CN117696445A - Efficient express sorting method based on mechanical arm - Google Patents

Efficient express sorting method based on mechanical arm Download PDF

Info

Publication number
CN117696445A
CN117696445A CN202311608925.XA CN202311608925A CN117696445A CN 117696445 A CN117696445 A CN 117696445A CN 202311608925 A CN202311608925 A CN 202311608925A CN 117696445 A CN117696445 A CN 117696445A
Authority
CN
China
Prior art keywords
package
pose
ith
grabbing
path
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202311608925.XA
Other languages
Chinese (zh)
Inventor
侯健
张旭
谢永强
汪明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhongke Weizhi Technology Co ltd
Original Assignee
Zhongke Weizhi Technology Co ltd
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 Zhongke Weizhi Technology Co ltd filed Critical Zhongke Weizhi Technology Co ltd
Priority to CN202311608925.XA priority Critical patent/CN117696445A/en
Publication of CN117696445A publication Critical patent/CN117696445A/en
Pending legal-status Critical Current

Links

Landscapes

  • Manipulator (AREA)

Abstract

The method comprises the steps of carrying out planning on a placement path by adopting a double-thread parallelization processing mode in the process of controlling the mechanical arm to grab a package according to the grabbing path, carrying out grabbing path planning of the next sorting cycle by adopting the double-thread parallelization processing mode in the process of controlling the mechanical arm to move according to the placement path, carrying out action and path planning operation by adopting the double-thread parallelization processing mechanical arm, and only consuming action time of two mechanical arm actuators grabbing and placing the package in the process of sorting the package each time, thereby parallelizing the time of path planning algorithm and image point cloud data processing time required by the mechanical arm to carry out the action, shortening sorting time consumption and greatly improving sorting efficiency.

Description

Efficient express sorting method based on mechanical arm
Technical Field
The application relates to the technical field of logistics, in particular to a high-efficiency express sorting method based on a mechanical arm.
Background
Along with the high-speed development of logistics industry, the quantity and the variety of package express delivery are more and more rich, and the links such as package sorting and distribution are challenged greatly. The parcel sorting is one of important links in the logistics transportation of the express delivery, and express delivery personnel need to sort a large number of piled parcels to a cross conveyor belt one by one, so that different parcels are conveyed to different areas according to different information (such as destinations) of the parcels, and follow-up treatment is carried out.
However, the existing manual sorting efficiency is low, and the rapid sorting requirement is difficult to meet, so that the existing automatic sorting method based on machine vision combined with the mechanical arm is gradually applied, but the movement of the mechanical arm is time-consuming, so that the automatic sorting efficiency is not ideal.
Disclosure of Invention
Aiming at the problems and the technical requirements, the application provides a high-efficiency express sorting method based on a mechanical arm, and the technical scheme of the application is as follows:
a high-efficiency express sorting method based on a mechanical arm comprises the following steps:
initializing a sorting cycle parameter i=1;
determining the package pose of the ith target package in the package separation area based on machine vision, and planning a grabbing path based on the package pose of the ith target package;
in the process that the control mechanical arm drives the end effector to move to grasp the ith target package according to the planned grasping path, the step of planning the placement path based on the package pose of the ith target placement position is executed in parallel;
in the process that the mechanical arm is controlled to drive the end effector to move to place the grabbed ith target package to the ith target placement position according to the planned placement path, enabling i=i+1 and parallelly executing the steps of determining the package pose of the ith target package of the package separation area based on machine vision, and planning the grabbing path based on the package pose of the ith target package until the package separation area has no package.
The method for planning the grabbing path based on the package pose of the ith target package comprises the following steps:
determining a grabbing final point position of an ith sorting cycle based on the package position of an ith target package;
taking the initial pose of the mechanical arm as the grabbing and starting pose of the first sorting cycle, and determining the grabbing and starting pose of the ith sorting cycle according to the wrapping pose of the ith-1 target placement position for any i more than or equal to 2;
a random sampling path planning rule is utilized to draw a grabbing path from the grabbing starting position of the ith sorting cycle to the grabbing final position of the ith sorting cycle;
the grabbing final position and the grabbing starting position are positions of joints at the tail ends of the mechanical arms.
The method for planning the placement path based on the package pose of the ith target placement position comprises the following steps:
determining a placement final point pose of the ith sorting cycle based on the package pose of the ith target placement position;
determining a placement starting position of an ith sorting cycle based on the package position of the ith target package;
using random sampling path planning rule to draw a placement path from the placement start position of the ith sorting cycle to the placement end position of the ith sorting cycle;
the placement final position and the placement starting position are positions of joints at the tail ends of the mechanical arms.
The high-efficiency express sorting method further comprises the following steps:
determining the package height of the ith target package in the package separation area based on machine vision, determining a package coordinate system of the ith target package based on the package height of the ith target package and the corresponding package pose of any one of the capturing end position pose, the capturing starting position pose, the placing end position pose and the placing starting position pose of a tail end joint of the mechanical arm, and performing coordinate system conversion on the corresponding package pose under the world coordinate system based on the package coordinate system of the ith target package to obtain the pose of the tail end joint of the mechanical arm;
the package coordinate system of the ith target package is established by taking the center of the package position of the ith target package and the position which is positioned at half of the package height as the origin of coordinates.
The further technical proposal is that carrying out coordinate system conversion on the corresponding package pose under the world coordinate system to obtain the pose of the tail end joint of the mechanical arm comprises determining the pose of the tail end joint of the mechanical arm
world T wristworld T box * box T suction * suction T wrist
Wherein, world T box is the corresponding wrapping pose under the world coordinate system, box T suction is a transformation matrix between the end effector of the robotic arm and the package coordinate system of the ith target package, suction T wrist is a transformation matrix between the end joints of the manipulator and the end effector to which the end joints of the manipulator are connected.
The further technical scheme is that the end effector of the mechanical arm is a sucker, and the high-efficiency express sorting method further comprises the following steps:
determining the grabbing terminal position of the ith sorting cycle, translating downwards along the vertical direction by a preset distance to obtain the absorbing terminal position, and utilizing a random sampling path planning rule to draw an absorbing path from the grabbing terminal position of the ith sorting cycle to the absorbing terminal position of the ith sorting cycle;
the controlling the mechanical arm to drive the end effector to grasp the ith target package comprises:
the control mechanical arm drives the end effector to move to the grabbing final position of the ith sorting cycle according to the planned grabbing path, and the control mechanical arm drives the end effector to move to the grabbing final position of the ith sorting cycle according to the grabbing path to push down and suck the ith target package.
The high-efficiency express sorting method further comprises the following steps:
and after the track fusion smoothing algorithm is adopted to carry out smoothing treatment on the grabbing path and the sucking path, controlling the mechanical arm to drive the end effector to move according to the grabbing path and the sucking path after the smoothing treatment and grabbing the ith target package.
The further technical proposal is that the end surface of the sucker, which is contacted with the package, is made of soft material.
The method for determining the package pose of the ith target package in the package separation area based on machine vision comprises the following steps:
acquiring RGB images and depth data of a sorting working space through an RGBD camera;
image segmentation is carried out on the acquired RGB image to determine a parcel foreground area of each parcel in the parcel separation area;
and converting the depth data in the parcel foreground area of each parcel into three-dimensional point cloud data according to camera parameters of the RGBD camera, determining the parcel pose of each parcel based on the three-dimensional point cloud data in the parcel foreground area of each parcel, and determining the parcel pose of the ith target parcel.
The further technical scheme is that the planning of the grabbing path and the placing path further comprises:
and converting the depth data of the sorting working space into an occupied grid map of the working environment where the mechanical arm is located according to camera parameters of the RGBD camera, and planning a grabbing path and a placing path based on the occupied grid map.
The beneficial technical effects of this application are:
the method comprises the steps of planning a placement path by adopting a double-thread parallelization processing mode in the process of controlling the mechanical arm to grasp the package, planning a machine vision and a grasping path of the next sorting cycle by adopting the double-thread parallelization processing mode in the process of controlling the mechanical arm to grasp the package, so that the method is used for carrying out the work time consumption of only spending the grasping path and the placement path in a single sorting cycle of sorting a piece of package, the sorting time consumption is shortened, and the sorting efficiency is greatly improved.
In addition, the application uses the sucking disc to grasp the parcel, can adapt to the parcel of different sizes and materials, and the elasticity rope ladder material of terminal surface avoids excessively extruding the parcel. And aiming at the recognition error of machine vision, the sucking disc can more reliably adsorb and grasp the package by adding the sucking path, thereby being beneficial to improving the grasping accuracy and reliability. The method and the device can also perform uniform smoothing treatment on the grabbing path and the sucking path to form a smooth track, so that the mechanical arm has a uniform acceleration and deceleration process, and the control process is smoother and more efficient.
Drawings
Fig. 1 is an application scenario diagram of the efficient express sorting method of the present application.
Fig. 2 is a method flow diagram of an efficient express sorting method according to one embodiment of the present application.
FIG. 3 is a flow chart of a method for controlling a robotic arm to grasp a package in accordance with one embodiment of the present application.
Fig. 4 is another application scenario diagram of the efficient express sorting method of the present application.
Fig. 5 is another application scenario diagram of the efficient express sorting method of the present application.
Detailed Description
The following describes the embodiments of the present application further with reference to the accompanying drawings.
The application discloses a high-efficiency express sorting method based on a mechanical arm, please refer to an application scene diagram of the high-efficiency express sorting method shown in fig. 1, the method is developed based on a common form of the existing package sorting scene, a sorting working space comprises a conveying belt, the mechanical arm 1 and a vision camera 3, and a controller generally controls working states of all components, which are not shown in fig. 1. The conveyor belt comprises a packet-feeding conveyor belt, a packet-separating zone (hatched area in fig. 1) and a packet-discharging conveyor belt, the direction of conveyance of the packet-feeding conveyor belt being directed towards the packet-separating zone, the direction of conveyance of the packet-discharging conveyor belt being remote from the packet-separating zone, the direction of conveyance being shown by an arrow in fig. 1. The supply package conveyor conveys several packages stacked together to a package separation zone, fig. 1 taking 5 packages comprising the package separation zone as A, B, C, D, E, respectively, and the packages in fig. 1 are not stacked together for clarity of illustration. Then, each piece of package in the package separation area is sequentially separated and transferred onto a package discharging conveyor belt by the high-efficiency express sorting method, and the package discharging conveyor belt sequentially conveys the sorted single piece of package to a subsequent process.
The robotic arm 1 is typically disposed adjacent to the parcel separation zone, with the operating range of the robotic arm 1 covering the entire parcel separation zone for gripping parcels at various locations of the parcel separation zone. The operating area of the robotic arm 1 also covers a partial area of the outfeed conveyor belt, in particular the area of the outfeed conveyor belt near the parcel separation zone, so that the robotic arm 1 places the sorted individual parcels onto the outfeed conveyor belt.
The vision camera 3 is arranged above the sorting working space and vertically downwards, and the field of view range of the vision camera 3 covers the whole sorting working space and comprises a wrapping separation area and a working environment where the mechanical arm is located.
The present application uses the base coordinate system of the mechanical arm 1 as the world coordinate system O w X w Y w Z w After the application scene as in fig. 1 is built, the world coordinate system O will be also checked w X w Y w Z w And a camera coordinate system O of the vision camera 3 C X C Y C Z C Conversion calibration is carried out to determine the world coordinate system O w X w Y w Z w And a camera coordinate system O C X C Y C Z C The coordinate conversion relation of (2) is a common prior art, and is not described herein, and all coordinate systems established in the application take the XY axis on a horizontal plane and the Z axis on a vertical horizontal plane as an example. Based on the application scenario shown in fig. 1, the efficient express sorting method includes the following steps, please refer to the flowchart of fig. 2:
step 1, initializing a sorting cycle parameter i=1.
And 2, determining the package pose of the ith target package of the package separation area based on machine vision by using a vision camera 3.
In one embodiment, the vision camera 3 uses an RGBD camera to determine the package pose of the ith target package based on machine vision, comprising the steps of:
(1) RGB image and depth data of the sorting workspace are acquired by an RGBD camera.
(2) And carrying out image segmentation on the acquired RGB image to determine the package foreground area of each package in the package separation area.
(3) And converting the depth data in the parcel foreground area of each parcel into three-dimensional point cloud data according to camera parameters of the RGBD camera, determining the parcel pose of each parcel based on the three-dimensional point cloud data in the parcel foreground area of each parcel, and determining the parcel pose of the ith target parcel. The three-dimensional point cloud data in the wrapping foreground area is utilized to fit and determine the wrapping pose comprising the position and the pose of each piece of the package, the three-dimensional point cloud data in the wrapping foreground area can be utilized to fit and obtain the wrapping pose, the wrapping height of each piece of the package can be obtained, the specific implementation method is also commonly used in the prior art, and the step is not repeated.
After the package pose of each package is determined, the package needing to be sorted in the ith sorting cycle can be determined as the ith target package, and the package pose of the ith target package is correspondingly determined. The sorting of packages according to the current common methods, typically in order of package location from top to bottom, can be determined according to the current common methods.
And 3, planning a grabbing path based on the package pose of the ith target package.
After determining the package pose of the ith target package, a grabbing path can be planned based on the package pose of the ith target package, in another embodiment, depth data of a sorting working space is converted into an occupied grid map of the working environment where the mechanical arm is located according to camera parameters of the RGBD camera, then the grabbing path is planned based on the occupied grid map, the occupied grid map indicates environment barrier information of the working environment where the mechanical arm is located, and therefore a safe path which does not collide with an environment object can be planned.
And 4, in the process of controlling the mechanical arm to drive the end effector to move to grasp the ith target package according to the planned grasping path, the step of planning the placement path based on the package pose of the ith target placement position is executed in parallel.
That is, the method does not need to wait for the mechanical arm to finish the grabbing action to grab the package and then plan the placement path as in the conventional method, but plan the placement path by adopting a double-thread parallelization processing mode in the process of grabbing the package by the mechanical arm, so that the time consumption for sorting is reduced, and the sorting efficiency is improved.
The end joint of arm is connected with end effector, and the arm utilizes end effector to snatch the i target parcel, in order to adapt to the parcel of different shapes and size, uses the sucking disc as end effector in this application an embodiment, realizes snatching through inhaling after the sucking disc laminating upper surface of parcel, and the sucking disc is blown and is realized placing the parcel. And optionally, the end face of the sucker, which is in contact with the package, is made of soft materials, so that the sucker has certain elasticity, and damage to the package caused by the sucker in the process of absorbing and grabbing the package is reduced.
Similar to planning the grabbing path, the depth data of the sorting working space is converted into an occupied grid map of the working environment where the mechanical arm is located according to camera parameters of the RGBD camera, and then the placement path is planned based on the occupied grid map.
And 5, in the process of controlling the mechanical arm to drive the end effector to move to place the grabbed ith target package to the ith target placement position according to the planned placement path, enabling i=i+1 and parallelly executing the steps of determining the package pose of the ith target package in the package separation area based on machine vision and planning the grabbing path based on the package pose of the ith target package.
The sorting cycle is performed until it is determined that the parcel separation zone is not parcel, indicating that sorting of all parcels in the parcel separation zone has been completed, then the next batch of parcels can be controlled for the parcel conveyor to transfer to the separation parcel zone, and the method of the present application continues to sort.
The i-th target placement position here is a predetermined position on the outfeed conveyor belt, and as each parcel is sorted onto the outfeed conveyor belt and transported back by the outfeed conveyor belt, the target placement positions in each sorting cycle may be the same in practice, but this application will refer to the i-th target placement position for clarity.
The same as the grabbing process, the machine vision and grabbing path planning of the next time are not needed after the mechanical arm finishes the placing action like the conventional method, but the machine vision and grabbing path planning of the next sorting cycle is performed by adopting a double-thread parallelization processing mode in the process of controlling the mechanical arm to place the package, so that the sorting time is reduced, and the sorting efficiency is improved.
When the conventional mechanical arm sorts packages, each sorting cycle mainly has the time consumption of work of grabbing path planning, grabbing path executing, placing path planning and placing path executing when sorting single packages, but the time consumption of sorting single packages in each sorting cycle by the mechanical arm is shortened to the time consumption of work of grabbing path executing and placing path executing by the mechanical arm in a double-thread parallelization processing mode, so that the time consumption of each sorting cycle is shortened, and the sorting efficiency is greatly improved.
Next, the planning of the grabbing path and the planning of the placing path are respectively described:
1. and planning a grabbing path based on the package pose of the ith target package.
The method comprises the following steps, please refer to the flow chart shown in fig. 3:
(1) And determining the grabbing final point position of the ith sorting cycle based on the package position of the ith target package.
The grasping end point pose of the ith sorting cycle is the pose of the tail end joint of the mechanical arm, and the method for determining the grasping end point pose comprises the following steps:
as described in the above step 2, the package height of the ith target package in the package separation area can also be determined based on machine vision, and then the package coordinate system O of the ith target package is determined based on the package height of the ith target package and the corresponding package pose b X b Y b Z b Ith target packageThe XY axis direction may be established according to a predetermined standard with the center of the parcel position of the i-th target parcel and at half the parcel height as the origin of coordinates, as shown in fig. 1.
After the package coordinate system of the ith target package is determined, the package pose of the ith target package under the world coordinate system can be subjected to coordinate system conversion based on the package coordinate system of the ith target package to obtain the grabbing final point pose of the ith sorting cycle. Can be expressed as world T wristworld T box * box T suction * suction T wrist . Wherein, world T box the corresponding package pose under the world coordinate system is the package pose of the ith target package under the world coordinate system in the situation. box T suction Is a transformation matrix between an end effector end face coordinate system of the mechanical arm and a parcel coordinate system of an ith target parcel, and the end effector of the mechanical arm is provided with a pre-established end effector end face coordinate system O S X S Y S Z S When the suction cup grabs the ith target package, the suction cup end face is adsorbed on the upper surface of the ith target package, so that the end effector end face coordinate system O S X S Y S Z S And the parcel coordinate system O b X b Y b Z b The Z-axis direction differs by half of the wrapping height of the ith target wrapping, the XY-axis direction of the end effector end face coordinate system and the XY-axis direction of the wrapping coordinate system are known, so that the offset relationship can be determined, and after the wrapping coordinate system is determined, the transformation matrix between the end effector end face coordinate system of the mechanical arm and the wrapping coordinate system of the ith target wrapping can be determined by combining the wrapping height of the ith target wrapping box T suctionsuction T wrist The transformation matrix between the end joints of the mechanical arm and the end effector connected with the end joints of the mechanical arm is determined after the mechanical arm is built because the end joints are fixedly connected.
(2) In the first sorting cycle, the mechanical arm moves from the initial pose to the ith target package for grabbing, so that the initial pose of the mechanical arm is used as the grabbing position of the first sorting cycle. For example, the first target package is package a, then the state of fig. 1 is shifted to the state of fig. 4. After gripping the package a, the package a is moved to the i-th target placement position according to the placement path, as shown in fig. 5, and then, in the next sorting cycle, the next target package is gripped, for example, including E, from the state of fig. 5 to the package separation area. From the above examples, it can be seen that, starting from the second sorting cycle, the robotic arm is moved from the parcel pose of the target placement position of the last sorting cycle, so that the pick-up pose of the ith sorting cycle is determined for any i.gtoreq.2 according to the parcel pose of the ith-1 target placement position.
The grabbing starting position of the ith sorting cycle is also the position of the tail end joint of the mechanical arm, and is similar to the grabbing final position of the ith sorting cycle, and the grabbing starting position of the ith sorting cycle can be obtained by carrying out coordinate system conversion on the position of the package of the ith target placement position under the world coordinate system, and the conversion expression is similar.
(3) And drawing a grabbing path from the grabbing starting position of the ith sorting cycle to the grabbing final position of the ith sorting cycle by utilizing a random sampling path planning rule.
(4) Optionally, when the suction cup is used as the end effector, since the condition that the suction cup grabs the package is that the end face of the suction cup is attached to the upper surface of the package, but since the machine vision is inevitably in detection error, the mechanical arm may not attach the end face of the suction cup to the upper surface of the i-th target package at the grabbing end position of the i-th sorting cycle, so that reliable grabbing is not possible. Therefore, in order to ensure that the suction cup can stably and firmly suck the package, in one embodiment, the suction end position of the grasping end position of the ith sorting cycle is first determined, and the grasping end position is translated downwards along the vertical direction by a predetermined distance, wherein the predetermined distance is a self-defined value.
And then drawing a suction path from the grabbing final position of the ith sorting cycle to the suction final position of the ith sorting cycle by utilizing a random sampling path planning rule.
When the control mechanical arm drives the end effector to grasp the ith target package, the control mechanical arm drives the end effector to move to the grasping end position of the ith sorting cycle according to the planned grasping path, and then the control mechanical arm drives the end effector to move to the grasping end position of the ith sorting cycle according to the grasping path, so that the control effect of lowering the sucker by a preset distance along the vertical direction is realized, the sucker is enabled to press and absorb the ith target package, and the sucker is enabled to be attached to the upper surface of the package to be reliably absorbed.
In addition, the grabbing path and the absorbing path are further subjected to smoothing treatment by adopting a track fusion smoothing algorithm, so that the grabbing path and the absorbing path are treated as a continuous smoothing path, then the mechanical arm is controlled to drive the end effector to move according to the grabbing path and the absorbing path after the smoothing treatment and grab the ith target package, the mechanical arm acceleration and deceleration caused by the sectional control of two sections of paths are avoided, the control consistency can be improved, the mechanical arm moves along the continuous smoothing path according to a unified acceleration and deceleration process, and the executed track is smoother and more efficient.
2. Planning placement path based on package pose of ith target placement position
Similar to the planned grabbing path, the method comprises the following steps:
(1) And determining the placement final point pose of the ith sorting cycle based on the package pose of the ith target placement position. Similarly, the pose of the end point is the pose of the joint at the tail end of the mechanical arm, and the pose can be obtained by converting the coordinate system of the corresponding package pose under the world coordinate system, and is similar to the method, and the description is omitted.
(2) And determining the placement starting position of the ith sorting cycle based on the package position of the ith target package. Similarly, the placement start position refers to the position of the tail end joint of the mechanical arm, and can be obtained by converting a coordinate system of a corresponding package position under a world coordinate system, and similar to the method, the description is omitted.
(3) The random sampling path planning rule is utilized to draw a placement path from a placement start position of an ith sorting cycle to a placement end position of the ith sorting cycle.
What has been described above is only a preferred embodiment of the present application, which is not limited to the above examples. It is to be understood that other modifications and variations which may be directly derived or contemplated by those skilled in the art without departing from the spirit and concepts of the present application are to be considered as being included within the scope of the present application.

Claims (10)

1. The efficient express sorting method based on the mechanical arm is characterized by comprising the following steps of:
initializing a sorting cycle parameter i=1;
determining the package pose of the ith target package in the package separation area based on machine vision, and planning a grabbing path based on the package pose of the ith target package;
in the process that the control mechanical arm drives the end effector to move to grasp the ith target package according to the planned grasping path, the step of planning the placement path based on the package pose of the ith target placement position is executed in parallel;
in the process that the mechanical arm is controlled to drive the end effector to move to place the grabbed ith target package to the ith target placement position according to the planned placement path, enabling i=i+1 and executing the step of determining the package pose of the ith target package of the package separation area based on machine vision in parallel, and planning the grabbing path based on the package pose of the ith target package until the package separation area has no package.
2. The efficient express sorting method of claim 1, wherein the planning a grabbing path based on the package pose of the i-th target package comprises:
determining a grabbing final point position of an ith sorting cycle based on the package position of an ith target package;
taking the initial pose of the mechanical arm as the grabbing and starting pose of the first sorting cycle, and determining the grabbing and starting pose of the ith sorting cycle according to the wrapping pose of the ith-1 target placement position for any i more than or equal to 2;
a random sampling path planning rule is utilized to draw a grabbing path from the grabbing starting position of the ith sorting cycle to the grabbing final position of the ith sorting cycle;
the grabbing final position and the grabbing starting position are positions of joints at the tail ends of the mechanical arms.
3. The efficient express sorting method of claim 1, wherein the planning a placement path based on the package pose of the i-th target placement position comprises:
determining a placement final point pose of the ith sorting cycle based on the package pose of the ith target placement position;
determining a placement starting position of an ith sorting cycle based on the package position of the ith target package;
using random sampling path planning rule to draw a placement path from the placement start position of the ith sorting cycle to the placement end position of the ith sorting cycle;
the placement final position and the placement starting position are positions of joints at the tail ends of the mechanical arms.
4. The efficient express sorting method according to claim 2 or 3, further comprising:
determining the package height of an ith target package in a package separation area based on machine vision, determining a package coordinate system of the ith target package based on the package height of the ith target package and a corresponding package pose of any one of a grabbing final position pose, a grabbing starting position pose, a placing final position pose and a placing starting position pose of a tail end joint of a mechanical arm, and performing coordinate system conversion on the corresponding package pose under a world coordinate system based on the package coordinate system of the ith target package to obtain the pose of the tail end joint of the mechanical arm;
the package coordinate system of the ith target package is established by taking the center of the package position of the ith target package and the position which is positioned at half of the package height as the origin of coordinates.
5. The efficient express sorting method of claim 4, wherein transforming the corresponding package pose in the world coordinate system to the pose of the arm end joint comprises determining the pose of the arm end joint world T wristworld T box * box T suction * suction T wrist
Wherein, world T box is the corresponding wrapping pose under the world coordinate system, box T suction is a transformation matrix between the end effector of the robotic arm and the package coordinate system of the ith target package, suction T wrist is a transformation matrix between the end joints of the manipulator and the end effector to which the end joints of the manipulator are connected.
6. The efficient express sorting method according to claim 2, wherein the end effector of the mechanical arm is a suction cup, the efficient express sorting method further comprising:
determining the grabbing terminal position of the ith sorting cycle, translating downwards along the vertical direction by a preset distance to obtain the absorbing terminal position, and utilizing a random sampling path planning rule to draw an absorbing path from the grabbing terminal position of the ith sorting cycle to the absorbing terminal position of the ith sorting cycle;
the controlling the mechanical arm to drive the end effector to grasp the ith target package comprises:
the control mechanical arm drives the end effector to move to the grabbing final position of the ith sorting cycle according to the planned grabbing path, and the control mechanical arm drives the end effector to move to the grabbing final position of the ith sorting cycle according to the grabbing path to push down and suck the ith target package.
7. The efficient express sorting method of claim 6, further comprising:
and after the track fusion smoothing algorithm is adopted to carry out smoothing treatment on the grabbing path and the sucking path, controlling the mechanical arm to drive the end effector to move according to the grabbing path and the sucking path after the smoothing treatment and grabbing the ith target package.
8. The efficient express sorting method of claim 6, wherein the end surfaces of the suction cups, which are in contact with the packages, are made of soft materials.
9. The efficient express sorting method of claim 1, wherein the determining the package pose of the ith target package of the package separation zone based on machine vision comprises:
acquiring RGB images and depth data of a sorting working space through an RGBD camera;
image segmentation is carried out on the acquired RGB image to determine a parcel foreground area of each parcel in the parcel separation area;
and converting the depth data in the parcel foreground area of each parcel into three-dimensional point cloud data according to camera parameters of the RGBD camera, determining the parcel pose of each parcel based on the three-dimensional point cloud data in the parcel foreground area of each parcel, and determining the parcel pose of the ith target parcel.
10. The efficient express sorting method of claim 9, wherein planning the grasp path and the place path further comprises:
and converting the depth data of the sorting working space into an occupied grid map of the working environment where the mechanical arm is located according to camera parameters of the RGBD camera, and planning a grabbing path and a placing path based on the occupied grid map.
CN202311608925.XA 2023-11-28 2023-11-28 Efficient express sorting method based on mechanical arm Pending CN117696445A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311608925.XA CN117696445A (en) 2023-11-28 2023-11-28 Efficient express sorting method based on mechanical arm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311608925.XA CN117696445A (en) 2023-11-28 2023-11-28 Efficient express sorting method based on mechanical arm

Publications (1)

Publication Number Publication Date
CN117696445A true CN117696445A (en) 2024-03-15

Family

ID=90150652

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311608925.XA Pending CN117696445A (en) 2023-11-28 2023-11-28 Efficient express sorting method based on mechanical arm

Country Status (1)

Country Link
CN (1) CN117696445A (en)

Similar Documents

Publication Publication Date Title
CN112047113B (en) 3D visual stacking system and method based on artificial intelligence technology
US11654558B2 (en) Robotic system with piece-loss management mechanism
CN109969781B (en) Taking-out device, transfer device, taking-out method, and control device
WO2019056840A1 (en) Palletizing control device, system and method and storage medium
CN112405570A (en) Robotic multi-gripper assembly and method for gripping and holding objects
CN107597600A (en) Sorting system and method for sorting
US20200361091A1 (en) A robotic system with a coordinated transfer mechanism
CN112025701B (en) Method, device, computing equipment and storage medium for grabbing object
CN111993448B (en) Robotic multi-gripper assembly and method for gripping and holding objects
Nakamoto et al. High-speed and compact depalletizing robot capable of handling packages stacked complicatedly
KR102133878B1 (en) Automatic replacement device for jig to tray for semiconductor package
CN111282827B (en) Automatic workpiece feeding and quick sorting control method
US20230041343A1 (en) Robotic system with image-based sizing mechanism and methods for operating the same
JP2023115274A (en) Extracting device
CN116728399A (en) System and method for a robotic system with object handling
CN113307042B (en) Object unstacking method and device based on conveyor belt, computing equipment and storage medium
CN115485216A (en) Robot multi-surface gripper assembly and method of operating the same
CN109641706B (en) Goods picking method and system, and holding and placing system and robot applied to goods picking method and system
CN117696445A (en) Efficient express sorting method based on mechanical arm
US11485015B2 (en) System for eliminating interference of randomly stacked workpieces
JP6600026B2 (en) Extraction device and method
CN115848715A (en) Disordered sorting robot, system and method
KR102169074B1 (en) Robot for connecting rod transfer using electromagnet
CN212190122U (en) Automatic workpiece feeding device
US20240157565A1 (en) Robotic system transfer unit cell and method of operation thereof

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination