CN114358145A - Forklift unloading method, forklift and computer-readable storage medium - Google Patents
Forklift unloading method, forklift and computer-readable storage medium Download PDFInfo
- Publication number
- CN114358145A CN114358145A CN202111546284.0A CN202111546284A CN114358145A CN 114358145 A CN114358145 A CN 114358145A CN 202111546284 A CN202111546284 A CN 202111546284A CN 114358145 A CN114358145 A CN 114358145A
- Authority
- CN
- China
- Prior art keywords
- goods
- position information
- forklift
- point cloud
- cloud data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Forklifts And Lifting Vehicles (AREA)
Abstract
The invention discloses a forklift unloading method, a forklift and a computer readable storage medium, and belongs to the technical field of forklifts. The method comprises the steps of obtaining point cloud data of a carriage and goods on a flat car parked at a preset position, obtained by first detection equipment, and obtaining image data of the flat car, obtained by second detection equipment, wherein the first detection equipment and the second detection equipment are both positioned right above the preset position; determining the position information of the goods on the flat car according to the point cloud data of the carriage and the goods and the image data; determining a driving path according to the position information of the forklift and the position information of the goods, and driving to a warehouse location point based on the driving path; determining the position of a tray obtained by third detection equipment at the library site, wherein the third detection equipment is positioned on a forklift; the technical scheme of forking the goods on the tray position solves the problem that the forklift can not accurately unload the goods, and improves the unloading precision of the forklift.
Description
Technical Field
The invention relates to the technical field of forklifts, in particular to a forklift unloading method, a forklift and a computer readable storage medium.
Background
With the development of the intelligent industry and intelligent logistics, the warehouse logistics tends to be automated more and more, and the unmanned forklift plays a very important role. During unloading of the flat car, the unmanned forklift is used for forking goods on the flat car and transporting the goods to a certain specified position. At present, when the storage position of goods on a flat car is identified to have errors, the phenomenon of deviation insertion or falling insertion is easily caused to occur in the unloading process of the unmanned forklift, so that the unmanned forklift can not smoothly unload the goods.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a forklift unloading method, a forklift and a computer readable storage medium, and aims to solve the technical problem that the forklift cannot accurately unload goods.
In order to achieve the aim, the invention provides a forklift unloading method, which comprises the following steps:
acquiring point cloud data of a carriage and goods on a flat car parked at a preset position, which is acquired by first detection equipment, and acquiring image data of the flat car, which is acquired by second detection equipment, wherein the first detection equipment and the second detection equipment are both positioned right above the preset position;
determining the position information of the goods on the flat car according to the point cloud data of the carriage and the goods and the image data;
determining a driving path according to the position information of the forklift and the position information of the goods, and driving to a warehouse location point based on the driving path;
determining the position of a tray obtained by third detection equipment at the library site, wherein the third detection equipment is positioned on a forklift;
and forking the goods on the position of the tray.
Optionally, the step of determining the position information of the goods on the flat car according to the point cloud data of the carriage and the goods and the image data comprises:
inputting image information of the flat car into a first preset target detection model to obtain a cargo detection frame, wherein the first preset target detection model is obtained by training according to preset cargo position information;
extracting point cloud data of the cargo detection frame from the point cloud data of the carriage and the cargo;
and determining the position information of the goods on the flat car according to the point cloud data of the goods detection frame.
Optionally, the step of determining the position information of the goods on the flat car according to the point cloud data of the goods detection frame includes:
performing data processing on the point cloud data of the cargo detection frame to obtain the position information of the cargo under a laser radar coordinate system, wherein the data processing sequentially comprises discrete point cloud data filtering processing and point cloud data fitting processing;
and converting the position information of the goods in the laser radar coordinate system into the position information of the goods in a map coordinate system based on a preset rotation matrix and a preset translation matrix, and taking the position information of the goods in the map coordinate system as the position information of the goods on the flat car.
