Tray fork taking method, device and electronic equipment

Abstract

This invention provides a pallet picking method, apparatus, and electronic device. The method includes determining a first detection result corresponding to a target pallet, the first detection result being determined based on the number of first laser points falling into each reference grid in a reference grid map; determining a second detection result corresponding to the target pallet, the second detection result being determined based on the number of second laser points falling into each reference grid in the reference grid map; and determining whether to continue picking up the target pallet according to the socket boundary recognition result based on the first detection result and the second detection result. This solution can automatically detect whether there are abnormalities in the pallet and its goods, such as pallet and goods positional shifts caused by forklifts hitting the goods, or pallet abnormalities caused by ground hole collapse, effectively avoiding pallet positional shifts or goods hitting caused by inaccurate positioning, low picking accuracy, or other situations, thus increasing the safety of pallet picking.

Description

Technical Field

[0001] This invention relates to the field of warehousing and logistics technology, and in particular to a pallet forklift method, apparatus, and electronic equipment. Background Technology

[0002] With the increasing intelligence of smart manufacturing and warehousing logistics, pallets are being gradually adopted for functions such as loading and automated stacking of goods. For complex warehousing environments, precise pallet handling can be achieved by recognizing the pallet's slots. However, after pallet recognition but before autonomous pallet handling, there is a certain probability that the pallet may collide with or be pushed, causing it to shift or even damage goods, thus affecting subsequent pallet handling. Summary of the Invention

[0003] This invention provides a pallet forklift method, apparatus, electronic device, and storage medium to enable automatic detection of any abnormalities in the pallet and its contents during pallet forklift operations.

[0004] In a first aspect, embodiments of the present invention provide a pallet forklift method, the method comprising:

[0005] The first detection result corresponding to the target tray is determined. The first detection result is determined based on the number of first laser points falling into each reference grid in the reference grid map. The first laser point is the laser point in the first laser point cloud used to describe the first reference surface. The first reference surface is the surface of the target tray closer to the lidar when using lidar to identify the socket boundary of the target tray.

[0006] The second detection result corresponding to the target tray is determined. The second detection result is determined based on the number of second laser points falling into each reference grid in the reference grid map. The second laser point is the laser point in the second laser point cloud used to describe the second reference surface. The second reference surface is the surface of the target tray close to the lidar side when the target tray is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by using lidar to identify the socket boundary of the target tray.

[0007] Based on the first detection result and the second detection result, determine whether to continue to pick up the target pallet according to the socket boundary recognition result.

[0008] Secondly, embodiments of the present invention also provide a pallet forklift device, the device comprising:

[0009] The first determining module is used to determine the first detection result corresponding to the target tray. The first detection result is determined based on the number of first laser points falling into each reference grid in the reference grid map. The first laser points are laser points in the first laser point cloud used to describe the first reference surface. The first reference surface is the surface of the target tray closer to the lidar when using lidar to identify the socket boundary of the target tray.

[0010] The second determining module is used to determine the second detection result corresponding to the target tray. The second detection result is determined based on the number of second laser points falling into each reference grid in the reference grid map. The second laser point is the laser point in the second laser point cloud used to describe the second reference surface. The second reference surface is the surface of the target tray close to the laser radar side when the target tray is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by using laser radar to identify the socket boundary of the target tray.

[0011] The forklift control module is used to determine, based on the first detection result and the second detection result, whether to continue forking the target pallet according to the socket boundary identification result.

[0012] Thirdly, this invention also provides an electronic device, the electronic device comprising:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the pallet fork lifting method described in any of the above embodiments.

[0016] Fourthly, this invention also provides a computer-readable medium storing computer instructions that cause a processor to execute the pallet fork removal method described in any of the above embodiments.

[0017] In this embodiment of the invention, when picking up a target pallet according to the recognition result of the socket boundary, a first detection result is determined based on the number of first laser points falling into each reference grid in the reference grid map corresponding to the target pallet. The first laser points are laser points in the first laser point cloud on the surface of the target pallet near the LiDAR when the socket boundary of the target pallet is identified using LiDAR. A second detection result is determined based on the number of second laser points falling into each reference grid in the reference grid map corresponding to the target pallet. The second laser points are laser points in the second laser point cloud on the surface of the target pallet near the LiDAR when the target pallet is picked up according to the socket boundary recognition result after the socket boundary recognition of the target pallet is performed using LiDAR. Based on the first detection result and the second detection result, it is determined whether to continue picking up the target pallet according to the socket boundary recognition result. This solution uses the relatively accurate pallet forward surface point cloud detection results pre-identified during the pallet's socket boundary recognition as a benchmark. If the pallet's pose moves during the forklift process, the pallet forward surface point cloud detection results will change. In particular, when the change in the pallet forward surface point cloud detection results is large, it is considered that the pallet has a large pose shift. It can automatically detect whether there are any abnormalities in the pallet and the goods on it, such as the pallet and goods on it shifting due to forklift arm collision, or the pallet's abnormal state caused by ground hole collapse. It effectively avoids pallet pose shift or collision caused by inaccurate positioning, low forklift accuracy, or other situations, thus increasing the safety of pallet handling.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] The above and other features, advantages, and aspects of the various embodiments of the present invention will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 This is a schematic diagram of a pallet forklift method provided in an embodiment of the present invention;

