布；
    控制所述操作用机器人运动到所述第一状态，并控制所述末端执行器获持所述被操作物；
    根据所述运动规划控制所述操作用机器人运动到所述第二状态；
    控制所述末端执行器放置所述被操作物。
  22. 一种机器人，其特征在于，包括：
    感知装置，用于感测被操作物；
    操作用机器人，包括自由端，该自由端设置有末端执行器，
    至少一个处理器，用于：
    根据所述被操作物得到所述末端执行器的第一状态，以及将该被操作物执行放置所处的第二状态，获取运动规划；所述第一状态与所述第二状态包括位置、姿态、速度、加速度、角速度、角加速度、几何外形和/或重量分布；
    控制所述操作用机器人运动到所述第一状态，并控制所述末端执行器获持所述被操作物；
    根据所述运动规划控制所述操作用机器人运动到所述第二状态；
    控制所述末端执行器放置所述被操作物。
PCT/CN2018/075036 2018-02-02 2018-02-02 拣货方法、系统及其应用的获持与放置系统、机器人 WO2019148441A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201880002481.6A CN109641706B (zh) 2018-02-02 2018-02-02 拣货方法、系统及其应用的获持与放置系统、机器人
PCT/CN2018/075036 WO2019148441A1 (zh) 2018-02-02 2018-02-02 拣货方法、系统及其应用的获持与放置系统、机器人

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/075036 WO2019148441A1 (zh) 2018-02-02 2018-02-02 拣货方法、系统及其应用的获持与放置系统、机器人

Publications (1)

Publication Number Publication Date
WO2019148441A1 true WO2019148441A1 (zh) 2019-08-08

Family

ID=66060080

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/075036 WO2019148441A1 (zh) 2018-02-02 2018-02-02 拣货方法、系统及其应用的获持与放置系统、机器人

Country Status (2)

Country Link
CN (1) CN109641706B (zh)
WO (1) WO2019148441A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220088778A1 (en) * 2020-09-23 2022-03-24 Dexterity, Inc. Velocity control-based robotic system

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110654599A (zh) * 2019-09-29 2020-01-07 珠海格力智能装备有限公司 装箱设备和电饭煲包装生产线
CN111347426B (zh) * 2020-03-26 2021-06-04 季华实验室 一种基于3d视觉的机械臂精确放置轨迹规划方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202845347U (zh) * 2012-08-13 2013-04-03 Abb技术有限公司 一种机器人分拣系统
CN105269580A (zh) * 2014-06-25 2016-01-27 上银科技股份有限公司 机械手臂的安全控制方法
CN106965180A (zh) * 2017-04-13 2017-07-21 北京理工大学 流水线上瓶子的机械臂抓取装置与方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1310986A1 (de) * 2001-11-08 2003-05-14 F & K Delvotec Bondtechnik GmbH Chipträgerplatten-Wechselmechanismus
US7794194B2 (en) * 2007-09-14 2010-09-14 Seagate Technology Llc Pick and place work piece flipper
CN201458340U (zh) * 2009-07-06 2010-05-12 北京京城清达电子设备有限公司 一种基板立式挂架的装载装置
JP5642759B2 (ja) * 2012-10-31 2014-12-17 ファナック株式会社 物品取出装置及び物品取出方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202845347U (zh) * 2012-08-13 2013-04-03 Abb技术有限公司 一种机器人分拣系统
CN105269580A (zh) * 2014-06-25 2016-01-27 上银科技股份有限公司 机械手臂的安全控制方法
CN106965180A (zh) * 2017-04-13 2017-07-21 北京理工大学 流水线上瓶子的机械臂抓取装置与方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220088778A1 (en) * 2020-09-23 2022-03-24 Dexterity, Inc. Velocity control-based robotic system

Also Published As

Publication number Publication date
CN109641706B (zh) 2021-04-30
CN109641706A (zh) 2019-04-16

Similar Documents

Publication Publication Date Title
US11501445B2 (en) Robotic system with automated package scan and registration mechanism and methods of operating the same
US11905116B2 (en) Controller and control method for robot system
US11654558B2 (en) Robotic system with piece-loss management mechanism
US20240017417A1 (en) Method and computing system for performing motion planning based on image information generated by a camera
JP2020121887A (ja) ロボットシステムの制御装置及び制御方法
US11648676B2 (en) Robotic system with a coordinated transfer mechanism
US20210308866A1 (en) Adaptive grasp planning for bin picking
JP2018020423A (ja) ロボットシステム及びピッキング方法
JP2016144841A (ja) ３次元センサを備えた搬送ロボットシステム
WO2019148441A1 (zh) 拣货方法、系统及其应用的获持与放置系统、机器人
US11833690B2 (en) Robotic system with dynamic motion adjustment mechanism and methods of operating same
US20240042613A1 (en) Robotic system to control multiple robots to perform a task cooperatively
JP6741329B1 (ja) グリッパ装置のツールを変更するシステム
CN115703232A (zh) 具有基于图像的尺寸确定机制的机器人系统及其操作方法
CN115744272A (zh) 机器人多表面夹持器组件及其操作方法
US20220088778A1 (en) Velocity control-based robotic system
JP2021088019A (ja) ロボットシステム及びロボットシステムの制御方法
CN114746224A (zh) 机器人工具及其操作方法
US20230052515A1 (en) System and method for robotic object placement
US20230071488A1 (en) Robotic system with overlap processing mechanism and methods for operating the same
US20240157565A1 (en) Robotic system transfer unit cell and method of operation thereof
WO2024038323A1 (en) Item manipulation system and methods
EP4395965A1 (en) Robotic system with overlap processing mechanism and methods for operating the same
CN115946107A (zh) 用于可打开对象的机器人抓持器总成和拾取对象的方法
CN114683299A (zh) 机器人工具及其操作方法

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: 18903505

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18903505

Country of ref document: EP

Kind code of ref document: A1