TW202226137A - Method and system for controlling a handling machine and non-volatile computer readable recording medium - Google Patents

Abstract

A method and a system for controlling a handling machine and a non-volatile computer readable recording medium are provided. The method includes: analyzing image data to obtain contour surface data corresponding to a target object from the image data; analyzing the contour surface data to obtain characteristic data which reflects a posture of the target object in a physical space; generating control data according to the characteristic data, wherein the control data is suitable for controlling the handling machine to transport the target object in response to the posture of the target object in the physical space.

Description

Transporter control method, system, and non-volatile computer-readable recording medium

The present invention relates to a conveyer control technology, and more particularly, to a conveyer control method, system and non-volatile computer-readable recording medium.

With the change of people's transaction patterns and the increasing demand for automated logistics management such as smart warehousing, more and more logistics companies hope to use automated handling devices to independently complete the handling of goods and the loading and unloading of goods. However, the existing image recognition technology cannot be directly applied to the logistics management system. The reason is that the goods to be handled and/or the pallets carrying the goods are often arranged irregularly in the physical space. Therefore, even if the handling device can identify the goods to be handled, it still cannot accurately control the extension arm or the clamp to be inserted into the pallet groove under the goods at a specific angle, so as to carry the pallet together with the goods above. In addition, the packaging of the goods to be transported and/or the pallets carrying the goods may also have defects or damage in appearance, which increases the difficulty of image recognition.

The present invention provides a handling machine control method, system and non-volatile computer-readable recording medium, which can improve the efficiency of the handling machine in performing automated cargo handling.

An embodiment of the present invention provides a method for controlling a transporter, which includes: analyzing image data to obtain profile data corresponding to a carrier in the image data; analyzing the profile data to obtain feature data of the carrier, wherein the characteristic data reflects the posture of the carrying object in the physical space; and control data is generated according to the characteristic data, wherein the control data is adapted to control the handling machine in response to the carrying object in the physical space in the posture to carry the load.

Embodiments of the present invention further provide a handling machine control system, which includes a handling machine and a control host. The control host is coupled to the handler. The control host is used for analyzing the image data to obtain the contour surface data corresponding to the carrier in the image data. The control host is further configured to analyze the profile surface data to obtain characteristic data of the carrying object, wherein the characteristic data reflects the posture of the carrying object in the physical space. The control host is further configured to generate control data according to the characteristic data. The transporter is used for transporting the carrier in response to the posture of the carrier in the physical space according to the control data.

An embodiment of the present invention further provides a non-volatile computer-readable recording medium, which stores a program code, and the program code is executed by a processor to: analyze image data to obtain a contour corresponding to a carrier in the image data surface data; analyzing the profile surface data to obtain characteristic data of the bearing, wherein the characteristic data reflects the posture of the bearing in the solid space; and generating control data according to the characteristic data, wherein the control Data is adapted to control the handling machine to handle the carrier in response to the attitude of the carrier in the physical space.

Based on the above, after analyzing the image data to obtain the contour surface data corresponding to the bearing object in the image data, the contour surface data can be further analyzed to obtain the characteristic data of the bearing object, which reflects that the bearing object is in the physical space gesture. Then, control data can be generated based on the characteristic data. In particular, the control profile is adapted to control the handling machine to handle the target in response to the pose of the carrier in the physical space. In this way, the efficiency of the handling machine in performing automated cargo handling can be effectively improved.

FIG. 1 is a schematic diagram of a handling machine control system according to an embodiment of the present invention. Referring to FIG. 1 , a system (also referred to as a transporter control system) 10 includes a transporter 11 , a control host 12 and a carrier 13 . The number of the carrier 11 , the control host 12 and the carrier 13 can be one or more, which is not limited in the present invention.

The transporter 11 is used to transport the load 13 . For example, the handling machine 11 may have a movement and rotation mechanism to perform actions such as advancing, retreating and/or turning on the ground. In addition, the carrier 11 may have extension arms 101 and 102 . For example, the carrier 11 can control the extension arms 101 and 102 to move vertically or horizontally. Thereby, the carrier 11 can use the extension arms 101 and 102 to carry the load 13 . In one embodiment, the handler 11 may be a stacker, a pallet truck, a pallet truck, a forklift, a forklift, or the like. In one embodiment, the extension arms 101 and 102 can also be implemented as jigs, pallets, or mechanical arms that can be used to carry the carrier 13. A flat or three-dimensional structure for carrying objects. The control host 12 can be a desktop computer, a notebook computer, a tablet computer, an industrial computer, a server or other types of computer devices with data transmission and processing functions. The carrier 11 can communicate with the control host 12 .

1 and the following embodiments, the carrier 13 is a pallet as an example. Goods can be placed on the carrier 13 . There may be grooves 131 and 132 below the carrier 13 . The groove 131 can be regarded as an insertion port of the extension arm 101 , and the groove 132 can be regarded as an insertion port of the extension arm 102 . The carrier 11 can insert the extension arms 101 and 102 into the grooves 131 and 132, respectively. After the extension arms 101 and 102 are inserted into the grooves 131 and 132 respectively, the carrier 11 can control the extension arms 101 and 102 to lift the load 13 . It should be noted that, in other unmentioned embodiments, the carrier 13 may also include other types of carriers, as long as they can be carried by the carrier 11 . In addition, the appearance of the transporter 11 in FIG. 1 is only a schematic diagram, and its specific appearance can be changed according to the actual type of the transporter 11 .

It should be noted that, in the embodiment of FIG. 1 , the extending arms 101 and 102 of the carrier 11 are not aligned with the grooves 131 and 132 of the carrier 13 . In this state, the extension arms 101 and 102 of the carrier 11 cannot be inserted into the grooves 131 and 132 of the carrier 13 smoothly to move the carrier 13 . The control host 12 can instruct the carrier 11 to move to an appropriate position to carry the load 13 .

In one embodiment, the transporter 11 is further provided with an image capturing interface 103 . The image capture interface 103 is used for capturing external images. For example, the image capture interface 103 may include optical elements such as a lens and a photosensitive element. In the embodiment of FIG. 1 , the image capturing interface 103 may be disposed in front of the transporter 11 to capture images in front of the transporter 11 . However, in an embodiment, the image capturing interface 103 can also be disposed at any position of the transporter 11 to capture images in other directions.

In one embodiment, the image captured by the image capture interface 103 (ie, the target image) includes at least a part of the image of the carrier 13 to be transported. That is, at least a part of the image of the carrier 13 will appear in the target image. The image capturing interface 103 can generate image data DATA(image) according to the captured target image. The image data DATA(image) may contain information about the current posture of the carrier 13 in the physical space. The physical space refers to the space where the carrier 13 and the transporter 11 actually exist. For example, the image data DATA (image) can reflect the relative positional relationship between the carrier 13 and the carrier 11 in the physical space.

The transporter 11 can transmit the image data DATA (image) to the control host 12 . The control host 12 may analyze the image data DATA(image) to obtain contour surface data corresponding to the carrier 13 in the image data DATA(image). The control host 12 can analyze the profile data to obtain characteristic data of the carrier 13 . The characteristic data can reflect the posture of the carrier 13 in the physical space. Then, the control host 12 can generate control data DATA(control) according to the characteristic data. The control data DATA(control) is suitable for controlling the carrier 11 to carry the carrier 13 in response to the attitude of the carrier 13 in the physical space.

FIG. 2 is a schematic diagram of controlling the movement of a transporter to transport a load according to an embodiment of the present invention. Referring to FIG. 2 , following the embodiment of FIG. 1 , according to the image data DATA(image), the control host 12 can generate the control data DATA(control) and transmit the control data DATA(control) to the transporter 11 . The control data DATA(control) may include control signals for instructing the transporter 11 to move.

According to the control data DATA(control), the carrier 11 can move to a position suitable for carrying the carrier 13 in response to the current posture of the carrier 13 in the physical space, as shown in FIG. 2 . For example, in this position, the extension arms 101 and 102 of the carrier 11 can be aligned with the grooves 131 and 132 of the carrier 13 . At this time, as long as the carrier 11 moves forward, the extension arms 101 and 102 can be inserted into the grooves 131 and 132 of the carrier 13 to move the carrier 13 . In other words, in one embodiment, the control data DATA(control) is adapted to drive the carrier 11 to insert the extension arms 101 and 102 into the grooves 131 and 132 of the carrier 13 , so as to carry the carrier 13 by the extension arms 101 and 102 .

In an embodiment of FIG. 2 , during the moving process of the transporter 11 , the transporter 11 can continuously capture target images and return corresponding image data DATA (image) to the control host 12 . According to the continuously received image data DATA(image), the control host 12 can continuously correct the moving trajectory of the carrier 11 through the control data DATA(control) until the carrier 11 moves to a position suitable for carrying the load 13 .

It should be noted that, in another embodiment, the control host 12 may also be integrated into the transporter 11 . In this way, the transporter 11 can complete the automatic transporting operation through its own image capturing and data processing mechanism.

FIG. 3 is a functional block diagram of a control host according to an embodiment of the present invention. Referring to FIG. 3 , the control host 12 includes a processor 31 , a storage circuit 32 and an output/output (I/O) interface 33 . The processor 31 is used to control the whole or part of the operation of the control host 12 . For example, the processor 31 may include a central processing unit (CPU), or other programmable general-purpose or special-purpose microprocessors, digital signal processors (DSP), programmable Controllers, Application Specific Integrated Circuits (ASICs), Programmable Logic Devices (PLDs) or other similar devices or combinations of these devices. It should be noted that, in the following embodiments, the description of the processor 31 is equivalent to the description of the control host 12 .

The storage circuit 32 is coupled to the processor 31 and used for storing data. For example, the storage circuit 32 may include a volatile storage circuit and a non-volatile storage circuit. The volatile storage circuit is used for volatile storage of data. For example, the volatile storage circuit may include random access memory (RAM) or similar volatile storage media. The non-volatile storage circuit is used for non-volatile storage of data. For example, the non-volatile storage circuit may include read only memory (ROM), solid state disk (SSD) and/or conventional hard disk drive (HDD) or similar non-volatile storage media.

The output/output interface 33 is coupled to the processor 31 and used for transmitting signals. For example, the processor 31 may receive input signals or transmit output signals via the output/output interface 33 . For example, the output/output interface 33 may include various input/output devices such as a network connection interface, a mouse, a keyboard, a screen, a touch panel, and/or a speaker.

In one embodiment, the storage circuit 32 can be used to store the image data 301 . For example, the image data 301 may be stored in the storage circuit 32 according to the image data DATA(image) of FIG. 1 . The processor 31 can read the image data 301 from the storage circuit 32 and generate the control data DATA(control) in FIG. 2 according to the image data 301 .

In one embodiment, the storage circuit 32 further stores the image recognition module 302 . The image recognition module 302 can perform image recognition operations such as machine vision. The processor 31 can perform image recognition on the image data 301 (that is, the data of the target image) through the image recognition module 302 and generate control data DATA(control) according to the recognition result. The image recognition module 302 can be trained to recognize a target object (eg, the carrier 13 of FIG. 1 ) from the image data 301 . In particular, the image recognition module 302 can be trained to improve the recognition accuracy of the target.

In one embodiment, the image recognition module 302 can also be implemented as a hardware circuit. For example, the circuit of the image recognition module 302 can be implemented inside the processor 31 or independent of the processor 31, which is not limited in the present invention.

In one embodiment, the processor 31 can analyze the image data 301 through the image recognition module 302 to obtain the contour surface data corresponding to the carrier 13 in the image data 301 . For example, the processor 31 may identify one or more regions (also referred to as target regions) in the target image through the image recognition module 302 . Each target area includes the image of the carrier 13 recognized by the image recognition module 302 . Then, the processor 31 can obtain the contour surface data corresponding to the carrier in the image data 301 according to the identified target area.

FIG. 4 is a schematic diagram of a target image according to an embodiment of the present invention. In this embodiment, the image 41 (ie, the target image) presents the carrier 13 and the goods 15 (or other items) placed above the carrier 13 . Please refer to FIG. 3 and FIG. 4 , in this embodiment, the image data 301 can reflect the image 41 . Specifically, the image data 301 may at least include image color information and image size information in the image 41 .

In one embodiment, the processor 31 can analyze the image data 301 through the image recognition module 302 to recognize the carrier 13 in the image 41 . The image recognition module 302 can circle the area where the carrier 13 is located as the area 401 . In other words, the area 401 includes at least a part of the image of the carrier 13 recognized by the image recognition module 302 .

FIG. 5 is a schematic diagram of a contour image of a carrier according to an embodiment of the present invention. Referring to FIG. 3 and FIG. 5 , following the embodiment of FIG. 4 , the processor 31 can generate an image 51 according to the recognition result of the carrier 13 by the image recognition module 302 . For example, the processor 31 can filter out the image data other than the area 401 in FIG. 4 to generate the image 51 according to the recognition result of the carrier 13 by the image recognition module 302 . Thus, the image 51 may (only) contain the outline 501 of the carrier 13 within the area 401 . In one embodiment, the operation of filtering out the image data other than the area 401 can also be regarded as filtering out the background image other than the image of the carrier 13 . In one embodiment, the image 51 is also referred to as an outline image of the carrier 13 . The processor 31 can analyze the image data within the image range covered by the outline 501 to obtain information corresponding to the pixel distribution of the carrier 13 in the original image data 301 . Then, the processor 31 can generate characteristic data of the carrier 13 according to the pixel distribution information.

FIG. 6 is a schematic diagram of characteristic data of a carrier according to an embodiment of the present invention. Referring to FIGS. 3 and 6 , following the embodiment of FIG. 5 , the outline 501 of the carrier 13 may be composed of a plurality of pixel points 61 . Each pixel point 61 can also be called a feature point. Each pixel point 61 corresponds to a virtual coordinate in the virtual space u-v. The virtual space u-v consists of the u-axis plane and the v-axis plane. The u-axis plane and the v-axis plane are perpendicular to each other.

In one embodiment, the processor 31 may determine the feature vectors 601 and 602 of the carrier 13 in the virtual space u-v according to the distribution state of the pixel points 61 . The feature vector 601 reflects the position of the long axis of the contour 501 of FIG. 5 in the virtual space u-v. The feature vector 602 reflects the position of the short axis of the contour 501 in the virtual space u-v. The feature vectors 601 and 602 can jointly reflect the posture of the carrier 13 in the virtual space u-v.

In one embodiment, the processor 31 can obtain information about the included angle Ø between the feature vectors 601 and 602 in the virtual space u-v and a reference plane 603 . The processor 31 can obtain the relative positional relationship between the carrier 13 and the transporter 11 in the physical space according to the information of the included angle Ø. Then, the processor 31 can generate control data DATA(control) according to the relative positional relationship.

FIG. 7 is a schematic diagram of controlling the movement of a transporter to transport a load according to an embodiment of the present invention. 3 and FIG. 7, following the embodiment of FIG. 6, in one embodiment, the processor 31 may map the angle Ø in the virtual space u-v to the angle ϴ in the physical space. This mapping can be accomplished by a conversion equation. The included angle ϴ can reflect an angle difference between the extension arms 101 and 102 of the carrier 11 and the grooves 131 and 132 of the carrier 13 . The processor 31 can generate control data DATA(control) according to the included angle ϴ. Thereby, the control data DATA(control) can drive the transporter 11 to move to a position suitable for carrying the load 13, and the movement amount of the transporter 11 satisfies the angle difference defined by the included angle ϴ. In this position, the extending arms 101 and 102 of the carrier 11 can be aligned with the grooves 131 and 132 of the carrier 13 .

In one embodiment, the obtained contour surface data may also include contour data of images of different sides of the carrier 13 . The processor 31 can generate corresponding characteristic data according to the contour data of the images of different side surfaces of the carrier 13 .

FIG. 8 is a schematic diagram of a contour image of a carrier according to an embodiment of the present invention. Referring to FIG. 3 and FIG. 8 , in one embodiment, it is assumed that the image 81 is the target image. The processor 31 can recognize the contour surfaces 801 and 802 from the image 81 through the image recognition module 302 . The contour surface 801 includes at least a partial image of a side (also referred to as the first side) of the carrier 13 . The contour surface 802 includes at least a partial image of the other side (also referred to as the second side) of the carrier 13 . The processor 31 can obtain, according to the recognition result of the image recognition module 302 , the contour surface data (also referred to as the first contour surface data) corresponding to the contour surface 801 in the image data 301 and the contour surface corresponding to the contour surface 802 in the image data 301 data (also known as the second profile data). In other words, the first contour surface data includes data in the image data 301 related to the image of the first side surface of the carrier 13 , and the second contour surface data includes data in the image data 301 related to the image of the second side surface of the carrier 13 . material. The processor 31 can generate characteristic data of the carrier 13 according to the first profile data and the second profile data.

In one embodiment, the processor 31 can obtain the contour ratio reflected by at least one of the first contour surface data and the second contour surface data. The processor 31 can generate characteristic data of the carrier 13 according to the outline ratio. For example, the processor 31 may count the total number of pixels on a certain axis in the contour surfaces 801 and 802 to obtain the lengths D1 and D2, respectively. The lengths D1 and D2 can respectively reflect the length ratios of the contour surfaces 801 and 802 in the overall contour of the carrier 13 . The processor 31 can generate characteristic data of the carrier 13 according to the lengths D1 and D2. Then, the processor 31 can generate control data DATA(control) according to the characteristic data.

In one embodiment, the processor 31 may use the ratio of the lengths D1 and D2 as the characteristic data of the carrier 13 . The processor 31 may map the ratio of the lengths D1 and D2 to the included angle ϴ in the physical space. This mapping can be accomplished by a conversion equation. The processor 31 can generate control data DATA(control) according to the included angle ϴ, so as to drive the transporter 11 to move to a position suitable for carrying the load 13, and the movement amount of the transporter 11 satisfies the angle difference defined by the included angle ϴ. The specific operation details are as described in the embodiment of FIG. 7 , which will not be repeated here.

In one embodiment, the processor 31 can also evaluate the position information and attitude information of the carrier in the physical space according to the obtained feature data (eg, the feature vectors 601 and 602 in FIG. 6 ). The processor 31 can generate the control data DATA(control) according to the information.

It should be noted that, in the aforementioned embodiments, operations such as image recognition and feature data extraction are performed on a single carrier in the physical space, thereby driving the carrier to move to an appropriate position to carry the carrier. However, in another embodiment, even if there are multiple bearers (which can be stacked or dispersed) in the physical space, the control host can perform image recognition for these bearers one by one according to the operation means mentioned in the previous embodiment. And instruct the handling machine to automatically perform subsequent handling behaviors.

An embodiment of the present invention also provides a non-volatile computer-readable recording medium. The non-volatile computer-readable recording medium has program codes stored thereon. A processor in the computer (eg, the processor 31 in FIG. 3 ) can execute (or run) the code to perform the functions and operations mentioned above.

FIG. 9 is a flowchart of a method for controlling a transporter according to an embodiment of the present invention. Referring to FIG. 9 , in step S901 , the image data is analyzed to obtain contour surface data corresponding to the carrier in the image data. In step S902, the profile data is analyzed to obtain characteristic data of the carrier, wherein the characteristic data reflects the posture of the carrier in the physical space. In step S903, control data is generated according to the characteristic data, wherein the control data is suitable for controlling the carrier to carry the carrier in response to the posture of the carrier in the physical space.

However, each step in FIG. 9 has been described in detail as above, and will not be repeated here. It should be noted that, each step in FIG. 9 may be implemented as a plurality of codes (eg, software modules) or circuits (eg, circuit modules), which are not limited in the present disclosure. In addition, the method of FIG. 9 can be used in conjunction with the above exemplary embodiments, and can also be used alone, which is not limited by the present disclosure.

To sum up, the main control device can evaluate the attitude of the load in the physical space according to the information related to the load in the obtained image data, and then drive the transporter to automatically move to a suitable position to carry the load according to the attitude. bearer. In one embodiment, even if the placement position and/or placement angle of the carrier in the physical space is irregular, the handling machine can still automatically adjust the insertion angle of the extension arm relative to the carrier, so as to smoothly lift and hold the carrier. Carry this load. In this way, the efficiency of the handling machine in performing automated cargo handling can be effectively improved.

Although the present disclosure has been disclosed above with examples, it is not intended to limit the present disclosure. Anyone with ordinary knowledge in the technical field may make some changes and modifications without departing from the spirit and scope of the present disclosure. The scope of protection of the present disclosure shall be determined by the scope of the appended patent application.

10: Handling machine control system 11: Transporter 101, 102: Extension Arm 103: Image capture interface 12: Control host 13: Bearer 15: Cargo 131, 132: Grooves DATA(image): image data DATA(control): control data 31: Processor 32: Storage circuit 301: Video data 302: Image recognition module 33: Output/Output interface 41, 51, 81: Images 401: Area 501: Outline of the carrier 61: Pixels 601, 602: Eigenvectors 603: Reference plane 801, 802: Profile Surface D1, D2: Distance S901~S903: Steps

FIG. 1 is a schematic diagram of a handling machine control system according to an embodiment of the present invention. FIG. 2 is a schematic diagram of controlling the movement of a transporter to transport a load according to an embodiment of the present invention. FIG. 3 is a functional block diagram of a control host according to an embodiment of the present invention. FIG. 4 is a schematic diagram of a target image according to an embodiment of the present invention. FIG. 5 is a schematic diagram of a contour image of a carrier according to an embodiment of the present invention. FIG. 6 is a schematic diagram of characteristic data of a carrier according to an embodiment of the present invention. FIG. 7 is a schematic diagram of controlling the movement of a transporter to transport a load according to an embodiment of the present invention. FIG. 8 is a schematic diagram of a contour image of a carrier according to an embodiment of the present invention. FIG. 9 is a flowchart of a method for controlling a transporter according to an embodiment of the present invention.

S901~S903: Steps

Claims (21)

A handling machine control method, comprising: analyzing an image data to obtain a profile surface data corresponding to a carrier in the image data; analyzing the profile data to obtain a characteristic data of the carrier, wherein the characteristic data reflects the posture of the carrier in a physical space; and A control data is generated according to the characteristic data, wherein the control data is suitable for controlling the carrier to carry the carrier in response to the posture of the carrier in the physical space. The handling machine control method according to claim 1, further comprising: capturing a target image by an image capture interface, wherein the target image includes at least a part of the image of the carrier; and The image data is generated according to the captured target image. The transporter control method according to claim 2, wherein the image capturing interface is disposed on the transporter. The handling machine control method of claim 1, wherein the step of analyzing the image comprises: An image recognition is performed on the image data by an image recognition module, and the image recognition module is trained to recognize the carrier from the image data. The handling machine control method as claimed in claim 1, wherein the step of analyzing the profile data to obtain the characteristic data of the carrier comprises: analyzing the profile data to obtain information on a pixel distribution in the image data corresponding to the carrier; and The characteristic data is generated according to the information of the pixel distribution. The conveyer control method according to claim 5, wherein the step of generating the characteristic data according to the information of the pixel distribution comprises: A feature vector is generated according to the information of the pixel distribution, wherein the feature vector is used to reflect the posture of the carrier in a virtual space. The method for controlling a transporter according to claim 6, wherein the step of generating the control data according to the characteristic data comprises: obtaining information about an included angle between the feature vector in the virtual space and a reference plane; Obtain a relative positional relationship between the carrier and the carrier in the physical space according to the information of the included angle; and The control data is generated according to the relative positional relationship. The handling method of claim 1, wherein the profile data includes a first profile data and a second profile data, and the step of analyzing the profile data to obtain the characteristic data of the carrier includes the following steps: : obtaining a profile ratio reflected by at least one of the first profile data and the second profile data; and The characteristic data is generated according to the outline ratio. The handling method of claim 8, wherein the first contour surface data includes data related to an image of a first side surface of the carrier in the image data, and the second contour surface data includes the image data information in relation to an image of a second side face of the carrier. The control method for a transporter as claimed in claim 1, wherein the control data is adapted to drive the transporter to insert an extension arm into an insertion opening of the carrier, so as to transport the carrier by the extension arm. A handling machine control system, comprising: a handling machine; and a control host, coupled to the handling machine, Wherein the control host is used for analyzing an image data to obtain a profile data corresponding to a carrier in the image data, The control host is further used for analyzing the profile data to obtain a characteristic data of the carrier, wherein the characteristic data reflects the posture of the carrier in a physical space, The control host is further configured to generate a control data according to the characteristic data, and The transporter is used for transporting the carrier in response to the posture of the carrier in the physical space according to the control data. The handling machine control system according to claim 11, further comprising: an image capture interface, coupled to the control host, Wherein the image capture interface is used to capture a target image, the target image includes at least a part of the image of the carrier, and The image capturing interface is further used for generating the image data according to the captured target image. The transporter control system of claim 12, wherein the image capture interface is disposed on the transporter. The handler control system of claim 11, wherein analyzing the image comprises: An image recognition is performed on the image data by an image recognition module, and the image recognition module is trained to recognize the carrier from the image data. The handler control system of claim 11, wherein the operation of analyzing the profile data to obtain the characteristic data of the carrier comprises: analyzing the profile data to obtain information on a pixel distribution in the image data corresponding to the carrier; and The characteristic data is generated according to the information of the pixel distribution. The transporter control system according to claim 15, wherein the operation of generating the characteristic data according to the information of the pixel distribution comprises: A feature vector is generated according to the information of the pixel distribution, wherein the feature vector is used to reflect the posture of the carrier in a virtual space. The handling machine control system of claim 16, wherein the operation of generating the control data according to the characteristic data comprises: obtaining information about an included angle between the feature vector in the virtual space and a reference plane; Obtain a relative positional relationship between the carrier and the carrier in the physical space according to the information of the included angle; and The control data is generated according to the relative positional relationship. The handling machine control system of claim 11, wherein the profile data includes a first profile data and a second profile data, and the operation of analyzing the profile data to obtain the characteristic data of the carrier comprises: : obtaining a profile ratio reflected by at least one of the first profile data and the second profile data; and The characteristic data is generated according to the outline ratio. The handler control system of claim 18, wherein the first profile data includes data related to an image of a first side surface of the carrier in the image data, and the second profile data includes the image data information in relation to an image of a second side face of the carrier. The transporter control system of claim 11, wherein the transporter is further configured to insert an extension arm into an insertion port of the carrier according to the control data, so as to transport the carrier by the extension arm. A non-volatile computer-readable recording medium, wherein the non-volatile computer-readable recording medium stores program code, and the program code is executed by a processor to: analyzing an image data to obtain a profile surface data corresponding to a carrier in the image data; analyzing the profile data to obtain a characteristic data of the carrier, wherein the characteristic data reflects the posture of the carrier in a physical space; and A control data is generated according to the characteristic data, wherein the control data is suitable for controlling the carrier to carry the carrier in response to the posture of the carrier in the physical space.

Images