[0021] Figure 2a This is a schematic diagram of a forklift operation for a three-legged, double-hole pallet provided in an embodiment of the present invention;

[0022] Figure 2b This is a schematic diagram of a forklift operation for a double-legged single-hole pallet provided in an embodiment of the present invention;

[0023] Figure 2c This is a schematic diagram of an embodiment of the present invention for detecting a three-legged, double-hole tray;

[0024] Figure 2d This is a schematic diagram of a method for detecting a double-legged single-hole tray provided in an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of a pallet fork lifting device provided in an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device for implementing a pallet fork lifting method provided in an embodiment of the present invention. Detailed Implementation

[0027] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0028] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0029] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0030] It should be noted that the concepts of "first" and "second" mentioned in this invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0031] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0032] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0033] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0034] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application program, server, or storage medium executing the operation of this invention, based on the prompt message.

[0035] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0036] It is understood that the above notification and user authorization process is merely illustrative and does not constitute a limitation on the implementation of the present invention. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present invention.

[0037] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0038] Figure 1 This is a schematic flowchart of a pallet picking method provided in an embodiment of the present invention. The present invention is applicable to situations where pallet position is deviated when picking up a pallet according to the recognition result of the pallet socket boundary, so as to pick up the pallet correctly. The method can be executed by a pallet picking device, which can be implemented in the form of software and / or hardware, and is generally integrated on any electronic device with network communication function, such as a mobile terminal, PC or server.

[0039] like Figure 1 As shown, the pallet forklift method of this invention may include the following process:

[0040] S110. Determine the first detection result corresponding to the target tray. The first detection result is determined based on the number of first laser points falling into each reference grid in the reference grid map. The first laser point is the laser point in the first laser point cloud used to describe the first reference surface. The first reference surface is the surface of the target tray closer to the lidar when using lidar to identify the socket boundary of the target tray.

[0041] See Figure 2a and Figure 2b A pallet consists of a pallet body and pallet support legs. The pallet body is used to carry and place items, and the pallet support legs are connected to the lower end of the pallet body to support the pallet body. The area between the pallet support legs is the pallet insertion area. When lifting a pallet with a forklift, the boundary position of the pallet support legs can be identified to determine the boundary of the pallet insertion area, and the pallet can then be lifted and moved based on the boundary position of the pallet insertion holes. Pallets can be classified into two-legged single-hole pallets and three-legged double-hole pallets when viewed from the forklift direction.

[0042] See Figure 2a and Figure 2b The target pallet is the pallet selected from multiple candidate pallets after the unmanned forklift receives a pallet picking task. When the target pallet needs to be picked up, its storage area can be determined, and the LiDAR can be moved to one side of the target pallet's storage area according to that location. The surface of the target pallet's support leg closest to the LiDAR during laser scanning is designated as the first reference surface. A laser point cloud describing the first reference surface can be acquired by the LiDAR and designated as the first laser point cloud.

[0043] See Figure 2c and Figure 2d To detect the distribution of laser points in the first laser point cloud, a reference grid map can be configured for the target tray. This reference grid map consists of multiple arrayed reference grids, each corresponding to a different coordinate position. For each reference grid in the reference grid map, its coverage area is described by coordinates. Each first laser point in the first laser point cloud is projected onto each reference grid in the reference grid map according to its coordinates. The number of first laser points falling into each reference grid in the reference grid map is determined, and the first detection result for the target tray is obtained based on the number of first laser points in each reference grid. The coordinates of each first laser point falling into a reference grid are located within the coverage area of ​​that reference grid.

[0044] As an optional but non-limiting implementation, determining the first detection result corresponding to the target tray includes the following steps A1-A3:

[0045] Step A1: Determine the first grid attribute value of each reference grid in the reference grid map used by the target pallet. The first grid attribute value is the number of first laser points falling into the reference grid in the reference grid map when using LiDAR to identify the socket boundary of the target pallet.

[0046] Step A2: Based on the first grid attribute value of each reference grid in the reference grid map, determine the first grid state value of each reference grid in the reference grid map used by the target tray. The first grid state value is used to measure the density of the first laser point in the reference grid relative to other reference grids when using LiDAR to identify the socket boundary of the target tray.

[0047] Optionally, the first grid state value of each reference grid in the reference grid map is determined based on the ratio between the first grid attribute value of the reference grid and the first grid attribute value of the target grid, where the target grid is the reference grid with the most laser points falling into it among all the reference grids in the reference grid map.

[0048] See Figure 2c and Figure 2d For a pre-configured reference grid map, the size of the reference grid is the area to be cropped from the laser point cloud, and the default size of the reference grid is 1cm. The first grid attribute value of each reference grid is represented by a decimal between [0,1]. The first grid state value of each reference grid is determined by the density of the first laser point in the reference grid relative to other reference grids when using LiDAR to identify the socket boundary of the target tray. The first grid state value of the reference grid is calculated as follows:

[0049]

[0050] in, To determine the density of the first laser point in the i-th reference grid relative to other reference grids when using LiDAR to identify the socket boundary of a target tray, To reference the number of the first laser point in the i-th grid of the raster map, This refers to the number of the first laser point in the reference grid with the most points among all reference grids in the reference grid map.

[0051] Step A3: Based on the first grid attribute value and the first grid state value of each reference grid, determine the first detection result corresponding to the target tray.

[0052] Optionally, the first detection result corresponding to the target tray is determined based on the weighted sum of the first grid attribute value of each reference grid in the reference grid map and the first grid state value of the corresponding reference grid.

[0053] Optionally, the first detection result corresponding to the target tray is calculated as follows:

[0054]

[0055] in, The first detection result corresponding to the target tray. Let n be the number of first laser points falling into a reference grid in the reference grid map when using LiDAR to identify the socket boundary of the target tray. This refers to the density of the first laser point in the i-th reference grid cell relative to other reference grid cells when using LiDAR to identify the socket boundary of a target tray. Taking a nine-grid reference grid as an example, the state values ​​of the first grid cell for each reference grid cell are O1, O2, and O3 respectively. 3…… O9, the first grid attribute values ​​of the reference grid are P1P2P3....P9, and the first detection result corresponding to the target tray is... =O 1* P1+O2P2+O3P3+...+O9P9.

[0056] As an optional but non-limiting implementation, the first grid attribute value of each reference grid in the reference grid map used by the target tray is determined, including the following steps B1-B2:

[0057] Step B1: Determine the first laser point cloud corresponding to the target tray. The first laser point cloud includes multiple first laser points.

[0058] Optionally, determining the first laser point cloud corresponding to the target tray includes: when starting the socket boundary identification of the target tray using a lidar, determining the third laser point cloud corresponding to the target tray, wherein the third laser point cloud is the laser point cloud obtained by using a lidar to perform laser scanning towards the storage area where the target tray is located when using a lidar to perform socket boundary identification of the target tray; and extracting the first laser point cloud corresponding to the target tray from the third laser point cloud based on the three-dimensional coordinates of each laser point in the third laser point cloud.

[0059] Wherein, the first laser point cloud is a laser point cloud describing the first reference surface, the first laser point is a laser point in the first laser point cloud used to describe the first reference surface, and the first reference surface is the surface of the target tray near the laser radar side when using laser radar to identify the socket boundary of the target tray.

[0060] Optionally, determining the third laser point cloud corresponding to the target tray includes: when using a lidar to identify the socket boundary of the target tray, performing a laser scan operation on the target tray by aligning the lidar with the storage area where the target tray is located; merging the laser point clouds obtained by performing at least two consecutive laser scan operations to obtain the third laser point cloud corresponding to the target tray, wherein the vertical position is offset and adjusted in different laser scan operations.

[0061] Optionally, based on the three-dimensional coordinates of each laser point in the third laser point cloud, the first laser point cloud corresponding to the target tray is extracted from the third laser point cloud, including: generating multiple reference rays from the origin of the reference coordinate system along the horizontal axis of the reference coordinate system, the multiple reference rays being used to equally divide the longitudinal range of the storage area where the target tray is located; controlling the reference rays to stop when they hit the third laser point in the third laser point cloud, and obtaining the third laser point at the horizontal axis coordinate range where it was hit; filtering out the third laser points that are directed away from the surface of the tray on the reference side by slope filtering, obtaining the remaining third laser points and determining them as the first laser point cloud corresponding to the support leg of the target tray; wherein, the reference coordinate system takes the position of the lidar as the coordinate origin, the direction of tray picking up the target tray as the horizontal axis, the left and right direction of the target device to which the lidar belongs when picking up the target tray as the vertical axis, and the vertically upward direction as the vertical axis.

[0062] Step B2: Based on the three-dimensional coordinates of multiple first laser points and the position range of each grid in the reference grid map, project the multiple first laser points onto each grid in the reference grid map to obtain a first grid attribute value that describes the number of first laser points falling into each grid in the reference grid map when using LiDAR to identify the socket boundary of the target tray.

[0063] S120. Determine the second detection result corresponding to the target tray. The second detection result is determined based on the number of second laser points falling into each reference grid in the reference grid map. The second laser point is the laser point in the second laser point cloud used to describe the second reference surface. The second reference surface is the surface of the target tray near the laser radar side when the target tray is picked up according to the hole boundary recognition result after the laser radar is used to identify the hole boundary of the target tray.

[0064] See Figure 2a and Figure 2bAfter identifying the socket boundaries of the target pallet using LiDAR, when picking up the target pallet according to the socket boundary identification results, the LiDAR is controlled to move to one side of the storage area where the target pallet is located. Similarly, the surface of the target pallet support leg closest to the LiDAR side when picking up the target pallet according to the socket boundary identification results is recorded as the second reference surface. At this time, the second reference surface can be laser scanned, and the LiDAR can acquire a laser point cloud that can describe the second reference surface, which is recorded as the second laser point cloud.

[0065] See Figure 2c and Figure 2d Similarly, to detect the distribution of laser points in the second laser point cloud, the same reference grid map is used. For each reference grid in the reference grid map, each second laser point is projected onto its corresponding reference grid according to its coordinates in the second laser point cloud. The number of second laser points falling into each reference grid is determined, and the second detection result corresponding to the target tray is obtained based on the number of second laser points in each reference grid. The coordinates of each second laser point falling into a reference grid are located within the coverage area of ​​the corresponding reference grid.

[0066] As an optional but non-limiting implementation, determining the second detection result corresponding to the target tray includes the following steps C1-C3:

[0067] Step C1: Determine the second grid attribute value of each reference grid in the reference grid map used by the target pallet. The second grid attribute value is the number of second laser points that fall into the reference grid in the reference grid map when the target pallet is picked up by forklift according to the socket boundary recognition result after the socket boundary recognition of the target pallet is performed by LiDAR.

[0068] Step C2: Based on the second grid attribute values ​​of each reference grid in the reference grid map, determine the second grid state value of each reference grid in the reference grid map used by the target pallet. The second grid state value is used to measure the density of the second laser point in the reference grid relative to other reference grids when the target pallet is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by LiDAR on the target pallet.

[0069] Optionally, the second grid state value of each reference grid in the reference grid map is determined based on the ratio between the second grid attribute value of the reference grid and the second grid attribute value of the target grid, where the target grid is the reference grid with the most laser points falling into it among all the reference grids in the reference grid map.

[0070] See Figure 2c and Figure 2d Using the same reference grid map, the second grid attribute value of each reference grid is represented by a decimal between [0,1]. The second grid state value of each reference grid is determined by the density of the second laser point in the reference grid relative to other reference grids when using LiDAR to identify the socket boundary of the target tray. The second grid state value of the reference grid is calculated as follows:

[0071]

[0072] in, To determine the density of the second laser point in the i-th reference grid relative to other reference grids when using LiDAR to identify the socket boundary of a target tray, To reference the number of the second laser point in the i-th grid of the raster map, This refers to the number of the second laser point in the reference grid with the most points among all reference grids in the reference grid map.

[0073] Step C3: Based on the second grid attribute value and second grid state value of each reference grid, determine the second detection result corresponding to the target tray.

[0074] Optionally, the second detection result corresponding to the target tray is determined based on the weighted sum of the second grid attribute values ​​of each reference grid in the reference grid map and the second grid state value of the corresponding reference grid.

[0075] Optionally, the second detection result corresponding to the target tray is calculated as follows:

[0076]

[0077] in, The second detection result corresponding to the target tray. Let n be the number of second laser points falling into a reference grid in the reference grid map when using LiDAR to identify the socket boundary of the target tray. This refers to the density of the second laser point in the i-th reference grid relative to other reference grids when using LiDAR to identify the socket boundary of a target tray.

[0078] As an optional but non-limiting implementation, the second grid attribute values ​​of each reference grid in the reference grid map used by the target tray are determined, including the following steps D1-D2:

[0079] Step D1: Determine the second laser point cloud corresponding to the target tray. The second laser point cloud includes multiple second laser points.

[0080] Optionally, determining the second laser point cloud corresponding to the target tray includes: after using a lidar to identify the socket boundaries of the target tray, and when it is detected that the target tray is to be picked up according to the socket boundary identification result, determining the fourth laser point cloud corresponding to the target tray. The fourth laser point cloud is the laser point cloud obtained by using a lidar to perform a laser scan towards the storage area where the target tray is located when preparing to pick up the target tray according to the socket boundary identification result; and extracting the second laser point cloud corresponding to the target tray from the fourth laser point cloud based on the three-dimensional coordinates of each laser point in the fourth laser point cloud.

[0081] Wherein, the second laser point cloud is the laser point cloud describing the second reference surface, the second laser point is the laser point in the second laser point cloud used to describe the second reference surface, and the second reference surface is the surface of the target pallet closer to the laser radar side when the target pallet is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by laser radar.

[0082] Optionally, determining the fourth laser point cloud corresponding to the target pallet includes: after identifying the socket boundary of the target pallet using a lidar, and when it is detected that the target pallet is to be picked up by forklift according to the socket boundary identification result, performing a laser scan operation on the target pallet by aiming the lidar toward the storage area where the target pallet is located; merging the laser point clouds obtained by performing at least two consecutive laser scan operations to obtain the fourth laser point cloud corresponding to the target pallet, wherein the different laser scan operations are offset and adjusted in the longitudinal position.

[0083] Optionally, based on the three-dimensional coordinates of each laser point in the fourth laser point cloud, the second laser point cloud corresponding to the target tray is extracted from the fourth laser point cloud, including: generating multiple reference rays from the origin of the reference coordinate system along the horizontal axis of the reference coordinate system, the multiple reference rays being used to equally divide the longitudinal range of the storage area where the target tray is located; controlling the reference rays to stop when they hit the fourth laser point in the fourth laser point cloud, and obtaining the fourth laser point at the horizontal axis coordinate range where it was hit; filtering out the fourth laser points that are directed away from the surface of the tray on the reference side by slope filtering, obtaining the remaining fourth laser points and determining them as the second laser point cloud corresponding to the support leg of the target tray; wherein, the reference coordinate system takes the position of the lidar as the coordinate origin, the direction of tray picking up the target tray as the horizontal axis, the left and right direction of the target device to which the lidar belongs when picking up the target tray as the vertical axis, and the vertically upward direction as the vertical axis.

[0084] Step D2: Based on the three-dimensional coordinates of multiple second laser points and the position range of each grid in the reference grid map, project the multiple second laser points onto each grid in the reference grid map to obtain a second grid attribute value, which describes the number of second laser points falling into each grid in the reference grid map when the target tray is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by LiDAR.

[0085] S130. Based on the first detection result and the second detection result, determine whether to continue to pick up the target pallet according to the socket boundary recognition result.

[0086] Based on the first detection result corresponding to the relatively accurate point cloud of the target pallet's forward surface, which was pre-identified during the socket boundary recognition of the pallet, if the pallet's pose moves after socket boundary recognition using LiDAR or during the process of picking up the target pallet according to the socket boundary recognition result, the number of point clouds in each grid will change. At this time, the second detection result corresponding to the point cloud of the target pallet's forward surface can be calculated and compared with the previous first detection result to determine whether the target pallet's pose has shifted significantly. If the target pallet does not show a pose shift at different time points, the picking up of the target pallet according to the socket boundary recognition result continues. If the pallet shows a significant pose shift at different time points, the picking up of the target pallet according to the socket boundary recognition result is stopped.

[0087] As an optional but not limited implementation, based on the first detection result and the second detection result, it is determined whether to continue to pick up the target pallet according to the socket boundary recognition result, including steps E1-E2:

[0088] Step E1: Based on the first detection result and the second detection result, determine the pallet pose state of the target pallet. The pallet pose state is used to describe whether the target pallet has a pose shift at different time points.

[0089] Step E2: Based on the pallet pose of the target pallet, determine whether to continue to pick up the target pallet according to the socket boundary recognition result.

[0090] Optionally, based on the first detection result and the second detection result, the pallet pose state of the target pallet is determined, including: if there is a difference between the first detection result and the second detection result, and the difference between the two detection results is greater than or equal to a preset difference threshold, then the pallet pose state of the target pallet is determined to be that the target pallet has experienced pose shift at different time points.

[0091] Optionally, based on the first detection result and the second detection result, the pallet pose state of the target pallet is determined, including: if there is no difference between the first detection result and the second detection result, or if there is a difference, the difference between the two detection results is less than a preset difference threshold, then the pallet pose state of the target pallet is determined to be that the target pallet has not shown any pose deviation at different time points.

[0092] As an optional but not limited implementation, the vertical height of each first laser point in the first laser point cloud and the vertical height of each second laser point in the second laser point cloud are within a preset height range. The lower limit of the preset height range is greater than the height of the storage area where the target pallet is located, and the upper limit of the preset height range is less than the height of the upper surface of the target pallet. A 0.2m thick portion of the laser point cloud is cropped from the middle of the laser point cloud to remove the influence of the ground and the surface of the goods on the pallet.

[0093] In this embodiment of the invention, the solution uses the relatively accurate pallet forward surface point cloud detection result pre-identified during the identification of the pallet's insertion hole boundary as a benchmark. If the pallet's pose moves during the forklift process, the pallet forward surface point cloud detection result will change. In particular, when the change in the pallet forward surface point cloud detection result is large, it is considered that the pallet has experienced a large pose shift. It can automatically detect whether there are any abnormalities in the pallet and the goods on it, such as the pallet and goods on it shifting due to forklift arm collision, or the pallet's abnormal state caused by ground hole collapse. This effectively avoids pallet pose shift or collision caused by inaccurate positioning, low forklift accuracy, or other situations, thereby increasing the safety of pallet lifting.

[0094] Figure 3 This is a schematic diagram of a pallet forklift device provided in an embodiment of the present invention. The present invention is applicable to situations where pallet position is deviated when pallet is forklifted according to the recognition result of the pallet insertion hole boundary in order to correctly forklift the pallet. The pallet forklift device can be implemented in the form of software and / or hardware, and is generally integrated on any electronic device with network communication function, such as a mobile terminal, PC or server.

[0095] like Figure 3 As shown, the pallet forklift device of this embodiment may include: a first determining module 310, a second determining module 320, and a forklift control module 330. Wherein:

[0096] The first determining module 310 is used to determine the first detection result corresponding to the target tray. The first detection result is determined based on the number of first laser points falling into each reference grid in the reference grid map. The first laser points are laser points in the first laser point cloud used to describe the first reference surface. The first reference surface is the surface of the target tray closer to the laser radar when using laser radar to identify the socket boundary of the target tray.

[0097] The second determining module 320 is used to determine the second detection result corresponding to the target tray. The second detection result is determined based on the number of second laser points falling into each reference grid in the reference grid map. The second laser point is the laser point in the second laser point cloud used to describe the second reference surface. The second reference surface is the surface of the target tray close to the laser radar side when the target tray is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by laser radar.

[0098] The forklift control module 330 is used to determine whether to continue forking the target pallet according to the socket boundary recognition result based on the first detection result and the second detection result.

[0099] Based on the technical solutions of the above embodiments, optionally, determining the first detection result corresponding to the target tray includes:

[0100] Determine the first grid attribute value of each reference grid in the reference grid map used by the target pallet. The first grid attribute value is the number of first laser points falling into the reference grid in the reference grid map when the target pallet is identified by LiDAR for the socket boundary.

[0101] Based on the first grid attribute value of each reference grid in the reference grid map, the first grid state value of each reference grid in the reference grid map used by the target pallet is determined. The first grid state value is used to measure the density of the first laser point in the reference grid relative to other reference grids when using LiDAR to identify the socket boundary of the target pallet.

[0102] Based on the first grid attribute value and the first grid state value of each reference grid, the first detection result corresponding to the target tray is determined.

[0103] Based on the technical solutions of the above embodiments, optionally, determining the first grid attribute value of each reference grid in the reference grid map used by the target tray includes:

[0104] The target tray is determined to correspond to a first laser point cloud, wherein the first laser point cloud includes a plurality of first laser points;

[0105] Based on the three-dimensional coordinates of multiple first laser points and the position range of each grid in the reference grid map, the multiple first laser points are projected onto each grid in the reference grid map to obtain a first grid attribute value that describes the number of first laser points falling into each grid in the reference grid map when using LiDAR to identify the socket boundary of the target tray.

[0106] Based on the technical solutions of the above embodiments, optionally, determining the target tray corresponding to the first laser point cloud includes:

[0107] When starting the use of LiDAR to identify the socket boundary of the target tray, a third laser point cloud corresponding to the target tray is determined. The third laser point cloud is the laser point cloud obtained by using LiDAR to perform laser scanning towards the storage area where the target tray is located when using LiDAR to identify the socket boundary of the target tray.

[0108] Based on the three-dimensional coordinates of each laser point in the third laser point cloud, the first laser point cloud corresponding to the target tray is extracted from the third laser point cloud.

[0109] Based on the technical solutions of the above embodiments, optionally, determining the second detection result corresponding to the target tray includes:

[0110] Determine the second grid attribute value of each reference grid in the reference grid map used by the target pallet. The second grid attribute value is the number of second laser points that fall into the reference grid in the reference grid map when the target pallet is picked up by forklift according to the socket boundary recognition result after the socket boundary recognition of the target pallet is performed by LiDAR.

[0111] Based on the second grid attribute value of each reference grid in the reference grid map, the second grid state value of each reference grid in the reference grid map used by the target pallet is determined. The second grid state value is used to measure the density of the second laser point in the reference grid relative to other reference grids when the target pallet is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by LiDAR on the target pallet.

[0112] Based on the second grid attribute value and second grid state value of each reference grid, the second detection result corresponding to the target tray is determined.

[0113] Based on the technical solutions of the above embodiments, optionally, determining the second grid attribute values ​​of each reference grid in the reference grid map used by the target tray includes:

[0114] The target tray is determined to correspond to a second laser point cloud, wherein the second laser point cloud includes multiple second laser points;

[0115] Based on the three-dimensional coordinates of multiple second laser points and the position range of each grid in the reference grid map, the multiple second laser points are projected onto each grid in the reference grid map to obtain a second grid attribute value, which describes the number of second laser points falling into each grid in the reference grid map when the target tray is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by LiDAR.

[0116] Based on the technical solutions of the above embodiments, optionally, determining the target tray corresponding to the second laser point cloud includes:

[0117] After using LiDAR to identify the socket boundaries of the target tray, and when it is detected that the target tray is to be picked up according to the socket boundary identification result, the fourth laser point cloud corresponding to the target tray is determined. The fourth laser point cloud is the laser point cloud obtained by using LiDAR to perform laser scanning towards the storage area where the target tray is located when the target tray is to be picked up according to the socket boundary identification result.

[0118] Based on the three-dimensional coordinates of each laser point in the fourth laser point cloud, the second laser point cloud corresponding to the target tray is extracted from the fourth laser point cloud.

[0119] Based on the technical solutions of the above embodiments, optionally, the vertical height of each first laser point in the first laser point cloud and the vertical height of each second laser point in the second laser point cloud are within a preset height range, wherein the lower limit of the preset height range is greater than the height of the storage area where the target tray is located, and the upper limit of the preset height range is less than the height of the upper surface of the target tray.

[0120] Based on the technical solutions of the above embodiments, optionally, based on the first detection result and the second detection result, it is determined whether to continue to forklift the target pallet according to the socket boundary identification result, including...

[0121] Based on the first detection result and the second detection result, the pallet pose state of the target pallet is determined. The pallet pose state is used to describe whether the target pallet has a pose shift at different time points.

[0122] Based on the pallet pose of the target pallet, determine whether to continue picking up the target pallet according to the socket boundary recognition result.

[0123] Based on the technical solutions of the above embodiments, optionally, determining the pallet pose state of the target pallet based on the first detection result and the second detection result includes:

[0124] If there is a difference between the first detection result and the second detection result, and the difference between the two detection results is greater than or equal to a preset difference threshold, then the pallet pose state of the target pallet is determined to be that the target pallet has experienced pose shift at different time points.

[0125] If there is no difference between the first detection result and the second detection result, or if there is a difference and the difference between the two detection results is less than a preset difference threshold, then the pallet pose state of the target pallet is determined to be that the target pallet has not shown pose deviation at different time points.

[0126] The technical solution provided by this invention uses the relatively accurate pallet forward surface point cloud detection result pre-identified when identifying the socket boundary of the pallet as a benchmark. If the pallet pose moves during the forklift process, the pallet forward surface point cloud detection result will change. In particular, when the change in the pallet forward surface point cloud detection result is large, it is considered that the pallet has a large pose shift. It can automatically detect whether there are any abnormalities in the pallet and the goods on it, such as the pallet and the goods on it shifting due to fork arm collision, or the pallet state being abnormal due to ground hole collapse. It effectively avoids pallet pose shift or collision caused by inaccurate positioning, low forklift accuracy, or other situations, thereby increasing the safety of pallet lifting.

[0127] The pallet forklift device provided in the embodiments of the present invention can execute the pallet forklift method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the pallet forklift method.

[0128] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of the present invention.

[0129] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Refer to the following... Figure 4 It illustrates an electronic device suitable for implementing embodiments of the present invention (e.g., Figure 4 The diagram below shows the structure of the terminal device or server 400. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0130] like Figure 4 As shown, electronic device 400 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from storage device 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of electronic device 400. The processing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. An edit / output (I / O) interface 405 is also connected to bus 404.

[0131] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 400 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0132] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the pallet retrieval method shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 409, or installed from a storage device 408, or installed from a ROM 402. When the computer program is executed by the processing device 401, it performs the functions defined in the pallet retrieval method of the embodiments of the present invention.

[0133] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0134] The electronic device provided in this embodiment of the invention and the pallet fork lifting method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0135] This invention provides a computer storage medium storing a computer program that, when executed by a processor, implements the pallet fork lifting method provided in the above embodiments.

[0136] It should be noted that the computer-readable medium described above in this invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0137] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0138] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0139] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0140] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: determine a first detection result corresponding to the target tray, the first detection result being determined based on the number of first laser points falling into each reference grid in a reference grid map, the first laser points being laser points in a first laser point cloud used to describe a first reference surface, the first reference surface being the surface of the target tray closer to the lidar when using lidar to identify the socket boundary of the target tray; determine a second detection result corresponding to the target tray, the second detection result being determined based on the number of second laser points falling into each reference grid in the reference grid map, the second laser points being laser points in a second laser point cloud used to describe the first reference surface, the second reference surface being the surface of the target tray closer to the lidar when using lidar to identify the socket boundary of the target tray and then forking the target tray according to the socket boundary identification result; and, based on the first detection result and the second detection result, determine whether to continue forking the target tray according to the socket boundary identification result.

[0141] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0142] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0143] The units described in the embodiments of the present invention can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0144] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0145] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0146] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0147] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the invention. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0148] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for picking up a pallet with a forklift, characterized in that, The method includes: The first detection result corresponding to the target tray is determined. The first detection result is determined based on the number of first laser points falling into each reference grid in the reference grid map. The first laser point is the laser point in the first laser point cloud used to describe the first reference surface. The first reference surface is the surface of the target tray closer to the lidar when using lidar to identify the socket boundary of the target tray. The second detection result corresponding to the target tray is determined. The second detection result is determined based on the number of second laser points falling into each reference grid in the reference grid map. The second laser point is the laser point in the second laser point cloud used to describe the second reference surface. The second reference surface is the surface of the target tray close to the lidar side when the target tray is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by using lidar to identify the socket boundary of the target tray. Based on the first detection result and the second detection result, determining whether to continue picking up the target pallet according to the socket boundary recognition result; determining whether to continue picking up the target pallet according to the socket boundary recognition result based on the first detection result and the second detection result includes: determining the pallet pose state of the target pallet based on the first detection result and the second detection result, the pallet pose state being used to describe whether the target pallet has a pose shift at different time points; and determining whether to continue picking up the target pallet according to the socket boundary recognition result based on the pallet pose state of the target pallet.

2. The method according to claim 1, characterized in that, Determine the first detection result corresponding to the target tray, including: Determine the first grid attribute value of each reference grid in the reference grid map used by the target pallet. The first grid attribute value is the number of first laser points falling into the reference grid in the reference grid map when the target pallet is identified by LiDAR for the socket boundary. Based on the first grid attribute value of each reference grid in the reference grid map, the first grid state value of each reference grid in the reference grid map used by the target pallet is determined. The first grid state value is used to measure the density of the first laser point in the reference grid relative to other reference grids when using LiDAR to identify the socket boundary of the target pallet. Based on the first grid attribute value and the first grid state value of each reference grid, the first detection result corresponding to the target tray is determined.

3. The method according to claim 2, characterized in that, Determine the first grid attribute value of each reference grid in the reference grid map used by the target tray, including: The target tray is determined to correspond to a first laser point cloud, wherein the first laser point cloud includes a plurality of first laser points; Based on the three-dimensional coordinates of multiple first laser points and the position range of each grid in the reference grid map, the multiple first laser points are projected onto each grid in the reference grid map to obtain a first grid attribute value that describes the number of first laser points falling into each grid in the reference grid map when using LiDAR to identify the socket boundary of the target tray.

4. The method according to claim 1, characterized in that, Determine the second detection result corresponding to the target tray, including: Determine the second grid attribute value of each reference grid in the reference grid map used by the target pallet. The second grid attribute value is the number of second laser points that fall into the reference grid in the reference grid map when the target pallet is picked up by forklift according to the socket boundary recognition result after the socket boundary recognition of the target pallet is performed by LiDAR. Based on the second grid attribute value of each reference grid in the reference grid map, the second grid state value of each reference grid in the reference grid map used by the target pallet is determined. The second grid state value is used to measure the density of the second laser point in the reference grid relative to other reference grids when the target pallet is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by LiDAR on the target pallet. Based on the second grid attribute value and second grid state value of each reference grid, the second detection result corresponding to the target tray is determined.

5. The method according to claim 4, characterized in that, Determine the second grid attribute values ​​of each reference grid cell in the reference grid map used by the target tray, including: The target tray is determined to correspond to a second laser point cloud, wherein the second laser point cloud includes multiple second laser points; Based on the three-dimensional coordinates of multiple second laser points and the position range of each grid in the reference grid map, the multiple second laser points are projected onto each grid in the reference grid map to obtain a second grid attribute value, which describes the number of second laser points falling into each grid in the reference grid map when the target tray is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by LiDAR.

6. The method according to claim 1, characterized in that, The vertical height of each first laser point in the first laser point cloud and the vertical height of each second laser point in the second laser point cloud are within a preset height range. The lower limit of the preset height range is greater than the height of the storage area where the target tray is located, and the upper limit of the preset height range is less than the height of the upper surface of the target tray.

7. The method according to claim 6, characterized in that, Based on the first detection result and the second detection result, the pallet pose state of the target pallet is determined, including: If there is a difference between the first detection result and the second detection result, and the difference between the two detection results is greater than or equal to a preset difference threshold, then the pallet pose state of the target pallet is determined to be that the target pallet has experienced pose shift at different time points. If there is no difference between the first detection result and the second detection result, or if there is a difference and the difference between the two detection results is less than a preset difference threshold, then the pallet pose state of the target pallet is determined to be that the target pallet has not shown pose shift at different time points.

8. A pallet forklift device, characterized in that, The device includes: The first determining module is used to determine the first detection result corresponding to the target tray. The first detection result is determined based on the number of first laser points falling into each reference grid in the reference grid map. The first laser points are laser points in the first laser point cloud used to describe the first reference surface. The first reference surface is the surface of the target tray closer to the lidar when using lidar to identify the socket boundary of the target tray. The second determining module is used to determine the second detection result corresponding to the target tray. The second detection result is determined based on the number of second laser points falling into each reference grid in the reference grid map. The second laser point is the laser point in the second laser point cloud used to describe the second reference surface. The second reference surface is the surface of the target tray close to the laser radar side when the target tray is picked up according to the socket boundary recognition result after the socket boundary recognition is performed by using laser radar to identify the socket boundary of the target tray. The forklift control module is used to determine, based on the first detection result and the second detection result, whether to continue forking the target tray according to the socket boundary recognition result; determining whether to continue forking the target tray according to the socket boundary recognition result based on the first detection result and the second detection result includes: determining the tray pose state of the target tray based on the first detection result and the second detection result, the tray pose state being used to describe whether the target tray has a pose shift at different time points; and determining whether to continue forking the target tray according to the socket boundary recognition result based on the tray pose state of the target tray.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the pallet fork method as described in any one of claims 1-7.

Images