Optionally, before the step of determining a travel path according to the position information of the forklift and the position information of the cargo, and traveling to a depot site based on the travel path, the method further includes:
determining a discharge sequence according to the position information of the goods;
establishing an incidence relation between the position information of the goods and the position information of the detection points;
and storing the association relationship between the position information of the goods and the position information of the detection points in a preset database based on the unloading sequence.
Optionally, the step of determining a travel path according to the position information of the forklift and the position information of the cargo, and traveling to the warehouse location based on the travel path includes:
when a discharging request of a target cargo is received, acquiring the position information of a library site related to the position information of the target cargo from the preset database;
and determining a driving path according to the position information of the forklift and the position information of the base site, and driving the forklift to the base site based on the driving path.
Optionally, the step of determining the tray position obtained by the third detection device at the library site includes:
acquiring image information of the goods acquired by the third detection equipment;
inputting the image information of the goods into a second preset target detection model to obtain a tray detection frame, wherein the second preset target detection model is obtained by training according to preset tray position information;
extracting point cloud data of the tray detection frame from the point cloud data corresponding to the image information;
and determining the position of the tray according to the point cloud data of the tray detection frame.
Optionally, before the step of determining the tray position according to the point cloud data of the tray detection frame, the method further includes:
and sequentially carrying out discrete point filtering processing, normal vector filtering processing, point cloud smoothing processing and plane segmentation processing on the point cloud data of the tray detection frame to obtain the point cloud data of the tray detection frame after data processing.
Optionally, the step of determining the tray position according to the point cloud data of the tray detection frame includes:
obtaining point cloud data of a goods center according to the point cloud data of the tray detection frame;
acquiring the goods category, and determining the actual size information of the goods fork entry according to the goods category;
and obtaining the position of the pallet according to the point cloud data of the center of the goods and the actual size information of the goods fork inlet.
In addition, to achieve the above object, the present invention also provides a forklift including: a memory, a processor and a forklift off-loading program stored on the memory and executable on the processor, the forklift off-loading program being configured to implement the steps of the forklift off-loading method as described above.
In addition, to achieve the above object, the present invention further provides a computer-readable storage medium having a forklift unloading program stored thereon, where the forklift unloading program, when executed by a processor, implements the steps of the forklift unloading method as described above.
In the technical scheme of this application, this application obtains by first check out test set and berths the point cloud data of carriage and goods on the flatbed of predetermineeing the position to obtain by second check out test set and obtain the image data of flatbed, thereby according to the point cloud data of carriage and goods and image data tentatively confirm the positional information of goods on the flatbed. After the position information of the goods on the flat car is determined, the driving path of the forklift is determined according to the position information of the forklift and the position information of the goods, and the forklift is driven to a storage position in front of the storage position based on the driving path. After the forklift runs to the warehouse location point in front of the warehouse location, the position of the pallet obtained by the third detection equipment is determined through the warehouse location point, and the pallet on the position of the pallet is forked, so that the position of the pallet is accurately identified and forked by the warehouse location point, the problem that the forklift cannot complete unloading due to errors of the fork entering angle or the fork entering position is solved, and the unloading precision of the forklift is improved.
Drawings
FIG. 1 is a schematic diagram of a fork lift truck in a hardware operating environment according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a first embodiment of the forklift unloading method of the invention;
fig. 3 is a detailed flowchart of step S120 of the forklift unloading method according to the first embodiment of the present invention;
fig. 4 is a schematic flow chart of the forklift unloading method according to the first embodiment of the invention before step S140;
fig. 5 is a detailed flowchart of step S140 of the forklift unloading method according to the first embodiment of the invention;
fig. 6 is a detailed flowchart of step S150 of the forklift unloading method according to the first embodiment of the invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a forklift in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the forklift may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of a forklift, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, the memory 1005, which is a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a forklift off-load program.
In the forklift shown in fig. 1, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the forklift according to the present invention may be provided in the forklift, and the forklift calls the forklift unloading program stored in the memory 1005 through the processor 1001 and executes the forklift unloading method according to the embodiment of the present invention.
The embodiment of the invention provides a forklift unloading method, and referring to fig. 2, fig. 2 is a flow schematic diagram of a first embodiment of the forklift unloading method.
In this embodiment, the forklift unloading method includes:
step S110, point cloud data of a carriage and goods on the flat car parked at a preset position, which are obtained by a first detection device, are obtained, and image data of the flat car, which are obtained by a second detection device, are obtained, wherein the first detection device and the second detection device are both located right above the preset position.
And step S120, determining the position information of the goods on the flat car according to the point cloud data of the carriage and the goods and the image data.
And step S130, determining a driving path according to the position information of the forklift and the position information of the goods, and driving to a warehouse location point based on the driving path.
Step S140, determining the position of the pallet obtained by the third detection device on the forklift at the library site.
And S150, forking the goods on the position of the tray.
In this embodiment, the first detection device is a solid-state lidar device. The second detection device is an RGB camera, and the RGB camera is used for target detection. The preset position is the parking position of the flat car, the preset position is any position in the area, and the preset position can be set to be multiple. The system comprises a solid laser radar device, an RGB camera, a communication connection device and an unmanned forklift, wherein the solid laser radar device and the RGB camera are installed right above each preset position in advance, and the solid laser radar device and the RGB camera are installed together in a combined mode and establish a communication connection relation with the unmanned forklift. The first detection device is used for acquiring point cloud data of a carriage and goods parked at a preset position. The second detection device is used for collecting image data of the flat car. After the solid-state laser radar equipment acquires point cloud data of a carriage and goods parked at the preset position and the RGB camera acquires image data of a flat car parked at the preset position, position information of the goods under a map coordinate system is sent to the unmanned forklift, so that the unmanned forklift determines the position information of the goods on the flat car after receiving the position information of the goods under the map coordinate system. After the solid-state laser radar equipment and the RGB camera are installed, the solid-state laser radar equipment and the RGB camera are calibrated, so that the solid-state laser radar equipment and the RGB camera are in the same coordinate system. After the solid-state laser radar equipment and the RGB camera are calibrated, the conversion of a laser radar coordinate system to a preset rotation matrix and a preset translation matrix of a map coordinate system for the unmanned forklift to run can be determined.
Specifically, when receiving that the staff starts the loading task, solid-state laser radar equipment launches radar signal towards the flatbed, will radar signal's reflection signal and camera acquisition image information send and handle on the peripheral hardware industrial computer, send the industrial computer of unmanned fork truck with the result of handling finally. In order to more accurately obtain the position of the goods on the flat car, the image information of the goods on the flat car is acquired, and the position information of the goods on the flat car is obtained by combining the image information of the goods and the point cloud data of the carriage and the goods.
In this embodiment, after the position information of the goods on the flat car, the unmanned forklift needs to be driven to the position of the storage location, and the position of the goods in the carriage is more accurately identified at the position of the storage location, so that the angle information of the fork and the position information of the fork are obtained. Specifically, the position information of the unmanned forklift detected by the positioning sensor of the unmanned forklift is obtained. And determining a driving path of the unmanned forklift according to the position information of the forklift and the position information of the goods, so that the unmanned forklift drives to a warehouse location point based on the driving path. The goods on the flat car have corresponding position information, and each position information has a corresponding storage position.
In the present embodiment, after the unmanned forklift travels to the garage location based on the travel path, the pallet position is determined at the garage location. Specifically, a third detection device on the forklift is started at the warehouse location to detect the position of the pallet. And the third detection equipment acquires image information, inputs the acquired image information into a YOLO deep learning target detection model so as to obtain the position of the pallet, wherein the YOLO deep learning target detection model is used for both the second detection equipment and the third detection equipment, and the third detection equipment acquires the coordinates of the cargo center point by means of data acquired by point cloud. After the position of the pallet is detected, the angle information of the fork entering of the multi-fork of the unmanned forklift and the position information of the fork entering can be determined, and therefore the multi-fork is controlled to pick the goods on the position of the pallet based on the angle information of the fork entering and the position information of the fork entering. The third detection device may be an RGB camera, and the RGB camera may be configured to acquire image information and point cloud data.
In the technical scheme of this application, this application obtains by first check out test set and berths the point cloud data of carriage and goods on the flatbed of predetermineeing the position to obtain by second check out test set and obtain the image data of flatbed, thereby according to the point cloud data of carriage and goods and image data tentatively confirm the positional information of goods on the flatbed. After the position information of the goods on the flat car is determined, the position information of the forklift is acquired. And determining a driving path of the forklift according to the position information of the forklift and the position information of the goods, and driving to a storage location in front of the storage location based on the driving path. After the forklift runs to the warehouse location point in front of the warehouse location, the position of the pallet obtained by the third detection equipment is determined through the warehouse location point, and the pallet on the position of the pallet is forked, so that the position of the pallet is accurately identified and forked by the warehouse location point, the problem that the forklift cannot complete unloading due to errors of the fork entering angle or the fork entering position is solved, and the unloading precision of the forklift is improved.
Further, referring to fig. 3, a second embodiment of the forklift truck unloading method according to the present invention provides a technical solution for determining location information of goods on the flat car according to the point cloud data of the car and the goods and the image data, and based on the embodiment shown in fig. 1, the determining the location information of the goods on the flat car according to the point cloud data of the car and the goods and the image data includes:
step S121, inputting image information of the flat car into a first preset target detection model to obtain a cargo detection frame, wherein the first preset target detection model is obtained by training according to preset cargo position information;
step S122, extracting point cloud data of the cargo detection frame from the point cloud data of the carriage and the cargo;
and S123, determining the position information of the goods on the flat car according to the point cloud data of the goods detection frame.
In this embodiment, after point cloud data of a carriage and goods and image information of a flat car are acquired, in order to preliminarily obtain position information of the goods on the flat car, second detection equipment acquires the image information of the flat car, and inputs the image information of the flat car into a first preset target detection model to obtain a goods detection frame. The first preset target detection model is obtained by training according to preset goods position information. The first preset target detection model is a YOLO target detection model, and the cargo detection frame can be obtained through the YOLO target detection model.
In this embodiment, after the cargo detection frame is obtained, point cloud data on the cargo detection frame is obtained from point cloud data of a carriage and cargo, and then position information of the cargo on the flat car is determined according to the point cloud data on the cargo detection frame. Specifically, after point cloud data on a cargo detection frame is acquired from point cloud data of a carriage and cargo, the point cloud data of the cargo detection frame is subjected to data processing, and the data processing sequentially comprises discrete point cloud data filtering processing and point cloud data fitting processing. For example, point cloud filtering is adopted, outliers are deleted, a cargo plane is fitted by using a RANSAC method, and finally, the coordinates (x0, y0, z0 and angle0) of the center of the cargo are obtained through a minimum outsourcing rectangle, so that the position information of the cargo on the flat car is obtained.
In this embodiment, the position information of the cargo obtained through data processing is the position information of the cargo in the laser radar coordinate system. After the position information of the goods in the laser radar coordinate system is obtained, the position information of the goods in the laser radar coordinate system needs to be converted into the position information of the goods in the map coordinate system, so that the final position information of the goods on the flat car is obtained. Specifically, the position information of the goods in the laser radar coordinate system is converted into the position information of the goods in the map coordinate system based on a preset rotation matrix and a preset translation matrix, and the position information of the goods in the map coordinate system is used as the position information of the goods on the flat car.
In the technical scheme of the embodiment, the image information of the flat car is input into the first preset target detection model to obtain the goods detection frame, and the point cloud data on the goods detection frame is extracted from the point cloud data of the carriage and the goods, so that the position information of the goods on the flat car is preliminarily determined according to the point cloud data of the goods detection frame.
Further, referring to fig. 4, a third embodiment of the forklift truck unloading method according to the present invention provides a technical solution before the step of determining a travel route from the position information of the forklift truck and the position information of the cargo and traveling to a depot site based on the travel route, wherein the step of determining the travel route from the position information of the forklift truck and the position information of the cargo and traveling to the depot site based on the travel route further includes, before the step of determining the travel route from the position information of the forklift truck and the position information of the cargo and traveling to the depot site based on the travel route shown in fig. 1:
and step S210, determining a discharging sequence according to the position information of the cargos.
Step S220, establishing an association relationship between the position information of the cargo and the position information of the detection point.
Step S230, storing the association relationship between the position information of the cargo and the position information of the detection point in a preset database based on the unloading sequence.
In this embodiment, after the position information of the cargo is obtained, the unloading order is determined according to the position information of the cargo, and the unloading order is transmitted to the depot management system. The unloading sequence can be set according to the actual situation. For example, the discharge sequence may be arranged from inside to outside, from top to bottom. Optionally, the discharge sequence is used to indicate a discharge sequence of the cargo. The position information of each cargo has the position information of the corresponding detection point. The position information of the goods and the position information of the detection points can be set according to actual conditions. And establishing the association relationship between the position information of the goods and the position information of the detection point. And storing the association relationship between the position information of the goods and the position information of the detection points in a preset database based on the unloading sequence.
In the technical solution of this embodiment, the unloading order is determined according to the position information of the cargo. And establishing the association relationship between the position information of the goods and the position information of the detection point. And storing the incidence relation between the position information of the goods and the position information of the detection points in a preset database based on the unloading sequence, so as to realize the ordered unloading of the unmanned forklift.
Further, referring to fig. 5, a fourth embodiment of a forklift truck unloading method according to the present invention provides a method for determining a travel route from position information of a forklift truck and position information of a load and traveling to a depot site based on the travel route, wherein the method for determining a travel route from position information of a forklift truck and position information of a load and traveling to a depot site based on the travel route according to the embodiment shown in fig. 4 comprises:
step S131, when receiving a discharge request of a target cargo, obtaining location information of a depot point associated with the location information of the target cargo from the preset database.
And step S132, determining a driving path according to the position information of the forklift and the position information of the base site, and driving the forklift to the base site based on the driving path.
In this embodiment, when receiving a discharge request of a target cargo, the unmanned forklift acquires location information of a library site associated with the location information of the target cargo from a preset database. And determining a driving path according to the position information of the forklift and the position information of the base site. And when the unmanned forklift receives the unloading request of the target goods, the dispatching forklift is driven to the warehouse location point according to the driving path. The unloading operation is cyclically performed through the unloading sequence, so that the cargos on the flat car are all unloaded.
In the technical scheme of the embodiment, when the unloading request of the target goods is received, the position information of the warehouse location point is obtained from the preset database, so that the driving path of the forklift is determined according to the position information of the warehouse location point and the position information of the forklift, the forklift can drive to the warehouse location point based on the driving path, and the navigation of the forklift is realized.
Further, referring to fig. 6, a fifth embodiment of the forklift truck unloading method according to the present invention provides a specific solution for determining the position of the tray obtained by the third detection device at the garage location, and based on the embodiment shown in fig. 1, the determining the position of the tray obtained by the third detection device at the garage location includes:
step S141, acquiring image information of the cargo acquired by the third detection device.
Step S142, inputting the image information of the goods into a second preset target detection model to obtain a tray detection frame, wherein the second preset target detection model is obtained by training according to preset tray position information.
And S143, extracting the point cloud data of the tray detection frame from the point cloud data corresponding to the image information.
And step S144, determining the position of the tray according to the point cloud data of the tray detection frame.
In this embodiment, optionally, image information of the cargo acquired by the third detection device is acquired; and inputting the image information of the goods into a second preset target detection model to obtain a tray detection frame, wherein the second preset target detection model is obtained by training according to preset tray position information. And extracting the point cloud data of the tray detection frame from the point cloud data corresponding to the image information. And sequentially carrying out discrete point filtering processing, normal vector filtering processing, point cloud smoothing processing and plane segmentation processing on the point cloud data of the tray detection frame to obtain the point cloud data of the tray detection frame after data processing. And obtaining point cloud data of the goods center according to the point cloud data of the tray detection frame. And acquiring the cargo category, and determining the actual size information of the cargo fork entry according to the cargo category. And obtaining the position of the pallet according to the point cloud data of the center of the goods and the actual size information of the goods fork inlet.
Optionally, image information of the cargo acquired by the third detection device is acquired; inputting the image information of the goods into a second preset target detection model to obtain a tray detection frame, wherein the second preset target detection model is obtained by training according to preset tray position information; extracting point cloud data of the edge of the tray detection frame from the point cloud data corresponding to the image information; obtaining point cloud data of the goods center according to the point cloud data of the tray detection frame; acquiring the goods category, and determining the actual size information of the goods fork entry according to the goods category; and obtaining the position of the pallet according to the point cloud data of the center of the goods and the actual size information of the goods fork inlet.
Specifically, when the unmanned forklift reaches a warehouse location in front of the goods, the third detection device on the unmanned forklift starts to work. And acquiring image information of the goods acquired by the third detection equipment, and recalculating the most appropriate anchor frame proportion type in the training data set by using a genetic algorithm + k mean value based on a YOLO target detection model. And training a tray detection model, inputting the preprocessed RGB-D data collected by the third detection equipment into a YOLO target detection model to obtain a tray detection frame, extracting point cloud data of a position corresponding to the tray detection frame from the point cloud data corresponding to the image information, and inputting the point cloud data into a point cloud segmentation module. The point cloud segmentation module sequentially performs discrete point filtering processing, normal vector filtering processing, point cloud data smoothing processing and plane segmentation processing on point cloud data corresponding to the tray detection frame, so that surface point cloud of the tray is obtained according to the point cloud data after the point cloud data processing, and the position of the tray is obtained according to the point cloud of the surface of the tray. When the position of the pallet is obtained, the position information and the angle information of the fork entering of the unmanned forklift can be further determined according to the position of the pallet.
In the technical scheme of this embodiment, the tray detection frame is obtained by inputting image information acquired by the third detection device into the second preset target detection model. And extracting the point cloud data of the tray detection frame from the point cloud data corresponding to the image information. And determining the position of the pallet according to the point cloud data of the pallet detection frame, so that the position information and the angle information of the fork entering of the unmanned forklift are accurately determined.
Based on the same inventive concept, embodiments of the present application further provide a computer-readable storage medium, where a forklift unloading program is stored, and when the forklift unloading program is executed by a processor, the above steps of forklift unloading are implemented, and the same technical effects can be achieved, and are not described herein again to avoid repetition.
Since the computer-readable storage medium provided in the embodiments of the present application is a computer-readable storage medium used for implementing the method in the embodiments of the present application, based on the method described in the embodiments of the present application, those skilled in the art can understand the specific structure and modification of the computer-readable storage medium, and thus details are not described herein. Any computer-readable storage medium that can be used with the methods of the embodiments of the present application is intended to be within the scope of the present application.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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 system. Without further limitation, an element defined by the phrase "comprising a forklift dump" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A forklift unloading method is characterized by comprising the following steps:
acquiring point cloud data of a carriage and goods on a flat car parked at a preset position, which is acquired by first detection equipment, and acquiring image data of the flat car, which is acquired by second detection equipment, wherein the first detection equipment and the second detection equipment are both positioned right above the preset position;
determining the position information of the goods on the flat car according to the point cloud data of the carriage and the goods and the image data;
determining a driving path according to the position information of the forklift and the position information of the goods, and driving to a warehouse location point based on the driving path;
determining the position of a tray obtained by third detection equipment at the library site, wherein the third detection equipment is positioned on a forklift;
and forking the goods on the position of the tray.
2. The forklift unloading method of claim 1, wherein the step of determining the position information of the cargo on the flat bed truck from the point cloud data of the carriage and the cargo and the image data comprises:
inputting image information of the flat car into a first preset target detection model to obtain a cargo detection frame, wherein the first preset target detection model is obtained by training according to preset cargo position information;
extracting point cloud data of the cargo detection frame from the point cloud data of the carriage and the cargo;
and determining the position information of the goods on the flat car according to the point cloud data of the goods detection frame.
3. The method for unloading a forklift truck of claim 2, wherein the step of determining the position information of the load on the flat car from the point cloud data of the load detection frame comprises:
performing data processing on the point cloud data of the cargo detection frame to obtain the position information of the cargo under a laser radar coordinate system, wherein the data processing sequentially comprises discrete point cloud data filtering processing and point cloud data fitting processing;
and converting the position information of the goods in the laser radar coordinate system into the position information of the goods in a map coordinate system based on a preset rotation matrix and a preset translation matrix, and taking the position information of the goods in the map coordinate system as the position information of the goods on the flat car.
4. The method for unloading a forklift truck of claim 1, wherein the step of determining a travel path from the position information of the forklift truck and the position information of the cargo and traveling to the depot site based on the travel path further comprises:
determining a discharge sequence according to the position information of the goods;
establishing an incidence relation between the position information of the goods and the position information of the detection points;
and storing the association relationship between the position information of the goods and the position information of the detection points in a preset database based on the unloading sequence.
5. The method for unloading a forklift truck of claim 4, wherein the step of determining a travel path from the position information of the forklift truck and the position information of the cargo and traveling to a depot location based on the travel path comprises:
when a discharging request of a target cargo is received, acquiring the position information of a library site related to the position information of the target cargo from the preset database;
and determining a driving path according to the position information of the forklift and the position information of the base site, and driving the forklift to the base site based on the driving path.
6. A method for unloading a forklift truck as defined in claim 1, wherein said step of determining the position of the pallet at said garage site obtained by a third inspection apparatus comprises:
acquiring image information of the goods acquired by the third detection equipment;
inputting the image information of the goods into a second preset target detection model to obtain a tray detection frame, wherein the second preset target detection model is obtained by training according to preset tray position information;
extracting point cloud data of the tray detection frame from the point cloud data corresponding to the image information;
and determining the position of the tray according to the point cloud data of the tray detection frame.
7. The method for unloading a forklift truck of claim 6, wherein said step of determining the position of the pallet from the point cloud data of the pallet detection frame further comprises:
and sequentially carrying out discrete point filtering processing, normal vector filtering processing, point cloud smoothing processing and plane segmentation processing on the point cloud data of the tray detection frame to obtain the point cloud data of the tray detection frame after data processing.
8. Method for unloading a forklift truck as claimed in claim 6 or 7, wherein the step of determining the position of the pallet from the point cloud data of the pallet detection frame comprises:
obtaining point cloud data of a goods center according to the point cloud data of the tray detection frame;
acquiring the goods category, and determining the actual size information of the goods fork entry according to the goods category;
and obtaining the position of the pallet according to the point cloud data of the center of the goods and the actual size information of the goods fork inlet.
9. A forklift, characterized in that it comprises: a memory, a processor and a forklift off-load program stored on the memory and executable on the processor, the forklift off-load program being configured to implement the steps of the forklift off-load method as claimed in any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that the storage medium has stored thereon a forklift off-loading program which, when executed by a processor, carries out the steps of the forklift off-loading method as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111546284.0A CN114358145A (en) | 2021-12-16 | 2021-12-16 | Forklift unloading method, forklift and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111546284.0A CN114358145A (en) | 2021-12-16 | 2021-12-16 | Forklift unloading method, forklift and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114358145A true CN114358145A (en) | 2022-04-15 |
Family
ID=81100078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111546284.0A Pending CN114358145A (en) | 2021-12-16 | 2021-12-16 | Forklift unloading method, forklift and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114358145A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114890173A (en) * | 2022-06-02 | 2022-08-12 | 未来机器人（深圳）有限公司 | Cargo loading method and device, computer equipment and storage medium |
| CN116341772A (en) * | 2023-05-31 | 2023-06-27 | 未来机器人（深圳）有限公司 | Library position planning method and device, electronic equipment and storage medium |
| WO2024051025A1 (en) * | 2022-09-07 | 2024-03-14 | 劢微机器人科技(深圳)有限公司 | Pallet positioning method, device, and equipment, and readable storage medium |
| WO2024077716A1 (en) * | 2022-10-11 | 2024-04-18 | 劢微机器人科技(深圳)有限公司 | Local path planning method for amr |
-
2021
- 2021-12-16 CN CN202111546284.0A patent/CN114358145A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114890173A (en) * | 2022-06-02 | 2022-08-12 | 未来机器人（深圳）有限公司 | Cargo loading method and device, computer equipment and storage medium |
| WO2024051025A1 (en) * | 2022-09-07 | 2024-03-14 | 劢微机器人科技(深圳)有限公司 | Pallet positioning method, device, and equipment, and readable storage medium |
| WO2024077716A1 (en) * | 2022-10-11 | 2024-04-18 | 劢微机器人科技(深圳)有限公司 | Local path planning method for amr |
| CN116341772A (en) * | 2023-05-31 | 2023-06-27 | 未来机器人（深圳）有限公司 | Library position planning method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114358145A (en) | Forklift unloading method, forklift and computer-readable storage medium | |
| US11747432B2 (en) | Object tracking method and system | |
| CN114455511B (en) | Fork truck loading method and equipment and computer readable storage medium | |
| US20210216966A1 (en) | Yard management system | |
| RU2571580C2 (en) | Method and device enabling use of objects with predetermined coordinates for locating industrial vehicles | |
| US20180082249A1 (en) | Autonomous Vehicle Content Identification System and Associated Methods | |
| CN111115511B (en) | Unloading and loading method based on intelligent navigation forklift | |
| US20220414585A1 (en) | Methods and systems for transportation dock management | |
| WO2018033933A1 (en) | An automatic container position detection system | |
| CN114494453A (en) | Automatic loading and unloading method and automatic loading and unloading system based on radar and camera | |
| CN115826580A (en) | Cargo handling method and device, equipment and storage medium | |
| WO2019125669A1 (en) | Container auto-dimensioning | |
| CN114648233A (en) | Dynamic station cargo carrying method and system | |
| CN117875839A (en) | Material handling method, device, equipment and storage medium based on forklift | |
| CN114742503B (en) | Intelligent logistics car sharing method and device based on deep learning | |
| CN115271615A (en) | Cross-border transportation method and device, electronic equipment and storage medium | |
| CN112101862B (en) | Method, system and storage medium for transporting and warehousing goods | |
| CN113627757A (en) | Cargo loading method, device, equipment and storage medium for logistics transport vehicle | |
| CN112085130A (en) | Goods management method and device, computer equipment and storage medium | |
| CN113525988B (en) | Lightweight logistics storage working condition monitoring method and device based on Internet of things technology and electronic equipment | |
| CN116142678A (en) | Automatic warehouse-in and warehouse-out method, freight car and storage medium | |
| US20230297953A1 (en) | Devices, systems, and methods for freight logistics and asset management | |
| CN115170650B (en) | Container vehicle-mounted position identification method and device, electronic equipment and storage medium | |
| CN116468348A (en) | Cargo handling method, internet of things system, electronic equipment and storage medium | |
| CN115817538A (en) | Control method, device, equipment and medium for unmanned card concentrator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |