CN112678724B - Intelligent forklift and control method thereof - Google Patents

Intelligent forklift and control method thereof Download PDF

Info

Publication number
CN112678724B
CN112678724B CN201910993598.1A CN201910993598A CN112678724B CN 112678724 B CN112678724 B CN 112678724B CN 201910993598 A CN201910993598 A CN 201910993598A CN 112678724 B CN112678724 B CN 112678724B
Authority
CN
China
Prior art keywords
path
tray
pallet
pose
intelligent forklift
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.)
Active
Application number
CN201910993598.1A
Other languages
Chinese (zh)
Other versions
CN112678724A (en
Inventor
俞毓锋
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.)
Beijing Jizhijia Technology Co Ltd
Original Assignee
Beijing Jizhijia 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 Beijing Jizhijia Technology Co Ltd filed Critical Beijing Jizhijia Technology Co Ltd
Priority to CN201910993598.1A priority Critical patent/CN112678724B/en
Publication of CN112678724A publication Critical patent/CN112678724A/en
Application granted granted Critical
Publication of CN112678724B publication Critical patent/CN112678724B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Forklifts And Lifting Vehicles (AREA)

Abstract

The specification discloses an intelligent forklift and a control method thereof, after the intelligent forklift moves to a first goods taking position of a fork-taking tray through a first forward path, the intelligent forklift can be firstly controlled to lift to the height of the tray, then images of the tray are collected, the pose of the tray is determined according to the images, when the pose deviation of the tray is determined to be larger than a preset threshold value, a second goods taking position of the fork-taking tray is determined, a second forward path reaching the second goods taking position is determined, then a first backward path reaching the second forward path is determined, and finally the intelligent forklift moves to the second goods taking position through the first backward path and the second forward path, so that the fork-taking tray is achieved. The position of the intelligent forklift can be automatically adjusted to fork the pallet, so that the requirement on the positioning accuracy of the intelligent forklift is reduced, and the problem that the intelligent forklift cannot fork the goods due to the fact that errors of the stacked positions of the pallet are accumulated for many times is solved.

Description

Intelligent forklift and control method thereof
Technical Field
The application relates to the technical field of warehouse logistics, in particular to an intelligent forklift and a control method thereof.
Background
At present, goods in a warehouse are taken and placed by using a forklift.
In the prior art, in order to enable an intelligent forklift to accurately pick and place goods in a goods pile, a method which is generally adopted is to determine the stacking position of the goods in a warehouse, and when the intelligent forklift stacks the goods or forks the goods, the position of the intelligent forklift is monitored, so that the intelligent forklift reaches the stacking position of the goods and then stacks or forks the goods.
Errors may exist in the position of the pallet when stacked with different fork lift trucks, such as differences in the front to back position, side to side position or orientation angle of the pallet. When the stacking times are large, errors of the stacking positions can be accumulated continuously, and even if the forklift reaches the stacking positions, the forklift still cannot fork goods due to the accumulation of the errors of the stacking positions of the pallets.
In the prior art, in order to reduce error accumulation of stacking positions, the method generally adopted is to improve the positioning accuracy of the forklift, but the error accumulation cannot be avoided. And when the manual control forklift and the intelligent forklift exist in the warehouse at the same time, the precision of the manual control forklift is difficult to achieve the precision of the intelligent forklift, and the difficulty of the intelligent forklift for forking goods is further increased.
Disclosure of Invention
The embodiment of the specification provides an intelligent forklift and a control method thereof, which are used for partially solving the problem that in the prior art, goods are difficult to fork and take due to the fact that accumulation of stacking errors cannot be avoided by a method for forking goods based on positioning accuracy of the intelligent forklift.
The embodiment of the specification adopts the following technical scheme:
this specification provides an intelligent fork truck, intelligent fork truck includes: processor, image sensor, action mechanism, fork mechanism, the processor includes: image sensor control module, position appearance determine module, path planning module, action mechanism control module and fork mechanism control module, wherein:
the path planning module is configured to determine a first pickup position of the intelligent forklift for picking up the pallet and determine a first forward path for the intelligent forklift to reach the first pickup position;
the actor control module is configured to send a first action command to the actor according to the first forward path;
the action mechanism moves to the first goods taking position through the first advancing path according to the received first action instruction;
the fork mechanism control module is configured to send a lifting instruction to the fork mechanism after the action mechanism moves to the first goods taking position;
The fork mechanism controls the fork to be lifted to the height of the tray according to the received lifting instruction;
the image sensor control module is configured to send an image acquisition instruction to the image sensor after the fork mechanism lifts the fork to the height of the tray;
the image sensor collects the image of the tray according to the received image collecting instruction and returns the image to the pose determining module;
the pose determination module is configured to determine a pose of the tray according to the image and determine that a pose deviation of the tray is greater than a preset threshold;
if the pose deviation of the pallet is larger than a preset threshold value, the path planning module is configured to determine a second goods picking position where the pallet is picked by the intelligent forklift, determine a second forward path where the intelligent forklift reaches the second goods picking position, and determine a first backward path where the intelligent forklift reaches the second forward path according to the second forward path;
the action mechanism control module is configured to send a second action instruction to the action mechanism according to the second forward path and the first backward path, and the action mechanism moves to the second goods taking position through the first backward path and the second forward path according to the received second action instruction, so that the pallet fork taking is realized.
Optionally, the pose determination module is configured to determine, according to the image, a stacking position of the pallet and an orientation of the pallet as the pose of the pallet, and determine whether a pose deviation of the pallet is greater than a preset threshold.
Optionally, the pose determination module is configured to determine whether a deviation between the stacking position of the pallet and the position of the intelligent forklift exceeds a first preset value, determine whether a deviation between the orientation of the pallet and the orientation of the intelligent forklift exceeds a second preset value, and if any of the determination results is yes, determine that the pose deviation of the pallet is greater than a preset threshold value.
Optionally, the path planning module is configured to determine a second goods picking position where the intelligent forklift forks the pallet according to the stacking position of the pallet, the orientation of the pallet and a preset goods picking range, determine a second forward path where the intelligent forklift reaches the second goods picking position, and determine a first backward path from the first goods picking position to the second forward path according to the second forward path and the first goods picking position.
Optionally, the image sensor control module is configured to send an image acquisition instruction to the image sensor after the action mechanism moves to the second picking position through the second forward path;
The image sensor acquires the image of the tray again according to the received image acquisition instruction and returns the image to the pose determining module;
the pose determining module is configured to re-determine the pose of the tray according to the image and judge whether the pose deviation of the tray is larger than a preset threshold value;
if the pose deviation of the pallet is larger than a preset threshold, the path planning module is configured to determine a third goods picking position, a third forward path and a second backward path, so that the action mechanism moves to the determined third goods picking position through the second backward path and the third forward path until the pose deviation of the pallet is determined to be not larger than the preset threshold by the pose determination module, and the pallet is picked.
Optionally, the larger the pose deviation of the pallet is, the longer the path of any determined retreating path is.
Optionally, the image sensor control module is configured to send a real-time image acquisition instruction to the image sensor during the movement of the action mechanism to the second pick location via the second forward path;
the image sensor collects images of the tray in real time according to the received real-time image collecting instruction and returns the images to the pose determining module;
The pose determining module is configured to determine the pose deviation of the current tray according to the acquired image and send the pose deviation to the path planning module;
the path planning module is configured to determine a deviation between the current actual driving direction of the action mechanism and the second advancing path according to the pose deviation of the tray, and adjust the current actual driving direction to be consistent with the direction of the second advancing path according to the determined deviation until the action mechanism moves to the second goods taking position.
The control method of the intelligent forklift provided by the specification comprises the following steps:
determining a first advancing path of the intelligent forklift to reach a first goods taking position according to the first goods taking position of the intelligent forklift fork taking tray;
moving to the first pickup location via the first forward path;
after the pallet fork is lifted to the height of the pallet, collecting an image of the pallet;
determining the pose of the tray according to the image;
if the position and posture deviation of the tray is larger than a preset threshold value, determining a second goods taking position where the tray is forked by the intelligent forklift, determining a second forward path where the intelligent forklift reaches the second goods taking position, and determining a first backward path where the intelligent forklift reaches the second forward path according to the determined second forward path;
And the pallet is moved to the second goods taking position through the first backward path and the second forward path, so that the pallet is forked.
Optionally, determining a tray pose of the tray according to the image specifically includes:
and determining the stacking position of the tray and the orientation of the tray according to the image as the pose of the tray.
Optionally, the deviation of the pose of the tray is greater than a preset threshold, specifically including:
judging whether the deviation between the stacking position of the pallet and the position of the intelligent forklift exceeds a first preset value or not, and judging whether the deviation between the orientation of the pallet and the orientation of the intelligent forklift exceeds a second preset value or not;
if any judgment result is yes, determining that the pose deviation of the tray is greater than a preset threshold value;
and if the judgment result is negative, determining that the pose deviation of the tray is not greater than a preset threshold value.
Optionally, determining a second pickup position where the tray is picked by the intelligent forklift, determining a second forward path where the intelligent forklift reaches the second pickup position, and determining a first backward path where the intelligent forklift reaches the second forward path according to the determined second forward path, specifically includes:
Determining a second goods taking position for the intelligent forklift to fork the tray according to the stacking position of the tray, the orientation of the tray and a preset goods taking range;
determining a second advancing path of the intelligent forklift to the second goods taking position;
and determining a first backward path from the first goods taking position to the second forward path according to the second forward path and the first goods taking position.
Optionally, the pallet fork is realized by moving to the second pickup position through the first backward path and the second forward path, and the pallet fork specifically includes:
after the intelligent forklift moves to the second goods taking position through the second advancing path, the images of the pallets are collected again;
re-determining the pose of the tray according to the re-acquired image;
judging whether the pose deviation of the tray is not larger than a preset threshold value or not;
if yes, the pallet is forked;
if not, determining a third goods taking position, a third forward path and a second backward path, and moving to the determined third goods taking position through the second backward path and the third forward path until the pose determining module determines that the pose deviation of the tray is not greater than a preset threshold value, so as to realize forking of the tray.
Optionally, the larger the pose deviation of the pallet is, the longer the path of any determined retreating path is.
Optionally, moving to the second pickup position through the second forwarding path specifically includes:
acquiring images of the tray in real time during movement to the second pick-up position via the second forwarding path;
determining the deviation between the current actual driving direction of the intelligent forklift and the second advancing path according to the image acquired in real time;
and adjusting the current actual driving direction to be consistent with the direction of the second advancing path according to the determined deviation until the current actual driving direction is moved to the second goods taking position.
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:
after the intelligent forklift moves to a first goods taking position of a fork-taking tray through a first forward path, the intelligent forklift can be controlled to lift to the height of the tray, then images of the tray are collected, the pose of the tray is determined according to the images, when the pose deviation of the tray is determined to be larger than a preset threshold value, a second goods taking position of the fork-taking tray is determined, a second forward path reaching the second goods taking position is determined, then a first backward path of the intelligent forklift reaching the second forward path is determined, and finally the intelligent forklift moves to the second goods taking position through the first backward path and the second forward path to achieve the fork-taking tray. By determining the second forward path reaching the second goods taking position, even if the intelligent forklift is at the first goods taking position, if the stacking position of the tray has an error (namely, the pose deviation of the tray is greater than a preset threshold), and the tray cannot be forked, the intelligent forklift can determine the second goods taking position, the second forward path and the first backward path according to the pose deviation of the tray, so that the intelligent forklift can be adjusted to the second goods taking position along the first backward path and the second forward path in sequence, and the tray can be forked. Because the position of the intelligent forklift can be automatically adjusted to fork the pallet, the requirement on the positioning precision of the intelligent forklift is reduced, and the problem that the intelligent forklift cannot fork the goods due to the fact that errors of the stacked positions of the pallet are accumulated after the pallet is stacked for many times is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic diagram of the operation of an embodiment of a system for controlling the stacking and forking of goods;
fig. 2 is a schematic diagram of an intelligent forklift provided in an embodiment of the present specification;
fig. 3 is a schematic structural diagram of a processor in an intelligent forklift provided in an embodiment of the present specification;
FIG. 4 is a schematic diagram of a first forward path provided by embodiments of the present description;
FIG. 5 is a schematic diagram of determining a second pickup location provided by an embodiment of the present description;
FIG. 6 is a schematic diagram of a first backward path and a second forward path provided in an embodiment of the present disclosure;
FIG. 7 is a schematic diagram of a deviation of a current actual travel direction from the second forward path provided by embodiments of the present description;
fig. 8 is a schematic diagram of a pallet forking process of the intelligent forklift provided in the embodiment of the present disclosure;
fig. 9 is a schematic control flow diagram of the intelligent forklift provided in the embodiment of the present specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more apparent, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step are within the scope of the present application.
Referring to fig. 1, fig. 1 is a schematic diagram illustrating an operation of an embodiment of a system for controlling stacking and forking of goods in a warehousing environment. The system comprises: the intelligent forklift 10, the remote server 20, the stock area 30 and the picking workstation 40, the stock area 30 contains a plurality of pallets 31 with goods, the pallets 31 with goods can be stacked into one group and arranged in the form of array between different groups to be placed in the stock area 30, or the stock area 30 contains a plurality of shelves, and the pallets 31 with goods can be placed on the shelves. Wherein, stock goods can be directly placed on the tray 31, or stock containers are placed on the tray 31, and various stock goods are contained in the stock containers.
The worker operates the server 20 through the operation panel 100, the server 20 wirelessly communicates with the intelligent forklift 10, and the intelligent forklift 10 performs tasks such as forking, stacking, and carrying under the control of the server 20. For example, the server 20 selects a pallet 31 on a shelf where a cargo space is placed or a pallet 31 where a cargo is stacked for an order based on the stock information, and the pallet 31 places an inventory container containing the order cargo of the order. In addition, the server 20 selects the picking workstation 40 and the intelligent forklift 10 for the order, plans a picking range from the original position to the tray 31 for the intelligent forklift 10, and drives the intelligent forklift 10 according to a navigation path from the tray 31 to the picking workstation 40. In order to plan a navigation path for the intelligent forklift 10, a working area of the intelligent forklift 10 (the working area at least includes the stock area 30 and the area where the picking workstation 40 is located) may be divided into a plurality of sub-areas (i.e., cells) in advance, and the intelligent forklift 10 moves from sub-area to form a motion track.
The tray 31 can be loaded with stock containers such as a bin or a tray, the bin can contain stock articles with parts removed (such as canned coke), and the tray can be used for placing stock articles with an entire tray (such as an entire box of coke). The intelligent lift truck 10 may fork the pallet 31 and transport to the picking station 40 to supply the item picking operation. Of course, other suitable loading methods for the trays 31 may be used to load bins or other types of inventory receptacles, and are within the scope of this disclosure.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 2 is a schematic diagram of an intelligent forklift provided in an embodiment of the present specification, where the intelligent forklift includes: a processor 200, a fork mechanism 201, an image sensor 202, an action mechanism 203, and the processor 200 includes: an image sensor control module 2001, a pose determination module 2002, a path planning module 2003, an action mechanism control module 2004 and a fork mechanism control module 2005, and fig. 3 is a schematic structural diagram of a processor provided in an embodiment of the present disclosure.
Wherein:
the path planning module 2003 is configured to determine a first pickup location of the intelligent forklift pallet fork and determine a first forward path for the intelligent forklift to reach the first pickup location.
Specifically, this tray is the tray that this intelligence fork truck need fork when the executive task. For example, the smart forklift requires a pallet on which the fork-picked goods are placed. In this specification, when the intelligent forklift needs to fork a pallet, the path planning module 2003 may receive a pallet position sent by the warehouse server, determine a first pickup position for forking the pallet according to the pallet position, perform path planning according to the position of the intelligent forklift and the first pickup position, and determine a first forward path for the intelligent forklift to reach the first pickup position.
Wherein, each tray position is stored in the warehouse server, and the tray position comprises coordinates and the height of the tray. In addition, when the forklift forks the goods, the position of the forklift cannot overlap with the position of the pallet, so the path planning module 2003 may determine the first pickup position according to the coordinates of the pallet position and the preset pickup range. The pick-up range can be determined according to the coordinates and a preset radius, and the value of the preset radius is set according to needs, for example, 1 meter and 1.5 meters are not limited in this specification. Therefore, the path planning module 2003 may plan a path according to the position of the pallet and the position of the intelligent forklift, determine a first pickup position on the planned path according to the preset pickup range, and determine a first forwarding path from the position of the intelligent forklift to the first pickup position.
In addition, this goods scope of getting is the scope that this intelligence fork truck can fork the tray, that is to say when this goods scope of getting, if the orientation of this intelligence fork truck fork satisfies the orientation of inserting the fork hole of this tray, then this intelligence fork truck's fork can fork the tray.
Fig. 4 is a schematic diagram of a first forward path provided in this specification, where the position of the intelligent forklift is point a, the position of the pallet to be forked is point b, the first pickup position is point c, the circle of the dotted line is a preset pickup range, the point c of the first pickup position is an intersection point of the planned path and the pickup range, the dotted line is a path planned by the path planning module, and the solid line is the first forward path and is points a to c.
The path planning module 2003, upon determining the first forward path, may send the first forward path to the mobility mechanism control module 2004.
The mobile mechanism control module 2004 may send a first mobile command to the mobile mechanism 203 according to the first forwarding path, the first mobile command being used to move the mobile mechanism 203 to the first pickup position through the first forwarding path.
The fork mechanism control module 2005 sends a lifting command to the fork mechanism 201 after the moving mechanism 203 moves to the first pick-up position.
Specifically, when the action mechanism 203 moves according to the received first action command, the path planning module 2003 may monitor the position of the smart forklift, and control the action mechanism 203 to stop moving when the position of the smart forklift reaches the first pickup position. The path planning module 2003 may also send a first notification message to the fork mechanism control module 2005, where the fork mechanism control module 2005 determines that the action mechanism 203 has moved to the first pickup position according to the received first notification message, and sends a lifting command to the fork mechanism 201, and the fork mechanism 201 controls the forks to be lifted to the height of the pallet according to the received lifting command.
In addition, the lifting instruction includes a height at which the pallet fork needs to be lifted, and specifically, the height may be determined by the path planning module 2003 when the pallet position is obtained from the warehouse server, and the determined height is carried in the first notification message and sent to the pallet fork mechanism control module 2005, so that the pallet fork mechanism control module 2005 may determine the lifting instruction according to the height of the pallet in the communication message. Wherein the tray height may be determined by the warehouse server based on the number of layers or stack height recorded when the trays are stacked. For example, assuming the pallet is stacked on a shelf, the warehouse server may record the number of layers the pallet is stacked on at the time of stacking, and determine the height at which the pallet is stacked based on the shelf single layer height and the number of layers. Or when the pallet is stacked with other goods and pallets, the warehouse server may record the height at which the pallet is stacked.
The fork mechanism 201 controls the forks to be raised to the height of the pallet in response to the received lift command.
In order to avoid the problem that the pallet fork cannot fork the pallet due to errors in stacking positions, in this specification, the posture deviation of the pallet can be determined through the acquired images of the pallet, and when the position deviation is larger than a preset threshold value, the position of the pallet fork of the intelligent forklift is adjusted.
Specifically, the image sensor 202 of the smart forklift is located on the fork base, as shown in fig. 2, so that the image sensor 202 can collect an image of the pallet and determine the posture of the pallet based on the collected image, after the fork mechanism 201 controls the fork to be lifted to the height of the pallet according to the lifting instruction, feedback can be sent to the fork mechanism control module 2005, and when receiving the feedback, the fork mechanism control module 2005 can determine the height of the fork to be lifted to the pallet and send second notification information to the image sensor control module 2001.
The image sensor control module 2001 determines that the fork has been lifted to the height of the pallet according to the reception and transmission of the second notification information, and transmits an image capturing instruction to the image sensor 202.
The image sensor 202 captures an image of the pallet according to the received image capturing instruction, and returns to the pose determination module 2002.
The pose determination module 2002 may determine the stacking position of the pallet and the orientation of the pallet as the pose of the pallet from the image of the pallet. And determining whether the pose deviation of the tray is greater than a preset threshold.
Wherein, the position and the orientation of stacking of this tray can be relative position and relative orientation with this intelligent fork truck, perhaps through the current position coordinate and current fork orientation of this intelligent fork truck, determine the position of stacking and the orientation of this tray in the map coordinate system, and the difference between the two is whether to carry out the coordinate system conversion, adopts which kind of this description does not do the restriction, specifically can set up as required.
Specifically, when the image sensor 202 is a depth camera, the pose determination module 2002 may perform local image matching (e.g., image matching by performing convolution) according to the collected depth image and a standard image template of a pallet stored in advance, determine an image of the pallet in the depth image, determine a stacking position of the pallet at the position of the depth image according to the image of the pallet part in the depth image, and determine the orientation of the pallet according to the depth value of each pixel point in the image of the pallet part. For example, assuming that the image of the tray portion has a deviation of 10 pixels from the center point position of the depth image, the relative position deviation between the tray and the image sensor can be converted and determined according to the internal parameters of the depth camera, and the stacking position of the tray can be determined. Since the depth value of the depth image characterizes the distance between the pixel point and the image sensor 202, the deflection of the tray with respect to the image sensor 202 can be characterized according to the depth value of each pixel point in the image belonging to the tray portion, and thus the orientation of the tray can be determined.
In addition, if the image sensor 202 is not a depth camera and only images are captured, the pose determination module 2002 may determine the stacking position of the pallet and the orientation of the pallet through a pre-trained neural network model. The training sample adopted by the neural network model during training contains the image of the tray, and the stacking position and the stacking orientation of the tray during image acquisition aiming at each training sample. When the neural network model is trained through the training samples, the model parameters in the neural network model are adjusted for the optimization target by minimizing the stacking position of the output of the neural network model and the stacking position of the training samples, and minimizing the orientation of the output of the neural network model and the orientation of the training samples.
Note that the stacking position of the pallet determined from the image at this time is different from the coordinates in the pallet position. The coordinates in the pallet position are the positions recorded by the warehouse server and not the positions where the actual pallets are located, for example, the center of mass position of the cargo space x is (m, n) and when a pallet is placed in the cargo space x, the warehouse server can determine the coordinates in the pallet position to be (m, n). The stacking position of the tray is the actual stacking position of the tray determined by image processing, and the stacking position of the tray can be (m + q, n + p) along with the above example, that is, the stacking error generated when the tray is stacked includes p and q.
For example, if a pallet to be forked is placed on a shelf, the coordinate position of the pallet to be forked may be a predetermined position coordinate corresponding to a cargo space of the shelf, and due to stacking errors, when the pallet is placed on the position coordinate corresponding to the cargo space, the actual stacking position of the pallet is not the position coordinate corresponding to the cargo space, so that it is necessary to acquire an image of the pallet to determine the actual stacking position of the pallet and the orientation of the pallet, that is, the pallet pose of the pallet.
After the pose determination module 2002 determines the pose of the pallet, it may determine whether a deviation between the stacking position of the pallet and the position of the intelligent forklift exceeds a first preset value, and determine whether a deviation between the orientation of the pallet and the orientation of the intelligent forklift exceeds a second preset value, if any determination result is yes, determine that the pose deviation of the pallet is greater than a preset threshold, and if no, determine that the pose deviation of the pallet is not greater than the preset threshold.
The pose determining module 2002 may determine a perpendicular line of the orientation of the pallet according to the orientation of the pallet, determine projections of the stacking position of the pallet and the position of the intelligent forklift on the perpendicular line, and then determine whether the projection distance on the perpendicular line exceeds a first preset value. The pose determination module 2002 may determine an included angle between the orientation of the pallet and the orientation of the smart forklift when determining the deviation between the orientation of the pallet and the orientation of the smart forklift, and determine whether the included angle exceeds a second preset value. Of course, the first preset value and the second preset value may be set according to needs, and the description is not limited thereto, for example, if the difference between the width of the pallet fork hole and the width of the pallet fork is 5cm, the first preset value may be 5 cm.
Further, the pose determination module 2002 may send forking information to the action mechanism control module 2004 and the fork mechanism control module 2005 when it is determined that the pose deviation of the pallet is not greater than the preset threshold, the action mechanism control module 2004 may control the action mechanism 203 to advance to insert the forks into the fork holes of the pallet, and the fork mechanism control module 2005 may control the fork mechanism 201 to lift after the forks are inserted into the fork holes of the pallet, so as to fork the pallet.
Further, if the pose determination module 2002 determines that the pose deviation of the tray is greater than a preset threshold, the pose determination module 2002 may send information that the position needs to be adjusted to the path planning module 2003.
After receiving the information that the position needs to be adjusted, the path planning module 2003 may first determine a second pickup position where the intelligent forklift forks the pallet according to the stacking position of the pallet, the orientation of the pallet, and a preset pickup range.
Specifically, the path planning module 2003 may determine, according to the stacking position of the tray and the orientation of the tray, a path to be adjusted to the stacking position according to the orientation as the forking path. Then, according to the preset picking range, a second picking position is determined in the fork picking path to which the adjustment is required, as shown in fig. 5.
Fig. 5 is a schematic diagram for determining a second pickup position provided in the present specification. The direction in which the image sensor 202 is seen to capture the image is at an angle to the orientation of the pallet, which may be specifically the centroid of the pallet, i.e., the solid circle in fig. 5, and the orientation of the pallet is shown by the arrow, and the path through the stacking position according to the orientation is the dashed line in fig. 3, and the forking path to which adjustment is required. The dotted line circle is a preset goods taking range determined by the stacking position, and the intersection point of the boundary of the hollow circle as the goods taking range and the fork taking path needing to be adjusted to is the second goods taking position.
Next, the path planning module 2003 determines a second forward path for the intelligent forklift to reach the second pickup location.
Specifically, the path planning module 2003 may determine a starting point of a second forward path on the forking path to be adjusted according to the deviation between the stacking position of the pallet and the position of the intelligent forklift and the deviation between the orientation of the pallet and the orientation of the intelligent forklift determined by the pose determination module 2002, and determine the second forward path by using the second picking position as a terminal point.For example, the path planning module 2003 may determine the L according to the formula 1+L2、L1R × h and L2The path length of the second forward path is determined t × y. L represents the length from the start point to the end point of the second advancing path, L1Indicating a determined path component, L, based on the deviation of the stacking position of the pallet from the position of the intelligent forklift (e.g., the first pickup position)2The distance component determined according to the deviation of the orientation of the tray and the orientation of the intelligent forklift is shown, r and t are respectively preset parameters, h is the deviation of the stacking position of the tray and the position of the intelligent forklift, and y is the deviation of the orientation of the tray and the orientation of the intelligent forklift. Here, the positional deviation and the orientation deviation have already been described when the aforementioned pose determination module 2002 determines the pallet pose deviation, and are not repeated here. Assuming that r is 100, t is 15, h is 0.05m, and y is 5 degrees, L is determined to be 80.
Alternatively, the path planning module 2003 may also determine, according to the current location (i.e., the first pickup location) of the intelligent forklift, a moving trajectory of the intelligent forklift when the pallet is picked up at the current location as a current trajectory, determine, as an adjustment trajectory, a moving trajectory of the intelligent forklift when the pallet is picked up via the second forward path, and then determine, according to a deviation between the current trajectory and the adjustment trajectory, a starting point of the second forward path on the pickup path to be adjusted. For example, if the angle between the current trajectory and the adjustment trajectory is 3 degrees, the path planning module 2003 may determine a starting point on the second forward path according to the angle of the included angle, for example, if it is assumed that the distance between the starting point and the end point on the second forward path is determined according to the formula L ═ α × β, L represents the distance, β represents the angle of the included angle, and α is a predetermined constant, such as 10 m.
Finally, the path planning module 2003 may determine a first backward path from the first pickup position to the second forward path according to the second forward path and the first pickup position.
In addition, the path planning module 2003 may use a smooth curve from the first pickup position to the start point of the second forward route as the backward route when generating the first backward route. For example, a curve from the first pickup position to the start point of the second travel path is generated using a bezier curve or a quintic polynomial curve, but the present specification is not limited to a specific manner of generating a smooth curve.
Alternatively, the path planning module 2003 may also determine a first backward path from the first pickup position to the starting point of the second forward path according to the area where the intelligent forklift can travel, for example, a path from a detour to the starting point, which is not limited in this specification, as long as the intelligent forklift can reach the starting point according to the first backward path.
Further, if the posture deviation of the pallet is larger, it indicates that the distance that the intelligent forklift needs to move when the intelligent forklift is adjusted to the standard forking path according to the smooth curve is longer, and therefore, if the posture deviation of the pallet is larger, the determined distances of the first backward path and the second forward path are longer.
Fig. 6 is a schematic diagram of a first backward path and a second forward path provided in an embodiment of the present disclosure. The current positions of the intelligent forklift A and the intelligent forklift B, namely the solid original points, are included in fig. 6, namely the first goods taking positions respectively corresponding to the intelligent forklift A and the intelligent forklift B. And, the intelligent forklift a and the intelligent forklift both determine the same second advancing path, i.e., the dotted line in fig. 6, and respectively determine the starting point, i.e., the hollow origin. If the posture deviation of the pallet determined by the intelligent forklift a is smaller than the posture deviation of the pallet determined by the intelligent forklift B, the determined distance between the starting point a 'of the second advancing path of the intelligent forklift a and the second goods taking position (namely the terminal point) is closer, and the distance between the starting point B' of the second advancing path of the intelligent forklift B and the second goods taking position is farther.
It should be noted that, although in the above example, the formula adopted to determine the path length of the second forward path is a linear formula, that is, the pose deviation and the path are in a linear relationship, the present specification does not limit whether the pose deviation and the path are in a linear relationship or an exponential relationship, as long as the pose deviation and the path are in a positive correlation. For example, formula L 1Change to L when r × h1Log (h) +1 to determine the path component,the position deviation is exponentially and positively correlated with the course.
The path planning module 2003 may send the determined first backward path and second forward path to the actor control module 2004. The actor control module 2004 may send a second action command to the actor 203 according to the second forward path and the first backward path. The action mechanism 203 moves to the second goods-taking position through the first backward path and the second forward path according to the received second action instruction, so as to realize the fork-taking of the pallet.
Specifically, after the action mechanism 203 reaches the second picking position, the path planning module 2003 may send forking information to the action mechanism control module 2004 and the fork mechanism control module 2005, so that the action mechanism control module 2004 may control the action mechanism 203 to advance to insert the forks into the fork holes of the tray, and the fork mechanism control module 2005 may control the fork mechanism 201 to lift after the forks are inserted into the fork holes of the tray, so as to fork the tray.
Based on the intelligent forklift shown in fig. 2, after the intelligent forklift moves to the first goods taking position of the forking tray through the first forward path, the intelligent forklift can be controlled to lift to the height of the tray, then the image of the tray is collected, the pose of the tray is determined according to the image, when the pose deviation of the tray is determined to be larger than a preset threshold value, the second goods taking position of the forking tray is determined, the second forward path reaching the second goods taking position is determined, then the intelligent forklift reaches the first backward path of the second forward path, and finally the intelligent forklift moves to the second goods taking position through the first backward path and the second forward path, so that the forking tray is achieved. By determining the second forward path reaching the second goods taking position, even if the intelligent forklift has an error in the stacking position of the pallet at the first goods taking position (namely, the posture deviation of the pallet is greater than a preset threshold value), and the pallet cannot be forked, the intelligent forklift can determine the first backward path according to the second forward path, so that the intelligent forklift can be adjusted to the second goods taking position along the first backward path and the second forward path in sequence and can fork the pallet. Because the position of the intelligent forklift can be automatically adjusted to fork the pallet, the requirement on the positioning precision of the intelligent forklift is reduced, and the problem that the intelligent forklift cannot fork the goods due to the fact that errors of the stacked positions of the pallet are accumulated after the pallet is stacked for many times is solved.
In addition, because the intelligent forklift has a problem of positioning error when positioning, when the intelligent forklift advances along the second advancing path, an actual traveling path may deviate, and in order to reduce an influence caused by the positioning error, in this specification, the intelligent forklift can adjust a traveling direction of the intelligent forklift in a process of moving to the second pickup position along the second advancing path, so that the actual traveling direction of the intelligent forklift is made to coincide with the direction of the second advancing path.
Specifically, first, the image sensor control module 2001 may send a real-time image capturing instruction to the image sensor 202 during the moving mechanism 203 moves to the second pick-up position along the second forward path.
The image sensor 202 may collect the image of the tray in real time according to the received collecting instruction, and return to the pose determining module 2002.
The pose determining module 2002 may determine the current pose deviation of the tray in real time according to the received image, and send the pose deviation to the path planning module 2003.
The path planning module 2003 may determine the current actual driving direction of the action mechanism 203 according to the current posture deviation of the pallet, and determine the deviation of the current actual driving direction from the second forwarding path, as shown in fig. 7. The arrow in fig. 7 shows the actual direction of travel of the smart forklift, and the dashed line is the second forward path. The deviation may specifically be an angle between the current actual driving direction and the second forward path.
The path planning module 2003 may adjust the travel path of the intelligent forklift according to the determined deviation until the intelligent forklift moves to the pickup range. Specifically, the path planning module 2003 may send the adjusted path to the action mechanism control module 2004 in a manner of minimizing the deviation according to the determined deviation, the action mechanism control module 2004 sends a third movement instruction to the action mechanism 203 according to the adjusted path, and the action mechanism 203 finely adjusts the travel direction according to the third movement instruction, so that the pose deviation of the pallet acquired at the next moment is reduced, that is, the action mechanism control module 2004 sends the third movement instruction for adjusting the actual travel direction, so that the action mechanism 203 adjusts the current actual travel direction to be consistent with the direction of the second forward path.
Further, since the second forward path determined by the path planning module 2003 may also have a certain deviation, and therefore, when the intelligent forklift reaches the second pickup position along the second forward path, the situation that the posture deviation of the pallet is still large may occur, in this specification, the intelligent forklift may determine the third pickup position, the third forward path, and the second backward path again, and after reaching the third pickup position, determine whether the posture deviation of the pallet determined again is greater than the preset threshold, if so, continue to repeat the above process until it is determined that the posture deviation of the pallet is not greater than the preset threshold, thereby achieving pallet forking.
Specifically, the image sensor control module 2001 sends an image capturing instruction to the image sensor 202 after the moving mechanism 203 moves to the second pick-up position through the second forward path.
The image sensor 202 re-acquires the image of the tray according to the received image acquisition instruction, and returns to the pose determination module 2002.
The pose determination module 2002 re-determines the pose of the pallet according to the image, and determines whether the pose deviation of the pallet is greater than a preset threshold.
If the pose deviation of the pallet is greater than the preset threshold, the path planning module 2003 may determine a third pick-up position, a third forward path and a second backward path, which are consistent with the process of determining the second pick-up position, the second forward path and the first backward path at the first pick-up position by the path planning module 2003, the action mechanism control module 2004 may send a fourth action command to the action mechanism 203 according to the determined third forward path and the determined second backward path, the action mechanism 203 sequentially moves to the third pick-up position through the second backward path and the third forward path, the image sensor 202 continues to acquire images, and the pose determination module 2002 determines whether the pose deviation of the pallet is greater than the preset threshold according to the image of the pallet recently acquired by the image sensor 202, if not, the above process is repeated until the pose determination module 2002 determines that the pose deviation of the pallet is not greater than the preset threshold, the pallet is taken out by forking.
And if the posture deviation of the pallet is determined to be not greater than the preset threshold value at any goods taking position, the intelligent forklift forks the pallet.
That is to say, when the intelligent forklift is at any goods taking position, as long as the posture deviation of the tray is determined to be larger than the preset threshold, the path planning module 2003 can determine the advancing path for re-forking the tray, and the process can be repeated until the posture deviation of the tray is determined to be not larger than the preset threshold, so that the forking of the tray is realized.
Further, the specification also provides a schematic diagram of a process of forking a tray of the intelligent forklift, as shown in fig. 8, after the intelligent forklift reaches the first goods-picking position a along the first forward path, it is determined that the posture deviation of the tray is greater than the preset threshold value, the intelligent forklift reverses to the second forward path through the first backward path, then drives to the second goods-picking position B along the second forward path, and forks the tray.
Based on the intelligent forklift shown in fig. 2, the present specification also provides a control method of the intelligent forklift, as shown in fig. 9.
Fig. 9 is a schematic control flow diagram of the intelligent forklift provided in this specification, which may specifically include the following steps:
s300: and determining a first advancing path of the intelligent forklift to reach the first goods taking position according to the first goods taking position of the intelligent forklift fork taking tray.
In this specification, the intelligent forklift can receive order information sent by the server, determine a pallet to be forked, and determine the position of the pallet. And moved to the pick range of the pallet to fork the pallet through the subsequent steps.
Specifically, since the server records the stacking position of the goods when the goods are stacked in the warehouse at present, the order information may include the stacking position of the pallet, and the intelligent forklift may determine the position of the pallet according to the stacking position. Or when the pallet is put on shelf, the server records the goods position of the pallet, the order information can contain the position of the goods position, and the intelligent forklift can determine the position of the pallet according to the position of the goods position. Certainly, the specific determination of the position of the pallet is a necessary step when the intelligent forklift forks to pick up and stack goods, and various mature methods exist in the prior art, and this description is not repeated.
The intelligent forklift can determine a first goods taking position according to the position of the tray and a preset goods taking range, and then plan a path according to the position of the intelligent forklift and the first goods taking position to determine a first advancing path.
S302: moving to the first pick location via the first forward path.
S304: after the forks are lifted to the height of the pallet, images of the pallet are collected.
S306: and determining the pose of the tray according to the image.
In this specification, the intelligent forklift can lift the pallet to the height of the pallet after reaching the first goods taking position, so that the image sensor on the pallet base collects the image of the pallet. The tray is placed on the tray.
In this specification, this intelligence fork truck can confirm the tray position appearance of this tray according to the image of gathering. Wherein, this tray position appearance includes the orientation of piling up position and this tray of this tray.
Specifically, the stacking position and the orientation of the pallet may be relative positions and relative orientations of the pallet and the intelligent forklift, or the stacking position and the orientation of the pallet in a map coordinate system are determined by coordinates of a current position (i.e., coordinates of a first pickup position) and a current fork orientation of the intelligent forklift, and a difference between the stacking position and the orientation of the pallet and the current position is whether to convert the coordinate system.
If the intelligent forklift acquires the depth image of the tray through the depth camera, the intelligent forklift can perform local image matching (for example, perform image matching through convolution) according to the acquired depth image and a pre-stored standard image template of the tray, and determine the image belonging to the tray in the depth image.
And then determining the stacking position of the tray at the position of the depth image according to the image belonging to the tray part in the depth image. And determining the orientation of the tray according to the depth value of each pixel point in the image belonging to the tray part.
For example, assuming that the image of the tray portion has a deviation of 10 pixels from the center point position of the depth image, the relative position deviation between the tray and the image sensor can be converted and determined according to the internal parameters of the depth camera, and the stacking position of the tray can be determined. Since the depth value of the depth image represents the distance between the pixel point and the image sensor, the deflection of the tray relative to the image sensor can be represented according to the depth value of each pixel point in the image belonging to the tray part, and therefore the orientation of the tray can be determined.
Or when the intelligent forklift adopts the non-depth camera to collect the images of the tray, the intelligent forklift can input the images of the tray into a pre-trained neural network model to obtain the tray pose of the tray. The neural network may be a convolutional neural network, a multi-layer perceptron, etc., and the specification does not limit what neural network model is specifically adopted.
S308: and if the position and posture deviation of the tray is larger than a preset threshold value, determining a second goods taking position where the tray is forked by the intelligent forklift, determining a second forward path where the intelligent forklift reaches the second goods taking position, and determining a first backward path where the intelligent forklift reaches the second forward path according to the determined second forward path.
In this specification, the intelligent forklift may determine whether a deviation between a stacking position of the pallet and a position of the intelligent forklift exceeds a first preset value, and determine whether a deviation between an orientation of the pallet and an orientation of the intelligent forklift exceeds a second preset value, if any determination result is yes, it is determined that a pose deviation of the pallet is greater than a preset threshold value, and if no determination result is obtained, it is determined that the pose deviation of the pallet is not greater than the preset threshold value.
And the larger the pose deviation is, the longer the path of any determined retreating path is.
In addition, in this specification, if it is determined that the pose deviation is not greater than the preset threshold value, the intelligent forklift may directly fork the pallet.
S310: and moving to the second goods taking position through the first backward path and the second forward path to realize forking the tray.
In this specification, after the first backward path is determined, the intelligent forklift can adjust the position to the second forward path through the first backward path, and move to the second goods picking position along the second forward path. After moving to the second goods taking position, the pallet is taken through a fork.
Specifically, the intelligent forklift adjusts the position to the second forward path according to the first backward path, and the orientation of the fork of the intelligent forklift is adjusted to point to the pallet. When the intelligent forklift moves, the intelligent forklift can move backwards to the second advancing path according to the first backward path, so that the pallet fork faces the pallet. Or after the intelligent forklift reaches the second advancing path through the first precise backward path, the pallet fork is adjusted to face the pallet. How this specification does not restrict is removed to this specific intelligence fork truck, as long as remove back this intelligence fork truck be located this second way of advancing, and the fork can towards this tray. Wherein the forks are directed towards the pallet, i.e. the direction of the forks coincides with the direction of the second advancement path.
Secondly, when the intelligent forklift moves to the second advancing path, the tray can be forked by the intelligent forklift along the second advancing path, and the situation that the pallet cannot be inserted into the tray cannot occur, so that the intelligent forklift can continue to move to the tray along the second advancing path until the intelligent forklift moves to the second goods taking position to stop, and the pallet is controlled to be forked by the pallet.
In addition, because the intelligent forklift has a problem of positioning error when positioning, when the intelligent forklift moves along the second forward path, an actual driving path may deviate, and in order to reduce the influence caused by the positioning error, in this specification, the intelligent forklift can acquire an image of the pallet in real time during the process of moving along the second forward path to the pickup range, determine the current actual driving direction of the intelligent forklift according to the acquired image, determine the deviation between the current actual driving direction and the second forward path, and finally adjust the current actual driving direction to be consistent with the direction of the second forward path according to the determined deviation until the intelligent forklift moves to the pickup range.
Specifically, the intelligent forklift can adjust the driving direction of the intelligent forklift in a mode of minimizing deviation according to the determined deviation. For example, if the deviation between the current actual driving direction and the second forward path is 5 degrees to the right, the driving direction of the intelligent forklift is controlled to be 5 degrees to the left.
Of course, the control process of the intelligent forklift specifically refers to the operations executed by the modules included in the processor 200 of the intelligent forklift, and detailed processes are not repeated in this specification. For example, the instruction of 5 degrees left is directly transmitted to the action mechanism, or the adjustment path of 5 degrees left from the current actual driving direction is determined first, and then the instruction is transmitted according to the adjustment path, so that the driving direction of the action mechanism is 5 degrees left.
Further, since the second forward path may also have a certain deviation, a situation that the posture deviation of the tray is still large when the intelligent forklift reaches the second pickup position along the second forward path may occur, in this specification, when the intelligent forklift determines that the posture deviation of the tray is still larger than the preset threshold at the second pickup position, the intelligent forklift may determine the third pickup position, the third forward path, and the second backward path, and after reaching the third pickup position, determine whether the posture deviation of the tray determined again is larger than the preset threshold, if so, continue to repeat the above process until it is determined that the posture deviation of the tray is not larger than the preset threshold, thereby achieving the purpose of forking the tray.
Specifically, the intelligent forklift can acquire the image of the tray again after moving to the second goods taking position through the second advancing path, and the pose of the tray is determined again according to the image. And judging whether the pose deviation of the tray is not greater than a preset threshold value. If yes, the pallet is forked.
If not, the intelligent forklift can determine a third goods taking position, a third forward path and a second backward path by adopting the same operation as the step S308, sequentially moves to the third goods taking position through the second backward path and the third forward path, acquires the images again to determine the images of the tray, judges whether the pose deviation of the tray is greater than a preset threshold value again, and repeats the process if not until the pose deviation of the tray is determined to be not greater than the preset threshold value, thereby realizing the forking of the tray.
When the intelligent forklift is at any goods taking position, as long as the posture deviation of the tray is determined to be larger than the preset threshold value, the forward path for re-forking the tray and the backward path to any backward path on the forward path can be determined by repeating the process of the step S308, and the process can be repeated until the posture deviation of the tray is determined to be not larger than the preset threshold value, so that the forking of the tray is realized.
The above process may specifically include, according to the control flow of the intelligent forklift: step 1, determining a first advancing path of the intelligent forklift reaching a first goods taking position according to the first goods taking position of the intelligent forklift forking tray. And 2, moving to the first goods taking position through the first advancing path, and lifting the fork to the height of the tray. And 3, acquiring an image of the tray, and determining the pose of the tray according to the image. And 4, judging whether the pose deviation of the tray is greater than a preset threshold value, if so, executing the step 5, and otherwise, executing the step 6. And 5, determining a second goods taking position where the tray is forked by the intelligent forklift, determining a second forward path where the intelligent forklift reaches the second goods taking position, determining a first backward path where the intelligent forklift reaches the second forward path according to the determined second forward path, moving to the second goods taking position through the first backward path and the second forward path, and executing the step 3. And 6, forking the tray.
Based on the intelligent forklift control method shown in fig. 2, after the intelligent forklift moves to the first goods taking position of the forking tray through the first forward path, the height of the forking tray lifted to the tray can be controlled firstly, then the image of the tray is collected, the pose of the tray is determined according to the image, when the pose deviation of the tray is determined to be larger than the preset threshold value, the second goods taking position of the forking tray is determined, the second forward path reaching the second goods taking position is determined, then the first backward path of the intelligent forklift reaching the second forward path is determined, and finally the intelligent forklift moves to the second goods taking position through the first backward path and the second forward path to fork the tray. By determining the second forward path reaching the second goods taking position, even if the intelligent forklift has an error in the stacking position of the pallet (namely, the posture deviation of the pallet is greater than a preset threshold) at the first goods taking position, and the pallet cannot be forked, the intelligent forklift can determine the first backward path according to the second forward path, so that the intelligent forklift can be adjusted to the second goods taking position along the first backward path and the second forward path in sequence, and can fork the pallet. Because the position of the intelligent forklift can be automatically adjusted to fork the pallet, the requirement on the positioning precision of the intelligent forklift is reduced, and the problem that the intelligent forklift cannot fork the goods due to the fact that errors of the stacked positions of the pallet are accumulated after the pallet is stacked for many times is solved.
Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
In the 90's of the 20 th century, improvements to a technology could clearly distinguish between improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements to process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is an integrated circuit whose Logic functions are determined by a user programming the Device. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present disclosure, and is not intended to limit the present disclosure. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims (14)

1. An intelligent forklift, characterized in that, intelligence forklift includes: processor, image sensor, action mechanism, fork mechanism, the processor includes: image sensor control module, position appearance determine module, path planning module, action mechanism control module and fork mechanism control module, wherein:
the path planning module is configured to determine a first pickup position of the intelligent forklift for picking up the pallet and determine a first forward path for the intelligent forklift to reach the first pickup position;
The actor control module is configured to send a first action command to the actor according to the first forward path;
the action mechanism moves to the first goods taking position through the first advancing path according to the received first action instruction;
the fork mechanism control module is configured to send a lifting instruction to the fork mechanism after the action mechanism moves to the first goods taking position;
the fork mechanism controls the fork to be lifted to the height of the tray according to the received lifting instruction;
the image sensor control module is configured to send an image acquisition instruction to the image sensor after the fork mechanism lifts the fork to the height of the tray;
the image sensor collects the image of the tray according to the received image collecting instruction and returns the image to the pose determining module;
the pose determination module is configured to determine a pose of the tray according to the image and determine that a pose deviation of the tray is greater than a preset threshold;
if the pose deviation of the pallet is larger than a preset threshold value, the path planning module is configured to determine a second goods picking position where the pallet is picked by the intelligent forklift, determine a second forward path where the intelligent forklift reaches the second goods picking position, and determine a first backward path where the intelligent forklift reaches the second forward path according to the second forward path;
The action mechanism control module is configured to send a second action instruction to the action mechanism according to the second forward path and the first backward path, and the action mechanism moves to the second goods taking position through the first backward path and the second forward path according to the received second action instruction, so that the pallet fork taking is realized.
2. The intelligent forklift of claim 1, wherein the attitude determination module is configured to determine a stacking position of the pallet and an orientation of the pallet as the attitude of the pallet from the image, and determine whether a deviation of the attitude of the pallet is greater than a preset threshold.
3. The intelligent forklift of claim 2, wherein the pose determination module is configured to determine whether a deviation between the stacking position of the pallet and the position of the intelligent forklift exceeds a first preset value, and determine whether a deviation between the orientation of the pallet and the orientation of the intelligent forklift exceeds a second preset value, and if either determination is positive, determine that the pose deviation of the pallet is greater than a preset threshold value.
4. The intelligent lift truck of claim 2, wherein the path planning module is configured to determine a second pick location at which the intelligent lift truck picks the pallet based on the stacking location of the pallet, the orientation of the pallet, and a preset pick range, determine a second forward path for the intelligent lift truck to reach the second pick location, and determine a first backward path for the intelligent lift truck to backward from the first pick location to the second forward path based on the second forward path and the first pick location.
5. The intelligent lift truck of claim 4, wherein the image sensor control module is configured to send an image capture instruction to the image sensor after the mobile mechanism moves to the second pickup location via the second forward path;
the image sensor acquires the image of the tray again according to the received image acquisition instruction and returns the image to the pose determining module;
the pose determining module is configured to re-determine the pose of the tray according to the image and judge whether the pose deviation of the tray is larger than a preset threshold value;
if the pose deviation of the pallet is larger than a preset threshold, the path planning module is configured to determine a third goods picking position, a third forward path and a second backward path, so that the action mechanism moves to the determined third goods picking position through the second backward path and the third forward path until the pose deviation of the pallet is determined to be not larger than the preset threshold by the pose determination module, and the pallet is picked.
6. The intelligent lift truck of claim 4, wherein the greater the deviation in pose of said pallet, the longer the path of any determined retreat path.
7. The intelligent lift truck of claim 4, wherein the image sensor control module is configured to send real-time image capture instructions to the image sensor during movement of the mobile mechanism to the second pickup location via the second forward path;
the image sensor collects images of the tray in real time according to the received real-time image collecting instruction and returns the images to the pose determining module;
the pose determining module is configured to determine the pose deviation of the current tray according to the acquired image and send the pose deviation to the path planning module;
the path planning module is configured to determine a deviation between the current actual driving direction of the action mechanism and the second advancing path according to the pose deviation of the tray, and adjust the current actual driving direction to be consistent with the direction of the second advancing path according to the determined deviation until the action mechanism moves to the second goods taking position.
8. A control method of an intelligent forklift is characterized by comprising the following steps:
determining a first advancing path of the intelligent forklift to reach a first goods taking position according to the first goods taking position of the intelligent forklift fork taking tray;
Moving to the first pickup location via the first forward path;
after the pallet fork is lifted to the height of the pallet, collecting an image of the pallet;
determining the pose of the tray according to the image;
if the position and posture deviation of the tray is larger than a preset threshold value, determining a second goods taking position where the tray is forked by the intelligent forklift, determining a second forward path where the intelligent forklift reaches the second goods taking position, and determining a first backward path where the intelligent forklift reaches the second forward path according to the determined second forward path;
and moving to the second goods taking position through the first backward path and the second forward path to realize forking the tray.
9. The method of claim 8, wherein determining a tray pose of the tray from the image comprises:
and determining the stacking position of the tray and the orientation of the tray according to the image as the pose of the tray.
10. The method of claim 9, wherein the pallet pose deviation is greater than a preset threshold, specifically comprising:
judging whether the deviation between the stacking position of the pallet and the position of the intelligent forklift exceeds a first preset value or not, and judging whether the deviation between the orientation of the pallet and the orientation of the intelligent forklift exceeds a second preset value or not;
If any judgment result is yes, determining that the pose deviation of the tray is larger than a preset threshold value;
and if the judgment result is negative, determining that the pose deviation of the tray is not greater than a preset threshold value.
11. The method of claim 9, wherein determining a second pickup location at which the intelligent forklift forks the pallet, determining a second forward path for the intelligent forklift to reach the second pickup location, and determining a first reverse path for the intelligent forklift to reach the second forward path based on the determined second forward path comprises:
determining a second goods taking position for the intelligent forklift to fork the tray according to the stacking position of the tray, the orientation of the tray and a preset goods taking range;
determining a second advancing path of the intelligent forklift to the second goods taking position;
and determining a first backward path from the first goods taking position to the second forward path according to the second forward path and the first goods taking position.
12. The method of claim 11, wherein moving to the second pickup position via the first reverse path and the second forward path effects forking of the tray, comprising:
After the intelligent forklift moves to the second goods taking position through the second advancing path, the images of the pallets are collected again;
re-determining the pose of the tray according to the re-acquired image;
judging whether the pose deviation of the tray is not larger than a preset threshold value or not;
if yes, the pallet is forked;
if not, determining a third goods taking position, a third forward path and a second backward path, and moving to the determined third goods taking position through the second backward path and the third forward path until the pose determining module determines that the pose deviation of the tray is not greater than a preset threshold value, so as to realize forking of the tray.
13. The method of claim 11, wherein the greater the deviation in pose of the pallet, the longer the path of any determined retreat path.
14. The method of claim 11, wherein moving to the second pickup location via the second forward path comprises:
acquiring images of the tray in real time during movement to the second pick-up position via the second forwarding path;
determining the deviation between the current actual driving direction of the intelligent forklift and the second advancing path according to the image acquired in real time;
And adjusting the current actual driving direction to be consistent with the direction of the second advancing path according to the determined deviation until the current actual driving direction is moved to the second goods taking position.
CN201910993598.1A 2019-10-18 2019-10-18 Intelligent forklift and control method thereof Active CN112678724B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910993598.1A CN112678724B (en) 2019-10-18 2019-10-18 Intelligent forklift and control method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910993598.1A CN112678724B (en) 2019-10-18 2019-10-18 Intelligent forklift and control method thereof

Publications (2)

Publication Number Publication Date
CN112678724A CN112678724A (en) 2021-04-20
CN112678724B true CN112678724B (en) 2022-06-10

Family

ID=75444952

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910993598.1A Active CN112678724B (en) 2019-10-18 2019-10-18 Intelligent forklift and control method thereof

Country Status (1)

Country Link
CN (1) CN112678724B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113511611B (en) * 2021-04-30 2022-09-16 深圳聚创致远科技有限公司 Production line AGV control system based on big data co-construction sharing
CN114634133B (en) * 2022-05-17 2022-09-09 江苏智库智能科技有限公司 Narrow roadway omnidirectional AGV (automatic guided vehicle) forklift and control method thereof
CN115562276A (en) * 2022-10-11 2023-01-03 劢微机器人科技(深圳)有限公司 Path planning method, device, equipment and computer readable storage medium
CN115848878B (en) * 2023-02-28 2023-05-26 云南烟叶复烤有限责任公司 AGV-based tobacco frame identification and stacking method and system
CN117555308B (en) * 2024-01-12 2024-04-26 泉州装备制造研究所 Tray recycling method, system and storage medium based on unmanned forklift

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015225450A (en) * 2014-05-27 2015-12-14 村田機械株式会社 Autonomous traveling vehicle, and object recognition method in autonomous traveling vehicle
US10640347B2 (en) * 2017-12-22 2020-05-05 X Development Llc Pallet tracking during engagement and disengagement
CN108640040B (en) * 2018-03-28 2020-03-27 华南农业大学 Pose adjusting path planning method of intelligent forklift
CN108584800A (en) * 2018-05-11 2018-09-28 华南农业大学 A kind of the automatic Pilot fork truck and automated storage and retrieval system of automatic loading and unloading cargo
CN109160451A (en) * 2018-08-01 2019-01-08 顺丰科技有限公司 Independent navigation unmanned fork lift, system and control method
CN109368552A (en) * 2018-10-22 2019-02-22 广州微牌智能科技有限公司 Pallet enters to pitch method, apparatus, system, equipment and storage medium
CN109650292B (en) * 2019-02-02 2019-11-05 北京极智嘉科技有限公司 The location regulation method and medium of a kind of intelligent forklift and intelligent forklift
CN109795830A (en) * 2019-03-04 2019-05-24 北京旷视科技有限公司 It is automatically positioned the method and device of logistics tray

Also Published As

Publication number Publication date
CN112678724A (en) 2021-04-20

Similar Documents

Publication Publication Date Title
CN112678724B (en) Intelligent forklift and control method thereof
JP7433339B2 (en) Intelligent warehousing system, processing terminal, warehousing robot and intelligent warehousing method
WO2021129563A1 (en) Container handling method employing dense storage
CN205397170U (en) Store in a warehouse intelligent transfer robot and handling system
US11377299B2 (en) Warehousing access system and method
EP3512785B1 (en) Integrated obstacle detection and payload centering sensor system
CN110727268A (en) Forklift device, forklift control method, and recording medium
CN109911272A (en) A kind of free code piling box method based on reference line criterion
CN111605945A (en) Article warehousing system and article warehousing method
CN113800167A (en) Equipment recycling and warehousing method and system based on 3D vision
EP4177016A1 (en) Methods, apparatuses and computer program products for providing a dynamic clearance system for depalletizing objects
CN109747887B (en) Automatic packaging system, mechanical arm, packaging method and device for warehousing articles
US20210347617A1 (en) Engaging an element
CN111762498A (en) Movable indicating equipment, picking system, picking method and server
WO2022242295A1 (en) Scheduling system and method for intelligent mobile robot
US20240211879A1 (en) Conveyance plan generation method, conveyance plan generation apparatus, and computer-readable storage medium
CN107538491B (en) Construction method of space coordinate system based on mechanical arm
CN214609590U (en) Box taking equipment
CN113313446B (en) Container management and control method, system, control equipment and storage medium
CN112686077A (en) Self-driven robot and obstacle identification method
CN214987861U (en) Storage goods picking system
US20240142985A1 (en) De-centralized traffic-aware navigational planning for mobile robots
Leitner et al. Designing Cartman: a cartesian manipulator for the Amazon Robotics Challenge 2017
CN115072235A (en) Goods taking method, automatic navigation vehicle and intelligent warehousing system
EP4292956A1 (en) Information processing device, information processing method, program, and system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
CB02 Change of applicant information

Address after: 100020 Beijing Chaoyang District Chuang Yuan Road 36 hospital 1 building 101

Applicant after: Beijing jizhijia Technology Co.,Ltd.

Address before: 100020 Beijing Chaoyang District Chuang Yuan Road 36 hospital 1 building 101

Applicant before: Beijing Geekplus Technology Co.,Ltd.

CB02 Change of applicant information
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant