An Unmanned Control Method, Device and Driverless Forklift for Automatic Loading and Unloading of Goods

Abstract

An unmanned control method, device and driverless forklift for automatic loading and unloading of goods are proposed in an embodiment of the present application. The method includes obtaining the position information of the driverless forklift and determining the application scenario information of the driverless forklift based on the position information; then obtaining the size information and position information of the goods pallet, and determining the fork height of the driverless forklift based on the size information of the goods pallet; then determining the position information of the first obstacle in the application scenario information, generating a movement path according to the position information, controlling the driverless forklift to move to the goods pallet according to the movement path, and controlling the fork to lift the goods pallet to the fork height of the driverless forklift. By controlling the driverless forklift to obtain multiple position information and generate a movement path, the driverless vehicle can automatically complete the loading and unloading of goods without manual operation, and can also effectively cope with special situations with obstacles, greatly meeting the automation requirements of the forklift.

Description

Technical Field

[0001] This application belongs to the technical field of forklift control, and particularly relates to an unmanned control method, device, and driverless forklift for automatic loading and unloading of goods. Background Art

[0002] As an industrial handling vehicle, a forklift can be used for loading, unloading, stacking, and short-distance transportation operations of packaged goods on a pallet. The handling capacity of a forklift usually depends on technical parameters such as its rated load capacity, load center distance, maximum lifting height, maximum traveling speed, mast tilt angle, and minimum turning radius.

[0003] Most existing forklifts are manually operated, and generally, the forklift is moved manually to handle goods, which is likely to consume a large amount of labor costs; a small number of forklifts can achieve semi-automation, but their dependence on manual labor is still relatively large, and the way of automatically controlling the movement of the forklift is too fixed to handle special situations, which will not only affect the use experience of the forklift but also pose certain safety hazards. Summary of the Invention

[0004] To better solve the above-mentioned problems, this application proposes an unmanned control method, device, and driverless forklift for automatic loading and unloading of goods, and its specific technical solutions are as follows:

[0005] In a first aspect, an embodiment of this application provides an unmanned control method for automatic loading and unloading of goods. The method is applied to a driverless forklift and includes:

[0006] Obtain the position information of the driverless forklift, and determine the application scenario information of the driverless forklift based on the position information of the driverless forklift;

[0007] Obtain the size information and position information of the goods pallet, and determine the fork height of the driverless forklift based on the size information of the goods pallet;

[0008] Determine the position information of the first obstacle in the application scenario information of the driverless forklift, and generate a movement path of the driverless forklift according to the position information of the driverless forklift, the position information of the goods pallet, and the position information of the first obstacle;

[0009] Control the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift, and control the fork of the driverless forklift to lift the goods pallet to the fork height of the driverless forklift.

[0010] In an alternative solution of the first aspect, determining the application scenario information of the driverless forklift based on the position information of the driverless forklift includes:

[0011] Obtain 3D point cloud data based on the position information of the driverless forklift;

[0012] Generate the application scenario information of the driverless forklift based on the 3D point cloud data.

[0013] In another alternative of the first aspect, after obtaining the 3D point cloud data based on the position information of the driverless forklift and before generating the application scenario information of the driverless forklift according to the 3D point cloud data, it further includes:

[0014] Input the 3D point cloud data into the trained deep learning neural network to obtain the scene features of the driverless forklift;

[0015] Generating the application scenario information of the driverless forklift based on the 3D point cloud data includes:

[0016] Generate the application scenario information of the driverless forklift according to the scene features of the driverless forklift;

[0017] Among them, the deep learning neural network is trained by the scene features corresponding to various known application scenario information and the 3D point cloud data corresponding to each scene feature.

[0018] In another alternative of the first aspect, generating the movement path of the driverless forklift according to the position information of the driverless forklift, the position information of the goods pallet, and the position information of the first obstacle includes:

[0019] Generate at least two first movement paths according to the position information of the driverless forklift and the position information of the goods pallet;

[0020] Determine the second movement path from at least two first movement paths according to the position information of the first obstacle;

[0021] Search for the historical movement path of the driverless forklift, and generate the movement path of the driverless forklift according to the second movement path and the historical movement path of the driverless forklift.

[0022] In another alternative of the first aspect, controlling the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift further includes:

[0023] When it is detected that there is a second fault object on the movement path of the driverless forklift, control the driverless forklift to stop moving;

[0024] Detect whether there is a second fault object on the movement path of the driverless forklift at a preset time interval;

[0025] When it is determined that there is no second fault object on the movement path of the driverless forklift, control the driverless forklift to move to the goods pallet.

[0026] In another alternative of the first aspect, after controlling the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift and controlling the forklift ruler of the driverless forklift to lift the goods pallet to the height of the forklift ruler of the driverless forklift, it further includes:

[0027] Obtain the position information of the freight car box, and generate a third movement path according to the position information of the freight car box and the position information of the goods pallet;

[0028] Control the driverless forklift to move to the freight car box according to the third movement path, and control the driverless forklift to move to a preset position inside the freight car box according to the preset movement path corresponding to the freight car box.

[0029] In another alternative of the first aspect, after controlling the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift and controlling the forklift ruler of the driverless forklift to lift the goods pallet to the height of the forklift ruler of the driverless forklift, it further includes:

[0030] When it is detected that the remaining power of the driverless forklift is lower than the preset power threshold, determine a target charging station within a preset distance range according to the position information of the driverless forklift;

[0031] Control the driverless forklift to move to the target charging station for charging until the remaining power of the driverless forklift is higher than or equal to the preset power threshold.

[0032] In a second aspect, an embodiment of the present application provides a driverless forklift, including:

[0033] A first recognition module, configured to obtain the position information of the driverless forklift and determine the application scenario information of the driverless forklift based on the position information of the driverless forklift;

[0034] A second recognition module, configured to obtain the size information and position information of the goods pallet, and determine the forklift ruler height of the driverless forklift based on the size information of the goods pallet;

[0035] A navigation generation module, configured to determine the position information of a first obstacle in the application scenario information of the driverless forklift, and generate a movement path of the driverless forklift according to the position information of the driverless forklift, the position information of the goods pallet, and the position information of the first obstacle;

[0036] A control movement module, configured to control the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift, and control the forklift ruler of the driverless forklift to lift the goods pallet to the height of the forklift ruler of the driverless forklift.

[0037] In an alternative of the second aspect, the first recognition module includes:

[0038] An acquisition unit, configured to acquire 3D point cloud data based on the position information of the driverless forklift;

[0039] A first generation unit, configured to generate application scenario information of the driverless forklift according to the 3D point cloud data.

[0040] In yet another alternative solution of the second aspect, the first recognition module further includes:

[0041] A model learning unit, configured to input the 3D point cloud data into a trained deep learning neural network after acquiring the 3D point cloud data based on the position information of the driverless forklift and before generating the application scenario information of the driverless forklift according to the 3D point cloud data, so as to obtain the scene features of the driverless forklift;

[0042] The first generation unit is specifically configured to generate application scenario information of the driverless forklift according to the scene features of the driverless forklift.

[0043] Wherein, the deep learning neural network is trained by the scene features corresponding to various known application scenario information and the 3D point cloud data corresponding to each scene feature.

[0044] In yet another alternative solution of the second aspect, the navigation generation module includes:

[0045] A second generation unit, configured to generate at least two first movement paths according to the position information of the driverless forklift and the position information of the goods pallet;

[0046] A determination unit, configured to determine a second movement path from at least two first movement paths according to the position information of the first obstacle;

[0047] A third generation unit, configured to search for the historical movement path of the driverless forklift, and generate the movement path of the driverless forklift according to the second movement path and the historical movement path of the driverless forklift.

[0048] In yet another alternative solution of the second aspect, the control movement module further includes:

[0049] When it is detected that there is a second fault object on the movement path of the driverless forklift, control the driverless forklift to stop moving;

[0050] Detect whether there is a second fault object on the movement path of the driverless forklift at a preset time interval;

[0051] When it is determined that there is no second fault object on the movement path of the driverless forklift, control the driverless forklift to move to the goods pallet.

[0052] In yet another alternative solution of the second aspect, the device further includes:

[0053] A processing module, configured to, after controlling an autonomous forklift to move to a goods pallet according to the movement path of the autonomous forklift and controlling the forklift forks of the autonomous forklift to lift the goods pallet to the height of the forklift forks of the autonomous forklift, obtain the position information of the freight car box, and generate a third movement path according to the position information of the freight car box and the position information of the goods pallet;

[0054] A control module, configured to control the autonomous forklift to move to the freight car box according to the third movement path, and control the autonomous forklift to move to a preset position inside the freight car box according to a preset movement path corresponding to the freight car box.

[0055] In yet another alternative of the second aspect, the device further includes:

[0056] A detection module, configured to, after controlling the autonomous forklift to move to the goods pallet according to the movement path of the autonomous forklift and controlling the forklift forks of the autonomous forklift to lift the goods pallet to the height of the forklift forks of the autonomous forklift, when it is detected that the remaining power of the autonomous forklift is lower than a preset power threshold, determine a target charging station within a preset distance range according to the position information of the autonomous forklift;

[0057] A charging module, configured to control the autonomous forklift to move to the target charging station for charging until the remaining power of the autonomous forklift is higher than or equal to the preset power threshold.

[0058] In a third aspect, an embodiment of the present application provides an unmanned control device for automatic loading and unloading of goods, including a processor and a memory;

[0059] The processor is connected to the memory;

[0060] The memory is used to store executable program code;

[0061] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the unmanned control method for automatic loading and unloading of goods provided in the first aspect or any implementation manner of the first aspect of the embodiments of the present application.

[0062] In a fourth aspect, an embodiment of the present application provides a computer storage medium, which stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, the unmanned control method for automatic loading and unloading of goods provided in the first aspect or any implementation manner of the first aspect of the embodiments of the present application can be implemented.

[0063] In the embodiments of the present application, when applying an unmanned forklift for automatic loading and unloading of goods, the position information of the unmanned forklift can be obtained first, and the application scenario information of the unmanned forklift can be determined based on the position information; then, the size information and position information of the goods pallet can be obtained, and the fork height of the unmanned forklift can be determined based on the size information of the goods pallet; then, the position information of the first obstacle can be determined in the application scenario information, and a movement path can be generated according to the position information. The unmanned forklift can be controlled to move to the goods pallet according to the movement path, and the fork is controlled to lift the goods pallet to the fork height of the unmanned forklift. By controlling the unmanned forklift to obtain multiple position information and generate a movement path, the unmanned vehicle can automatically complete the loading and unloading of goods without manual operation, and can also effectively cope with special situations with obstacles, greatly meeting the automation requirements of the forklift. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0065] Figure 1 It is a schematic flowchart of an unmanned control method for automatic loading and unloading of goods provided by an embodiment of the present application;

[0066] Figure 2 It is a schematic structural diagram of an unmanned forklift provided by an embodiment of the present application;

[0067] Figure 3 It is a schematic diagram of the movement effect of an unmanned forklift provided by an embodiment of the present application;

[0068] Figure 4 It is a schematic structural diagram of an unmanned forklift provided by an embodiment of the present application;

[0069] Figure 5 It is a schematic structural diagram of an unmanned control device for automatic loading and unloading of goods provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0070] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

[0071] In the following description, the terms "first" and "second" are for descriptive purposes only and should not be construed as indicating or implying relative importance. The following description provides multiple embodiments of the present application, and different embodiments can be replaced or combined. Therefore, the present application can also be considered to include all possible combinations of the same and / or different embodiments described. Thus, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments that include one or more of all other possible combinations of A, B, C, and D, even though such embodiments may not be explicitly described in the following content.

[0072] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes can be made to the functions and arrangements of the described elements without departing from the scope of the present application. Various processes or components can be appropriately omitted, substituted, or added to each example. For example, the described methods can be performed in a different order than the described order, and various steps can be added, omitted, or combined. In addition, the features described for some examples can be combined into other examples.

[0073] Please refer to Figure 1 , Figure 1 which shows a schematic flow diagram of an unmanned control method for automatic loading and unloading of goods provided by an embodiment of the present application.

[0074] As Figure 1 shown, this unmanned control method for automatic loading and unloading of goods can be applied to an unmanned forklift to achieve unmanned control of automatic loading and unloading of goods through the unmanned forklift. The method can at least include the following steps:

[0075] 102. Obtain the position information of the unmanned forklift and determine the application scenario information of the unmanned forklift based on the position information of the unmanned forklift.

[0076] In the embodiment of the present application, the specific structure of the unmanned forklift mentioned can be specifically referred to Figure 2 which shows a schematic structural diagram of an unmanned forklift. As Figure 2 shown, the unmanned forklift can at least include a traveling mechanism 201, a lifting mechanism 202, and two sets of fork rulers 203, where:

[0077] The traveling mechanism 201 can but is not limited to including tires, a chassis, a motor drive structure, etc., and is connected to the control system of the unmanned forklift to drive the unmanned forklift.

[0078] The lifting structure 202 may but is not limited to include a lifting rod, a motor drive structure, etc., and is connected to the control system of the driverless forklift to realize the automatic rising or falling of the lifting rod. Among them, the lifting structure 202 can be arranged on the traveling mechanism 201 and can drive two groups of fork rulers 203 to rise or fall along the moving direction of the lifting rod. It can be understood that the lifting rod of the lifting structure 202 can be used to control any one group of fork rulers 203 alone or two groups of fork rulers 203 at the same time, and it is set according to the user's cargo loading and unloading requirements.

[0079] The driverless forklift can also be provided with a steering encoder to control the steering of the driverless forklift according to the moving requirements, and the accuracy of the steering encoder can be but is not limited to being set between -1 degree and +1 degree. Of course, the control system of the driverless forklift mentioned in the embodiments of the present application can be but is not limited to using an FPGA autonomous driving chip and is not limited thereto.

[0080] Specifically, when applying the driverless forklift for automatic cargo loading and unloading, the position information of the driverless forklift can be obtained first, and the application scenario information of the driverless forklift can be determined based on the position information of the driverless forklift. Among them, the position information of the driverless forklift can be but is not limited to being determined according to the global positioning and navigation technology. For example, after the user starts the driverless forklift, the driverless forklift can automatically obtain the current position according to the global positioning and navigation technology, and its specific position information can be but is not limited to xx Province, xx City, xx District, xx Street.

[0081] Furthermore, after obtaining the current position of the driverless forklift, the scene objects around the driverless forklift can also be obtained at the current position of the driverless forklift, and the application scenario information of the driverless forklift can be determined according to the scene objects around the driverless forklift. Among them, the scene objects of the driverless forklift can be but is not limited to including the goods, shelves, truck boxes, road surface types, and obstacles placed around the driverless forklift. The road surface type can be a flat cement road surface, a smooth road surface, or a landslide road surface, etc. It can be understood that the application scenario information of the driverless forklift in the embodiments of the present application can be summarized from the obtained scene objects around the driverless forklift, and its specific but not limited to can be the application scenario type, such as a smooth road surface scenario type, a cement road surface scenario type, or a landslide road surface scenario type, or a type with many goods and few obstacles, a type with many goods and many obstacles, a type with few goods and many obstacles, or a type with few goods and few obstacles, etc.

[0082] As an option of the embodiments of the present application, determining the application scenario information of the driverless forklift based on the position information of the driverless forklift includes:

[0083] Obtaining 3D point cloud data based on the position information of the driverless forklift;

[0084] Generate the application scenario information of the driverless forklift based on the 3D point cloud data.

[0085] Specifically, after obtaining the current position of the driverless forklift, the scene objects around the driverless forklift can be scanned based on the lidar and inertial sensors installed on the driverless forklift to obtain the corresponding 3D point cloud data, and the surrounding scene map of the driverless forklift can be generated according to the 3D point cloud data. Then, the application scenario information of the driverless forklift can be determined from the surrounding scene map through, but not limited to, visual recognition algorithms. Among them, the surrounding scene map of the driverless forklift generated according to the 3D point cloud data may include the above-mentioned scene objects such as goods, shelves, truck boxes, road surface types, and obstacles placed around the driverless forklift.

[0086] It should be noted that during the movement of the driverless forklift, the position information of the driverless forklift can be obtained in real time, and the application scenario information of the driverless forklift can be determined in real time based on the position information of the driverless forklift. When the application scenario information of the driverless forklift determined in real time changes, the movement path of the driverless forklift can be changed accordingly.

[0087] It can be understood that the type of the inertial sensor here can be, but not limited to, IMU or RTK, and is not limited thereto.

[0088] As another option of the embodiment of the present application, after obtaining the 3D point cloud data based on the position information of the driverless forklift and before generating the application scenario information of the driverless forklift according to the 3D point cloud data, it further includes:

[0089] Input the 3D point cloud data into the trained deep learning neural network to obtain the scene features of the driverless forklift;

[0090] Generating the application scenario information of the driverless forklift according to the 3D point cloud data includes:

[0091] Generating the application scenario information of the driverless forklift according to the scene features of the driverless forklift.

[0092] Specifically, after obtaining the 3D point cloud data corresponding to the physical objects in the scene around the driverless forklift, the 3D point cloud data can be input into a trained deep learning neural network first to extract the scene features corresponding to the physical objects in the scene around the driverless forklift, so as to quickly generate the surrounding scene map of the driverless forklift according to the scene features of the driverless forklift. Then, the application scene information of the driverless forklift can be determined from the surrounding scene map through, but not limited to, visual recognition algorithms. Among them, the deep learning neural network can be trained by the scene features corresponding to various known application scene information and the 3D point cloud data corresponding to each scene feature, and its purpose is to extract the feature vectors corresponding to the scene from the 3D point cloud data. It can be understood that the deep learning neural network can also be used to learn the application scene information to output the corresponding application scene information according to the extracted feature vectors corresponding to the scene. The embodiments of the present application are not limited thereto.

[0093] It should be noted that in the embodiments of the present application, a neural network for learning the vehicle type and the size of the cargo pallet of the driverless forklift can also be set. The neural network can be used to output, but not limited to, the moving speed of the driverless forklift according to the input vehicle type and the size of the cargo pallet of the current driverless forklift, so as to ensure the stability of the driverless forklift during the process of moving the cargo pallet. Of course, in the embodiments of the present application, a neural network for learning other different types of information can also be set to further improve the moving stability of the driverless forklift, and the specific type and composition structure of the neural network are not limited.

[0094] 104. Obtain the size information and position information of the cargo pallet, and determine the fork height of the driverless forklift based on the size information of the cargo pallet.

[0095] Specifically, after obtaining the current position of the driverless forklift, the size of the cargo pallet and the current position of the cargo pallet can be further obtained, and the height at which the fork of the driverless forklift lifts the cargo pallet can be determined first according to the size of the cargo pallet. Among them, the size of the cargo pallet can include, but not limited to, the length, width and height of the cargo pallet, which can be input in advance manually or obtained by recognizing the surrounding scene map of the driverless forklift mentioned above. The driverless forklift can plan the contact length between the fork and the bottom of the cargo pallet according to the obtained width of the cargo pallet, and can plan the height at which the fork needs to lift the cargo pallet according to the obtained height of the cargo pallet. Here, the height at which the fork needs to lift the cargo pallet can include, but not limited to, the height for handling the cargo pallet or the height for moving the cargo pallet.

[0096] It can be understood that the method for the driverless forklift in the embodiment of the present application to determine the contact length between the fork ruler and the bottom of the goods pallet and the height that the fork ruler needs to lift the goods pallet can be, but is not limited to, obtained according to a preset distance - size list, and is not limited thereto.

[0097] It should be noted that, possibly, the driverless forklift can also identify the goods pallet in the above - mentioned surrounding scene map to calculate the current position of the goods pallet. Possibly, if the goods pallet is placed in a preset designated position in advance, the driverless forklift can also quickly determine the current position of the goods pallet according to the preset designated position. Possibly, the driverless forklift can also further obtain the current position of the goods pallet by means of the set camera, lidar, multi - vision sensor, and ultrasonic microphone.

[0098] 106. Determine the position information of the first obstacle in the application scenario information of the driverless forklift, and generate a moving path of the driverless forklift according to the position information of the driverless forklift, the position information of the goods pallet, and the position information of the first obstacle.

[0099] Specifically, after determining the application scenario information of the driverless forklift, the current position of the first obstacle can also be identified in the application scenario information of the driverless forklift to prevent the driverless forklift from colliding with the first obstacle during the movement to the goods pallet. Among them, the type of the first obstacle can be a static obstacle around the driverless forklift, such as, but not limited to, a shelf or other scene objects that hinder the movement of the driverless forklift.

[0100] It can be understood that during the movement of the driverless forklift to the goods pallet, the lidar and camera set on the driverless forklift can also be used to detect in real time whether there are other static obstacles, and when detecting other static obstacles, the moving path of the driverless forklift can be adjusted according to the current position of the other static obstacles to prevent the driverless forklift from colliding with other static obstacles during the movement to the goods pallet.

[0101] Furthermore, after identifying the current position of the first obstacle, a moving path of the driverless forklift can be generated according to the position information of the driverless forklift, the position information of the goods pallet, and the position information of the first obstacle.

[0102] As another alternative in the embodiment of the present application, generating a moving path of the driverless forklift according to the position information of the driverless forklift, the position information of the goods pallet, and the position information of the first obstacle includes:

[0103] Generate at least two first moving paths according to the position information of the driverless forklift and the position information of the goods pallet;

[0104] Determine a second movement path from at least two first movement paths according to the position information of the first obstacle;

[0105] Search for the historical movement path of the driverless forklift, and generate the movement path of the driverless forklift according to the second movement path and the historical movement path of the driverless forklift.

[0106] Specifically, when generating the movement path of the driverless forklift, multiple first movement paths can be determined first according to the current position of the driverless forklift and the current position of the goods pallet, and any one of the multiple first movement paths can enable the driverless forklift to move from the current position to the current position of the goods pallet.

[0107] Furthermore, paths that do not pass through the first obstacle can be filtered out from the multiple first movement paths according to the current position of the first obstacle, and the paths that do not pass through the first obstacle are used as the second movement path. It can be understood that the number of the second movement paths here can be, but is not limited to, one or more. Possibly, when the number of the second movement paths is one, the second movement path can be directly used as the movement path of the driverless forklift. Possibly, when the number of the second movement paths is multiple, the historical movement path of the driverless forklift can also be searched, the historical movement section including the current position of the driverless forklift and the current position of the goods pallet is filtered out from the historical movement path of the driverless forklift, and the movement path in the second movement path that is consistent with the historical movement section including the current position of the driverless forklift and the current position of the goods pallet is used as the movement path of the driverless forklift. Of course, if any one of the second movement paths is not consistent with the historical movement section including the current position of the driverless forklift and the current position of the goods pallet, the path with the shortest movement distance can also be selected from the second movement paths as the movement path of the driverless forklift.

[0108] It should be noted that the method for generating multiple first movement paths in the embodiments of the present application can refer to the existing navigation technology, and will not be elaborated here.

[0109] 108. Control the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift, and control the fork of the driverless forklift to lift the goods pallet to the height of the fork of the driverless forklift.

[0110] Specifically, after determining the moving path of the driverless forklift, the driverless forklift can be controlled to move to the cargo pallet according to the moving path of the driverless forklift, and the forklift of the driverless forklift can be controlled to lift the cargo pallet to the height of the fork ruler according to the determined fork ruler height. It can be understood that after the forklift of the driverless forklift lifts the cargo pallet to the height of the fork ruler, the cargo pallet can be, but is not limited to, moved to a specified position for loading and unloading to meet the different cargo loading and unloading needs of users.

[0111] As another option of the embodiment of the present application, controlling the driverless forklift to move to the cargo pallet according to the moving path of the driverless forklift further includes:

[0112] When it is detected that there is a second fault object on the moving path of the driverless forklift, control the driverless forklift to stop moving;

[0113] Detect whether there is a second fault object on the moving path of the driverless forklift at a preset time interval;

[0114] When it is determined that there is no second fault object on the moving path of the driverless forklift, control the driverless forklift to move to the cargo pallet.

[0115] Specifically, during the process of the driverless forklift moving to the cargo pallet, the lidar and camera set on the driverless forklift can also be used to detect in real time whether there is a second obstacle, so as to further improve the safety of the driverless forklift. The second obstacle can be, but is not limited to, dynamic obstacles such as walking personnel and small animals, and the position of the second obstacle can change in real time. When it is detected that there is a second obstacle, the driverless forklift can be controlled to stop moving in time, and it is detected multiple times at a preset time interval whether there is still a second fault object on the moving path of the driverless forklift. The driverless forklift can be controlled to continue moving until there is no such second fault object.

[0116] As another option of the embodiment of the present application, after controlling the driverless forklift to move to the cargo pallet according to the moving path of the driverless forklift and controlling the fork ruler of the driverless forklift to lift the cargo pallet to the height of the fork ruler of the driverless forklift, it further includes:

[0117] Obtain the position information of the freight car box, and generate a third moving path according to the position information of the freight car box and the position information of the cargo pallet;

[0118] Control the driverless forklift to move to the freight car box according to the third moving path, and control the driverless forklift to move to a preset position inside the freight car box according to the preset moving path corresponding to the freight car box.

[0119] After the forklift of the driverless forklift lifts the goods pallet to the height of the forklift of the driverless forklift, the driverless forklift and the goods pallet can be placed in the truck box according to user requirements. Specifically, the current position of the truck box can be obtained first, and a third movement path can be generated according to the current position of the truck box and the position information of the goods pallet. The determination method of the third movement path can refer to the method of obtaining the movement path of the driverless forklift according to the first movement path above, and will not be elaborated here.

[0120] Furthermore, after controlling the driverless forklift to move to the truck box according to the third movement path, the driverless forklift can be controlled to move to a preset position inside the truck box according to a preset movement path corresponding to the truck box. Among them, the preset movement path corresponding to the truck box can be the path for the driverless forklift to move from the door of the truck box to the preset position inside the truck box, and it can be determined according to, but not limited to, the internal dimensions of the truck box.

[0121] Reference can also be made here to Figure 3 the schematic diagram of the movement effect of a driverless forklift provided by the embodiment of the present application shown. As Figure 3 , the driverless forklift 301 can first move to the goods pallet according to the movement path and lift the goods pallet to the height of the forklift of the driverless forklift, and then move to the door of the truck box 302 on the first plane 303 according to the third movement path. The height of the first plane 303 can be, but not limited to, the same as the bottom surface of the door of the truck box 302, so as to facilitate the driverless forklift 301 to smoothly enter the truck box 302. Then, the driverless forklift 301 can be controlled to move into the truck box 302 along the preset movement path corresponding to the truck box 302 until the preset position. It can be understood that the truck box 302 can be fixedly parked on the second plane 304, and the second plane 304 remains relatively unchanged with the bottom surface of the door of the truck box 302.

[0122] As another option of the embodiment of the present application, after controlling the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift and controlling the forklift of the driverless forklift to lift the goods pallet to the height of the forklift of the driverless forklift, it further includes:

[0123] When it is detected that the remaining power of the driverless forklift is lower than the preset power threshold, a target charging station is determined within a preset distance range according to the position information of the driverless forklift;

[0124] Control the driverless forklift to move to the target charging station for charging until the remaining power of the driverless forklift is higher than or equal to the preset power threshold.

[0125] Specifically, when it is detected that the remaining power of the driverless forklift is lower than the preset power threshold, one or more charging stations within a preset range can be determined according to the current position of the driverless forklift. If there are multiple charging stations, the charging station closest to the current position of the driverless forklift can be used as the target charging station, and the driverless forklift can be controlled to move to the target charging station for charging. It can be understood that when it is detected that the remaining power of the driverless forklift is lower than the preset power threshold, a warning message can also be sent or a warning light can be flashed to timely remind the staff to perform charging-related operations. The preset power threshold can be, but is not limited to, set to 20% of the total power.

[0126] Further, when the remaining power of the driverless forklift is higher than or equal to the preset power threshold, charging of the driverless forklift can be stopped, and the driverless forklift can be controlled to move to the initially determined position.

[0127] Please refer to Figure 4 , Figure 4 which shows a schematic structural diagram of a driverless forklift provided by an embodiment of the present application.

[0128] As Figure 4 described, the driverless forklift can at least include a first identification module 401, a second identification module 402, a navigation generation module 403, and a control movement module 404, where:

[0129] The first identification module 401 is configured to obtain the position information of the driverless forklift and determine the application scenario information of the driverless forklift based on the position information of the driverless forklift.

[0130] The second identification module 402 is configured to obtain the size information and position information of the goods pallet, and determine the fork height of the driverless forklift based on the size information of the goods pallet.

[0131] The navigation generation module 403 is configured to determine the position information of the first obstacle in the application scenario information of the driverless forklift, and generate a movement path of the driverless forklift according to the position information of the driverless forklift, the position information of the goods pallet, and the position information of the first obstacle.

[0132] The control movement module 404 is configured to control the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift, and control the fork of the driverless forklift to lift the goods pallet to the fork height of the driverless forklift.

[0133] In some possible embodiments, the first identification module includes:

[0134] An acquisition unit, configured to acquire 3D point cloud data based on the position information of the driverless forklift.

[0135] A first generation unit for generating application scenario information of an autonomous forklift based on 3D point cloud data.

[0136] In some possible embodiments, the first recognition module further includes:

[0137] A model learning unit for, after obtaining 3D point cloud data based on the position information of the autonomous forklift and before generating application scenario information of the autonomous forklift according to the 3D point cloud data, inputting the 3D point cloud data into a trained deep learning neural network to obtain scene features of the autonomous forklift;

[0138] The first generation unit is specifically configured to generate application scenario information of the autonomous forklift according to the scene features of the autonomous forklift.

[0139] Wherein, the deep learning neural network is trained by scene features corresponding to various known application scenario information and 3D point cloud data corresponding to each scene feature.

[0140] In some possible embodiments, the navigation generation module includes:

[0141] A second generation unit for generating at least two first movement paths according to the position information of the autonomous forklift and the position information of the goods pallet;

[0142] A determination unit for determining a second movement path from at least two first movement paths according to the position information of the first obstacle;

[0143] A third generation unit for searching for the historical movement path of the autonomous forklift and generating the movement path of the autonomous forklift according to the second movement path and the historical movement path of the autonomous forklift.

[0144] In some possible embodiments, the control movement module further includes:

[0145] When a second fault object is detected on the movement path of the autonomous forklift, controlling the autonomous forklift to stop moving;

[0146] Detecting whether there is a second fault object on the movement path of the autonomous forklift at a preset time interval;

[0147] When it is determined that there is no second fault object on the movement path of the autonomous forklift, controlling the autonomous forklift to move to the goods pallet.

[0148] In some possible embodiments, the device further includes:

[0149] A processing module, configured to, after controlling an autonomous forklift to move to a goods pallet according to a movement path of the autonomous forklift and controlling a forklift fork of the autonomous forklift to lift the goods pallet to the height of the forklift fork of the autonomous forklift, obtain position information of a freight car box, and generate a third movement path according to the position information of the freight car box and the position information of the goods pallet;

[0150] A control module, configured to control the autonomous forklift to move to the freight car box according to the third movement path, and control the autonomous forklift to move to a preset position inside the freight car box according to a preset movement path corresponding to the freight car box.

[0151] In some possible embodiments, the apparatus further includes:

[0152] A detection module, configured to, after controlling the autonomous forklift to move to the goods pallet according to the movement path of the autonomous forklift and controlling the forklift fork of the autonomous forklift to lift the goods pallet to the height of the forklift fork of the autonomous forklift, when detecting that the remaining power of the autonomous forklift is lower than a preset power threshold, determine a target charging station within a preset distance range according to the position information of the autonomous forklift;

[0153] A charging module, configured to control the autonomous forklift to move to the target charging station for charging until the remaining power of the autonomous forklift is higher than or equal to the preset power threshold.

[0154] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented by means of software and / or hardware. The "units" and "modules" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete a specific function, where the hardware can be, for example, a Field-Programmable Gate Array (FPGA), an Integrated Circuit (IC), etc.

[0155] Each processing unit and / or module of the embodiments of the present application can be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or can be implemented by software that executes the functions described in the embodiments of the present application.

[0156] Please refer to Figure 5 , Figure 5 , which shows a schematic structural diagram of an unmanned control device for automatic loading and unloading of goods provided by an embodiment of the present application.

[0157] As Figure 5 shown, the unmanned control device 500 for automatic loading and unloading of goods may include: at least one processor 501, at least one network interface 505, a user interface 503, a memory 505, and at least one communication bus 502.

[0158] Among them, the communication bus 502 can be used to realize the connection and communication of each of the above components.

[0159] Among them, the user interface 503 may include buttons, and the optional user interface may further include a standard wired interface and a wireless interface.

[0160] Among them, the network interface 505 can but is not limited to including a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0161] Among them, the processor 501 may include one or more processing cores. The processor 501 connects various parts within the entire electronic device 500 by using various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 505, and by calling the data stored in the memory 505, the processor 501 executes various functions of the routing device 500 and processes data. Optionally, the processor 501 can be implemented in at least one of the hardware forms of DSP, FPGA, and PLA. The processor 501 can integrate one or a combination of several of CPU, GPU, and modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for the rendering and drawing of the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 501 and can be implemented separately by a single chip.

[0162] Among them, the memory 505 may include RAM and may also include ROM. Optionally, the memory 505 includes a non-transitory computer-readable medium. The memory 505 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 505 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing each of the above method embodiments, etc.; the data storage area can store the data involved in each of the above method embodiments. Optionally, the memory 505 can also be at least one storage device located far from the aforementioned processor 501. As Figure 3 shown, the memory 505, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an unmanned control application program for automatic goods loading and unloading.

[0163] Specifically, the processor 501 can be used to call the unmanned control application program for automatic goods loading and unloading stored in the memory 505 and specifically perform the following operations:

[0164] Obtain the position information of the driverless forklift, and determine the application scenario information of the driverless forklift based on the position information of the driverless forklift;

[0165] Obtain the size information and position information of the goods pallet, and determine the fork height of the driverless forklift based on the size information of the goods pallet;

[0166] Determine the position information of the first obstacle in the application scenario information of the driverless forklift, and generate a moving path of the driverless forklift according to the position information of the driverless forklift, the position information of the goods pallet, and the position information of the first obstacle;

[0167] Control the driverless forklift to move to the goods pallet according to the moving path of the driverless forklift, and control the fork of the driverless forklift to lift the goods pallet to the fork height of the driverless forklift.

[0168] In some possible embodiments, determining the application scenario information of the driverless forklift based on the position information of the driverless forklift includes:

[0169] Obtain 3D point cloud data based on the position information of the driverless forklift;

[0170] Generate the application scenario information of the driverless forklift according to the 3D point cloud data.

[0171] In some possible embodiments, after obtaining the 3D point cloud data based on the position information of the driverless forklift and before generating the application scenario information of the driverless forklift according to the 3D point cloud data, it further includes:

[0172] Input the 3D point cloud data into a trained deep learning neural network to obtain the scene features of the driverless forklift;

[0173] Generating the application scenario information of the driverless forklift according to the 3D point cloud data includes:

[0174] Generate the application scenario information of the driverless forklift according to the scene features of the driverless forklift;

[0175] Among them, the deep learning neural network is trained by the scene features corresponding to various known application scenario information and the 3D point cloud data corresponding to each scene feature.

[0176] In some possible embodiments, generating the moving path of the driverless forklift according to the position information of the driverless forklift, the position information of the goods pallet, and the position information of the first obstacle includes:

[0177] Generate at least two first moving paths according to the position information of the driverless forklift and the position information of the goods pallet;

[0178] Determine a second moving path from at least two first moving paths according to the position information of the first obstacle;

[0179] Find the historical movement path of the driverless forklift, and generate the movement path of the driverless forklift according to the second movement path and the historical movement path of the driverless forklift.

[0180] In some possible embodiments, controlling the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift further includes:

[0181] When detecting a second obstacle on the movement path of the driverless forklift, control the driverless forklift to stop moving;

[0182] Detect whether there is a second obstacle on the movement path of the driverless forklift at a preset time interval;

[0183] When it is determined that there is no second obstacle on the movement path of the driverless forklift, control the driverless forklift to move to the goods pallet.

[0184] In some possible embodiments, after controlling the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift and controlling the fork of the driverless forklift to lift the goods pallet to the height of the fork of the driverless forklift, it further includes:

[0185] Obtain the position information of the freight car box, and generate a third movement path according to the position information of the freight car box and the position information of the goods pallet;

[0186] Control the driverless forklift to move to the freight car box according to the third movement path, and control the driverless forklift to move to a preset position inside the freight car box according to the preset movement path corresponding to the freight car box.

[0187] In some possible embodiments, after controlling the driverless forklift to move to the goods pallet according to the movement path of the driverless forklift and controlling the fork of the driverless forklift to lift the goods pallet to the height of the fork of the driverless forklift, it further includes:

[0188] When detecting that the remaining power of the driverless forklift is lower than the preset power threshold, determine a target charging station within a preset distance according to the position information of the driverless forklift;

[0189] Control the driverless forklift to move to the target charging station for charging until the remaining power of the driverless forklift is higher than or equal to the preset power threshold.

[0190] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the above method are implemented. Among them, the computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0191] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0192] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0193] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0194] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0195] In addition, in each embodiment of the present application, the various functional units can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0196] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned memory includes: USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs, etc., all of which can store program codes.

[0197] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory, and the memory can include: flash drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc.

[0198] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. After considering the specification and practicing the present disclosure herein, those skilled in the art will readily think of other implementations of the present disclosure. This application aims to cover any variations, uses, or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An unmanned control method for automatic loading and unloading of goods, characterized in that, The method is applied to an unmanned forklift and includes: Obtaining the position information of the unmanned forklift, and determining the application scenario information of the unmanned forklift based on the position information of the unmanned forklift; wherein, the types of scene entities in the application scenario information include the goods, shelves, truck boxes, road surface types, and obstacles placed around the unmanned forklift; Obtaining the size information and position information of the goods pallet, and determining the fork height of the unmanned forklift based on the size information of the goods pallet; wherein, it further includes: determining the contact length between the fork and the bottom of the goods pallet based on the size information of the goods pallet; Determining the position information of the first obstacle in the application scenario information of the unmanned forklift, and generating the movement path of the unmanned forklift according to the position information of the unmanned forklift, the position information of the goods pallet, and the position information of the first obstacle; Controlling the unmanned forklift to move to the goods pallet according to the movement path of the unmanned forklift, and controlling the fork of the unmanned forklift to lift the goods pallet to the fork height of the unmanned forklift; Wherein, it further includes a neural network, and the neural network outputs the movement speed of the unmanned forklift according to the input vehicle type of the unmanned forklift and the size information of the goods pallet to ensure the stability of the unmanned forklift during the process of moving the goods pallet.

2. The method according to claim 1, wherein The determining the application scenario information of the unmanned forklift based on the position information of the unmanned forklift includes: Obtaining 3D point cloud data based on the position information of the unmanned forklift; Generating the application scenario information of the unmanned forklift according to the 3D point cloud data.

3. The method according to claim 2, characterized in that, After obtaining the 3D point cloud data based on the position information of the unmanned forklift and before generating the application scenario information of the unmanned forklift according to the 3D point cloud data, it further includes: Inputting the 3D point cloud data into a trained deep learning neural network to obtain the scene features of the unmanned forklift; The generating the application scenario information of the unmanned forklift according to the 3D point cloud data includes: Generating the application scenario information of the unmanned forklift according to the scene features of the unmanned forklift; Wherein, the deep learning neural network is trained by the scene features corresponding to various known application scenario information and the 3D point cloud data corresponding to each scene feature.

4. The method according to claim 1, wherein The generating the movement path of the unmanned forklift according to the position information of the unmanned forklift, the position information of the goods pallet, and the position information of the first obstacle includes: Generating at least two first movement paths according to the position information of the unmanned forklift and the position information of the goods pallet; Determining a second movement path from the at least two first movement paths according to the position information of the first obstacle; Searching for the historical movement path of the unmanned forklift, and generating the movement path of the unmanned forklift according to the second movement path and the historical movement path of the unmanned forklift.

5. The method according to claim 1, wherein Controlling the driverless forklift to move to the cargo pallet according to the moving path of the driverless forklift further includes: When detecting a second obstacle on the moving path of the driverless forklift, controlling the driverless forklift to stop moving; Detecting whether there is the second obstacle on the moving path of the driverless forklift at a preset time interval; When determining that there is no second obstacle on the moving path of the driverless forklift, controlling the driverless forklift to move to the cargo pallet.

6. The method according to any one of claims 1-5, characterized in that, After controlling the driverless forklift to move to the cargo pallet according to the moving path of the driverless forklift and controlling the fork of the driverless forklift to lift the cargo pallet to the height of the fork of the driverless forklift, it further includes: Obtaining the position information of the freight car box, and generating a third moving path according to the position information of the freight car box and the position information of the cargo pallet; Controlling the driverless forklift to move to the freight car box according to the third moving path, and controlling the driverless forklift to move to a preset position inside the freight car box according to a preset moving path corresponding to the freight car box.

7. The method according to any one of claims 1-5, characterized in that, After controlling the driverless forklift to move to the cargo pallet according to the moving path of the driverless forklift and controlling the fork of the driverless forklift to lift the cargo pallet to the height of the fork of the driverless forklift, it further includes: When detecting that the remaining power of the driverless forklift is lower than a preset power threshold, determining a target charging station within a preset distance according to the position information of the driverless forklift; Controlling the driverless forklift to move to the target charging station for charging until the remaining power of the driverless forklift is higher than or equal to the preset power threshold.

8. An unmanned forklift, characterized in that, Including: A first recognition module, configured to obtain the position information of the driverless forklift and determine the application scenario information of the driverless forklift based on the position information of the driverless forklift; wherein, the scene physical object types in the application scenario information include the goods, shelves, freight car boxes, road surface types, and obstacles placed around the driverless forklift; A second recognition module, configured to obtain the size information and position information of the cargo pallet, and determine the fork height of the driverless forklift based on the size information of the cargo pallet; wherein, it further includes: determining the contact length between the fork and the bottom of the cargo pallet based on the size information of the cargo pallet; A navigation generation module, configured to determine the position information of a first obstacle in the application scenario information of the driverless forklift, and generate the moving path of the driverless forklift according to the position information of the driverless forklift, the position information of the cargo pallet, and the position information of the first obstacle; A control movement module, configured to control the driverless forklift to move to the cargo pallet according to the moving path of the driverless forklift, and control the fork of the driverless forklift to lift the cargo pallet to the height of the fork of the driverless forklift; Among them, a neural network is further included, and the neural network outputs the moving speed of the driverless forklift according to the vehicle type of the driverless forklift and the size information of the cargo pallet, so as to ensure the stability of the driverless forklift during the process of moving the cargo pallet.

9. An unmanned control device for automatic loading and unloading of goods, characterized in that, It includes a processor and a memory; The processor is connected to the memory; The memory is used to store executable program codes; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the method according to any one of claims 1-7 is implemented.

Images