Machine, System

Abstract

One or more of the above embodiments are machines related to agriculture, recognize crops based on information obtained from one or more sensors, recognize the environment around the machine, judge whether the operation of agricultural work is possible or not by AI based on crop information and environmental information, machine, is provided

Description

Technical Field

[0001] The present invention relates to a machine or a system.

Background Art

[0002] The statements in this section only provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] Patent Document 1 discloses a temperature control system for an agricultural greenhouse.

Prior Art Document

Patent Document

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the inventor recognized that at least the above-described embodiments have a disadvantage in that there is no configuration capable of efficiently automating agriculture.

Means for Solving the Problems

[0006] At least one aspect of the present disclosure provides a machine related to agriculture, which recognizes crops based on information obtained from one or more sensors, recognizes the environment around the machine, and determines whether an agricultural operation can be performed by AI based on the crop information and the environmental information, the machine .

Effects of the Invention

[0007] In this configuration, at least, there is an advantage of being able to efficiently automate agriculture.

[0008] These and other aspects, features, and advantages of the present disclosure will become apparent from the following detailed written description of the preferred embodiments and aspects taken in conjunction with the following drawings, but modifications and variations can be made without departing from the spirit and scope of the novel concepts of the present disclosure. Aspects in certain embodiments of the present disclosure can be combined with, or replaced by, one or more of the aspects in another disclosed embodiment, as long as they do not conflict.

Best Mode for Carrying Out the Invention

[0009] In the following disclosure, many different embodiments and examples are provided for implementing different features of the presented subject matter. To simplify the present disclosure, specific examples of components and arrangements are disclosed below. Of course, these are merely examples and are not intended to be limiting. For example, a structure in which a first feature is covered by, or in contact with, a second feature disclosed subsequently may include embodiments in which the first and second features are formed so as to be in direct contact, as well as embodiments in which additional features are formed between the first and second features so that the first and second features are not in direct contact. Further, in the present disclosure, reference numerals and / or letters may be repeated in various examples. Such repetition is for the sake of brevity and clarity and does not in itself require a relationship between the various embodiments and / or the configurations being described. Further, when a first element is described as being "connected" or "coupled" to a second element, such description includes embodiments in which the first and second elements are directly connected or coupled to each other, as well as embodiments in which the first and second elements are indirectly connected or coupled to each other with one or more other elements intervening therebetween.

[0010] As used herein, the description "at least one of" encompasses all exemplified variations. For example, the description "comprises at least one of A, B, or C" is synonymous with "consisting of A, B, C and combinations thereof", and encompasses all possible variations of A, B, C, A + B, A + C, B + C, and A + B + C. In the present disclosure, the disclosure of an embodiment combining two or more components can be implemented as an embodiment in which any one or more components are separated, as long as there is no contradiction or unless otherwise described herein. For example, the description "implementing A, B, and C" is synonymous with "comprising of A, B or C and combinations thereof", and encompasses all possible variations of A, B, C, A + B, A + C, B + C, and A + B + C.

[0011] In the present disclosure, the disclosure of using a machine, an electronic operator, or a computer can include embodiments of a method, a recording medium, a device, or a program. The description "A is B" used herein can be replaced with "A includes B", as long as there is no contradiction or unless otherwise described herein.

[0012] The terms in the present disclosure, including the terms described in the claims, can be interpreted in consideration of the descriptions and drawings described in the specification, and further, as long as there is no contradiction with the suggestions in the present disclosure, based on matters that one or more members of the public have so named, indicated, understood, or implemented, or that are possible, in the past, present, or future. Regarding the operation method used in at least one or more embodiments, the following embodiments can be adopted. The description of JP6456303, which well explains at least one or more embodiments, is cited for explanation (hereinafter, citation starts).

[0013] As used herein, the term "computer", as known in the art, generally includes a processor, a memory such as a hard drive, disk drive or flash drive or memory stick, or other non-transitory computer-readable medium or non-transitory storage device, at least one information storage / search device, such as a keyboard, mouse, pointing and touch device, touch screen, or microphone, at least one input device, and a display structure such as a well-known computer screen. Additionally, a computer may include one or more network connections, such as a wired or wireless connection. As known in the art, such a computer or computer system may include more or less of the items listed above and is not limited to, for example, tablet computers or smart devices, but includes other electronic media and electronic devices.

[0014] As used herein, the term "cloud" or "cloud computing" refers to a centralized and virtualized computing facility where all computing resources are shared. For application systems and subsystems, since they are all within the "cloud", it is no longer possible to refer to a specific machine.

[0015] As used herein, the term "Distributed Internet Service System" refers to a distributed Internet service platform that transforms Internet applications for execution in various computing environments. The DIS system distributes Internet applications, including content, data, and logic, via a Component Distribution Server / Asset Distribution Server to any number and type of devices along the network to whatever extent appropriate. Through DIS, Internet applications can be hosted and centrally managed as services based on each user's needs, locally cached and executed at the user's device or nearby locations while maintaining their integrity. Web-enabled computing devices can be upgraded with DIS software to become DIS-compliant to enjoy and execute distributed Internet services. The Distributed Internet Service System is fully described in any one of the patent families of U.S. Patent Nos. 7,136,857, 7,150,015, 7,181,731, 7,209,921, 7,430,610, 7,685,183, 7,685,577, 7,752,214, 8,326,883, 8,386,525, 8,443,035, 8,458,142, 8,458,222, 8,473,468, 8,527,545, and 8,650,226, and U.S. Patent Publications Nos. 2012 / 0005205 and 2013 / 0091252, all of which are jointly owned by OPI40, Holdings, Inc. and are hereby incorporated by reference. (End of citation)

[0016] Regarding the operation method used in at least one or more embodiments, the following embodiments can be taken for the conventional Internet method that does not use a distributed Internet. The description of JP7113047, which well explains at least one or more embodiments, will be cited for explanation (hereinafter, citation starts).

[0017] Embodiments including the matters specifically disclosed in this specification can provide an automatic response system realized in a form that actually converses with humans based on artificial intelligence, thereby enabling a more natural conversation with the user while quickly and conveniently processing inquiries, reservations, delivery orders, and the like.

[0018] The plurality of electronic devices 110, 120, 130, 140 may be fixed terminals or mobile terminals realized by a computer system. Examples of the plurality of electronic devices 110, 120, 130, 140 include AI speakers, smartphones, mobile phones, navigation devices, PCs (personal computers), notebook PCs, digital broadcast terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablets, game consoles, wearable devices, IoT (internet of things) devices, VR (virtual reality) devices, AR (augmented reality) devices, and the like. As an example, in FIG. 1, an AI speaker is shown as the electronic device 110. However, in the embodiments of the present invention, the electronic device 110 may mean one of various physical computer systems that can communicate with other electronic devices 120, 130, 140 and / or servers 150, 160 via the network 170 using substantially wireless or wired communication methods.

[0019] The communication method is not limited, and it may include not only a communication method using a communication network that the network 170 can include (for example, a mobile communication network, a wired Internet, a wireless Internet, a broadcast network, a satellite network, etc.), but also short-range wireless communication between devices. For example, the network 170 may include any one or more of networks such as a PAN (personal area network), a LAN (local area network), a CAN (campus area network), a MAN (metropolitan area network), a WAN (wide area network), a BBN (broadband network), and the Internet. Further, the network 170 may include any one or more of network topologies including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or hierarchical network, etc., but is not limited thereto.

[0020] Servers 150 and 160 may each be implemented by one or more computer devices that communicate with a plurality of electronic devices 110, 120, 130, 140 via a network 170 to provide instructions, code, files, content, services, and the like. For example, server 150 may be a system that provides a first service to a plurality of electronic devices 110, 120, 130, 140 connected via network 170, and server 160 may also be a system that provides a second service to a plurality of electronic devices 110, 120, 130, 140 connected via network 170. As a more specific example, server 150 may provide, as the first service, a service (such as an automatic response service, for example) targeted by the corresponding application to a plurality of electronic devices 110, 120, 130, 140 through an application that is a computer program installed and executed on the plurality of electronic devices 110, 120, 130, 140. As another example, server 160 may provide, as the second service, a service that distributes files for installation and execution of the above-described application to a plurality of electronic devices 110, 120, 130, 140.

[0021] FIG. 2 is a block diagram for explaining the internal configurations of an electronic device and a server in an embodiment of the present invention. In FIG. 2, the internal configuration of electronic device 110 and the internal configuration of server 150 are described as examples for the electronic device. Also, the other electronic devices 120, 130, 140 and server 160 may have the same or similar internal configurations as the above-described electronic device 110 or server 150.

[0022] The electronic device 110 and the server 150 may include memories 211 and 221, processors 212 and 222, communication modules 213 and 223, and input / output interfaces 214 and 224. The memories 211 and 221 may be non-transitory computer-readable recording media, and may include non-transitory mass storage devices such as RAM (random access memory), ROM (read only memory), disk drives, SSDs (solid state drives), flash memories, and the like. Here, non-transitory mass storage devices such as ROM, SSD, flash memory, and disk drive may be included in the electronic device 110 or the server 150 as separate non-transitory recording devices distinct from the memories 211 and 221. Also, the memories 211 and 221 may record an operating system and at least one program code (for example, code for a browser installed and executed in the electronic device 110, an application installed in the electronic device 110 for providing a specific service, etc.). Such software components may be loaded from a computer-readable recording medium different from the memories 211 and 221. Such another computer-readable recording medium may include computer-readable recording media such as a floppy (registered trademark) drive, disk, tape, DVD / CD-ROM drive, memory card, and the like. In other embodiments, the software components may be loaded into the memories 211 and 221 through the communication modules 213 and 223 which are not computer-readable recording media. For example, at least one program may be loaded into the memories 211 and 221 based on a computer program (for example, the above-described application) installed by a file distributed by a file distribution system (for example, the above-described server 160) that distributes developer or application installation files via the network 170.

[0023] The processors 212 and 222 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. The instructions may be provided to the processors 212 and 222 by the memories 211 and 221 or the communication modules 213 and 223. For example, the processors 212 and 222 may be configured to execute instructions received according to program code recorded in a recording device such as the memories 211 and 221.

[0024] The communication modules 213 and 223 may provide a function for the electronic device 110 and the server 150 to communicate with each other via the network 170, or may provide a function for the electronic device 110 and / or the server 150 to communicate with other electronic devices (for example, the electronic device 120) or other servers (for example, the server 160). As an example, a request generated by the processor 212 of the electronic device 110 according to program code recorded in a recording device such as the memory 211 may be transmitted to the server 150 via the network 170 under the control of the communication module 213. Conversely, control signals, instructions, contents, files, etc. provided under the control of the processor 222 of the server 150 may be received by the electronic device 110 through the communication module 213 of the electronic device 110 via the communication module 223 and the network 170. For example, control signals, instructions, contents, files, etc. received through the communication module 213 may be transmitted to the processor 212 and the memory 211, and the contents and files may be recorded in a recording medium (the non-transitory recording device described above) that the electronic device 110 may further include.

[0025] The input / output interface 214 may be means for interfacing with an input / output device 215. For example, the input device may include devices such as a keyboard, a mouse, a microphone, a camera, etc., and the output device may include devices such as a display, a speaker, a tactile feedback device, etc. As another example, the input / output interface 214 may be means for interfacing with a device in which functions for input and output are integrated into one, such as a touch screen. The input / output device 215 may be composed of the electronic device 110 and one device. Also, the input / output interface 224 of the server 150 may be means for interfacing with a device (not shown) for input or output that can be connected to or included in the server 150. As a more specific example, when the processor 212 of the electronic device 110 processes the instructions of the computer program loaded in the memory 211, a service screen or content configured using the data provided by the server 150 or the electronic device 120 may be displayed on the display through the input / output interface 214.

[0026] Also, in other embodiments, the electronic device 110 and the server 150 may include more components than the components shown in FIG. 2. However, it is not necessary to clearly show most of the conventional components in the figure. For example, the electronic device 110 may be realized to include at least a part of the above-described input / output device 215, or may further include other components such as a transceiver, a camera, various sensors, a database, etc. As a more specific example, when the electronic device 110 is an AI speaker, various components such as various sensors generally included in the AI speaker, a camera module, various physical buttons, buttons using a touch panel, an input / output port, a vibrator for vibration, etc. may be realized to be further included in the electronic device 110. (End of citation)

[0027] A machine is disclosed. According to at least one embodiment, the user terminal consists of a control unit, a RAM, a storage unit, a graphics processing unit, a communication interface, and an interface unit, and they are respectively connected by an internal bus. In at least one embodiment, the user terminal includes the terminal owned by the user. On the other hand, it includes not only the terminal owned by the user, but also terminals whose owners are other than the user (including sellers and traders of goods and services, governments and local governments). As an example, a terminal provided for the use of the person receiving the provision, advertisement, or promotion (hereinafter referred to as "such provision, etc." in this paragraph) of goods or services (including items to be transferred or lent), a terminal provided for such provision, etc., and a terminal related to the provision of such goods or services received by the person receiving such provision, etc. That is, it includes terminals owned by others to whom the user is only temporarily permitted to use, and terminals lent to the user.

[0028] According to at least one embodiment, the control unit is composed of a CPU and a ROM. The control unit executes the program stored in the storage unit to control the user terminal. The RAM is the work area of the control unit. The storage unit is a storage area for storing programs and data. The control unit reads the program and data from the RAM for processing. By processing the program and data loaded into the RAM, the control unit outputs a drawing command to the graphics processing unit.

[0029] According to at least one embodiment, the graphics processing unit is connected to the display unit. The display unit has a display screen. When the control unit outputs a drawing command to the graphics processing unit, the graphics processing unit outputs a video signal for displaying an image on the display screen. Here, the display unit may be a touch panel equipped with a touch sensor. The touch panel of this display unit functions as an input unit.

[0030] According to at least one embodiment, the communication interface can be connected to a communication network wirelessly or by wire, and can transmit and receive data with a server device via the communication network. The data received via the communication interface is loaded into the RAM and processed by the control unit. An external memory (e.g., an SD card, etc.) is connected to the interface unit.

[0031] According to at least one embodiment, the user terminal is not particularly limited as long as it is a computer device having a display screen and an input unit. Examples of the user terminal include a conventional mobile phone, a tablet terminal, a smartphone, a desktop or notebook personal computer, etc. It may also be composed of a VR goggle, that is, a screen (or two display panels, one for each eye) attached to a frame (or a headset) fixed or attached to the head by a strap. The user terminal has an audio output unit.

[0032] According to at least one embodiment, the user terminal can be communicatively connected to a server device via a communication network. It can transmit or receive information through a communication connection via the communication network.

[0033] According to at least one embodiment, the server device includes at least a control unit, a RAM, a storage unit, and a communication interface, which are connected by an internal bus respectively.

[0034] According to at least one embodiment, the control unit is composed of a CPU and a ROM, executes the program stored in the storage unit, and controls the server device. Also, the control unit has an internal timer for measuring time. The RAM is a work area of the control unit. The storage unit is a storage area for storing programs and data. The control unit reads the program and data from the RAM, and performs program execution processing based on the information received from the user terminal, etc.

[0035] Disclosed is AI. According to at least one embodiment, artificial intelligence includes machine learning, deep learning, generative AI, large language models, LLMs, foundation models, generative AI. Generative AI uses transformers and employs a number of mechanisms called attention. Self-supervised learning and Extract Prediction are used. In this case, the AI can guess the next word. Given a sentence, it guesses the next word from the sentence up to that point. A large number of supervised learning problems are created. As a result, an AI that can guess the next word can be created. Generative AI can predict grammar structures, topic connections, and the likelihood that a person of a certain style will write a certain sentence. Furthermore, generative AI can learn the structure, causal relationships, and knowledge behind just guessing the next sentence. Generative AI has a high speed of scaling, and the greater the number of parameters, the higher the accuracy. Ordinary statistics and machine learning will overfit if the model parameters are made too large compared to the data sample size. LLMs increase in accuracy as the number of parameters is increased. One generative AI has 175 billion parameters. Generative AI is trained with supervised learning to have smooth conversations. It is taught not to say strange things. It writes reviews or acts as a call center operator.

[0036] According to at least one embodiment, a Large Language Model (LLM) is, non-exhaustively, a natural language processing model of machine learning constructed using a large amount of dataset and deep learning technology. Generally, it is adapted to various natural language processing (NLP) tasks such as text classification, generation, sentiment analysis, text summarization, and question answering by using a method called "fine-tuning" for training on specific tasks. According to at least one embodiment, self-supervised learning is close to human essential intelligence. When humans act, they always predict the next event and the next input. In the process, they can learn the structure of the external world. Predicting the next word is an essential intelligence and is considered to be similar to what the cerebral cortex does. According to at least one embodiment, a large language model memorizes all the input information but generalizes to the extent necessary to predict the next word. It does not generalize all the information from the beginning. A large language model requires capacity to memorize information. Also, parameters are required for this purpose. According to at least one embodiment, a large language model is equipped with models of 175 billion parameters and eight models of 220 billion parameters.

[0037] According to at least one embodiment, videos and images are represented as a set of visual patches, which are small data units similar to the text tokens of an LLM. Patches can effectively represent models of visual data and are used as a very scalable and effective representation for training generative models with various types of videos and images. First, a video is compressed into a low-dimensional latent space, and then the representation is decomposed into spatio-temporal patches to convert the video into patches.

[0038] According to at least one embodiment, a Video compression network is a network that reduces the dimension of visual data, receives raw videos as input, and outputs a temporally and spatially compressed latent representation. An AI is trained in this compressed latent space and then generates videos within this compressed latent space.

[0039] According to at least one embodiment, given a compressed input video, Spacetime Latent Patches extract a series of spatio-temporal patches that function as transformer tokens. With the patch-based representation, Sora can be trained on videos and images of various resolutions, lengths, and aspect ratios, and control the size of the generated video by placing randomly initialized patches at inference time into a grid of appropriate size.

[0040] According to at least one embodiment, the AI is a diffusion model and is trained to predict the original "clean" patches when noisy patches (and conditional information such as text prompts) are input. The AI is a diffusion transformer, which exhibits remarkable scaling properties in various areas such as language modeling, computer vision, and image generation. The diffusion transformer is also effective as a video generation model. As the computational cost of training increases, the quality of the samples improves significantly for the AI.

[0041] According to at least one embodiment, the AI applies caption regeneration technology to train a highly explanatory caption model and then uses it to generate text captions for all videos in the training set. Training highly explanatory captions improves not only the overall quality of the generated videos but also the faithfulness of the text. Utilize GPT to convert short user prompts into long detailed captions and send them to the model. This enables the AI to generate high-quality videos that exactly follow the user's prompts.

[0042] According to at least one embodiment, in natural language processing, vectorization can be performed by AI along the following process. First, cleaning processing of the given text is performed as preprocessing. In the cleaning process, unnecessary words such as JavaScript code and HTML tags included in the text are removed. Since these codes are used for display on the Internet, they are generally information not used in natural language processing. Subsequently, the text is segmented into word level by morphological analysis. Morphological analysis is to classify natural language sentences written in characters into the smallest language units with meaning. As morphological analysis tools, "MeCab", "JUMAN", and "JANOME" can be used. In normalization, words with the same meaning such as writing variations are unified into one word. Stop words are words that are excluded from processing for reasons such as not being usable in natural language processing. Examples of stop words include those that do not have meaning alone, such as particles and auxiliary verbs among words. When calculating vectors, these may be removed and only meaningful words may be targeted. Vectorization may also be performed without removing these stop words. Vectorization is a process of converting a word, which is a character string, into a vector. By vectorization, word data is converted into numerical data. When converting a word into a vector, it is performed by a method called Bag of Words or distributed representation. Bag of Words is a method of vectorizing a text by using the number of occurrences of words that appear in the given text. Since it focuses on how many words appear in the text, the order of words and texts is not considered. Distributed representation is a method of vectorizing by focusing on the meaning of words. By vectorizing the meaning of words, it is possible to give vectors close to words with similar meanings and usage, and the relationship between words can also be expressed by vectors. By expressing in vectors, addition and subtraction of the meanings of words are possible. The application process can utilize the natural language converted into numerical data as input for machine learning. Specifically, the vectorized natural language is input into a classifier to perform text classification.Examples of tools utilized herein include "TensorFlow", "scikit-learn", "PyTorch", etc.

[0043] Disclosed is a machine. In at least one embodiment, the machine may exist as a combination of one or more embodiments or functions in the present disclosure.

[0044] The machine includes a machine that can move itself or a machine equipped with self - movable power. The machine may be equipped with an image acquisition device. The machine includes a robot. The machine has communication means and can communicate with other computers, computing facilities, the cloud, the Internet, applications, and information. As an example, the machine includes a machine that moves by at least one or more wheels, including a bicycle. The bicycle is a vehicle or machine that moves autonomously without a driver. Furthermore, the machine includes a machine that walks or runs with at least one or more movable parts. As an example, it is capable of bipedal walking. As an example, it includes a humanoid robot. The humanoid robot has at least two movable parts, which correspond to feet. The machine includes a robot or humanoid robot that integrates artificial intelligence (AI) and robotics. These machines can utilize autonomous driving technology and machine learning algorithms to act autonomously while recognizing the surrounding situation. The machine is equipped with AI technology and sensors. Thereby, it can recognize the surrounding environment in real - time and select appropriate actions. For example, it can move while avoiding obstacles or communicate with people around it. The machine includes a machine that flies using power. As an example, it includes a drone. The aircraft includes airplanes, helicopters, gliders, airships, and other devices specified by government ordinances that can be used for aviation. The aircraft may be equipped with one or more propellers. The drone is equipped with an image acquisition device. The drone can take pictures. The images include thermography.

[0045] Disclosed is an image acquisition device or means. In at least one embodiment, the image acquisition device can be implemented by any of the machines and devices described in the present disclosure. As a non-exhaustive example, the image acquisition device includes a device that captures an image and converts it into digital data. Digital cameras (which capture still images and moving images and store them on a recording medium), video cameras (which mainly capture moving images), webcams (which are connected to a personal computer and used for video conferencing, live streaming, etc.), surveillance cameras (which are installed for security purposes and record images constantly), and smartphone cameras. "Image" in the present disclosure is a term with a very broad meaning. Generally, it refers to an image created by light, that is, visual information that can be captured by seeing with the eyes. That is, "image" includes thermography (a technique for visualizing invisible heat). Thermography uses an infrared camera to detect infrared rays emitted from an object and displays the intensity in different colors to capture the temperature distribution as an image. Naturally, the "image acquisition device" includes a device for acquiring thermography.

[0046] Disclosed is a method for acquiring human motion data using motion capture. In at least one embodiment, motion capture includes a technique for recording the movement of a person or an object as digital data. The optical method digitizes the three-dimensional position and posture of markers attached to the object with multiple infrared cameras. The inertial method measures the displacement and posture of inertial sensors attached to the object. Markerless (video-based) reads the silhouette of the object with a video camera and estimates the position of the bones. A person can choose according to the purpose of the service provided. For example, a person doing work. The work can be any physical movement regardless of its mode, including light work. For example, transporting luggage to a predetermined location, loading and unloading it, cooking, farming, welding, performing a predetermined task on a factory line, and cleaning. This includes cases where two or more people cooperate to perform work. In this case, it includes performing a certain work and delivering the resulting product to the next predetermined one.

[0047] Disclosed is a method for training motion data with AI. In at least one embodiment, actual human motion capture clips are collected. Next, reinforcement learning is used to train a control policy that mimics human motion. The policy is trained in a physical simulation to track the pose of the reference motion at each time step. Next, by using various reference motions in the reward function, the simulated robot can be trained to mimic various skills.

[0048] Disclosed is a method for generating adaptable motions according to environmental changes around a machine. In at least one embodiment, since the simulator generally provides only a rough approximation of the real world, the policy trained in simulation may have degraded performance when deployed to an actual robot. Therefore, a high sample efficiency potential space adaptation technique is used to transfer the policy trained in simulation to the real world. First, to encourage the policy to learn robust motions against changes in dynamics, physical quantities such as the mass and friction of the robot are changed to randomize the dynamics of the simulation. Since the values of these parameters can be accessed during training in simulation, they can also be mapped to a low-dimensional representation using the learned encoder. This encoding is passed as an additional input to the policy during training. Since the physical parameters of the actual robot are not known in advance, when deploying the policy to the actual robot, the encoder is removed and a series of parameters that allow the robot to normally execute the target skill in the real world are directly searched in the potential space. With this technique, the policy can be adapted to the real world using real-world data. In the above approach, the policy can be trained in simulation and adapted to the real world.

[0049] However, when the task involves complex and diverse physical phenomena, it is also necessary to learn directly from real-world experience. Develop an automatic learning system with software and hardware components using multi-task learning procedures, learners with safety constraints, and some carefully designed hardware and software components. Multi-task learning generates a learning schedule that directs the robot towards the center of the workspace, preventing the robot from leaving the training area. Also, design safety constraints to reduce the number of falls. This safety constraint is solved by the double gradient descent method. In each rollout, the scheduler selects a task where the desired walking direction is towards the center. For example, if there are two tasks, forward and backward, when the robot is at the back of the workspace, the forward task is selected, and vice versa for the backward task. During the episode, the learner executes the double gradient descent procedure to iteratively optimize rather than treating both the task objective and the safety constraint as a single goal. If the robot falls, the automatic stand-up controller is called to proceed to the next episode.

[0050] Obtain information on environmental changes around the machine and perform training using that variable. By this method, it is possible to generate operations adaptable to environmental changes. Obtain information related to human work and, based on that information, generate operations adaptable to environmental changes around the machine. For example, a factory line refers to a production method of flow work that processes and assembles products and parts flowing on a belt conveyor or the like. In an automobile factory line, the motion data of the worker is obtained using motion capture. The machine learns the motion data by AI. The machine performing the work includes any of the machines described in this specification. It may be a humanoid robot (hereinafter referred to as a "working machine"). The working machine adapts to environmental changes around the machine. The working machine is given physical parameters about the environment. For example, it includes information on the shape, coefficient of friction, locations that should not be touched, and combinations of one or more of these of the article that is the work target flowing on the factory line. The working machine uses the physical parameters to perform actions adapted to the real world. The physical parameters may be given to the working machine or it may search for them by itself using sensors or the like. In this way, the working machine can autonomously capture actions adapted to the actual environment while imitating the actions of humans as reference actions. According to this embodiment, there are the convenience and industrial applicability that at least automation applicable based on human actions can be realized.

[0051] When generating an operation, a method for recognizing the environment around a machine based on information obtained from one or more sensors and changing the operation based on the acquired information is disclosed. In at least one embodiment, the sensors include those that can acquire data on variables or physical parameters regarding the environment around the machine, regardless of their type. As an example, it includes LiDAR, cameras, force sensors, and combinations of one or more of these. LiDAR irradiates laser light and measures the distance to an object and the shape of the object based on the information of the reflected light. LiDAR (lidar) can grasp the distance, shape, and positional relationship of a preceding vehicle, a pedestrian, a building, etc. in three dimensions. The machine searches for or acquires physical parameters by itself. For example, by using a camera or the like, understand the speed of the work target article flowing on the factory line, calculate how many seconds the operation must be performed within that speed, and increase the driving speed of the machine so that the work can be completed within that time. As a result of the inventors' sincere consideration, it has been found that by changing the operation based on the acquired information, the quality of the work of the working machine is improved. In particular, in the case of LiDAR, extremely accurate physical parameters regarding the shape and distance of an object can be acquired. Therefore, it is difficult for noise in learning and calculation based on the physical parameters to occur, and as a result, the behavior based on the result of the learning has high quality. This effect was not known at all in the prior art and has novelty and remarkable effects. According to this embodiment, there is the convenience and industrial applicability that at least automation applicable based on human actions can be realized.

[0052] Disclosed is a method for acquiring motion data of human motion using an image, learning the motion data by reinforcement learning, and generating an adaptive motion for a motion similar to or different from the motion. In at least one embodiment, motion data of human motion is acquired using an image. For example, there is an image acquisition device above a person's head, and the image acquisition device captures the person's motion. The person's motion may be any physical motion regardless of its form, including speech and gestures. There is an image acquisition device beside the person, including acquiring an image of the way of walking while carrying a load. There is an image acquisition device on the ceiling of a large warehouse, including acquiring an image of the path the person walks. The machine performs region estimation. Based on the image, when the feature points of the person's body enter the specified region, the person's motion is detected. For example, it is detected that the wrist has entered the region for picking up a part. The machine performs pose estimation. The feature points of the person's body are learned, and the person's pose is detected. For example, it is detected how the person takes out and assembles a tool. The machine performs background estimation. The feature image in the background is learned to classify the background. For example, it is detected whether a driver is being used during work. The machine performs object detection. An image that matches the learned image is detected from the set region in the image. For example, it is detected whether a predetermined tool is being used. The machine learns the motion data by reinforcement learning.

[0053] Reinforcement learning maximizes the score by feeding back the score for the output. In reinforcement learning, pre-prepared training data such as supervised learning and unsupervised learning is not used. Two functions, an agent and an environment, are utilized. The agent is the AI model to be developed. The agent receives the "state" from the environment as input. The environment often uses a simulator, and the agent receiving the input from the environment is sometimes called "observation". The agent that observes the environment returns an output corresponding thereto or a random output (takes an action). What kind of output to produce and what kind of operation or action to take vary depending on whether the development target is robot control. Basically, they are all numerical values or codes output by a function, but the values and meanings vary depending on whether the AI to be developed is a block-breaking game, a program for Go or Shogi. The environment receives the output of the agent and returns a new state as its reaction. At this time, a "reward" is also given to the agent depending on the state. The reward (Reword) is also called a score and is numerical information. The agent observes the environment, takes some action, and selects the action that maximizes the reward. The relationship between the evaluation of the action and the reward (and sometimes a penalty) is considered by humans and given to the AI as a parameter. This is an important tuning point that determines the functions and systems in reinforcement learning. In reinforcement learning, through this repetition, the agent is taught what actions to take to effectively achieve the task. Instead of humans programming the control of the servo motors for a robot to walk without falling or the operation of the paddle to eliminate many blocks without dropping the ball in a block-breaking game, the machine (agent) is allowed to try and error. For example, for walking, if moving the motor that extends one foot forward causes the balance to be lost and the robot falls, no reward is obtained or the reward becomes negative. Next, another motor is moved. If that control that shifts the center of gravity of the pivot foot does not cause it to fall, the reward increases, and that operation is incorporated into the control as an effective one. The basis of the processing in reinforcement learning is an algorithm or method for observing the environment and selecting / determining the next action. The amount of information given by the environment is diverse. In the case of the Othello game, the amount of information is small immediately after the start.As the board progresses, the number, position, and arrangement of stones become more diverse. At this time, mathematical methods such as regression analysis and probability theory, or evaluation by a neural network, are used to grasp and evaluate the board state. Reinforcement learning can also be regarded as a "function". An agent is a function that receives values (states) from the environment as input and outputs the next action. The environment can also be regarded as a function that receives the agent's action as input and returns a new state. Different from AI that learns using static data (supervised learning and unsupervised learning), reinforcement learning can also be said to be a dynamic learning method that adjusts the next process according to the output result (reward) of the function. The reward can be regarded as "the evaluation of the environment's reaction to the agent's random action". Maximizing the reward means comparing the state change (this is called "value") when the agent does not take a random action with the state change (value) when taking a random action, and adopting the one with a higher value as the "policy (a series of successful actions)". Calculating the value is done by two functions, the state-value function and the action-value function. The state-value function calculates the value when not taking a random action. The action-value function calculates the value when taking a random action. As a result, when the action-value function is higher, the random action is incorporated into the policy as the correct action. As a result, the AI can learn the moves that lead to victory for each board state and the control method for the motors for the robot to walk.

[0054] The machine learns the operation data through reinforcement learning. The machine learns the optimal actions by itself through trial and error. For example, in a logistics warehouse, it learns about the task of transporting a predetermined item to a predetermined location. It conducts reinforcement learning on how to hold the item, how to move to minimize the required time, etc. As a result, it generates actions adaptable to human-like or different actions. According to this embodiment, there are the advantages and industrial applicability of realizing at least more efficient automation than when humans work.

[0055] The machine further discloses a method of recognizing a feedback action of a human gesture, voice, gaze, or a combination of one or more of these when performing the generated action, evaluating the action generated based on the feedback action, and changing the action based on the evaluation. In at least one embodiment, the machine acquires an image of a human around the machine by an image acquisition device. The machine acquires sound by a sound acquisition device. The sound to be acquired may be around the machine, or may be the sound of the location around the device by a sound acquisition device physically separated from the machine. The machine recognizes the feature amount of a human face from the image and recognizes the human face. Further, the feature amount of the expression of the human face is recognized, and the gaze of the human is estimated or recognized from the image of the human eyes. Further, the gesture of the person is estimated from the image of the person. A gesture includes body movements and hand gestures, but is not limited to the hands, and may be any physical movement regardless of its form. For each action, a value serving as a reward is set for the machine. For example, a high reward is set for the action of making a circle with the hand, and a low reward is set for the action of making a cross with the hand. In the case of sound, a high reward is set for the sound of "OK", and a low reward is set for the sound of "no good". In the case of the line of sight, a high reward is set for the line of sight directed towards the machine, and a low reward is set for the line of sight not directed towards the machine. In such a manner, the machine can recognize the feedback action. The machine evaluates the action generated based on the feedback action, and by performing reinforcement learning with reference to the reward, changes the action based on the evaluation. For example, the machine performs a predetermined operation on a factory line. A human observes the action and says "OK" or makes a cross gesture. Then, the machine recognizes the feedback action, evaluates the action generated based on the feedback action, and changes the action based on the evaluation. As a result of the inventor's earnest consideration, the result of self-learning or trial and error of only the machine is not necessarily the best result considered by humans. The result of learning different from the human intention may be beneficial to humans in some cases, but may also produce conflicting results. Therefore, by humans providing feedback on the actions of the machine and incorporating this information as a reward into reinforcement learning, it is possible to produce the best learning result in line with the human intention.This effect was not known at all in the prior art and has novelty and remarkable effects.

[0056] The machine further discloses a method of acquiring an execution video of the generated operation, learning by AI based on the execution video, and changing the operation based on the acquired information. In at least one embodiment, the video acquisition device includes the case where it is provided in the machine and the case where it exists independently of the machine. The video acquisition device acquires an execution video of the operation executed by the machine. This video includes still images and moving images. In the case of moving images, it includes a series of moving images from before the operation is generated to after it is generated. The machine learns by AI based on the video. For example, when the video is about the machine being a humanoid robot and the work at the hand of the robot, acquiring the video with the video acquisition device of the machine is included. When the video is about the robot moving inside a large warehouse or an operation using the whole or part of the robot, according to the operation, the video is acquired with a video acquisition device different from the robot. This is because there may be cases where more data with a large amount of information about the overall movement of the robot can be acquired. The learning method includes, firstly, reinforcement learning. In the case of reinforcement learning, the machine autonomously evaluates the operation appearing in the video, sets a reward value, and based on that reward value, learns whether to imitate the operation, not to imitate it, and in which part of the overall operation to imitate / not to imitate. For example, if it falls, the reward value of that operation is low. Secondly, there is supervised learning or unsupervised learning. Supervised learning processes learning data with correct answers and outputs the correct answer. Unsupervised learning extracts patterns and features of input data by computational processing. The user of the machine gives information on whether it is the correct answer for the video. For example, the user gives the correct answer to the video judged to be the best among the videos of a number of machines. In addition, for prohibited actions that should not be performed in the video, an incorrect answer is given to the video in which such an action was performed. The machine learns the actions related to the correct video based on this information. In the case of unsupervised learning, clustering analysis (clustering) and dimensionality reduction of videos, etc. are performed. Then, the user gives information on whether it is the correct answer for the cluster. The machine learns based on this information.

[0057] Disclosed is learning without a teacher. In cluster analysis, "cluster" in English means "cluster" or "lump", and refers to a state where things with similar characteristics are gathered. That is, cluster analysis is an analysis method for grouping similar things (things with similar feature quantities) from a large amount of data into several groups. Creating a group of data with similar characteristics by this method is called "clustering". Clustering is a classification in a state where there is no correct answer data. Classification can be performed, but the meaning of each group may not be clear. The results may need to be interpreted by humans. Types of cluster analysis include "hierarchical clustering" used when the number of classification targets is small, and "non-hierarchical clustering" applied when there are a large number of classification targets. Hierarchical clustering hierarchically groups data with similar features one by one in the order of clusters, and repeats until finally becoming one large cluster. Since the process is visualized in a diagram like a tournament table (tree diagram), it is an analysis method that makes it easy to grasp the characteristics of the data. Also, non-hierarchical clustering does not have a hierarchical structure. It is only necessary to set in advance how many clusters to divide into, and the data is divided according to the number of those clusters. There is also a method in which the machine automatically divides without determining the number.

[0058] Learning is not limited to only the machine that performed the operation. The machine acquires an execution video of the generated operation, transmits the video to a machine other than the machine that performed the operation, and a machine other than the machine that performed the operation learns by AI based on the execution video and changes its operation based on the acquired information. As a result of the inventor's earnest consideration, in the conventional method, since each robot learns machine learning independently, data obtained by the machine's trial and error behavior cannot be learned by other robots. Therefore, the collective intelligence of the robots could not be improved at the shortest speed. According to this method, when a plurality of machines perform work, the learning materials in a certain machine can also be learned by other machines, so the intelligence of the entire machine is synergistically improved. This effect was not known at all in the conventional technology and has novelty and remarkable effects.

[0059] It can also be implemented as a program for operating the machine described in any of this specification.

[0060] Disclosed is a method for changing the operation of a machine based on a received request or learning data, comprising communication means for transmitting and receiving information to and from a server or other machine. In at least one embodiment, the machine comprises communication means for transmitting and receiving information to and from a server or other machine. As described above, the machine can acquire video or the like from another machine or server and learn based on the video or the like. As a result of the learning, the operation of the machine can be changed. The machine can change its operation based on a request from another machine. For example, it is the case where two or more machines cooperate to perform work. In a logistics facility, Machine A transports an article to a predetermined position and delivers the article to Machine B. In this case, Machine A requests Machine B to receive the article. The method of request includes a method of transmitting a request or signal by an electromagnetic method. Machine B receives the request and receives the article. As a result of the inventor's earnest consideration, it has been found that the method of changing the operation of a machine based on the received request or learning data can also learn and improve the actions of the operations in which two or more machines cooperate. This effect was not known at all in the prior art and has novelty and remarkable effects.

[0061] Disclosed is a method comprising means for avoiding a collision with a human, an obstacle, or a machine other than itself. In at least one embodiment, the machine uses an image acquired by an image acquisition device to detect an obstacle or a machine other than itself (hereinafter referred to as "obstacle, etc.") in the traveling direction of the machine. When there is an obstacle, etc., the machine changes its course or temporarily stops moving until the obstacle, etc. disappears. In another embodiment, the machine has a device for transmitting its own position information. This device includes GPS. The machine transmits its own position information to another machine or a server. The machine receives the position information of another machine or the position information of an obstacle, etc. from another machine or a server. The position information of an obstacle, etc. includes information transmission from the machine that detected its existence or a method by which a user registers the fact. Based on the received position information of another machine, the machine changes its course to avoid a collision with an obstacle, etc. or temporarily stops moving until the obstacle, etc. disappears. According to this embodiment, there is the convenience and industrial applicability that the work in which at least two or more machines cooperate can be automated.

[0062] Disclosed is a method comprising control means for cooperating with a machine or a human other than itself. In at least one embodiment, the method described anywhere in this specification is employed. The machine acquires an image of a human around the machine by an image acquisition device. When there is a human around, the machine changes its course so as not to collide with the human or temporarily stops moving until an obstacle, etc. disappears. The image is analyzed, and based on the image, the work being done by the human is taken over. For example, if a human is carrying an article and the machine takes over that article. According to this embodiment, there is the convenience and industrial applicability that at least the machine and the human can cooperate in work. There is the convenience and industrial applicability that at least the work in which the machine and the human cooperate can be automated.

[0063] Disclosed is a method that includes energy efficiency means for improving its own energy consumption efficiency, plans its own operations based on calculations by the efficiency means, or performs control or charging to minimize the motor output or operating speed according to the work content. In at least one embodiment, the machine sets a reward regarding its own energy consumption amount during reinforcement learning. The machine performs an operation in a certain work and obtains the energy consumption amount regarding the operation. The power measurement means can measure the consumed power regardless of the means. It includes a power meter, a watt checker, and an energy monitor. The power measurement means includes a method mounted on the machine itself and a method not mounted on the machine itself but mounted on a supply device that supplies power to the machine. The machine identifies the amount of power consumed during its own operation. The calculation can be obtained by calculating the difference in power consumption before and after the machine performs a certain operation. The supply device obtains the power consumption amount related to the operation for each machine and each operation. The machine performs reinforcement learning with a reward based on the power consumption amount. The lower the power consumption amount, the higher the reward. The machine will take actions with less power consumption through reinforcement learning. As a result, the same work can be carried out with less power consumption. According to this embodiment, there are convenience and industrial applicability in reducing at least the power consumption related to the work of the machine or realizing the efficiency improvement of the power consumption amount.

[0064] Disclosed is a method for transmitting its own learning data to a machine other than itself. In at least one embodiment, the method described in any of this specification is used. The machine transmits its own learning data to a machine or server other than itself. The machine receives learning data related to a machine other than itself from a machine or server other than itself. The machine changes its operation based on the received learning data or learns using the learning data. By this method, the machine can inherit the learning data of other machines, so there are convenience and industrial applicability in improving the learning efficiency.

[0065] The content disclosed in this specification can also be configured as a system.

[0066] Disclosed is agriculture. In at least one embodiment, agriculture, regardless of its form, is an organic production industry that uses land to cultivate crops, raises livestock to produce materials necessary for food, clothing, and shelter, utilizes the power of the land to cultivate useful plants, raises useful animals, includes agricultural processing, forestry, and one or more combinations thereof.

[0067] Disclosed is a method for recognizing crops based on information obtained from one or more sensors. In at least one embodiment, the sensor, regardless of its form, includes a machine that acquires information around the device as some variable. The sensor includes an image acquisition device. The machine includes a humanoid robot. The working machine may be equipped with the sensor itself, or the sensor may be separate from the working machine. For example, the sensor may be provided on the farm separately from the working machine, another working machine may be equipped with the sensor, and the information acquired from the sensor is transmitted, and a machine without the sensor may receive it. The machine analyzes the image. The machine can recognize the crops by background estimation or image analysis. For example, the machine refers to an image of a plant without tomatoes and detects the difference from the acquired image. The machine detects the red video as the difference. The machine stores or searches the data and searches for what the red video is identical or similar to. If it is similar to tomatoes, it is recognized as tomatoes, and if it is similar to strawberries, it is recognized as strawberries.

[0068] Disclosed is a method for recognizing the environment around a machine. In at least one embodiment, the method described anywhere in this specification is utilized. The sensors include those that can acquire data on variables or physical parameters regarding the environment around the machine regardless of their type. As an example, it includes LiDAR, cameras, force sensors, and combinations of one or more of these. The sensors include hygrometers and soil moisture meters. A soil moisture meter is a device that measures the amount of moisture contained in the soil. As a result of the inventors' sincere consideration, in a farm, the environment around the machine varies daily depending on the season and weather. Therefore, when the machine moves within the farm under the same conditions, it cannot be applied to the different environments. For example, in the case of a humanoid robot, it will fall on muddy ground. In a farm, the strength of the footing can be predicted by machines that measure moisture such as hygrometers and soil moisture meters. The machine recognizes the possibility that the ground under its feet is muddy based on the information from the soil moisture meter. This effect was not known at all in the prior art and has novelty and remarkable effects.

[0069] Disclosed is a method for an AI to determine whether farming operations can be performed based on crop information and environmental information. In at least one embodiment, the machine provides crop information to the AI. The crop information includes images of the crops. Further, the machine may be equipped with a refractometer and a hardness meter. The machine recognizes the crops around it, uses these machines on the crops, and obtains information on their sugar content, hardness, and combinations thereof. The refractometer may be of any type as long as it can measure the sugar content. It includes a refractometer and a non-destructive sugar meter. The refractometer calculates the sugar content by measuring the refractive index of light traveling straight through water or air. The non-destructive sugar meter irradiates near-infrared light and measures it with a sensor. It utilizes the property that sugar easily absorbs light of a specific wavelength and measures without damaging the crop. The hardness meter may be of any type as long as it can measure the hardness. A durometer presses against a sample and reads the indicated value. There is also a method of pressing a needle against the object to be measured. As a result of the inventors' sincere consideration, if any of the refractometer, hardness meter, or combinations thereof are used, the machine can sufficiently determine whether the crop is ripe. In the prior art, even if it was known that the color of the crop had changed, the machine could not determine its texture, taste, or softness. A machine equipped with a refractometer and a hardness meter can automatically determine the ripeness of the crop. This effect was not known at all in the prior art and has novelty and remarkable effects. The environmental information includes any information related to meteorology, temperature, humidity, images of the environment, and combinations of one or more of these. For example, the temperature has reached a certain level or above or below, the humidity has reached a certain level or above or below, a typhoon is approaching, it is raining, images of plants (e.g., the plant has turned brown and is withering), and information on combinations of these. Such information is related to the maturity of the crop or takes precedence over information on the maturity of the crop and can be information for determining whether the crop should be harvested. Whether farming operations can be performed may be any farming operation regardless of its form. For example, it includes harvesting the crop, not harvesting it, applying fertilizer, watering, weeding, thinning, and combinations of one or more of these. The AI includes AI trained with supervised learning, reinforcement learning, unsupervised learning, and combinations of one or more of these.For example, learn whether the combinations of information disclosed in this specification should be harvested. For example, a sugar content exceeding a predetermined value and an intensity below a predetermined value can be the conditions for harvesting. Also, if the sugar content is 10% below the predetermined value and the intensity is 10% above the predetermined value, but according to the image of the plant, the plant is withering, it can be the condition for harvesting. The user of the machine can set the conditions for harvesting and perform supervised learning. Even without being given the correct answer, the machine learns the conditions for harvesting based on the data sent from the machine daily, with the reward of harvesting under the condition of the highest sugar content. As a result of the inventor's earnest consideration, by combining the machine for acquiring such data and the AI for learning, agricultural operations can be correctly and efficiently automated. This effect was not known at all in the prior art and has novelty and remarkable effects.

[0070] When it is determined that the AI is operable, a method for generating the operation is disclosed. In at least one embodiment, the machine generates an operation based on the determination of the AI. For example, when the AI determines that a crop should be harvested, the machine harvests that crop.

[0071] The machine includes a humanoid robot. As a result of the inventor's earnest consideration, in agriculture, a humanoid robot may be particularly useful. As a result of the inventor's earnest consideration, it was found that when the machine is a humanoid robot, the convenience is greatly improved. Since the farm is designed to suit a two-legged walking human, a bicycle or a drone may not be able to act satisfactorily. For example, it is difficult to go to a terraced field by bicycle, and it is difficult for a drone to fly into a place where branches are intricate or near the ground. It was found that a two-legged walking robot is optimal as a configuration of a machine for entering such places and any farm and harvesting crops. That is, since a humanoid robot has a movable range and size similar to or similar to that of a human, it can generally surely reach the plants that a human can harvest, and is the most excellent in versatility. Therefore, one of the most preferable forms for providing services is a humanoid robot. This effect was not known at all in the prior art and has novelty and remarkable effects.

[0072] Disclosed is a method for learning operation data related to past generated operations through reinforcement learning and generating adaptive operations for crops targeted by the past operations or for operations or environments similar to or different from the environment in which the past operations were generated. The method described anywhere in this specification is incorporated. The machine learns operation data related to past generated operations through reinforcement learning. For example, when the ground is muddy, the variables of ground strength and friction are different. Suppose the machine loses balance and falls in such a case of different variables. No reward is obtained or it becomes negative. Next, if another motor is operated and it does not fall in the control that shifts the center of gravity of the axle, the reward increases, so that operation is incorporated into the control as an effective one. In this way, adaptive operations are generated for operations or environments similar to or different from the environment in which the past operations were generated. Suppose the machine tries to harvest oranges and accidentally crushes them. In this case, no reward is obtained or it becomes negative. Next, if the strength of the motor is changed and the oranges can be harvested without being crushed, the reward increases, so that operation is incorporated into the control as an effective one. Next year, when harvesting oranges again, if the oranges are crushed in the same old way, further reinforcement learning is performed to harvest the soft oranges of that year without crushing them. In this way, adaptive operations are generated. According to this embodiment, there are at least the convenience and industrial applicability that at least agricultural operations can be automated with high quality.

[0073] Disclosed is a method in which two or more of the above-described machines exist in the same field, and the machines cooperate in operation by communicating the operation or position of one machine in the field. In at least one embodiment, the method described anywhere in this specification is employed. The machine communicates with other machines. When another machine is harvesting a row of crops, the machine harvests a different row of crops. "Two or more machines cooperate in operation" can also be replaced with "two or more machines exist in the same field, and the operation of the machine is changed based on the information obtained by communicating the operation or position of one machine in the field." That is, if the machine changes its own actions based on the information obtained from other machines, it can naturally take coordinated actions. For example, when harvesting a row of crops, when a machine that harvests crops from the front of the same row comes, the action is changed to move to another row so as not to collide with that machine. According to this embodiment, there are the advantages and industrial applicability that farming operations can be efficiently performed using at least two or more machines.

[0074] Disclosed is a method of determining a movement path in a field based on information about the environment around the machine and moving while avoiding obstacles. In at least one embodiment, the method described anywhere in this specification is employed. The obstacles include other machines. The information about the environment around the machine may include fallen trees and puddles. This information is generated from the video acquisition device of the machine, the video acquisition device provided on the farm, or the video acquisition device of other machines. The video acquisition device of other machines includes, for example, a mode in which a drone acquires video of the farm. The machine recognizes obstacles through background estimation and image analysis. The machine determines a movement path in the field based on the information about the obstacles. The machine identifies a route that does not pass through the obstacles in order to go around all the places to walk in the field. As a result of the inventor's earnest consideration, a system combining a humanoid robot for work and a drone for acquiring video is particularly effective. That is, farming work cannot be completed solely by a drone, and a humanoid robot cannot sufficiently obtain information about the environment of the farm. By combining the two, it becomes possible to automatically generate actions adapted to the environment. This effect was not known at all in the prior art and has novelty and remarkable effects.

[0075] Disclosed is a method for a robot to walk. The method described anywhere in this specification is incorporated.

[0076] The embodiments described in this specification can also be implemented as a system.

[0077] The embodiments described in this specification can also be implemented as a program.

[0078] Disclosed is a method for determining the growth state of crops or the presence or absence of diseases by image recognition, and using AI to determine whether to generate operations such as harvesting, fertilizing, pest control, or a combination of one or more of these according to the determination. In at least one embodiment, the machine determines the growth state of the crops. For example, a video acquisition device acquires variables of the pigments of the crops. If the crops are withering, this pigment changes. If the crops are healthy, the pigment changes. Diseases can be determined by comparison with an image of a normal plant. If a ladybug is reflected, it can be seen that there are pests. The machine causes these information to be determined by AI. The AI performs supervised learning by being labeled as correct or incorrect for the actions taken in the past in such a situation. Or, it performs reinforcement learning. The AI determines whether to perform operations such as harvesting, fertilizing, pest control, or a combination of one or more of these. The AI includes an AI that has been subjected to supervised learning or reinforcement learning for the results of combining two or more of these. As a result of the inventor's earnest consideration, as a special circumstance in agriculture, the combination of harvesting, fertilizing, and pest control changes the yield and quality of the crops. Therefore, learning based on two or more variables is effective. This effect was not known at all in the prior art and has novelty and remarkable effects.

[0079] Disclosed is a method for obtaining meteorological data and specifying, by AI, operations to be generated based on meteorological information, environmental information around a machine, and crop information. In at least one embodiment, meteorological data includes data representing the state of the Earth regardless of its form. It includes data representing phenomena observed in the atmosphere and ocean, such as rain, clouds, wind, and waves. The current state of the Earth is being observed worldwide on land, at sea, and from space using various sensors and machines. And starting from the current observation data, the future state of the Earth can be predicted by calculating the time change of the Earth using a supercomputer according to physical laws. This includes these information and information processed based on this information. The meteorological data includes meteorological data covering two or more days. The meteorological data includes meteorological prediction data for the day after tomorrow and later. The machine may obtain meteorological data by itself, or may receive meteorological data transmitted from the outside. As a result of the inventors' sincere consideration, as agricultural-specific circumstances, meteorological information, environmental information around the machine, and crop information interact with each other. Even if it can be determined based on the environmental information around the machine and crop information that fertilization should be carried out, there may be cases where it should be determined based on meteorological information that fertilization should not be carried out. Conversely, even if it can be determined based on crop information and meteorological information that harvesting should be carried out, there may be cases where it should be determined based on the environmental information around the machine that harvesting should not be carried out. In other words, even if machine learning or reinforcement learning is performed using only one or two of these, the actions of the machine may fail due to the presence of other variables, resulting in poor learning efficiency. Thus, by comprehensively learning these three variables, the machine can automatically perform appropriate agricultural actions. This effect was not known at all in the prior art and has novelty and remarkable effects.

[0080] Disclosed is a method for changing the operation of a machine based on the information of a field acquired by a drone. In at least one embodiment, the method described anywhere in this specification is employed. For example, the drone can acquire weather information, environmental information around the machine, crop information, or one or more combinations thereof. The drone is equipped with a hygrometer to measure the humidity of the atmosphere, uses an image acquisition device to recognize the presence of fallen trees in the field, and approaches the crop to measure the sugar content using a refractometer. Based on these variables, the machine changes its behavior. According to this embodiment, there are the convenience and industrial applicability of optimally automating agriculture by emphasizing at least machines with multiple different attributes.

[0081] Disclosed is a method for a machine to communicate and connect with a terminal other than the machine and change the operation of the machine based on a request from the terminal and a judgment by AI. In at least one embodiment, the method described anywhere in this specification is employed.

[0082] Disclosed is a method for a machine equipped with lifting means to recognize the environment around the machine and approach a crop based on crop information and environmental information. In at least one embodiment, the lifting means includes a mechanical mechanism that raises its own coordinates to a higher position regardless of its form, including a stair lift or a platform lift. For example, it includes an elevator. The machine recognizes based on the information obtained by the image acquisition device that the crop to be harvested is above the machine. The machine recognizes that the crop is not located within its movable range. In that case, the machine uses the lifting means to harvest the crop. For example, if the ground is not muddy based on the environmental information, a humanoid robot uses its own lifting means to harvest. If the ground is muddy, it communicates with another machine, a drone, to harvest the crop. The robot is equipped with an arm and a cutting machine, grabs the crop with the arm, and cuts the stem with the cutting machine to harvest the crop. Since the robot is equipped with image acquisition means, it can distinguish and recognize the crop and the stem. According to this embodiment, there are the convenience and industrial applicability of efficiently harvesting at least crops at high positions.

[0083] Disclosed is a method of issuing a voice alert warning that it is in operation by a voice output unit when the approach of a person is detected by a sensor. In at least one embodiment, the machine detects the approach of a person by a sensor or an image acquisition device. When a person approaches to a predetermined distance, the machine issues a voice alert warning that it is in operation by a voice output unit. The voice alert may be any sound regardless of its form. Any sound is sufficient because a person can determine that it is a warning. It may be a stored voice of "Working!", or simply a buzzer. As a result of the inventor's earnest consideration, due to the specific circumstances of the field, the view is blocked by plants, so there is a risk of collision when a person and a machine work intensively. Furthermore, since the machine sprays blades during harvesting and weeding, and toxic chemicals during pest control, the risk is particularly high. In this case, it may be preferable that the machine itself performing the work has a function of issuing an alert. In other embodiments, even if it is not the voice output unit provided in the machine itself performing the work, an alert is issued from the voice output unit of another machine. For example, the earphone worn by a person may be the voice output unit, or the voice output unit provided in the field may be used. This effect was not known at all in the prior art and has novelty and remarkable effects.

[0084] The following discloses an overview of the embodiments described above.

[0085] A machine related to agriculture, recognizes crops based on information obtained from one or more sensors, recognizes the environment around the machine, and based on the crop information and the environmental information, determines whether the operation of the agricultural work is possible by AI, the machine

[0086] The above machine, when AI determines that it is operable, generates the operation, the machine

[0087] The above machine, Learn the operation data related to the generated past operations through reinforcement learning, and generate adaptable operations for crops that were the target of the past operations or for operations or environments that are similar to or different from the environment in which the past operations were generated. Machine.

[0088] An agricultural system, where two or more of the above machines exist in the same field, and two or more machines cooperate to generate operations by communicating the operations or positions of one machine in the field. System

[0089] The above machine, determines the movement path within the field based on the information of the environment around the machine, and moves while avoiding obstacles. Machine

[0090] The above machine, where the machine is a walking robot. Machine

[0091] An agricultural system, where based on the information obtained by the above machine, the AI determines whether an operation is possible, and a working machine that performs each operation receives communication from the machine and executes the operation determined to be possible. System.

[0092] A program for moving the above machine.

[0093] An agricultural machine, which determines the growth state of crops or the presence or absence of diseases through image recognition, and uses AI to determine whether it is necessary to generate operations such as harvesting, fertilizing, pest control, or a combination of one or more of these according to the determination. Machine.

[0094] An agricultural machine, which acquires weather data, Based on meteorological information, environmental information around the machine, and crop information, the AI identifies the operations to be generated. Machine.

[0095] An agricultural system, Based on the information of the field acquired by the drone, Changes the operation of the above-mentioned machine. System.

[0096] The above-mentioned system, The machine communicates and connects with terminals other than the machine itself, Based on the request from the terminal and the judgment by the AI, changes the operation of the machine. Machine.

[0097] An agricultural machine, Equipped with lifting means, Recognizes the environment around the machine, Approaches the crop based on the information of the crop and the information of the environment. Machine.

[0098] The above-mentioned machine, When a human approach is detected by a sensor, The voice output unit issues a voice alert warning that it is in operation. Machine.

[0099] The invention according to the present disclosure only needs to be able to achieve at least one of the above-mentioned effects.

[0100] The terms in this disclosure, including those recited in the claims, can be interpreted in consideration of the descriptions and drawings set forth in the specification, and further, as long as they do not conflict with the suggestions in this disclosure, can be interpreted based on what one or more members of the public have so named, indicated, understood, or practiced, or what is possible, in the past, present, or future. In at least one embodiment, when observing the object or method in question, if one or more members of the public can reasonably understand or recognize that part or all of its configuration is included in the meaning of the terms described in this specification, then, as long as it does not conflict with the suggestions in this disclosure, it can be determined to be included in the meaning of the terms described in this specification. If all of the acts of not implementing all of this embodiment, having others at home or abroad implement a part of it, using the services of others, or having general consumers do so, or combining one or more of these acts, result in implementing all of this embodiment when all the acts are combined, then it is regarded as having implemented this embodiment. Regarding the terms in this specification, each includes the case of using them as the stem of a verb. In at least one embodiment, technical terms, symbols, and signs generally also include those commonly adopted in the relevant technical field.

[0101] As described above, the embodiments listed below, in an embodiment of this disclosure, aspects can be combined with or replaced by one or more of the aspects in another disclosed embodiment, as long as there is no conflict.

[0102] Embodiment 01. Robot tractor In at least one embodiment, the robotic tractor is equipped with a satellite positioning system (GNSS) and an inertial measurement unit, and autonomously travels within the field to perform operations such as tilling, sowing, and harvesting. A plurality of environmental sensors (e.g., LiDAR and cameras) are mounted on the vehicle body and used for obstacle detection and grasping the state of the driving road surface. The control unit generates a path based on high-precision map information and a pre-set work plan, and proceeds with the work while correcting the vehicle's posture and position in real time. Remote monitoring and instructions are possible through a wireless communication module, and automatic stop and notification are performed when an abnormality is detected. Such an autonomous driving agricultural machine can significantly reduce the manual driving work, and the work efficiency is improved by more than 20% compared to the conventional level. Furthermore, stable work is possible regardless of day or night, contributing to shortening the work time and labor saving in agricultural work.

[0103] Embodiment 02. Precision Weeding Robot In at least one embodiment, the precision weeding robot discriminates weeds and crops in real time by using a high-resolution camera and an AI image recognition algorithm, and performs the minimum necessary weeding treatment. The robot platform autonomously travels between the ridges using GPS or RTK positioning functions and moves to a specific weed position with a positional accuracy of several centimeters. As weeding means, configurations including physically pulling out weeds with a small mechanical arm and a nozzle system that sprays chemicals pinpoint are included. Each work head accesses individual plants with an accuracy of several centimeters, and selectively treats only weeds while minimizing the impact on the crops. With this robot, continuous weeding work can be performed in a wide range of fields, and the manual weeding labor can be significantly reduced. Also, due to the precise detection and local treatment by AI, the amount of herbicide used is reduced by nearly 90% compared to the conventional level, contributing to reducing the environmental load and suppressing the chemical impact on agricultural crops.

[0104] Embodiment 03. Fruit and Vegetable Harvesting Robot In at least one embodiment, the fruit and vegetable harvesting robot combines a manipulator-type robot arm and a multi-wavelength camera to automatically identify the ripeness and position of fruits and vegetables and harvest them. It is equipped with an algorithm that evaluates the color, shape, and size of fruits in real time through image processing and determines the ripeness and optimal harvesting time. A dedicated picking hand is attached to the end of the robot arm, which approaches the target fruit at an optimal angle and with proper force control to cut the fruit stalk or grip the fruit for harvesting. While moving on a mobile platform or rail, the robot can harvest hundreds of fruits per hour and can work stably even in high places or at night where it is difficult for humans to reach. By coordinating multiple robots in the field or facility, the harvesting efficiency can be further improved, and quality degradation and waste due to delayed harvesting can be reduced. Such an automatic harvesting technology can reduce the number of personnel required for harvesting work by about 30% and is expected to achieve uniform quality and increased yield (about 10% increase) of the harvested products.

[0105] Embodiment 04. Indoor greenhouse working robot In at least one embodiment, the indoor greenhouse working robot moves along rails or ceiling traveling mechanisms in the greenhouse and automatically monitors, manages, and provides harvesting assistance for cultivation beds. The robot is equipped with an environmental sensing module for measuring temperature, humidity, CO2 concentration, etc., and a high-resolution camera to constantly monitor the growth state and disease symptoms of plants. The control system instructs irrigation and ventilation as needed based on the sensing data and works in conjunction with the climate control system to maintain an optimal cultivation environment. It also has a robot arm and special nozzles and can perform tasks such as targeted spraying on detected pests and assisting in picking crops that have reached the optimal harvesting time. The robot repeatedly patrols a pre-programmed route to achieve frequent inspections and nighttime monitoring that are difficult for humans. This significantly reduces the manpower required for greenhouse management work and contributes to an improvement in the early detection rate of diseases (more than 20% improvement compared to the conventional level) and the stabilization of yields.

[0106] Embodiment 05. Cooperative work of multiple robots In at least one embodiment, in a multi-robot cooperative work system, a plurality of autonomous mobile robots cooperate via a wireless communication network to perform work in a vast field in parallel. Each robot adjusts its working area and role in real time through a central management server or mutual communication, and is equipped with a fail-safe mechanism in which other robots automatically cover for it even when some robots stop due to obstacle detection or battery replacement. Automatically covering means that another robot takes over the work that the stopped robot was performing, including performing the work that is the next step after the step that the robot was performing. For example, it is possible to coordinate processes such as one robot performing tillage while another subsequent robot performs seeding, and the work order and timing are optimized by an algorithm. The robots share sensing data and realize adaptive processing that utilizes information mutually, such as the subsequent robot adjusting the watering amount based on the soil condition information acquired by the preceding robot. By this cooperative operation, the working time can be shortened to less than half compared to the case of sequentially working with a single large machine, and the working efficiency of the entire field is improved dramatically. Also, the flexible scheduling of the robot group improves the machine operation rate, and it is expected to reduce the idle time of the equipment and achieve a cost dispersion effect due to a large number of small robots.

[0107] Embodiment 06. Pesticide spraying by drone In at least one embodiment, the pesticide spraying system using an agricultural drone precisely sprays pesticides and fertilizers from above the farmland by an autonomous flying drone. The drone is equipped with GPS navigation and a terrain following sensor, and while maintaining a constant altitude according to a pre-set flight path, it evenly sprays the entire crop. The spray nozzles are controlled by a pressure sensor and a flow control mechanism, and by automatically adjusting the spray volume according to the flight speed and altitude, it minimizes overlapping spraying and the scattering of the chemical liquid. One drone can cover an area of dozens of hectares per hour, enabling wide-area processing in a shorter time compared to conventional ground spraying. Also, spraying from the air is possible even in wet paddy fields or steep slopes where people cannot enter, contributing to the improvement of the safety of workers and the shortening of working hours. By this system, the optimization of pesticide usage is achieved. By spraying according to the target, the amount of chemical used can be reduced by about 30%, realizing the reduction of the chemical load on the environment and cost reduction.

[0108] Embodiment 07. Drone remote sensing In at least one embodiment, the drone remote sensing system measures the state of crops and farmland from above at high frequency by a drone equipped with a multispectral camera and a thermal infrared camera. The drone autonomously flies over the farmland in a grid pattern, acquires data including not only visible light but also near-infrared and thermal information, and grasps the stress state and moisture status of the crops. The acquired images are transmitted in real time to a ground base station, and early detection of disease spots, diagnosis of nutritional status, yield prediction, etc. are performed by AI analysis. It is possible to monitor dozens of hectares in one flight mission. Compared with satellite data, it has high spatial resolution and temporal resolution, and can detect even minute abnormalities in individual farmlands without missing them. The patrol frequency of the drone can be adjusted according to the weather. For example, by taking pictures several times a week, the progress of pest damage can be continuously tracked, and the appropriate control timing can be determined. By such aerial sensing technology, it becomes possible to find diseases at an early stage that were difficult to detect compared to conventional manual visual inspections, and it is expected to reduce the yield loss by more than 10% by optimizing the control.

[0109] Embodiment 08. Cooperative operation of multiple drones In at least one embodiment, in a multi-drone cooperative operation system, multiple drones fly simultaneously and efficiently monitor and operate on large-scale farmland through role sharing and communication cooperation. Each drone is connected by a common communication protocol and autonomously adjusts collision avoidance and area sharing by sharing each other's positions and planned routes in real time. For example, a leading drone can detect disease spots with a high-resolution camera, and another following drone can precisely spray pesticides at the coordinates. A ground station that oversees the entire drone group monitors the battery and tank levels of each aircraft and conducts mission management such as deploying replacement aircraft as needed. This mechanism optimizes the operation of individual drones, doubling the covered area per unit time compared to single operation, and enabling homogeneous monitoring and spraying in a short time even in large-scale fields. Furthermore, even if some drones malfunction or become detached due to strong winds or the like, the remaining aircraft automatically redistribute the responsible areas, providing high reliability and redundancy for the entire system.

[0110] Embodiment 09. Drone Pollination In at least one embodiment, a drone pollination system artificially performs pollen dissemination using small drones in orchards or greenhouses, promoting stable fruiting even in environments where natural pollination is difficult. The drones are equipped with fine brushes or air blowers, and realize pollination by directly blowing pollen while flying close to the flowers during the flowering period, or by contacting the pistils with a brush attached with pollen. The flight route is planned considering the positions of the flowers and covers the entire field in multiple passes to prevent pollination omission. By detecting the flowering state and position of the flowers through sensors and image recognition and taking an efficient flight pattern only for the open flowers, effective pollination is carried out while suppressing battery consumption. By applying this system to crops such as greenhouse-grown melons that require artificial pollination, the laborious and detailed pollination work by hand can be reduced, and a stable yield can be ensured even when natural pollinators such as bees are insufficient. The introduction of drone pollination is expected to improve the fruiting rate of fruit trees, which is particularly susceptible to natural conditions, and increase the harvest by about 15% compared to the conventional level through reliable pollination at the appropriate timing.

[0111] Embodiment 10. Federated Learning of Agricultural Data In at least one embodiment, federated learning is applied to agricultural data analysis to build a highly accurate machine learning model overall without sharing data collected from multiple farms and devices. Each farm locally holds soil sensor data, weather data, crop growth images, etc., and transmits only the gradients and parameters necessary for learning to the central model on the cloud. The central server updates the global model using the aggregated parameters and distributes the updated model to each farm, enabling each site to utilize a high-performance prediction model without directly accessing the data of other farms. For example, when building a disease detection model using this mechanism, it is possible to achieve model accuracy equivalent to learning data on the order of tens of thousands of images without leaking the image data of each farm to the outside, and the detection accuracy is improved by about 10% compared to the case of learning individually on each farm. Also, this method conforms to the privacy requirements and data regulations of each region and can be extended to other analysis fields such as varietal improvement and yield prediction. Furthermore, by utilizing such federated learning, data-distributed collaborative learning is realized, enabling advanced analysis and decision-making support based on large-scale data while ensuring security and privacy.

[0112] Embodiment 11. Production History Management Using Blockchain In at least one embodiment, a production history management system using blockchain technology records various data from the production to the distribution of agricultural products (such as the history of pesticide spraying during the cultivation period, the harvest date and time, the shipping history, etc.) in a distributed ledger. Each data entry is appended to the blockchain with a timestamp and an electronic signature, and once the information is recorded, it is shared and referenced by all relevant parties in a state that is difficult to tamper with. Producers automatically upload cultivation records from the field management system, and distributors and retailers append temperature management information and inventory status during shipping and transportation in real time, thus forming a complete history for each agricultural product. Consumers and inspection agencies can access the history information on the blockchain within the scope of public permission, and can easily verify the origin certification and organic certification history. With this system, food safety traceability has been significantly improved, and even if a quality problem occurs, the corresponding lot can be identified in seconds and recovery measures can be taken. Furthermore, by improving the transparency of the production history, consumer trust can be enhanced, and economic effects such as improving brand value and promoting transactions at appropriate prices can also be expected.

[0113] Embodiment 12. Data Sharing and Verification by Blockchain In at least one embodiment, the data sharing infrastructure using blockchain securely shares various sensor data and transaction information in the agricultural field among relevant parties and enables verification of data integrity. Sensor nodes (such as soil moisture sensors and weather observation devices) attach digital signatures to measurement data and regularly write it onto the blockchain network, and form a consensus among each node to reduce the risk of data tampering and disappearance. Farmers and advisory service providers, who are data consumers, can refer to the records on the blockchain to verify that the provided data is reliable and utilize it for growth analysis and appropriate agricultural guidance. In addition, by using the smart contract function on the blockchain, it is also possible to realize automatic granting of data access rights under specific conditions and automatic notification to relevant parties when abnormal values are detected. Conventionally, data sharing that required time for inter-organizational cooperation can now be performed in real time, and consistent data reliability is ensured even when the sensor installation entities are different. As a result, data-driven collaboration progresses throughout the entire agricultural IoT ecosystem, and a sustainable information infrastructure that combines convenience and security is constructed.

[0114] Embodiment 13. Smart Contract Automatic Transaction In at least one embodiment, an automated trading system that introduces smart contracts into agricultural transactions automates processes such as the buying and selling of agricultural products and the payment of insurance premiums based on pre-defined contract conditions on the blockchain. For example, in a wholesale contract for fresh vegetables, when the quality inspection data and the shipping quantity meet the predetermined conditions, the smart contract automatically executes the payment and electronically issues the relevant documents. Also, in agricultural insurance linked to weather sensors and satellite data, parameters such as insufficient rainfall or continuous high temperatures over a certain period are set as contract triggers, and when the conditions are met, the insurance premium is immediately paid without human intervention. Since the system operates on a blockchain network, all transaction histories and contract execution logs are stored in an unalterable form and function as objective evidence even in the event of disputes between parties. The introduction of smart contracts significantly reduces the time and cost involved in contract execution, and settlements and insurance premium payments that used to take several days in the past are completed in seconds to minutes. Furthermore, the risk of human error and payment delays is reduced, improving the reliability and efficiency of the entire agricultural supply chain.

[0115] Embodiment 14. AI Farm Management Support Platform In at least one embodiment, the AI agricultural support platform integrates various data collected from the fields (drone images, soil sensor values, weather data, market price information, etc.) and enhances cultivation management decision-making through machine learning. The analysis module on the cloud generates a crop growth prediction model based on past cultivation history and real-time environmental data, and proposes the optimal timing for harvest, fertilization, and irrigation. On the user interface of the platform, field maps, weather forecasts, and alert information are visualized on the dashboard, allowing farm managers to intuitively grasp the field situation from a PC or smartphone. Additionally, it is equipped with an AI chatbot and voice assistant, which can immediately provide appropriate agricultural technology advice and troubleshooting procedures in response to questions from farmers. By introducing this platform, traditional cultivation judgments that relied on experience and intuition become data-based, leading to improved productivity and risk reduction. In fact, in some pilot introductions, the yield has increased by an average of 10%, and a reduction in input resources such as fertilizers and water (about 20% reduction) has also been reported, quantitatively demonstrating the effectiveness of AI-based precision agriculture.

[0116] Embodiment 15. Disease omen detection system In at least one embodiment, the disease early warning detection system utilizes a sensor network deployed in the field and AI analysis to automatically detect early signs of crop diseases and pest damage. It combines multiple detection means such as cameras installed on the leaf surface, pest sensors installed in traps, and sensors that capture abnormal chemical composition changes in the soil to collect patterns that indicate the onset of diseases (e.g., subtle leaf discoloration or detection of pest-attracting pheromones). The aggregated data is analyzed by an AI model on an edge device or in the cloud to identify risk areas at an early stage before the disease spreads and issue alerts to relevant parties. The alerts include the estimated disease name and recommended control measures and are distributed as smartphone notifications or alerts on the farm management system. This system can suppress the initial spread of infections that were previously easily overlooked during visual inspections, and by early control, it is possible to reduce the damaged area by half. Furthermore, by accumulating occurrence history data, it is possible to model the timing and conditions of disease occurrence, which also contributes to formulating preventive measures plans.

[0117] Embodiment 16. Precision irrigation control based on environmental sensing In at least one embodiment, a precision irrigation control system that utilizes environmental sensing technology automatically adjusts the timing and amount of irrigation based on real-time data from soil moisture sensors and weather sensors in the field. The soil moisture sensors are buried at multiple locations in the field, measure the soil water tension and volumetric water content in the root zone, and transmit the data wirelessly. Weather sensors (temperature, humidity, solar radiation, wind speed, etc.) are also deployed around the field and are used in conjunction with estimating evapotranspiration and rainfall prediction. The control unit aggregates this data and controls pumps and valves to maintain the optimal soil moisture range set for each crop growth stage. For example, watering is automatically performed only in sections where dryness is detected, while irrigation is stopped in advance when rainfall is expected. Such decisions are made based on a rule-based or machine learning model. This precision irrigation significantly reduces waste of water resources (saving 20 to 30% compared to the conventional method), prevents nutrient runoff due to over-irrigation, and is expected to increase yields (by several percent to about 10%) by reducing crop stress.

[0118] Embodiment 17. Field weather monitoring and prediction In at least one embodiment, the field weather monitoring system installs high-precision weather observation devices on farmland, collects microclimate data, and uses it for local weather prediction and risk warnings. The sensor nodes measure parameters such as temperature, humidity, air pressure, wind direction and speed, solar radiation, and rainfall, and these real-time data are transmitted to the cloud via a wireless network. The collected data is input into a weather model, and extremely local (e.g., below 1 km mesh) rainfall predictions and signs of frost damage occurrence risks are calculated by machine learning methods using AI. The system notifies these prediction information to the farm management dashboard and mobile apps, and for example, when a frost warning is issued, alerts are automatically generated to prompt countermeasures such as pre-operating frost protection fans and installing covering materials. Also, specific action guidelines corresponding to various risks are presented, such as prompting inspections of drainage facilities for heavy rain predictions and giving instructions for house reinforcement in advance for strong wind predictions. This system greatly extends the response preparation time for local abnormal weather (able to issue warnings 1 to 2 days earlier than before), contributing to reducing crop damage caused by weather disasters and stable production.

[0119] Embodiment 18. Smart greenhouse environment control In at least one embodiment, the smart greenhouse environment control system monitors environmental parameters such as temperature, humidity, CO2 concentration, and light intensity in the greenhouse on a 24-hour basis, and automatically controls air conditioning equipment and irrigation equipment to maintain an optimal cultivation environment. Data from environmental sensing sensors arranged throughout the greenhouse is aggregated in a central control unit, and real-time feedback control is performed based on control algorithms according to preset target environmental conditions and the growth stage of the crop. Specifically, individual controls such as activating ventilation fans and shading curtains when the temperature rises above the target, and operating a dehumidifier when the humidity is too high, are combined. In addition, by considering solar radiation and weather forecast information, advanced control strategies are implemented, such as automatic lighting of supplementary light LEDs during insufficient sunlight and energy-efficient cooling using outdoor air cooling at night. Such integrated environmental control can provide ideal growth conditions for crops throughout the year. For example, in greenhouse cultivation of tomatoes, it has been reported that the yield has increased by more than 10% compared to the conventional method, and the energy consumption has been reduced by 15%. Furthermore, the remote monitoring and operation function of the system improves management efficiency and enables rapid response in the event of an abnormality, contributing to high-quality and stable production.

[0120] Embodiment 19. Precision fertilization system In at least one embodiment, the precision fertilization system is a variable fertilization technology that sprays fertilizers in the required amounts at the required locations based on the soil nutrient map of the field and the growth information of the crops. The content distribution of nitrogen, phosphorus, potassium, etc. in the field is grasped in advance through soil sample analysis or remote sensing, and a fertilization prescription for each section is created on the management software. The automatic fertilization machine (a spraying device mounted on a tractor or a robotic vehicle) travels under GPS guidance and controls the spraying amount in real time according to the prescription data. Specifically, the flow control valve mounted on the machine opens and closes in conjunction with the position information, and adjustments are made such as reducing the input amount in high-fertility areas and increasing it in deficient areas. As a result, while eliminating uneven growth due to over-fertilization or under-fertilization, the total amount of fertilizer used can be reduced, and the load on the environment such as nitrogen outflow can also be reduced. In demonstration experiments, cases have been reported where the introduction of precision fertilization reduced the chemical fertilizer usage by about 15% and maintained a yield equal to or higher than before, and it is expected as a technology that achieves both cost reduction and environmental protection.

[0121] Embodiment 20. Precision seeding system In at least one embodiment, the precision seeding system is a technology that optimizes the seeding density and depth of seeds according to the conditions of the field by an automatic seeder. Based on the pre-created soil fertility map, water permeability characteristics, past yield data, etc., the field is divided into multiple management zones, and the appropriate seeding amount (number of seeds / square meter) and row and plant spacing are calculated for each zone. The automatic seeder sows seeds at the correct position under GPS control, and the seed discharge rate is variably controlled according to the traveling speed by the mechanism of the seeding device. In addition, a depth control mechanism is provided, and the seeding depth is automatically adjusted while using pressure sensor feedback according to the hardness, softness, and moisture content of the soil. Through such precision seeding, the optimal planting density in each zone is ensured, leading to an improvement in the germination rate and a reduction in competition in the early growth stage. As a result, the production efficiency per material can be increased, and effects such as a reduction in seed usage (about 10% reduction) and an increase in yield (about 5% on average) can be expected.

[0122] Embodiment 21. Utilization of satellite remote sensing In at least one embodiment, the satellite remote sensing utilization system incorporates wide-area image data acquired by an Earth observation satellite into agricultural production and uses it for grasping the growth status of crops and environmental monitoring at the regional scale. The NDVI (Normalized Difference Vegetation Index) map generated from the multispectral satellite image visualizes the shades of vegetation for each field, enabling early detection of poorly growing areas and quantitative evaluation of the growth degree. Also, since satellite data is updated relatively frequently, such as on a weekly basis, it is possible to periodically overlook the situation of the entire vast agricultural area and macroscopically evaluate the impact of abnormal weather on crop yields and the supply-demand situation of irrigation water. The system automatically analyzes the received data from the satellite and provides decision-making support at the regional aggregation level, such as notifying the manager of an individual field of a warning (e.g., a tendency of vegetation decline in a specific field) if necessary. By combining satellite remote sensing with ground-based drone sensor data, multi-layered agricultural monitoring that utilizes both wide-area background information that cannot be covered by high-resolution data and local detailed information is realized. This method enables batch monitoring on a scale of several hundred square kilometers, which was previously difficult, and it is expected to quickly grasp the damage range during disasters and improve the accuracy of estimating the total agricultural production volume of the entire region (an accuracy improvement of about 15%).

[0123] Embodiment 22. AR / VR Remote Farm Support In at least one embodiment, a remote farm support system utilizing AR (augmented reality) and VR (virtual reality) technologies enables experts and managers who are not on-site to remotely check the field situation and give instructions. Local workers use AR-compatible smart glasses or smartphones, and field data and work procedure guidance are superimposed in real time on the camera images. Agricultural consultants and technicians in remote locations can visualize 3D models and live videos of the fields in a VR environment and observe and analyze the condition of the crops and the state of the soil as if they were on-site. Through two-way communication, experts can give specific instructions by AR-displaying points and annotations in the local workers' field of vision, or provide real-time advice while viewing the workers' hand-held videos. The introduction of this system makes it possible to provide advanced agricultural knowledge on-site even from geographically distant locations, significantly shortening the time to problem-solving. For example, when a disease occurs, experts can immediately conduct remote diagnosis and countermeasure guidance, so that responses that previously took several days can be completed within a few hours, contributing to the suppression of damage expansion and the maintenance of productivity.

[0124] Embodiment 23. Machine Predictive Maintenance In at least one embodiment, a predictive maintenance system for agricultural machinery attaches various sensors (such as vibration sensors, temperature sensors, and hydraulic sensors) to agricultural machines such as tractors and combines, and detects precursors of failures by constantly monitoring the state data of the equipment. Abnormal vibration and temperature rise patterns in the engine and hydraulic systems are analyzed by an AI model to identify parts that require maintenance before a failure occurs. Telemetry data transmitted from the machine is stored in the cloud, and deviations from the normal baseline are evaluated in real time by a statistical anomaly detection algorithm. When an anomaly is detected, the system sends a warning notification to the maintenance staff and presents specific inspection items and recommended replacement parts. This prevents work interruptions due to sudden machine failures and reduces repair costs and downtime. In fact, in farms where a predictive maintenance system has been introduced, it has been reported that the average operating rate of the machines has improved and the number of failures has decreased by more than 30% compared to the past.

[0125] Embodiment 24. Real-time processing by edge computing In at least one embodiment, edge computing technology is introduced into the agricultural IoT system, and real-time processing is performed near the data collection point to improve the response speed and reliability. The gateway devices and high-performance sensors installed in the field are locally equipped with CPUs and GPUs, and perform preprocessing of data and AI inference before transmitting the data to the cloud. For example, detecting abnormal behavior of cows from the camera images in the cowshed is performed on the edge side, and alert information is transmitted to the cloud only when an abnormality is detected, contributing to the saving of network bandwidth and privacy protection. In addition, the computers mounted on drones and agricultural machines immediately analyze the image data during flight, recognize the weed locations in the field on the spot, and issue weeding instructions, enabling immediate control without worrying about communication delays to the cloud. With the hybrid configuration of the edge and the cloud, flexible system operation is realized, which ensures autonomy through edge processing during normal times and is linked to the cloud during large-scale analysis and model updates. As a result, the efficiency of the entire data processing is improved and the response time is shortened (control feedback within a few seconds), and the robustness of the continuous operation of important functions even during communication failures is ensured.

[0126] Embodiment 25. Communication network for agriculture In at least one embodiment, the agricultural communication network system combines and uses LPWA (Low Power Wide Area) technology and 5G communication to stably connect a wide range of scattered sensor nodes and mobile machines. In a large-scale farmland, an LPWA network such as LoRaWAN or NB-IoT with low power consumption and capable of communicating over several kilometers is established so that fixed-point devices such as soil sensors and weather sensors can transmit data at low cost and for a long period of time through these networks. On the other hand, for automatic agricultural machines and real-time video transmission that require high-speed and low-latency communication, 5G base stations and private LTE networks are installed within the farm to achieve seamless transmission and reception of large-capacity data and stabilize remote control. The sensor data is once aggregated by a gateway device, and a mechanism is adopted to automatically allocate it to an appropriate network path (either via LPWA or via a high-speed network) according to the communication situation. Thereby, even in an environment with limited infrastructure such as a farm, while realizing a high-density IoT device arrangement, the communication cost is suppressed, and the real-time nature of important data is ensured. In an actual smart agriculture demonstration with enhanced communication environment, the loss of sensor data is almost zero, and the remote monitoring response delay of automatic machines is improved to less than half of the conventional level, resulting in a dramatic increase in operational reliability.

[0127] Embodiment 26. Farm Digital Twin In at least one embodiment, the farm digital twin system reproduces the actual farm environment and crop conditions in a virtual space and pre-evaluates the effects of agricultural measures through simulation and data analysis. Based on data such as soil, moisture, weather, and crop growth stages collected from each farm, a virtual farm model is constructed, and dynamic simulations of crop growth and water / nutrient circulation are performed. In the model, various scenarios can be tried, such as adjusting the fertilization amount and irrigation amount, changing the variety, and shifting the planting date back and forth. As a result, growth prediction, yield estimation, and the degree of impact on the environment are output. The simulation results are visualized, and farm managers can formulate an optimal cultivation plan after comparing and considering multiple measure plans. With this digital twin, improvement measures that are time-consuming and costly to experimentally test across the entire farm can be quickly verified in the virtual space, enabling risk-reducing decision-making based on scientific evidence. In ongoing research, examples have been reported where, as a result of optimizing measures through simulation using digital twins for some crops, it was possible to maintain the yield while reducing the water resource usage by 15% compared to the conventional level, demonstrating the effectiveness of this technology.

[0128] Embodiment 27. AI Planting Plan and Market Analysis In at least one embodiment, the planting plan and market analysis system utilizing AI comprehensively analyzes past production volume data, weather forecasts, market supply and demand trends, etc., and supports farmers in optimizing the crop varieties, planting areas, and shipping times for cultivation. The machine learning model has learned the seasonal variations in market prices and the impact of weather on yield and quality for each region, and can, for example, quantitatively propose crops with likely increasing demand in the next season and periods with low cultivation risks. Farmers can consider multiple scenarios presented by the system (e.g., a plan to increase Crop A and decrease Crop B) and make selections in light of their own business goals. Within the system, the expected revenue and expenditure, required material quantities, and labor input amounts are automatically calculated based on the proposed plans, and a function for comparing the economic viability and labor load of each scenario is also implemented. Such support for plan formulation by AI enables farmers to break away from planting plans relying on experience and intuition and make data-backed business decisions. As a result, effects such as reducing the risk of excessive inventory and price slumps due to market fluctuations and improving the profitability (an average profit increase of 5 to 10%) can be expected.

[0129] Embodiment 28. Smart livestock management In at least one embodiment, the smart livestock management system introduces sensors and automation technologies to the livestock farming site to monitor the health status of livestock, optimize the breeding environment, and achieve labor savings. Wearable sensors (such as acceleration sensors and heart rate sensors) attached to cows and pigs are used to obtain biometric information such as feeding and drinking amounts, activity levels, and body temperatures in real time, and AI is used to detect abnormal signs (such as signs of estrus and disease). Temperature, humidity, and harmful gas (such as ammonia) sensors and cameras are arranged in the livestock barn, and the comfort and hygiene status of the animals are monitored through environmental sensing and video analysis. Based on this data, the control system maintains a comfortable environmental range through automatic control of ventilation fans and mist spraying devices, and cooperates with feeding robots and automatic watering devices to supply appropriate feed and water. Furthermore, by introducing automatic milking robots and robot cleaners, labor savings and unmanned operation of milking and cleaning operations are realized. This system improves the accuracy of livestock health management through constant monitoring and automatic control, not only leading to a reduction in mortality and maintenance of production volume through early detection of diseases, but also significantly reducing the labor hours required for breeding management.

[0130] Embodiment 29. AI Diagnosis Support Platform In at least one embodiment, the AI diagnosis support platform analyzes images and sensor data of agricultural crops to automatically diagnose pests and diseases and growth abnormalities, and presents specific countermeasures to farmers. Farmers can take and send photos of crop leaves and fruits through a smartphone app, and an image recognition AI on the cloud determines the disease name and damage level. The AI model has been trained with more than dozens of pest and disease data sets and can identify symptoms of major diseases (such as powdery mildew and downy mildew) and pest damage with an accuracy of over 90%. Along with the diagnosis results, pesticides, organic control methods suitable for the pests and diseases, and the urgency of countermeasures are displayed, and contact information for nearby agricultural guidance agencies and links to relevant technical documents are also provided as needed. In addition, this platform also has the function of analyzing diagnostic data collected from multiple farmers to detect regional disease occurrence trends and new disease cases and issue warnings. With this AI diagnosis support, disease discrimination, which conventionally required consulting experts or took time, can now be done immediately on-site, contributing to preventing the spread of damage and ensuring yields through prompt response.

[0131] Embodiment 30. Vertical Farming Automation System In at least one embodiment, the vertical farming automation system enables high-density cultivation without manual intervention in a multi-layered plant factory (vertical farm) through the integrated control of the cultivation environment and robotics. Each cultivation tray installed on the shelf rack is incorporated with sensors for monitoring temperature, humidity, illuminance, and liquid fertilizer concentration. The central control device automatically adjusts the pumps, fans, intensity of LED lighting, and carbon dioxide supply amount to maintain uniform growth conditions throughout all layers. Also, self-propelled robotic arms and automated guided vehicles (AGVs) are introduced to automatically perform operations from seeding to harvesting, sorting, and packaging. For example, a series of processes such as the harvesting robot identifying and picking leafy vegetables at the appropriate harvesting time using AI image processing and the AGV collecting the harvested products from each shelf and transporting them to the packing area are carried out in cooperation. In this vertical farm, year-round production that is not affected by the outside air or weather is possible, the yield per unit area reaches dozens of times that of open-field cultivation, and the water usage is reduced by more than 90%. Furthermore, significant reduction in labor costs is achieved through production automation, and it is expected to be a next-generation agricultural management model that combines stable supply and high profitability.

[0132] Embodiment 31. In at least one embodiment, an AI-based smart irrigation control system. It is an irrigation control system that combines AI and a sensor network. It collects soil moisture sensors and meteorological data in real time, and a machine learning model calculates the optimal watering timing and amount. Based on the calculation results, it autonomously controls the valves and sprinklers in the field to achieve efficient utilization of water resources and reduction of crop stress.

[0133] Embodiment 32. In at least one embodiment, a group of AI-equipped automatic seeding robots. It is an automatic seeding system in which a group of small seeding robots equipped with AI operate in cooperation. Multiple robots autonomously navigate in the field based on self-position estimation using high-precision GPS and sensors and sow seeds uniformly. Image recognition using deep learning detects seeding omissions and duplications, and by mutually adjusting the routes and operations, efficient seeding and improved germination rate are achieved even in irregular or small-scale fields.

[0134] Embodiment 33. In at least one embodiment, an AI image recognition type autonomous weeding robot. It is an autonomous driving type weeding robot equipped with a high-resolution camera and AI image recognition technology. It discriminates crops and weeds in real time using a deep learning model, and only irradiates weeds with a laser or removes them with a robot arm. This can significantly reduce the use of herbicides while suppressing human labor and accurately controlling weeds in the field.

[0135] Embodiment 34. In at least one embodiment, a pest occurrence prediction AI-linked drone control system. It is a system that analyzes sensor data and meteorological information with machine learning AI to predict in advance the risk of pest occurrence in crops. Only when it is determined that the risk of occurrence is high, the autonomous flying drone is dispatched to the corresponding area, and the minimum necessary amount of pesticide spraying and release of natural enemy insects are precisely carried out. By early prediction and precise control, damage can be prevented, and the amount of pesticide used can be reduced to reduce the environmental impact and improve control efficiency.

[0136] Embodiment 35. In at least one embodiment, an autonomous flying type artificial pollination drone. It is a system that performs artificial pollination of plants by an AI-controlled drone. The drone detects the position of the flowers by the mounted camera and image recognition AI, and moves autonomously in the field or greenhouse. By spraying or blowing the target pollen, the pollen is accurately attached to each flower, and a stable pollination rate and yield can be ensured even in an environment where natural pollination by bees etc. is insufficient.

[0137] Embodiment 36. In at least one embodiment, an AI variety selection and crop rotation plan support system. It is an AI system that analyzes the soil conditions, meteorological data, past production records, etc. of a region as big data and proposes the selection of the optimal crop variety and crop rotation plan. The machine learning model simulates the growth prediction and disease occurrence risk of each crop, and calculates a cropping plan that maximizes the yield and maintains soil fertility for each field. This enables the formulation of a cultivation plan based on scientific grounds without relying on experience, contributing to the improvement of the efficiency and sustainability of agricultural management.

[0138] Embodiment 37. In at least one embodiment, an AI greenhouse environment automatic control system. It is a system in which AI optimally controls the environment inside the greenhouse. It is equipped with sensors such as temperature, humidity, light quantity, and carbon dioxide concentration, and calculates the target environment suitable for the crops in real time based on a growth model based on machine learning. According to the calculation results, it automatically controls ventilation fans, heaters, mist spraying devices, light-shielding curtains, etc., and always optimizes the greenhouse environment in response to changes in day and night and weather. This realizes the maximization of yield and the improvement of energy efficiency while reducing manual fine-tuning.

[0139] Embodiment 38. In at least one embodiment, an AI plant factory automatic management system. It is a system that fully automates the cultivation process in a completely artificial light type plant factory. The environmental sensor and the AI control unit optimize the light intensity, light quality of the lighting, the nutrient concentration of the culture solution, and the carbon dioxide supply amount in real time. On the other hand, automatic transport robots and robotic arms perform each operation from sowing to planting and harvesting unmanned. It enables stable production throughout the year and significant labor savings, and realizes high-efficiency crop production that is not affected by the weather.

[0140] Embodiment 39. In at least one embodiment, an AI harvested product sorting and preprocessing system. It is a system that automatically sorts and performs primary processing on agricultural products after harvesting. The crops flowing on the conveyor are imaged by a camera, and the size, color, shape, and degree of damage are determined by image analysis using deep learning, and sorted according to quality grades. Further, after sorting, preprocessing such as washing, peeling, and trimming is automatically performed by a robotic arm. This enables highly accurate sorting and uniform processing without relying on manual labor, contributing to the improvement of product quality and labor savings.

[0141] Embodiment 40. In at least one embodiment, an agricultural product automatic transport system. It is a transportation system that automates the transportation of harvested products both inside and outside the farm. From the field to the collection point or warehouse, autonomous tractors and AGVs (Automated Guided Vehicles) travel unmanned along the designated route while detecting obstacles with the sensors they are equipped with. The optimal route and vehicle queue are controlled by AI to achieve safe and efficient transportation. This realizes labor saving and speed improvement in the transportation work after harvesting.

[0142] Embodiment 41. In at least one embodiment, a distribution optimization system based on AI supply and demand prediction. It is a platform-type system that optimizes distribution based on the supply and demand prediction of agricultural products. The AI integratively analyzes market demand data, growth sensor information, inventory and price trends, and dynamically adjusts the harvest time, shipment volume, and delivery route. By linking the harvest timing and logistics to eliminate supply-demand imbalances and maintain freshness, it contributes to reducing food loss and maximizing profits. This automates the distribution plan and realizes the improvement of efficiency and profit of the entire value chain from producers and distributors to consumers.

[0143] Embodiment 42. In at least one embodiment, a weather-linked agricultural work plan AI system. It is an AI system that automatically formulates an agricultural work schedule in cooperation with weather data. Based on the weather forecast, the AI calculates the appropriate implementation date and time zone for each work such as sowing, fertilizing, pest control, and harvesting. When extreme weather such as typhoons, heavy rains, and sweltering days is predicted, it proposes countermeasure operations such as pest control and pre-harvest toppling in advance to reduce damage. The plan incorporating weather risks enhances work efficiency and safety and contributes to reducing weather-related losses.

[0144] Embodiment 43. In at least one embodiment, an extreme weather response automatic protection system. It is an automatic protection system for protecting farmland and facilities from abnormal weather. When the occurrence of heavy rain, strong wind, hail, late frost, etc. is detected by various sensors and forecast data, the AI quickly controls the protection device. Specifically, it takes measures such as deploying a windbreak shelter during strong winds, covering crops with an automatic covering device during hail forecasts, and driving a drainage pump during excessive rainfall. These automatic measures minimize crop damage caused by extreme weather and contribute to stable production.

[0145] Embodiment 44. In at least one embodiment, a plant biological information feedback control system. It is a system that monitors the biological information of crops in real time and feeds it back to the cultivation environment. The physiological responses of plants are measured by a stem diameter sensor, sap flow meter, leaf surface potential sensor, etc., and the AI analyzes the data to detect signs of stress and poor growth. According to the detection results, the amount of irrigation water, fertilization amount, temperature adjustment, etc. are automatically controlled, and adjustments are made immediately so that individual plants can grow under optimal environmental conditions. This can correct growth disorders at an early stage and improve yield and quality.

[0146] Embodiment 45. In at least one embodiment, the AI-controlled agricultural work support exoskeleton suit incorporates brushless motors with a peak torque of 30 Nm at the waist, knees, and shoulders, and monitors the operator's posture and joint loads at a 10 ms cycle using an IMU (9-axis inertial measurement unit) and flexible strain sensors. The AI controller learns the motion pattern using a long short-term memory (LSTM) model, and in repetitive tasks such as seedling tray transportation, anticipates the joint trajectory and predictively outputs the required assist torque 0.1 s in advance. The power source is a detachable 48 V lithium-ion battery pack (capacity 600 Wh), ensuring continuous operation for 4 hours in normal mode and allowing for replacement and rapid charging within 15 minutes at a battery station in the field. The suit weighs 9 kg but is equipped with a Peltier-type forced air-cooled backplate, suppressing the rise in the wearer's body surface temperature to within +1.5 °C even in a greenhouse in summer. As a safety mechanism, when overload is detected, the torque is released within 0.05 s, a warning vibration is generated by a fall prevention ratchet brake, and an abnormal log is transmitted to the management terminal via BLE communication. In the demonstration test, the lumbar muscle activity during repeated lifting of a 20 kg container was reduced by 48%, the subjective fatigue score (Borg Scale) per working hour improved by an average of 3 points, and the working duration of elderly workers was extended 1.6 times. Furthermore, by collaborating with the field IoT platform, work data is accumulated in the cloud and can be utilized for optimizing labor allocation during the peak agricultural season and updating personalized assist parameters for the exoskeleton.

[0147] A machine related to agriculture, The machine is a humanoid robot, Acquires operation data related to human agriculture, Learns the operation data by AI, Generates operations based on the learned data, crop information, and information on the environment around the machine or in the field. Machine

[0148] A machine related to agriculture, The machine is a humanoid robot, Acquires operation data related to human agriculture, Learns the operation data by AI, Generating an operation based on the learned data, weather information, environmental information around the machine or in the field, and crop information Machine

[0149] A machine related to agriculture, The machine is a humanoid robot, Acquiring any one or more of crop information, environmental information, and weather information, Requesting the AI to learn based on the acquired information, Generating an operation based on the learned data and the acquired information, Machine

[0150] A machine related to agriculture, judging whether an agricultural operation can be performed by the AI based on crop information or environmental information, The machine is a humanoid robot and generates operations by the AI, Machine

[0151] Regarding the above embodiments, the description of some or all of any one of the embodiments in this specification is incorporated by reference.

[0152] A machine related to agriculture, The machine is movable while in contact with land or a part of a building, Acquiring operation data related to human agriculture, Learning the operation data by the AI, Generating an operation based on the learned data, crop information, and environmental information around the machine or in the field, Machine

[0153] A machine related to agriculture, The machine is movable while in contact with land or a part of a building, Acquiring operation data related to human agriculture, Learning the operation data by the AI, Generating an operation based on the learned data, weather information, environmental information around the machine or in the field, and crop information, Machine

[0154] A machine related to agriculture, The machine is movable while in contact with land or a part of a building, acquires any one or more of crop information, environmental information, and weather information, requests AI to learn based on the acquired information, generates an operation based on the learned data and the acquired information, the machine

[0155] A machine related to agriculture, which determines whether an agricultural operation can be performed by AI based on crop information or environmental information, The machine is movable while in contact with land or a part of a building, and generates an operation by AI, the machine

[0156] Regarding the above embodiments, the description of some or all of any of the embodiments in this specification is incorporated by reference. In at least one embodiment, the machine includes a configuration that is movable on land regardless of its form. Land, regardless of its form, includes land or ground, a part of a building or a structural part, and the floor of a building (referred to as "land etc." in this specification). The machine has at least a part of its components movable in contact with land etc. As an example, it includes a self-propelled vehicle and a humanoid robot. Embodiments where land etc. is in contact with wheels, or land etc. is in contact with the hands or feet of a robot and moves are included. As already described, a structure where a first feature is covered by or in contact with a second feature to be subsequently disclosed may include embodiments where the first feature and the second feature are formed so as to be in direct contact, as well as embodiments where additional features are formed between the first feature and the second feature so that the first feature and the second feature are not in direct contact. That is, it is not necessarily limited to embodiments in contact with natural soil on land such as a farm field. Even in a state where a vinyl sheet (corresponding to an additional feature) is laid on the farm field, it is considered land. For a building fixed to land and constructed, a structure that is not fixed to land but in contact with land (such as a mobile cultivation facility, a tent, a temporary building, etc.), a plant factory, etc., the floor part thereof is considered land. The phrase "movable on land" can be mutually replaced with "movable while in contact with other objects", "movable while in contact with an object in the downward direction of gravity", "land vehicle", "land-based mobility module", "land-use mobility module" as long as there is no contradiction.

[0157] A machine related to agriculture, acquires operation data related to human agriculture, learns the operation data by AI, generates an operation based on the learned data, crop information, and information on the environment around the machine or in the farm field. The machine

[0158] A machine related to agriculture, acquires operation data related to human agriculture, learns the operation data by AI, Generating an operation based on the learned data, weather information, environmental information around the machine or in the field, and crop information Machine

[0159] A machine related to agriculture, Obtaining any one or more of crop information, environmental information, and weather information, Requesting AI to learn based on the obtained information, Generating an operation related to agriculture based on the learned data and the obtained information, Machine

[0160] A machine related to agriculture, judging whether an operation of agricultural work is possible by AI based on crop information or environmental information, Generating an operation by AI, Machine

[0161] Regarding the above embodiments, the description related to part or all of any embodiment in this specification is incorporated by reference.

[0162] The above machine, A machine characterized by comprising an image sensor for obtaining the operation data related to human agriculture.

[0163] The above machine, A machine characterized in that the learning of the operation data by AI is performed using a neural network.

[0164] The above machine, A machine characterized in that the crop information includes the type and growth stage of the crop.

[0165] The above machine, A machine characterized in that the environmental information around the machine or in the field includes the terrain information and weather information of the field.

[0166] The above machine, A machine characterized in that the machine is provided with a moving mechanism for autonomously moving in the field.

[0167] A machine related to agriculture, wherein the machine is a land mobility module, acquires action data related to agricultural operations, and generates operations by artificial intelligence, the machine

[0168] Regarding the above embodiments, the description related to some or all of any of the embodiments in this specification is incorporated by reference. In at least one embodiment, "action data related to agricultural operations" includes human action data, machine operation data, and combinations of one or more of these, regardless of its form. As long as there is no contradiction, "action data" and "operation data" are mutually replaceable.

[0169] As already described, the invention according to the present disclosure only needs to be able to achieve at least one of the above-described effects.

Claims

1. A machine related to agriculture, the machine is a humanoid robot, acquires operation data related to human agriculture, learns the operation data by AI, generates operations based on the learned data, crop information, and information on the environment around the machine or in the field. The machine

2. A machine related to agriculture, the machine is a humanoid robot, acquires operation data related to human agriculture, learns the operation data by AI, generates operations based on the learned data, weather information, information on the environment around the machine or in the field, and crop information. The machine

3. A machine related to agriculture, the machine is a humanoid robot, acquires any one or more of crop information, environmental information, and weather information, requests AI to learn based on the acquired information, generates operations based on the learned data and the acquired information. The machine

4. A machine related to agriculture, which determines whether an agricultural operation can be performed by AI based on crop information or environmental information, the machine is a humanoid robot and generates operations by AI. The machine

5. The machine according to Claim 1, characterized in that it is provided with an image sensor for acquiring the operation data related to human agriculture.

6. The machine according to Claim 1, characterized in that the learning of the operation data by AI is performed using a neural network.

7. The machine according to Claim 1, characterized in that the crop information includes the type and growth stage of the crop.

8. The machine according to Claim 1, characterized in that the information on the environment around the machine or in the field includes the terrain information and weather information of the field.

9. The machine according to Claim 1, characterized in that the machine is provided with a moving mechanism for autonomously moving within the field.