WO2023029776A1

WO2023029776A1 - Control method, apparatus and device for transfer robot, and storage medium

Info

Publication number: WO2023029776A1
Application number: PCT/CN2022/106222
Authority: WO
Inventors: 王馨浩; 唐丹
Original assignee: 上海快仓智能科技有限公司
Priority date: 2021-08-30
Filing date: 2022-07-18
Publication date: 2023-03-09
Also published as: CN113666304A

Abstract

Provided in the present application are a control method, apparatus and device for a transfer robot, and a storage medium. When a transfer robot lifts a target object using a fork, a traveling fork comes into contact with a lifting fork, and the lifting fork is configured to lift the target object to a preset height. The transfer robot further comprises a time-of-flight camera for identifying a target object. The control method comprises: when a transfer robot moves into a preset range of a first target position, controlling a time-of-flight camera to identify a target object in order to obtain the pose of the target object, wherein the first target position is the position where the transfer robot lifts the target object using the fork; determining a relative pose between the target object and the transfer robot according to the pose of the target object and the pose of the transfer robot; adjusting a speed vector of a moving wheel according to the relative pose; and controlling the moving wheel according to the speed vector, such that the transfer robot moves to the first target position.

Description

Control method, device, equipment and storage medium of handling robot

This application claims the priority of a Chinese patent application with application number 202111008279.4 filed with the China Patent Office on August 30, 2021, the entire contents of which are incorporated herein by reference.

technical field

The present application relates to the technical field of intelligent storage, for example, to a control method, device, device and storage medium of a handling robot.

Background technique

With the development of e-commerce, 3C commodities and logistics industry, large-scale storage warehouses at home and abroad are developing very rapidly. In order to improve the space utilization efficiency of the warehouse and facilitate manual or automatic handling, the goods are placed on industrial pallets in the warehouse. At present, the division of cargo spaces in large warehouses has become dense and three-dimensional. In a dense storage environment, the space between adjacent pallets for industrial pallets is designed to be within 15cm. In a dense storage environment, how to realize the rapid and accurate detection of industrial pallets by automated handling robots is an urgent problem to be solved.

Contents of the invention

Embodiments of the present application provide a control method, device, equipment, and storage medium for a handling robot, which can improve the forking accuracy and success rate of industrial pallets in a dense storage environment, and have strong adaptability to ambient light.

In the first aspect, the embodiment of the present application provides a handling robot, including:

Traveling fork, the bottom of the traveling fork is equipped with multiple sports wheels;

The lifting fork is arranged above the traveling fork, and the traveling fork is set to be able to descend to contact with the lifting fork, and is set to be able to rise to lift the target to a preset height;

The bracket is arranged at the ends of the traveling fork and the lifting fork;

The time-of-flight camera is arranged on the bracket and above the traveling fork, and the time-of-flight camera is set to identify the target object.

In the second aspect, the embodiment of the present application provides a control method of a handling robot, which is applied to the above-mentioned handling robot, and the control method includes:

When the handling robot moves to the preset range of the first target position, the time-of-flight camera is controlled to identify the target to obtain the pose of the target, and the first target position is the position where the handling robot picks up the target;

According to the pose of the target and the pose of the handling robot, determine the relative pose between the target and the handling robot;

Adjust the velocity vector of the moving wheel according to the relative pose;

The moving wheels are controlled according to the velocity vector, so that the handling robot moves to the first target position.

In the third aspect, the embodiment of the present application provides a control device for a handling robot, which is applied to the above-mentioned handling robot, and the control device includes:

The identification module is configured to control the time-of-flight camera to identify the target object when the transfer robot moves to the preset range of the first target position, so as to obtain the pose of the target object. The first target position is when the transfer robot forks the target object s position;

The relative pose determining module is configured to determine the relative pose between the target and the handling robot according to the pose of the target and the handling robot;

The velocity vector adjustment module is configured to adjust the velocity vector of the moving wheel according to the relative pose;

The motion control module is configured to control the moving wheels according to the velocity vector, so as to make the handling robot move to the first target position.

In a fourth aspect, the embodiment of the present application provides a control device for a handling robot, the device includes: at least one processor; and a memory connected to the at least one processor in communication; wherein, the memory stores information that can be executed by the at least one processor instructions, so that at least one processor can execute the control method of the above-mentioned handling robot.

In the fifth aspect, the embodiment of the present application provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions are run on the computer, the method in any one of the above aspects is executed.

Description of drawings

Fig. 1 shows a schematic structural view of a handling robot according to an embodiment of the present application;

Fig. 2 shows a schematic structural view of a handling robot and an industrial pallet according to an embodiment of the present application;

FIG. 3 shows a schematic diagram of a handling robot forking an industrial pallet according to an embodiment of the present application;

FIG. 4 shows a flow chart of a control method of a handling robot according to an embodiment of the present application;

FIG. 5 shows a schematic diagram of an application example of a control method for a handling robot according to an embodiment of the present application;

FIG. 6 shows a block diagram of a control device of a handling robot according to an embodiment of the present application;

Fig. 7 shows a block diagram of a control device of a handling robot according to another embodiment of the present application;

Fig. 8 shows a block diagram of a control device of a handling robot according to an embodiment of the present application.

In the picture:

101. Traveling fork; 102. Lifting fork; 103. Bracket; 104. TOF camera; 105. Power lifting device; 106. Sports wheel; 107. Industrial computer; 108. Micro switch; 109. Optical filter; 201. Target thing.

Detailed ways

Hereinafter, only exemplary embodiments are briefly described.

Fig. 1 shows a schematic structural diagram of a handling robot according to an embodiment of the present application. As shown in FIG. 1 , the transfer robot includes a walking fork 101 , a lifting fork 102 , a support 103 and a time of flight (Time of Flight, TOF) camera 104. Wherein, a plurality of moving wheels 106 are installed on the bottom of the walking fork 101, so that the transporting robot can walk. The lifting fork 102 is arranged on the top of the traveling fork 101 and can lift the target. The target object can be an empty industrial pallet or a loaded industrial pallet. As shown in FIG. 2 , an empty industrial pallet 201 is shown. The traveling fork 101 is configured to be capable of descending to contact the lifting fork 102 , and configured to be capable of ascending to lift the object to a preset height. When the transport robot picks up the target object, the lifting fork 102 descends to the upper surface of the walking fork 101, and the walking fork 101 is in surface contact with the lifting fork 102, that is, the upper surface of the walking fork 101 is attached to the lower surface of the lifting fork 102, and then They can be inserted into the socket of the industrial tray 201 together (as shown in FIG. 3 ).

The bracket 103 is provided at the ends of the traveling fork 101 and the lifting fork 102 to install the traveling fork 101 , the lifting fork 102 and the TOF camera 104 . The TOF camera 104 is located above the traveling fork 101 and is configured to recognize the target object 201 . The TOF camera can actively emit laser light of a certain wavelength, and then calculate the contour of the surrounding environment based on the returned laser data.

The bracket 103 is also configured to install other structures of the handling robot, such as a power lifting module 105 (such as a hydraulic cylinder and a transmission chain, etc.) of the lifting fork 102, an industrial computer 106, and the like. Among them, the industrial computer 107 can be used as a controller of the handling robot to realize functions such as central control (central control), operation control (motion control), and dynamic identification of objects. Among them, the central control function is used to realize the distribution and analysis of the control function of the handling robot, and can also realize the communication with the remote control system (Remote Control System, RCS); the operation control function is used to realize the synthesis of the speed vector of the moving wheel 106, and Control the motion wheel 106 to move according to its corresponding speed vector; the target dynamic recognition function is used to process the data collected by the TOF camera 104, combined with the dynamic recognition algorithm, to realize the dynamic recognition of industrial pallets.

It should be noted that the multiple functions of the industrial computer 107 can be implemented by corresponding software (modules), or can be integrated in one software. Exemplarily, in the embodiment of the present application, multiple functions are respectively implemented by corresponding modules, and data can be called from each other. For example: the identification data of the target dynamic identification function module can be transmitted to the central control function module, and the central control function module can distribute the received data to the operation control function module and so on.

In related technologies, point cloud processing is used for identification, which requires a large amount of dense computing support; there is also a method of forking industrial pallets at fixed points that relies on navigation and operation control accuracy, which has a great impact on the position of industrial pallets placed by manual or other automated devices. The angle and angle requirements are extremely high, and if the requirements are not met, the forking failure rate will be extremely high; there are also recognition algorithms based on ordinary visible light cameras, but they are very sensitive to ambient light and cannot achieve the performance of working under ambient light for 24 hours, and due to Acquisition accuracy is limited, it can only stop after walking near the target object, and then perform static identification, which is inefficient. However, the handling robot in the embodiment of the present application is equipped with a TOF camera, which is a global shutter camera, which can realize the dynamic recognition function of the handling robot while walking, and has strong adaptability to ambient light.

In one embodiment, a lens surface of the TOF camera 104 is provided with a filter 109, and the filter 109 is configured to filter visible light. As a result, the handling robot does not need to work in the visible light spectrum range, so that the handling robot can adapt to the light conditions at any time of the day and night, and realize 24-hour ambient light conditions, thereby improving the efficiency of cargo transfer and warehousing.

In one embodiment, the lifting fork 102 lifts the target object to a preset height and then stops lifting, which can avoid friction between the industrial pallet and the ground, thereby avoiding the loss or drop accident of the industrial pallet, and can reduce the load of the industrial pallet itself or the industrial pallet. The load on the tray is transferred to the moving wheels 106, thereby changing the sliding friction force into rolling friction force, reducing the work done by the handling robot and saving battery energy.

In one embodiment, the range of the preset height is 380 mm to 420 mm (including the endpoint value), preferably 400 mm, so as to avoid false alarms of obstacles caused by being scanned by the radar of the transport robot.

In one embodiment, the bracket 103 is also provided with a microswitch 108, which is set to generate an in-position signal after detecting that the object is placed in the preset position of the handling robot, and the in-position signal is set to trigger the lift fork 102 to lift Target. Exemplarily, the micro switch 108 may be disposed at the end of the movement stroke of the forked object.

Exemplarily, after the target triggers the micro switch 108 to generate the in-position signal, the lifting fork 102 delays a preset time period (such as 100 ms) to lift the target to a preset height.

Based on the transport robot in the embodiment of the present application, the embodiment of the present application further provides a method for controlling the transport robot. Exemplarily, the control method can be executed by the industrial computer 107 .

As shown in Figure 4, the control method of the handling robot in the embodiment of the present application includes:

Step S401: When the transfer robot moves to the preset range of the first target position, control the TOF camera to identify the target to obtain the pose of the target, and the first target position is the position where the transfer robot picks up the target;

Step S402: According to the pose of the target object and the pose of the handling robot, determine the relative pose between the target object and the handling robot;

Step S403: Adjust the velocity vector of the moving wheel according to the relative pose;

Step S404: Control the moving wheels according to the velocity vector, so as to make the transfer robot move to the first target position.

Exemplarily, as shown in Figure 5, the warehouse manager can use a handheld device (Personal Digital Assistant, PDA) to scan the industrial pallet (target object) that needs to be forked by the handling robot, and the built-in software of the PDA will package this operation into a data stream, and sent to the RCS system. After receiving this data stream, the RCS system will analyze the map position of the industrial pallet (the first target position), and then send the first target position to the central control function module of the handling robot, and the central control function module will verify the correctness of the target position information Or not, if the target position information is correct, check whether the functional modules of the transport robot are normal, and report an error message to the RCS system if the functional modules of the transport robot are abnormal.

Detect whether the functional modules of the handling robot are normal, including:

(1) Detect whether the signal of the TOF camera is normal. If the signal of the TOF camera is detected to be normal, detect whether the moving wheel is normal; if the signal of the TOF camera is detected to be abnormal, report the error message to the RCS system. Exemplarily, the method for detecting whether the signal of the TOF camera is normal includes: judging whether the heartbeat signal fed back by the TOF camera through the network card exists, and if there is a heartbeat signal fed back by the TOF camera through the network card, then determining that the signal of the TOF camera is normal; The heartbeat signal fed back by the camera through the network card will determine that the signal of the TOF camera is abnormal.

(2) Detect whether the moving wheels are normal. If the moving wheels are normal, check whether the operation control function module is normal; if the moving wheels are abnormal, enter the preset exception handling mechanism. Exemplarily, the method for detecting whether the moving wheel is normal includes: judging whether the heartbeat signal of the encoder of the moving wheel is normal.

(3) Detect whether the operation and control function module is normal. If the operation and control function module is normal, control the movement wheels to work, and then make the handling robot move; when the operation and control function module is abnormal, enter the preset exception handling mechanism . Detecting whether the operation control function module is normal includes: detecting whether the signal status of each hardware device linked to it, such as a micro switch, an encoder signal of a moving wheel, a horn, a light strip, and a hydraulic cylinder, is normal.

When it is detected that the functional modules of the handling robot are all normal, the central control functional module sends the first target position to the operation control function module, and the operation control function module synthesizes the velocity vector of the moving wheels according to the first target position, and sends the velocity vector The signals are sent to the encoders and angle controllers of the moving wheels, so that the moving wheels work according to their respective speed vectors, and then the handling robot moves (walks). During this process, the operation control function module will continue to judge whether the handling robot moves within the preset range (eg, 3 meters) of the first target position.

When the transport robot does not move to the preset range of the first target position, the operation control function module will continue to synthesize the velocity vector of the moving wheels, so that the transport robot continues to move toward the first target position.

When the handling robot moves to the preset range of the first target position, the central control function module will control the TOF camera to start working, that is, control the TOF camera to start collecting the surrounding environment data, and call the target dynamic recognition function module according to the surrounding environment data to determine the pose of the target.

Exemplarily, the pose is composed of the spatial position (x, y, z) of the object and the angle (roll, pitch, yaw) around the three coordinate axes, that is, the pose with 6 degrees of freedom.

Exemplarily, the target dynamic recognition function module sends the recognition data (the pose of the target object) to the central control function module after adding a time tag. The central control function module checks whether the received recognition data is normal. If the recognition data is not normal, it will continue to call the target dynamic recognition function module to obtain the pose of the target object; if the recognition data is normal, it will be sent to the operation control function module. The operation control function module determines the relative pose according to the pose of the target object and the pose of the handling robot, and adjusts the velocity vector of the moving wheel according to the relative pose, and sends the signal of the velocity vector to the encoder and angle control of the moving wheel controller until the relative pose meets the preset threshold condition. During this process, each moving wheel works according to its own velocity vector, thereby moving the handling robot to the first target position.

In this embodiment, the relative pose can be the relative pose between the center of the handling robot and the center of the TOF camera, which can be performed through camera hand-eye calibration. In this embodiment, the center of the transport robot is defined as the spatial intersection of the lines connecting the centers of all the moving wheels of the transport robot.

The control method of the embodiment of the present application collects environmental data through the TOF camera, and then obtains the pose of the target object, and controls the movement of the handling robot to the fork pick-up position according to the pose of the target object, and can accurately and dynamically identify the target object under the condition of intensive storage And fork fetching, without misidentification, and can improve the accuracy of fork fetching. During the dynamic recognition process of the target, the control method will not be affected by drastic changes in light (such as strong lighting, nights with an illuminance lower than 1 Lux, or when part of the target is sufficiently illuminated while another part is obviously insufficiently illuminated, etc.) situation), and the dynamic recognition of the target fails or affects the determination of the relative pose, thereby improving the success rate of forking. Moreover, according to the field experiment data, it only takes 100ms to identify once, which is much faster than the handling robot in the related technology, and the processing speed and running time have been greatly improved.

In the embodiment of the present application, the TOF camera does not work all the time, but starts to work after the handling robot travels to the preset range of the first target position, such as turning on the laser transmitter of the camera, etc., which can avoid unnecessary loss of energy, and then Improve the efficiency of energy use, reduce the charging time or charging times of the handling robot, prolong the working time of the handling robot, and then improve the handling efficiency in a dense storage environment.

In one embodiment, in step S401, controlling the TOF camera to identify the target to obtain the pose of the target may include: identifying multiple identification objects within the field of view of the TOF camera; pose, and the position of the target sent by the remote control system of the robot, determine the target from multiple identification objects; obtain the pose of the target.

For example, in a dense storage environment of industrial pallets (targets), first dynamically identify the front, left, and right industrial pallets (identifiers) within the field of vision, and give all dynamically identified industrial pallets Then, according to the target industrial pallet position (target position) sent by the RCS system, the industrial pallet with the highest possibility is selected as the target object, and then the pose of the target object is obtained. In this way, the recognition efficiency and accuracy can be improved, and stable dynamic recognition and segmentation can be realized.

In one embodiment, after step S404, it may also include: controlling the travel fork to move into the socket of the target, so as to trigger the micro switch on the bracket to generate an in-position signal; when the in-position signal is received, control the movement The wheels stop moving, and the lifting fork is controlled to lift the target object to a preset height; the navigation and handling robot moves to the second target position, and the second target position is the destination of the target object transported by the handling robot.

After the transfer robot reaches the first target position, the walking fork 101 moves into the socket of the industrial pallet (target) 201, thereby triggering the micro switch 108 to generate an in-position signal. This in-position signal indicates that the industrial pallet has been picked up by the travel fork 101 and is in place, and the central control function module will stop the motion control function module from continuing to synthesize the speed vector of the moving wheels within 50ms of the in-position signal, and issue the travel motor (issue the travel motor It is set to drive the motion wheel) stop signal, so as to avoid the space interference between the handling robot and the target industrial pallet beyond the relative attitude compensation, and prevent the overcurrent of the walking motor.

In one embodiment, after the in-position signal is triggered, the lifting fork 102 delays the preset time to lift the industrial pallet to the preset height, and the handling robot synthesizes the speed according to the map information of the destination sent by the RCS in a manner similar to the above Vector control motion wheels to make the handling robot move to the handling destination.

The control method of the embodiment of the present application can realize the accurate and stable dynamic identification and fork-picking of industrial pallets by the handling robot in the dense storage environment of the warehouse and the drastic changes in the lighting conditions.

Fig. 6 shows a structural block diagram of a control device for a transport robot according to an embodiment of the present application. As shown in Figure 6, the device may include:

The recognition module 601 is configured to control the TOF camera to recognize the target object to obtain the pose of the target object when the transfer robot moves to the preset range of the first target position. The first target position is when the transfer robot forks the target object s position;

The relative pose determining module 602 is configured to determine the relative pose between the target and the handling robot according to the pose of the target and the handling robot;

The velocity vector adjustment module 603 is configured to adjust the velocity vector of the moving wheel according to the relative pose;

The motion control module 604 is configured to control the moving wheels according to the velocity vector, so as to make the transfer robot move to the first target position.

In one embodiment, the identification module 601 is further configured to: identify multiple identification objects within the field of view of the TOF camera; Determine the target object among the recognition objects; obtain the pose of the target object.

In one embodiment, as shown in Figure 7, the control device further includes:

The trigger control module 701 is configured to control the walking fork to move into the socket of the target after the transfer robot moves to the first target position, so as to trigger the micro switch on the bracket to generate an in-position signal;

The lifting control module 702 is configured to control the moving wheels to stop moving and control the lifting fork to lift the target to a preset height when receiving the in-position signal;

The navigation module 703 is configured to guide the transport robot to move to a second target position, where the second target position is the destination of the target object transported by the transport robot.

For the functions of the modules in the device in the embodiment of the present application, reference may be made to the corresponding description in the above method, and details are not repeated here.

Fig. 8 shows a structural block diagram of a control device of a transport robot according to an embodiment of the present application. As shown in FIG. 8 , the control device includes: a memory 801 and a processor 802 , and instructions that can be executed on the processor 802 are stored in the memory 801 . The processor 802 implements the methods in the foregoing embodiments when executing the instructions. The number of memory 801 and processor 802 may be one or more. This control device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The control device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.

The control device may also include a communication interface 803 configured to communicate with external devices for interactive data transmission. Multiple devices are interconnected using different buses and may be mounted on a common motherboard or otherwise as desired. The processor 802 may process instructions executed within the control device, including storage in or on the memory, to display a Graphical User Interface (GUI) on an external input/output device, such as a display device coupled to the interface. GUI) commands for graphical information. In other embodiments, multiple processors or multiple buses may be used with multiple memories, and multiple processors, multiple buses, and multiple memories may be used, if desired. Likewise, multiple control devices may be connected, with multiple devices providing some of the necessary operation (eg, as a server array, a set of blade servers, or a multi-processor system). The bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 8 , but it does not mean that there is only one bus or one type of bus.

Optionally, if the memory 801, the processor 802, and the communication interface 803 are integrated on one chip, the memory 801, the processor 802, and the communication interface 803 may communicate with each other through an internal interface.

It should be understood that the above-mentioned processor can be a central processing unit (Central Processing Unit, CPU), and can also be other general-purpose processors, digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field Programmable Gate Array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or any conventional processor or the like. It should be noted that the processor may be a processor supporting Advanced RISC Machines (ARM) architecture.

The embodiment of the present application provides a computer-readable storage medium (such as the above-mentioned memory 801 ), which stores computer instructions, and when the program is executed by a processor, the method provided in the embodiment of the present application is implemented.

Optionally, the memory 801 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of the device, and the like. In addition, the memory 801 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 801 may optionally include memory located remotely relative to the processor 802, and these remote memories may be connected to the device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

Claims

A handling robot, comprising:

Traveling fork, the bottom of described traveling fork is equipped with a plurality of moving wheels;

A lifting fork is arranged above the traveling fork, the traveling fork is configured to be able to descend to contact with the lifting fork, and is configured to be able to rise to lift the target to a preset height;

a bracket provided at the ends of the traveling fork and the lifting fork;

A time-of-flight camera is arranged on the bracket and above the traveling fork, and the time-of-flight camera is configured to identify the target.
The handling robot according to claim 1, wherein the lens surface of the time-of-flight camera is provided with a filter, which is configured to filter visible light.
The handling robot according to claim 1, wherein the preset height ranges from 380mm to 420mm.
The handling robot according to claim 1, wherein a micro switch is further provided on the bracket, and the micro switch is configured to, after detecting that the target is placed at a preset position of the handling robot, An in-position signal is generated, and the in-position signal is configured to trigger the lifting fork to lift the target.
The handling robot according to any one of claims 1 to 4, wherein the target object is an empty industrial pallet or a loaded industrial pallet.
A control method for a handling robot, applied to the handling robot according to any one of claims 1 to 5, the control method comprising:

When the handling robot moves to a preset range of the first target position, the time-of-flight camera is controlled to identify the target to obtain the pose of the target, and the first target position is the The handling robot picks up the position of the target object;

determining the relative pose between the target and the handling robot according to the pose of the target and the pose of the handling robot;

adjusting the velocity vector of the moving wheel according to the relative pose;

The moving wheels are controlled according to the velocity vector, so that the transfer robot moves to the first target position.
The control method according to claim 6, wherein controlling the time-of-flight camera to identify the target to obtain the pose of the target comprises:

identifying a plurality of identifiers within the field of view of the time-of-flight camera;

Determining the target from the plurality of identifiers according to the poses of the plurality of identifiers and the position of the target sent by the robot remote control system;

Obtain the pose of the target.
The control method according to claim 6, wherein a micro switch is further provided on the support, and the micro switch is configured to, after detecting that the target object is placed at a preset position of the handling robot, generating an in-position signal configured to trigger the lifting fork to lift the target;

After the handling robot moves to the first target position, the control method further includes:

Controlling the travel fork to move into the socket of the target, so as to trigger the micro switch on the bracket to generate an in-position signal;

In the case of receiving the in-position signal, control the moving wheel to stop moving, and control the lifting fork to lift the target to the preset height;

navigating the transfer robot to move to a second target position, where the second target position is a destination for the transfer robot to transfer the target object.
A control device for a handling robot, applied to the handling robot according to any one of claims 1 to 5, the control device comprising:

The recognition module is configured to control the time-of-flight camera to recognize the target when the transfer robot moves to a preset range of the first target position, so as to obtain the pose of the target, the second A target position is the position where the transfer robot picks up the target object;

A relative pose determining module configured to determine the relative pose between the target and the handling robot according to the pose of the target and the pose of the handling robot;

a velocity vector adjustment module, configured to adjust the velocity vector of the moving wheel according to the relative pose;

A motion control module configured to control the moving wheels according to the velocity vector, so as to move the transfer robot to the first target position.
The control device according to claim 9, wherein the identification module is further configured to:

identifying a plurality of identifiers within the field of view of the time-of-flight camera;

Determining the target from the plurality of identifiers according to the poses of the plurality of identifiers and the position of the target sent by the robot remote control system;

Obtain the pose of the target.
The control device according to claim 9, further comprising:

The trigger control module is configured to control the walking fork to move into the socket of the target after the transfer robot moves to the first target position, so as to trigger the micro switch on the bracket to generate a position Signal;

The lifting control module is configured to control the moving wheels to stop moving, and control the lifting fork to lift the target to the preset height when receiving the in-position signal;

The navigation module is used to navigate the transfer robot to move to a second target position, and the second target position is a destination for the transfer robot to transfer the target object.
A control device for a handling robot, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 6 to 8 Methods.
A computer-readable storage medium, wherein computer instructions are stored in the computer-readable storage medium, and when the computer instructions are executed by a processor, the method according to any one of claims 6 to 8 is implemented.