Computer implementation method, system, and computer program product for autonomous roaming robotic devices that dynamically adjust sensors and models to perform actions using artificial intelligence (AI) (dynamic use of artificial intelligence (AI) models in AI-enabled autonomous robotic devices)

Abstract

To provide a computer-implemented method for dynamically using an artificial intelligence (AI) model in an AI enabled robotic device, a system, and a computer program product.SOLUTION: A method of dynamically adjusting, using AI, sensors and models of an autonomous roaming robotic device, includes receiving data regarding an asset at a computer of a roaming robotic device from sensors on the robotic device. The robotic device identifies the asset at a location using the sensors, and the robotic device has instructions, received from a control system, to inspect the location or items at the location. The data is analyzed using the computer of the robotic device. The analysis includes using historical data for the asset. An AI model is loaded using the computer of the robotic device, on the basis of the identification of the asset. The sensor is selected using the computer of the robotic device, for conducting inspection of the asset on the basis of, the analysis of the data and the AI model.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to the use of an artificial intelligence (AI) model in an AI-enabled autonomous roaming robot device, and more particularly, to the use of AI for adaptive sensing and model selection of a roaming edge device.

Background Art

[0002] In one example, a human such as an operator can record or define a mission for a robot, and the robot can execute the mission. In one example, a roaming edge device (RED), such as a robot device, can be used to navigate a location and complete an assigned task. In one example, the device can assist in inspection or maintenance in the manufacturing industry. The device can be given a specific mission for inspection, for example, can be pre-programmed at a specific location to perform the same type of inspection on the same type of asset. For example, the first mission can include the first robot performing a visual inspection of a number of fire extinguishers, and the second mission can include the second robot investigating the sounds audible from the HVAC system on the first floor. In this example, the robot needs to move twice even though the fire extinguishers and the HVAC are on the same floor. Thus, the robot can execute a pre-programmed mission and usually does not change the mission or make a decision on the robot device. Thus, one problem with current robot device systems is the inefficiency associated with the tasks and missions of the robot.

Summary of the Invention

Problems to be Solved by the Invention

[0003] This disclosure recognizes the shortcomings and problems associated with current artificial intelligence (AI)-enabled adaptive navigation technologies for improving the task performance of autonomous roaming robotic devices, and more specifically, for optimizing the sensing capabilities of mobile robotic devices, such as roaming edge devices (REDs). [Means for solving the problem]

[0004] For example, current robotic devices do not offer the flexibility for robotic devices equipped with multiple sensors to perform multiple AI workloads within the same mission or movement. The methods and systems of the present invention can enable a robot to dynamically switch to the use of different sensors as needed and to perform different AI workloads. According to the present invention, a robotic device can decide for itself which sensors to use for inference and which corresponding AI model to use, i.e., it can decide which sensors to use. Thus, the present invention enables a robot to use AI to intelligently decide for itself which sensors to use, i.e., decide which sensors to use, start the selected sensors, and receive data from the selected sensors in the robotic device.

[0005] One aspect of the present invention provides a computer implementation method for an autonomous roaming robot device that dynamically adjusts actions and models for actions using artificial intelligence (AI), comprising receiving data about an asset in the computer of the roaming robot device from one or more sensors of a plurality of sensors on the robot device in response to the identification of an asset at a location using one or more sensors. The robot device has instructions received from a control system to inspect a location or an item at a location. The method includes using the computer of the robot device to analyze the received data and historical data of the asset in order to refer to inspection instructions and inspection history related to the asset. The method includes using the computer of the robot device to select one of the plurality of sensors based on the analysis of the data. The method includes loading an AI model using the computer of the robot device based on the identification of the asset and the analysis of the data, and performing an asset inspection based on the AI ​​model to generate asset inspection data using the selected sensor.

[0006] In a related embodiment, the method further includes analyzing multiple AI models for applicability to an asset, identifying the asset, selecting an AI model from the multiple models based on data analysis and analysis of the multiple AI models, loading the selected AI model using a computer of a robotic device, and using the selected AI model and selected sensors to perform an asset inspection.

[0007] In a related embodiment, the AI ​​model may include an asset inspection protocol.

[0008] In a related embodiment, the method further includes using a computer of a robotic device to select one sensor from a plurality of sensors in order to perform an asset inspection based on an AI model, and using the selected sensor to perform an asset inspection based on the AI ​​model of the asset in order to generate asset inspection data.

[0009] In a related embodiment, the method may include determining an action relating to an asset based on asset inspection data, and communicating the action to a control system.

[0010] In a related aspect, the testing protocol may include the testing type and testing actions specific to that testing type.

[0011] In a related embodiment, the method may include using a computer of a robotic device to analyze asset inspection data obtained from an asset inspection, and determining the next action based on the analysis of the asset inspection data.

[0012] In a related embodiment, the method is to initiate the following action in the robotic device, the following action may further include initiating a second sensor among a plurality of sensors on the robotic device.

[0013] In a related embodiment, the method further includes enabling a third sensor among a plurality of sensors based on the type of asset; loading inputs for an AI model related to the type of asset for the generation of an AI model; capturing inspection data with the third sensor; analyzing the inspection data to determine another action based on the analysis of the asset inspection data; and initiating the following action in a robotic device, the following action including initiating a second sensor among a plurality of sensors on the robotic device.

[0014] In a related embodiment, the method further includes identifying a plurality of assets for inspection by a robotic device; identifying an AI model from a plurality of AI models corresponding to each of the identified plurality of assets; receiving data relating to each of the assets; analyzing the received data relating to each of the assets; selecting each of the sensors relating to the assets; loading each of the AI ​​models relating to the assets; and performing each of the asset inspections relating to the assets.

[0015] In related embodiments, sensor selection is performed by the computer of the robotic device without instructions from a control system regarding the selection.

[0016] In a related embodiment, the robotic device's computer initiates asset inspection based on an inspection protocol derived from an AI model, and the asset inspection performed by the robotic device is in response to the robotic device's computer.

[0017] In a related embodiment, the computer of the robotic device initiates the performance of asset inspection in response to an AI model.

[0018] In a related embodiment, the selection of sensors and the execution of asset inspections are not initiated in response to the control system.

[0019] In a related embodiment, the method further includes: identifying a second asset at a location using one or more sensors from a plurality of sensors of a roaming robot device; receiving data in the robot device's computer from one or more sensors relating to the second asset in response to the identification of the second asset at the location; analyzing the second data using the computer, the analysis of which includes using historical data of the second asset; generating another AI model based on the identification of the second asset using the analysis of the second data; analyzing the other AI model to generate a second inspection protocol for the second asset; selecting a second sensor from the plurality of sensors to initiate an inspection of the second asset based on the second inspection protocol; performing a second asset inspection using the selected second sensor to generate second asset inspection data; determining a second action relating to the second asset based on the second asset inspection data; and communicating the second action to a control system.

[0020] In a related aspect, the actions include alerts regarding assets.

[0021] In a related embodiment, the action includes communication to a person's device.

[0022] In a related aspect, the actions include asset maintenance activities.

[0023] In another aspect of the present invention, a system for an autonomous roaming robot device that dynamically adjusts sensors and models for performing actions using artificial intelligence (AI) may include a computer system. The computer system may include a computer processor, a computer-readable storage medium, and program instructions stored on the computer-readable storage medium. The program instructions are executable by the processor to cause the computer system to perform a function, the function being to receive data about an asset in the computer of the roaming robot device from one or more sensors of a plurality of sensors on the robot device in response to the identification of an asset at a location using one or more sensors, wherein the robot device has instructions received from a control system to inspect a location or an item at a location; to analyze the received data and asset history data using the computer of the robot device to refer to inspection instructions and inspection history related to the asset; to select one of the plurality of sensors based on the analysis of the data using the computer of the robot device; to load an AI model using the computer of the robot device based on the identification of the asset and the analysis of the data; and to perform an asset inspection based on the AI ​​model to generate asset inspection data using the selected sensor.

[0024] In another aspect according to the present invention, a computer program product for an autonomous roaming robot device that dynamically adjusts sensors and models for performing actions using artificial intelligence (AI) can include a computer-readable storage medium having program instructions implemented therein. The program instructions are executable by a computer to cause the computer to perform functions, and the functions include receiving, from one or more of a plurality of sensors on the robot device, data regarding an asset in a computer of the roaming robot device in response to identification of the asset at a location where one or more of the sensors are used, the robot device having an instruction received from a control system for inspecting the location or an item at the location; analyzing the received data and historical data of the asset using a computer of the robot device to reference inspection instructions and inspection history related to the asset; selecting one of the plurality of sensors using a computer of the robot device based on the analysis of the data; loading an AI model using a computer of the robot device based on the identification of the asset and the analysis of the data; and performing an asset inspection based on the AI model to generate asset inspection data using the selected sensor.

[0025] The above and other objects, features, and advantages of the present invention will become apparent in the exemplary embodiments of the present invention detailed below. These embodiments are to be read with reference to the accompanying drawings. Note that the illustrated contents are made easy to understand in order to facilitate understanding of the present invention by those skilled in the art in conjunction with the detailed description, and thus various features in the drawings are not to scale. The description of the drawings is as follows.

Brief Description of the Drawings

[0026] [Figure 1] FIG. 1 is a schematic block diagram showing an overview of a system, features or components of a system, and methodology of an autonomous roaming robot device that dynamically adjusts sensors and models for performing actions using artificial intelligence (AI) according to an embodiment of the present disclosure. [Figure 2] A flowchart showing a method for a self - roaming robot device to dynamically adjust sensors and models for performing actions using artificial intelligence (AI) including an AI model and data analysis, which is implemented using the system shown in FIG. 1 according to an embodiment of the present disclosure. [Figure 3] A functional schematic block diagram showing a series of operations and functional methodologies for explaining the functional features of the present disclosure related to the embodiment shown in the figure. It is a figure that can be implemented for a self - roaming robot device that dynamically adjusts sensors and models for performing actions using artificial intelligence (AI) including an AI model and data analysis, at least partially in cooperation with the system shown in FIG. 1. [Figure 4A] A flowchart showing another method for a self - roaming robot device to dynamically adjust sensors and models for performing actions using artificial intelligence (AI) including an AI model and data analysis, following from the flowchart of FIG. 2. [Figure 4B] A flowchart showing another method for a self - roaming robot device to dynamically adjust sensors and models for performing actions using artificial intelligence (AI) including an AI model and data analysis, following from the flowchart of FIG. 2. [Figure 5] A flowchart showing another method for a self - roaming robot device to dynamically adjust sensors and models for performing actions using artificial intelligence (AI) including an AI model and data analysis according to an embodiment of the present invention. [Figure 6] A block diagram showing another system for a self - roaming robot device to dynamically adjust sensors and models for performing actions using artificial intelligence (AI) including an AI model and data analysis according to an embodiment of the present invention. [Figure 7]This block diagram shows an embodiment of the present invention, in which an autonomous roaming robot device dynamically adjusts sensors and models for performing actions using artificial intelligence (AI), including AI models and data analysis. [Figure 8] This is a schematic block diagram showing a computer system according to an embodiment of the present disclosure, which can be incorporated in whole or in part into one or more computers or devices shown in Figure 1 and which cooperates with the systems and methods shown in the figure. [Figure 9] This is a schematic block diagram of a system depicting system components interconnected using a bus. These are components for use in all or part of the embodiments of the present disclosure, according to one or more embodiments of the present disclosure. [Figure 10] This is a block diagram showing a cloud computing environment according to an embodiment of the present invention. [Figure 11] This is a block diagram showing an abstraction model layer according to an embodiment of the present invention. [Modes for carrying out the invention]

[0027] The following description, with reference to the accompanying drawings, is provided to assist in a comprehensive understanding of the exemplary embodiments of the invention as defined by the claims and their equivalents. The following description includes various specific details to assist in such understanding, but these should be considered merely illustrative and for clarity and brevity. Therefore, as will be apparent to those skilled in the art, various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Furthermore, descriptions of well-known functions and configurations may be omitted.

[0028] The terms and phrases used in the following description and claims are not limited to their dictionary meanings, but are used solely to enable a clear and consistent understanding of the invention. Accordingly, as will be apparent to those skilled in the art, the exemplary embodiments of the invention described below are for illustrative purposes only and are not intended to limit the invention as defined by the appended claims and their equivalents.

[0029] The singular forms "a," "an," and "the" include plural references unless the context explicitly states otherwise. Therefore, for example, the reference "a component surface" includes references to one or more such surfaces unless the context explicitly states otherwise.

[0030] The embodiments and figures of this disclosure may have components identical or similar to those of other embodiments. Such figures and descriptive text illustrate further examples and embodiments of this disclosure.

[0031] Referring to Figures 1, 2, and 3, according to embodiments of the present disclosure, a computer implementation method 200 for optimizing the sensing capabilities of a roaming robotic device (or robot) using artificial intelligence (AI) includes the features described below. Embodiments of the present disclosure include operational actions or procedures or both. The computer implementation method 200 includes a set of operational blocks for implementing embodiments of the present disclosure, which may include the system shown in Figure 1. Operational blocks of the methods and systems of the present disclosure may include techniques, mechanisms, modules, etc., for implementing the functionality of the operations of the present disclosure.

[0032] Method 200 includes identifying an asset 150 at location 140 using one or more sensors 144 of a plurality of sensors on a roaming robot device 148, as in block 204. The robot device may include a computer 131 having AI capabilities for generating computer models, and the robot device has instructions 308 for inspecting locations or items at locations, received from a control system 170 that communicates with the robot.

[0033] Method 200 includes, in response to the identification 304 of asset 150 at a location using one or more sensors, such as in block 208, receiving data 312 about asset 150 from one or more sensors 144 of a plurality of sensors on the robotic device in the computer 131 of the roaming robotic device 148.

[0034] The method, as shown in block 212, includes using the computer of the robotic device to analyze received data 312 and historical data 314 concerning assets in order to refer to the inspection history of the relevant inspection instructions and assets. Such historical data can be stored in the knowledge corpus 196.

[0035] The method includes, as in block 216, using the computer of the robotic device to select one sensor 144 from among several sensors based on data analysis.

[0036] The method includes loading the AI ​​model 146 using the computer of the robotic device based on asset identification and data analysis, as shown in block 220.

[0037] If the method is determined to be unacceptable in block 224, the method returns to block 212. If the method is determined to be acceptable in block 224, the method continues to block 228.

[0038] The method includes performing an AI model-based action 350, such as an asset inspection, using selected sensors to generate asset inspection data 352, as shown in block 228. In one example, the method may transmit the asset inspection data 354 to a control system.

[0039] Referring to Figure 4A, in another embodiment of the present disclosure, Method 400, which follows Block 220 of Method 200 shown in Figure 2, includes analyzing multiple AI models for applicability to an asset, as in Block 404. The Method includes selecting multiple AI models based on asset identification, data analysis, and analysis of the multiple AI models, as in Block 406. The Method includes loading the selected AI models using a computer of a robotic device, as in Block 408, and performing an asset inspection using the selected AI models and selected sensors, as in Block 410. The Method continues to Block 212 of Method 200.

[0040] In another example, the AI ​​model includes an inspection protocol for an asset. In yet another example, the method may include using the computer of a robotic device to select one sensor from several sensors in order to perform an inspection of an asset based on the AI ​​model, and performing the asset inspection using the selected sensor to generate asset inspection data based on the AI ​​model for the asset. In yet another example, the method may include determining an action on the asset based on the asset inspection data and communicating the action to a control system. In yet another example, the inspection protocol includes an inspection type and an inspection action specific to the inspection type. In yet another embodiment, the method may include loading relevant AI model inputs for an identified asset in order to generate an AI model or simulation for use by a robot.

[0041] In another embodiment, the method includes analyzing asset inspection data from an asset inspection using a computer in a robotic device, and determining the next action based on the analysis of the asset inspection data. The method may also include initiating the next action in the robotic device, the next action may include a second sensor among a plurality of sensors on the robotic device. In one example, the method includes analyzing asset inspection data from an asset inspection, determining the next action based on the analysis of the asset inspection data, and communicating the next action to a control system.

[0042] In another embodiment, the method includes enabling a third sensor among a plurality of sensors based on the type of asset. The method may include loading relevant AI model inputs for the asset type for the generation of an AI model and capturing inspection data with the third sensor. The method may include analyzing the inspection data to determine other actions based on the analysis of the asset inspection data. The method may include initiating the following action on a robotic device, the following action may include a second sensor among a plurality of sensors on the robotic device.

[0043] Referring to Figure 4B, in another method 450 of the present disclosure, method 450 continues from block 204 of method 200 shown in Figure 2, and the method includes identifying a plurality of assets for inspection by a robotic device, as in block 454. Method 450 includes identifying an AI model from a plurality of AI models corresponding to each of the identified plurality of assets, as in block 456. Method 450 includes receiving data for each of the assets, as in block 458, and analyzing the received data for each of the assets, as in block 460. The method includes selecting a sensor for each of the assets, as in block 462. The method further includes loading an AI model for each of the assets, as in block 464, and performing an asset inspection for each of the assets, as in block 466.

[0044] The method may include the selection of sensors being performed by the computer of the robotic device without instructions from a control system regarding the selection.

[0045] The method may include the robotic device's computer initiating an asset inspection based on an inspection protocol derived from an AI model, and the robotic device responding to the computer's asset inspection.

[0046] The method may include the robotic device's computer initiating the performance of asset inspection in response to an AI model. The method may also include preventing the selection of sensors and the performance of asset inspection from starting in response to a control system.

[0047] The method may further include identifying a second asset at a location using one or more sensors from a plurality of sensors of a roaming robot device. In response to the identification of the second asset at a location, the method may receive data from one or more sensors relating to the second asset on the robot device's computer. The method may use the computer to analyze the second data, the analysis of which may include using historical data relating to the second asset. The method may use the analysis of the second data to generate another AI model based on the identification of the second asset. The method may analyze the other AI model to generate a second inspection protocol for the second asset. The method may select a second sensor from a plurality of sensors to initiate an inspection of the second asset based on the second inspection protocol. The method may perform a second asset inspection using the selected second sensor to generate second asset inspection data. Based on the second asset inspection data, the method may determine a second action relating to the second asset and communicate the second action to a control system.

[0048] In one example, the action includes an alert about an asset. In another example, the action includes communication with a person's device. In yet another example, the action includes maintenance activities for an asset.

[0049] Computer 131 may be integrated with or communicate with the robotic device 148 in the apparatus 130. Computer 190, located away from the apparatus 148, may communicate electronically with computer 172, in whole or in part, as part of the control system 170. The control system may include computer 172 having a computer-readable storage medium 173 capable of storing one or more programs 174, and a processor 175 for executing program instructions. The control system may also include a storage medium that may include registration or account data 182, or both 182, and a profile 183 of a user or entity (such entities may include robotic entities) as part of a user account 181. The user account 181 may be stored in the storage medium 180, which is part of the control system 170. The user account 181 may include registration and account data 182 and a user profile 183. The control system may also include computer 172 having a computer-readable storage medium 173 capable of storing programs or code embedded on the storage medium. The program code may be executed by the processor 175. Computer 172 can communicate with database 176. The control system 170 may also include database 176 for storing all or some of the data described above, as well as other data.

[0050] The control system may also communicate with a computer system 190 which may include a learning engine / module 192 and a knowledge corpus or database 196. The computer system 190 may also communicate with the computer 131 of the device 130 and may be remote from the user device 130. In another example, the computer system 190 may be all or part of the control system, or all or part of the device 130. As with other components of system 100, the description of the computer system 190 is provided as an example in this disclosure.

[0051] A new or different AI (artificial intelligence) ecosystem, or a technology / communication or IT (information technology) ecosystem, may include a local communication network 152 that can communicate with a communication network 160. System 100 may include a learning engine / module 192 that is at least part of a control system or can communicate with a control system, for generating a model or learning model. For example, the learning model may model a workflow in a new AI or IT ecosystem for a machine / device in the new ecosystem.

[0052] In another example, computer 131 may be part of device 130. The computer may include a processor 132 and a computer-readable storage medium 134, and may, in one example, store an application 135 that can implement all or part of the method of the disclosure. The application may include all or part of instructions for carrying out the method of the disclosure, which are implemented in code and stored in the computer-readable storage medium. Device 148 may include a display. Device 148 may, in whole or in part, operate in conjunction with a remote server via a communication network 160, such as the Internet.

[0053] The method includes analyzing the received data 340 in response to receiving data from a robotic device at a location, such as in block 208, using a control system for determining when the received data meets a threshold 344 for determining the quality of the data 346.

[0054] The method includes an analysis, as shown in block 212, which involves generating a model 346 based on received data, the model including a vector representation of the input detected by the sensor array 144 at location, and the input being at least a portion of the received data. The model can also be generated by an AI system, such as the output of at least a portion of an AI system analysis using machine learning.

[0055] The method includes, as in block 220, in response to the data received in the control system not meeting a threshold for determining quality, the robotic device communicating with a cloud server, such as a remote server 152, using cloud communication 150 to collaborate in updating a policy 350 to select a navigation action 354, and the cloud server communicating with the robot at location.

[0056] In another example, a cloud server that can or communicates with a robot can increase the ability to communicate with the robot in a location compared to a control system. In yet another example, the method could include receiving data from the robot into a cloud system and the cloud system determining the received data as meeting a threshold for determining the quality of the data.

[0057] For example, historical data collected from sensors, mobile robots, and machines can be inserted as part of the analysis of incoming data, including data from a knowledge corpus and historical database 196.

[0058] In one example, the robotic device could be a roaming edge device (RED) located at the end of the communication line for roaming edge devices in a given location. In another example, the robotic device could be at least semi-autonomous, and could perform tasks initiated by the robotic device without communication for the tasks from a control system.

[0059] In another example, a task could be initiated by a robotic device, and this might involve a computer local to the robotic device communicating and collaborating with a cloud server that provides updated policies. The computer local to the robotic device can initiate tasks based on the updated policies, and the robotic device can execute tasks in response to the computer local to the robotic device.

[0060] In another example, a computer local to the robotic device may initiate a task using AI analysis of data provided by a sensor array at the location, and the sensor array may include environmental data at the location. In another example, the task is not initiated in response to a control system. In another example, the environmental data may include environmental conditions. In yet another example, the threshold for determining quality includes an acceptable level of measured electronic noise with respect to quality, thereby, if the received data exceeds the threshold, the received data is unacceptable with respect to quality. In yet another example, the location in which the robotic device is operating may have low-quality electronic radio communication capabilities, e.g., suboptimal electronic radio communication capabilities.

[0061] In another example, cloud servers can enhance communication capabilities with robots located on-site compared to control systems.

[0062] In another example, the method involves receiving data from a robot to a cloud system, where the received data may meet a threshold for determining data quality.

[0063] Referring to Figure 4A, in another embodiment of the present disclosure, Method 400 can continue from block 220 of Method 200 shown in Figure 2, and Method 400 includes, as in block 404, initiating a task by the robotic device, which includes the local computer of the robotic device communicating and cooperating with a cloud server to bring up an updated policy.

[0064] Method 400 includes, as in block 406, using a computer local to the robotic device to initiate a task based on an updated policy. The method also includes, as in block 408, having the robotic device perform a task in response to the computer local to the robotic device.

[0065] Referring to Figure 4B, in another embodiment of the present disclosure, Method 450 can continue from block 220 of Method 200 shown in Figure 2, and Method 450 includes updating a model using a computer, the updated model including updating received data as in block 454. Method 450 includes updating the analysis of the data as in block 456. Method 450 includes secondly communicating with a cloud server to cooperate on another update of the policy for selecting a navigation action in response that the updated received data does not meet a threshold for determining quality, as in block 458. The method may further include iteratively updating the updated notification based on detecting changes in the parameters of the event.

[0066] <Other embodiments and examples> Referring to Figure 1, the device 130, which may also be called a user device or administrator device, includes a computer 131 having a processor 132 and a storage medium 134 in which an application 135 may be stored. The application can implement features of the method of this disclosure as instructions. A user can use the device 130 to connect to the learning engine 150. The device 130 includes the computer 131 and a display or monitor 138. The application 135 can implement the method of this disclosure and may be stored in the computer-readable storage medium 134. The device 130 may further include a processor 132 for running the application / software 135. The device 130 can communicate with a communication network 160, for example, the Internet.

[0067] User device 130 is understood to represent a similar device that may be for another user, as such a device may include a mobile device, a smart device, a laptop computer, etc.

[0068] In one example, the system of the present disclosure may include a control system 170 that communicates with a user device 130 via a communication network 160. The control system may incorporate all or part of an application or software for carrying out the method of the present disclosure. The control system may include a computer-readable storage medium 180 that can store account data or registration data or both 182. A user profile 183 is part of the account data and can be stored in the storage medium 180. The control system may include a computer 172 having a computer-readable storage medium 173 and a software program 174 stored therein. A processor 175 can be used to execute or implement instructions for the software program. The control system may also include a database 176.

[0069] In other examples and embodiments, profiles may be stored for entities such as users, participants, operators, human operators, or robotic devices. Such profiles can provide data and delivery history about users for analysis. In one example, a user may register or create an account using a control system 170 that can include one or more profiles 183 as part of registration or account data 182 or both. Registration can include a profile for each user with personalized data. For example, a user may register using a website via a computer and a GUI (Graphical User Interface) interface. Registration or account data 182 can include a profile 183 for an account 181 for each user. Such accounts can be stored on the control system 170, or a database 176 can be used for data storage. Users and associated accounts can refer to, for example, a person, or an entity, or a corporate entity, or a corporate department, or another machine such as an entity for automation, such as a system that uses artificial intelligence in whole or in part.

[0070] Furthermore, the methods and systems are discussed with reference to Figure 3, which is a functional system 300 including components and operations for embodiments of the present disclosure, and is used herein for reference when describing the operational steps of the methods and systems of the present disclosure. Furthermore, the functional system 300 according to embodiments of the present disclosure depicts the functional operations illustrating embodiments discussed herein.

[0071] Referring to Figure 3, in one embodiment of the present disclosure, System 300 may be used to identify event-related objects for use with respect to events by utilizing networked computer system resources. In Figure 3, similar components may have the same reference numerals as System 100 shown in Figure 1, and System 300 may include, or operate in cooperation with, computer implementation methods as shown in Figures 1 and 2.

[0072] <Other embodiments and examples> Referring generally to Figure 5, in one embodiment of the present disclosure, the system and method 500 may provide flexibility for a robotic device (also called a robot) equipped with multiple sensors to perform multiple AI workloads within the same movement. The disclosure may include a method that enables the robot to dynamically switch to use different sensors and perform different AI workloads as needed. The robot may independently determine which sensors and corresponding AI models to use for reasoning (e.g., procedures, instructions). Thus, the methods and systems of the present disclosure may include using an AI-enabled robotic device to perform a mission using different sensors and associated AI models, and providing an intelligent robot that can determine which sensors to use by itself dynamically adjusting to a target-rich environment, e.g., assets or items. Therefore, the robot can dynamically adjust to a target-rich environment and is not limited to pre-programmed missions or tasks with a limited range of data capture.

[0073] In embodiments of this disclosure, the robot is capable of acting independently without a predefined mission, for example, by locally determining an action plan, or determining or both actions the robot should take in detection and information gathering, and by initiating an action plan. In this way, the robot is autonomous. As an example, the robot has the ability to detect nearby objects and can identify whether those objects are assets / equipment that require maintenance by querying historical data in an asset catalog and finding out what inspections have been performed in the past. Based on the inspection results, the robot can take appropriate follow-up actions. Therefore, there is no need for a human operator to tell the robot what mission to perform.

[0074] For example, robots have the ability to load and execute multiple AI models on their own, without a predetermined mission set by a human operator.

[0075] In another example, embodiments of the present disclosure may include a robotic device that includes multiple sensors mounted on the robot, such as a PTZ (pan, tilt, zoom) camera, an infrared camera, a LiDAR camera, and a microphone. A GPU (Graphics Processing Unit) payload server has computing capabilities. The payload server can house multiple AI models, such as a visual inspection model, an acoustic inspection model, a thermal inspection model, and a time series model. The payload server can also house a program that helps the robot determine in real time which sensors to use and which AI models to run. The program may include components such as: an inbound component that captures data from the robot's sensors; a preprocessing component that processes the data as needed before sending it to the AI ​​models; an AI workload component that includes various AI models and libraries necessary to run models such as a visual inspection model, an acoustic inspection model, a thermal inspection model, or time series analysis; a postprocessing component that processes the inference results from the AI ​​models in a desired format; an outbound component that takes appropriate alerts or actions based on the inference results, for example, to send alerts to a human; and an orchestration component that provides basic operational logic to help the robot determine which sensors and AI models to use.

[0076] More specifically, referring to Figure 5, in one example, the methods and systems according to the present disclosure may include a robot or robotic device operating on a manufacturing floor. Method 500 includes, as in block 504, the robot performing a random walk or being mobile on a manufacturing floor.

[0077] Method 500, shown in Figure 5, involves a robot scanning assets in the periphery of the manufacturing floor, as shown in block 508. For example, the robot may take photographs with a camera while on the manufacturing floor, as shown in block 508. For example, the robot may be moving by walking or by other means such as rolling.

[0078] Method 500 may include the robot identifying objects within a surrounding area, as in block 512. In one example, the robot may have an object recognition model. Through object recognition, the robot identifies assets in the surrounding area. For example, a manufacturing floor may include an electrical transformer, fire extinguishers and HVAC units, two people (e.g., human operators or manufacturing personnel), a table and two chairs. In another embodiment, the robot may discover its own location relative to a sitemap. If the sitemap includes the locations of assets, the robot can easily communicate nearby assets without using an object recognition model. Humans are not assets / equipment, so the robot can exclude them.

[0079] The method involves searching for objects in enterprise asset management (EAM) software, as shown in block 516. For example, a robot can search for a maintenance list from an enterprise asset management system.

[0080] The method includes determining in block 520 whether the asset is on the maintenance list. If the asset is not on the maintenance list, the method may proceed to add the asset to the review list, as in block 532, and then to notify a human operator in block 542. If the asset is on the maintenance list in block 520, the method may search for past AI tasks in block 524. The method may then proceed to enable selected (one or more) sensors, as in block 526, and load the corresponding (one or more) AI models in block 528.

[0081] For example, a robot can identify asset objects (transformers, fire extinguishers, HVAC systems) from a maintenance list. For each asset near the robot, it can query historical data in the asset management system to find out what types of inspections have been performed on nearby assets. For instance, it might find that fire extinguishers have undergone visual inspections, transformers have undergone thermal inspections, and HVAC systems have undergone acoustic inspections in the past.

[0082] The method may include performing an AI task, as in block 536. In one example, the method may include a robot performing an AI-enabled task, such as inspection. For example, for each asset near the robot, the robot may perform the correct inspection based on historical inspections. In one example, the robot may enable the correct sensors, load the correct AI model at runtime if it differs from the one loaded into the robot, capture data with the sensors, perform inference with the selected AI model, capture the inference results of the inspection, and generate alerts as needed.

[0083] For example, when an asset is not listed in the maintenance list of the asset catalog (block 520), the robot can add the asset to a temporary list, as in block 532, and the robot can later notify a human operator of these new assets (as in block 542).

[0084] Method 500 includes generating an action 540 which may include activating a sensor such as a camera and capturing data such as an image. If there is no further action in block 540, the method may notify a human operator 542. If there is a further action in block 540, the method may record the inferred result, as in block 544.

[0085] For example, the method could include the robot switching to a different sensor and AI model as needed while inspecting nearby assets. In situations where different types of inspections are performed on the same asset, for instance, HVAC systems have undergone visual inspections for the past three years, while acoustic inspections were performed last year, the robot could compare the results of different AI models to determine which AI model performs better / is more accurate. The robot would then select the sensor and AI model that performs best for that asset. The robot could continue to move around, such as by walking, and continue inspecting nearby assets until it needs to recharge its battery.

[0086] The method may include proceeding to determine whether the battery level is acceptable, as in block 548. If the battery level is acceptable in block 548, the method may return to block 504. If the battery level is not acceptable in block 548, the robot may return to the charging station in block 550 to charge its battery.

[0087] Referring generally to Figures 6 and 7, the system 600 according to this disclosure includes a robot control system 604 which includes a robot 606 that can provide a payload or collect data using sensors or devices 608, and a computer-readable storage medium 610 having software 612 embedded therein for executing programming instructions for the robot. The system 604 includes a graphics processing unit (GPU) 614 and a central processing unit (CPU) 616. Devices 608 include a robot arm 620, a camera 622, a LiDAR (light detection and ranging) 624, a graphics system processor (GSP) 626, and a camera and infrared (IR) / thermal imaging system 628. Infrared light can be used to illuminate a region of interest.

[0088] The user 630 of the robotic device may include an operator 632, a production planner 634, a safety operator 636, an operations manager 638, or an original device manager 640. A cognitive solution 645 using cognitive analytics allows system 600 to provide a solution using the components described herein. The enterprise system 650 includes an asset management component 652, a maintenance management component 654, and an enterprise resource management (ERP) component 656. System 600 includes an automation system 660 and an external system 664. The automation system may include a building automation system (BAS), a building management system (BMD), or a building information modeling (BIM). The external system may include a weather system or a mapping system.

[0089] Components for System 600 may also include a catalog of assets held in the asset management system. For each asset, the management system may include historical data of the AI ​​pipeline / task of the inspection, defining which (one or more) sensors and (one or more) AI models were used, as well as follow-up actions (such as creating alerts or work orders). The robot may be equipped with multiple sensors, a payload server, multiple AI models, and a Smart Edge solution as described above. The AI ​​model training environment may include a development environment for data scientists to create different AI models before they are deployed on the edge side (i.e., on the robot). Wi-Fi connectivity may allow the robot to query the asset management system for asset information and historical AI tasks. In another embodiment, the robot has the ability to infer the same type of asset applied with the same type of (one or more) machine learning models and (one or more) sensors, so that it can be deployed in a new facility to perform inspections on its own without a predefined mission by a human operator.

[0090] In another example provided by this disclosure, the management system 700 may include an application manager 704 within a cloud computing environment 702 that includes a UI (user interface) 706, an Agbot (agricultural robot) 708, and an exchange 710, an MMS (multimedia messaging service) 712, and an SDO (standards development organization) 714. A field engineer 720 may access the UI 706 to register a robot. A developer 728 may define policies and services for the robot. The developer may use a push container to record data 724 in a registry in a database. A location, for example, a premises 730 on which a robot operates, may include an application 740 stored in the robot 765 and an application that receives input from the application manager 704. The application includes an agent 742 and a service 744 that provides input to a number of processes. The application 740 includes inbound data 750, preprocessing 752, commands and controls 754, analytical models 756, postprocessing 758, and outbound data 760.

[0091] <Other examples and embodiments> Accordingly, the methods and systems provided herein may include switching AI models when inspecting two or more different types of assets is to be performed, in light of the embodiments and examples described herein. At a high level, the robot can receive instructions to inspect assets in a certain area, and the robot can identify a first asset and look up historical data on what inspections have been performed. Based on the historical information, the robot can enable one or more sensors and select an AI model that leverages the sensors selected for the inspection and complete the inspection. The robot can continue to identify other assets in the area or a second asset. Asset identification can be completed by running an object detection AI model. The robot can look up historical data for the second asset. If the type of inspection performed on the second asset is different from the type of inspection performed on the first asset, the robot can enable one or more sensors and select a second AI model. The robot can perform the inspection using the selected second AI model and selected sensors. The robot continues to scan for assets in the area and perform inspections until all assets in the area have been inspected. For example, switching AI models can be done on the robot's computer or on an external server with which the robot communicates.

[0092] The operational blocks and system components shown in one or more figures may be similar to those shown in other figures. The diversity of operational blocks and system components illustrates the exemplary embodiments and aspects of the disclosure. For example, the methods shown may include aspects / operations previously shown and discussed in the disclosure, and in one example, are intended as exemplary embodiments that continue from a previous method shown in another flowchart.

[0093] <Additional Examples and Embodiments> In embodiments of the present disclosure shown in Figures 1 and 2, the computer may be a remote computer or part of a remote server, such as a remote server 1100 (Figure 8). In another embodiment, computer 131 may be part of a control system 170 and may provide the execution of the functions of the present disclosure. In yet another embodiment, the computer may be part of a mobile device and may provide the execution of the functions of the present disclosure. In yet another embodiment, the execution of some of the functions of the present disclosure may be shared between a control system computer and a mobile device computer, for example, the control system may function as a backend for one or more programs implementing the present disclosure, and the mobile device computer may function as a frontend for one or more programs.

[0094] The computer may be part of a mobile device or a remote computer communicating with the mobile device. In another example, the mobile device and the remote computer may work together to implement the method of the disclosure using stored program code or instructions for performing one or more features of the method described herein. In one example, the apparatus 130 may include a computer 131 having a processor 132 and a storage medium 134 for storing an application 135, and the computer includes a display 138. The application may incorporate program instructions for performing features of the disclosure using the processor 132. In another example, the application on the mobile device or computer software may have program instructions executable for a front-end software application that incorporates features of the method of the disclosure into the program instructions, while a back-end program or program 174 of the software application stored in the computer 172 of the control system 170 communicates with the computer on the mobile device to perform other features of the method. The control system 170 and the apparatus (e.g., mobile device or computer) 130 may communicate using a communication network 160, such as the Internet.

[0095] Accordingly, Method 100 according to embodiments of the present disclosure can be incorporated into one or more computer programs or applications 135 that are stored in an electronic storage medium 134 and executable by a processor 132 as part of a computer on a mobile device. For example, the mobile device may communicate with a control system 170, and in another example, a device such as a video feed device may communicate directly with the control system 170. Other users (not shown) may have similar mobile devices that communicate with the control system in the same way. The application may be stored in whole or in part on the computer or on the mobile device, and with the control system that communicates with the mobile device using a communication network 160, such as the Internet. It is assumed that the application has access to all or part of the program instructions for carrying out the method of the present disclosure. The program or application may communicate with a remote computer system via the communication network 160 (e.g., the Internet), access data, and collaborate with one or more programs stored on the remote computer system. Such interactions and mechanisms are described in more detail herein, with reference to components of a computer system such as a computer-readable storage medium, one embodiment of which is shown in Figure 8, and are described in more detail with reference to one or more computer systems 1010.

[0096] Therefore, in one example, the control system 170 communicates with a computer 131 or device 130, the computer may include an application or software 135. The computer 131, or the computer in the mobile device 130, communicates with the control system 170 using a communication network 160.

[0097] In another example, the control system 170 may have a front-end computer belonging to one or more users and a back-end computer implemented as a control system.

[0098] Referring to Figure 1, the device 130 may include a computer 131, a computer-readable storage medium 134, and an operating system, or a program, or both, or a software application 135, or both, which may include program instructions executable using a processor 132. These features are shown in Figure 1 herein, and other similar components and features are also present in one embodiment of a computer system shown in Figure 8 with reference to a computer system 1010 which may include one or more computer components.

[0099] The method according to this disclosure may include a computer as part of a control system for carrying out the features of the method according to this disclosure. In another example, the computer as part of a control system may cooperate with a mobile device computer that cooperates with a communication system for carrying out the features of the method according to this disclosure. In yet another example, the computer for carrying out the features of the method may be part of a mobile device and therefore the method may be carried out locally.

[0100] Specifically, with respect to the control system 170, one or more devices 130, or devices that may belong to one or more users in an example, can communicate with the control system 170 via a communication network 160. In the embodiment of the control system shown in Figure 1, the control system 170 includes a computer 172 that communicates with a database 176 and one or more programs 174 stored in a computer-readable storage medium 173. In the embodiment of the disclosure shown in Figure 1, the device 130 communicates with the control system 170 and one or more programs 174 stored in the computer-readable storage medium 173. The control system includes a computer 172 having a processor 175, which also has access to the database 176.

[0101] The control system 170 may include a storage medium 180 for maintaining user and user device registrations 182 for analyzing voice input. Such registrations may include a user profile 183 that can include user data supplied by the user in connection with account registration and configuration. In one embodiment, a method and system incorporating the present disclosure includes a control system (commonly referred to as the backend) that cooperates in combination with a frontend of the method and system, which may be an application 135. In one example, the application 135 is stored on a device, e.g., a computer or device on a location, and can access data and additional programs in the application's backend, e.g., the control system 170.

[0102] The control system may be part of the implementation of a software application, or it may represent a software application having a front-end user portion and a back-end portion that provides functionality, or both. In one embodiment, a method and system incorporating the present disclosure includes a control system (which may be commonly referred to as the back-end of the software application incorporating a portion of the method and system of the present embodiment) that works in conjunction with the front-end of a software application incorporating another portion of the method and system of the present application in the device, as shown in the example of a device 130 and computer 131 having application 135. Application 135 is stored in the device or computer and can access data and additional programs of (one or more) programs 174 stored in the back-end of the application, for example, the control system 170.

[0103] One or more programs 174 may include, in whole or in part, a set of executable steps for carrying out the method of the disclosure. A program incorporating the method may be stored in whole or in part on a computer-readable storage medium on a control system, or in whole or in part on a computer or device 130. The control system 170 may not only store user profiles, but in one embodiment it may also interact with a website for viewing on the display of a device such as a mobile device, or in another example, the internet, and may receive user input related to the method and system of the disclosure. Figure 1 depicts one or more profiles 183, but it is understood that the method may include multiple profiles, users, registrations, etc. It is assumed that multiple users or groups of users may use the control system to register and provide profiles for use in accordance with the method and system of the disclosure.

[0104] <Further Embodiments and Examples> Features shown in parts of diagrams, such as block diagrams, are understood to be functional representations of the features of the Disclosure. Such features are shown in embodiments of the Systems and Methods of the Disclosure for illustrative purposes to clarify the functionality of the features of the Disclosure.

[0105] The methods and systems disclosed herein may include a set of action blocks for carrying out one or more embodiments of the disclosure herein. In some examples, one or more action blocks in one or more figures may be similar to action blocks shown in other figures. A method shown in one figure may be another exemplary embodiment that includes aspects / actions shown in other figures and discussed above.

[0106] <Additional Embodiments and Examples> For example, account data, including user-related profile data and personal or other arbitrary data, may be collected and stored in, for example, the control system 170. Such data collection is understood to be carried out with the user's knowledge and consent and stored in a manner that protects privacy, which will be discussed in more detail below. Such data may include personal data and data relating to personal items.

[0107] For example, a user can register an account 181 with a user profile 183 on the control system 170, which will be discussed in more detail below. For example, data can be collected using the techniques described above, for example, using a camera, and the data can be uploaded to the user profile by the user. Users may include, for example, a corporate entity, or a corporate department, or a homeowner, or any end user, human operator, or robotic device, or other personnel of the company.

[0108] With regard to the collection of data relating to this disclosure, such uploading or generating of profiles is done voluntarily by one or more users and is therefore initiated by and with the user's consent. Thereafter, the user can opt in to establishing an account with a profile in accordance with this disclosure. Similarly, data received by the system, or entered, or received as input, is done voluntarily by one or more users and is therefore initiated by and with the user's consent. Thereafter, the user can opt in to entering data in accordance with this disclosure. Such user consent includes the user's choice to cancel such profile or account, or data entry, or both, and therefore, at the user's discretion, opt out of capturing communications and data. Furthermore, any stored or collected data is understood to be stored securely, unavailable without the user's consent, and intended to be unavailable to the public, unauthorized users, or both. Such stored data is understood to be deleted upon the user's request and deleted in a secure manner. Also, any use of such stored data is understood to be done only with the user's consent and approval, according to this disclosure.

[0109] In one or more embodiments of the present invention, one or more users may, with their consent and approval, voluntarily provide data or information or both in the process and opt in to or register with a control system in which the data is stored and used in one or more ways of the present disclosure. Alternatively, one or more users may register one or more user electronic devices for use in one or more ways and systems of the present disclosure. As part of registration, a user may also identify and authorize access to one or more activities or other systems (e.g., audio or video systems, or both). Such opt-in to registration and authorization of data collection or storage or both are optional, and a user may request deletion of data (including profiles or profile data, or both), deregistration, or opt-out of any registration, or a combination thereof. Such opt-out is understood to include the secure destruction of all data. The user interface may also allow a user or individual to delete all of their historical data.

[0110] <Other embodiments and examples> In one example, artificial intelligence (AI) may be used in whole or in part to generate a model or learning model, such as those discussed herein, in embodiments of this disclosure.

[0111] Artificial intelligence (AI) systems may include machines, computers, and computer programs designed to be intelligent or to reflect intelligence. Such systems may include computers that execute algorithms. AI may include machine learning and deep learning. For example, deep learning may include neural networks. AI systems may be cloud-based, that is, they may use cloud-based computing environments that have computing resources.

[0112] In another example, the control system 170 could be all or part of an artificial intelligence (AI) system. For instance, the control system could be one or more components of an AI system.

[0113] Furthermore, Method 100 according to embodiments of the present disclosure may be incorporated into an AI device, component, or part of an AI system, and it is understood that it may communicate with the respective AI system and component, as well as the respective AI system platform. Thus, a program or application incorporating the Method of the present disclosure as described above may become part of an AI system. In one embodiment of the present invention, it is assumed that a control system may communicate with an AI system, or in another embodiment, may become part of an AI system. The control system may also represent a software application having a front-end user portion and a back-end portion that provides functionality, which may, in one or more examples, interact with, encompass, or become part of a larger system, such as an AI system. In one example, an AI device may be all or part of a control system or a content delivery system or both, and may be associated with an AI system that is remote from the AI ​​device. Such an AI system may be represented by one or more servers that store a program on a computer-readable medium that can communicate with one or more AI devices. The AI ​​system may communicate with a control system, and in one or more embodiments, the control system may be all or part of an AI system, or vice versa.

[0114] As discussed herein, it is understood that downloadable data or downloadable data can be initiated using voice commands or using a mouse, touchscreen, etc. In such examples, a mobile device can be initiated by the user, or an AI device can be used with the user's consent and permission. Other examples of AI devices include devices with microphones, speakers, and access to a cellular or mobile network, communication network, or the Internet, such as a vehicle having a computer and cellular or satellite communication, or in another example, an IoT (Internet of Things) device such as a home appliance having cellular network or internet access.

[0115] <Further considerations regarding examples and embodiments> A set or group is understood to be a distinct collection of objects or elements. The objects or elements constituting a set or group can be anything, such as numbers, letters of the alphabet, other sets, or a number of people or users. It is further understood that a set or group can be a single element, such as a single thing or number; in other words, a set of single elements, such as one or more users or people or participants. Furthermore, it is understood herein that "machine" and "device" are used interchangeably to refer to machines or devices in one or more AI ecosystems or environments.

[0116] The descriptions of various embodiments of the present invention are presented for illustrative purposes only and are not intended to be exhaustive or to limit the embodiments disclosed herein. Similarly, examples of features or functionalities of the embodiments of the disclosure described herein, whether used in the description of a particular embodiment or cited as examples, are not intended to limit the embodiments of the disclosure described herein or to limit the embodiments described herein. Such examples are intended to be illustrative and non-exhaustive. It will be apparent to those skilled in the art that many modifications and changes are possible without departing from the scope and spirit of the embodiments described herein. The terms used herein have been selected to best describe the principles of the embodiments, their practical application to the technology found in the market or technical improvements, or to enable those skilled in the art to understand the embodiments described herein.

[0117] <Further examples and embodiments> Referring to Figure 8, one embodiment of the system or computer environment 1000 according to this disclosure includes a computer system 1010, shown in the form of a general-purpose computing device. Method 100 can be implemented, for example, by a program 1060 including program instructions, and is implemented on a computer-readable storage device, or more specifically, a computer-readable storage medium called a computer-readable storage medium, for example, commonly referred to as computer memory 1030. Such memory or computer-readable storage medium, or both, includes non-volatile memory or non-volatile storage, also known as non-temporary computer-readable storage medium or non-temporary computer-readable storage medium. For example, such non-volatile memory may be a disk storage device including one or more hard drives. For example, memory 1030 may include a storage medium 1034 such as RAM (Random Access Memory) or ROM (Read Only Memory), and a cache memory 1038. Program 1060 is executable by a processor 1020 of the computer system 1010 (to execute program steps, code, or program code). Additionally, additional data storage may be implemented as a database 1110 containing data 1114. The computer system 1010 and program 1060 are general representations of a computer and program that may be local to a user or provided as a remote service (e.g., as a cloud-based service), and in further examples may be provided using a website accessible via a communication network 1200 (e.g., interacting with a network, the internet, or a cloud service). The computer system 1010 is also understood herein to generally represent a computer device or computer contained in a device such as a laptop or desktop computer, or one or more servers, either alone or as part of a data center.The computer system may include a network adapter / interface 1026 and (one or more) input / output (I / O) interfaces 1022. The I / O interfaces 1022 enable data input and output to and from external devices 1074 that may be connected to the computer system. The network adapter / interface 1026 may provide communication between the computer system and a network commonly referred to as a communication network 1200.

[0118] Computer 1010 is sometimes described in the general context of computer system executable instructions, such as program modules, being executed by the computer system. Generally, a program module may include routines, programs, objects, components, logic, data structures, etc., that perform a specific task or implement a specific abstract data type. Method steps and system components and techniques may be implemented in modules of program 1060 to perform the tasks of each step of the method and system. Modules are generally represented in the figure as program module 1064. Program 1060 and program module 1064 can execute specific steps, routines, subroutines, instructions, or code of the program.

[0119] The method of this disclosure can be executed locally on a device such as a mobile device, or it can be executed on a server 1100 that may be remote and accessible using a communication network 1200. The program or executable instructions may also be provided as a service by a provider. Computer 1010 may be implemented in a distributed cloud computing environment where tasks are performed by remote processing units linked via the communication network 1200. In a distributed cloud computing environment, program modules may reside on both local and remote computer system storage media, including memory storage devices.

[0120] More specifically, the system or computer environment 1000 includes a computer system 1010, which is shown in the form of a general-purpose computing device with exemplary peripheral devices. The components of the computer system 1010 may include, for example, one or more processors or processing units 1020, a system memory 1030, and a bus 1014 that connects various system components, including the system memory 1030, to the processor 1020.

[0121] Bus 1014 represents one or more of several types of bus structures, including memory buses or memory controllers, peripheral buses, accelerated graphics ports, and processor or local buses using one of various bus architectures. Examples, but not limited to, such architectures include Industry Standard Architecture (ISA) buses, Microchannel Architecture (MCA) buses, Extended ISA (EISA) buses, Video Electronics Standards Association (VESA) local buses, and Peripheral Component Interconnect (PCI) buses.

[0122] Computer 1010 may include various computer-readable media. Such media may be any available media accessible by computer 1010 (e.g., a computer system or server) and may include both volatile and non-volatile media, as well as removable and non-removable media. Computer memory 1030 may include additional computer-readable media in the form of volatile memory such as random access memory (RAM) 1034, or cache memory 1038, or both. Computer 1010 may further include other removable / non-removable, volatile / non-volatile computer storage media, for example, a portable computer-readable storage medium 1072. In one embodiment, computer-readable storage medium 1050 may be provided for reading from and writing to a non-removable non-volatile magnetic medium. Computer-readable storage medium 1050 may be implemented, for example, as a hard disk drive. Additional memory and data storage may be provided, for example, as a storage system 1110 (e.g., a database) for storing data 1114 and communicating with processing unit 1020. The database may be stored on or be part of server 1100. Though not shown, a magnetic disk drive for reading from and writing to removable non-volatile magnetic disks (e.g., “floppy disks”) and an optical disk drive for reading from or writing to removable non-volatile optical disks such as CD-ROMs, DVD-ROMs, or other optical media may be provided. In such examples, each may be connected to bus 1014 by one or more data media interfaces. As further depicted and explained below, memory 1030 may include at least one program product that may include one or more program modules configured to perform the functions of embodiments of the present invention.

[0123] The methods described herein (one or more) may be implemented, for example, by one or more computer programs commonly referred to as program 1060, which may be stored in memory 1030 within a computer-readable storage medium 1050. Program 1060 may include program modules 1064. Program modules 1064 can generally perform functions or methodologies, or both, of embodiments of the present invention as described herein. One or more programs 1060 are stored in memory 1030 and are executable by a processing unit 1020. As an example, memory 1030 may store an operating system 1052, one or more application programs 1054, other program modules, and program data on the computer-readable storage medium 1050. It is understood that the programs 1060, operating system 1052, and (one or more) application programs 1054 stored on the computer-readable storage medium 1050 are similarly executable by the processing unit 1020. Furthermore, it is understood that Application 1054 and (one or more) Program 1060 are generally shown and may include all or part of all of the one or more applications and programs discussed in this disclosure, or vice versa, that is, Application 1054 and Program 1060 may include all or part of all of the one or more applications and programs discussed in this disclosure. It is also understood that the control system 170 communicating with the computer system may include all or part of the computer system 1010 and its components, or the control system may communicate with all or part of the computer system 1010 and its components as a remote computer system to achieve the control system functions described in this disclosure, or both. The control system functions may include, for example, storing, processing, and executing software instructions to perform the functions of this disclosure.Furthermore, it is understood that one or more computers or computer systems shown in Figure 1 may similarly include all or some of the computer system 1010 and its components, or that one or more computers may communicate with all or some of the computer system 1010 and its components as a remote computer system to achieve the computer functions described in this disclosure, or both.

[0124] In embodiments of the present disclosure, one or more programs may be stored in one or more computer-readable storage media such that the programs are implemented in or encoded in computer-readable storage media, or both. In one example, the stored programs may be executed by a processor or a computer system having a processor and may include program instructions that perform a method or cause a computer system to perform one or more functions. For example, in one embodiment of the present disclosure, a program that implements a method is implemented in or encoded in computer-readable storage media, which includes and is defined as a non-transient or non-transitory computer-readable storage medium. Thus, embodiments or examples of computer-readable storage media in the present disclosure do not include signals, and embodiments may include one or more non-transient or non-transitory computer-readable storage media. Thereafter, in one example, a program may be recorded in computer-readable storage media and become structurally and functionally interrelated with the medium.

[0125] Computer 1010 can also communicate with one or more external devices 1074 such as a keyboard and pointing device, a display 1080, one or more devices that enable a user to interact with computer 1010, or any device that enables computer 1010 to communicate with one or more other computer devices (e.g., a network card, modem, etc.). Such communication may occur via the input / output (I / O) interface 1022. A power supply 1090 can also be connected to the computer using a power supply interface (not shown). In addition, computer 1010 can communicate with one or more networks 1200 such as a local area network (LAN), a general wide area network (WAN), or a public network (e.g., the Internet), or a combination thereof, via the network adapter / interface 1026. As depicted, the network adapter 1026 communicates with other components of computer 1010 via the bus 1014. It should be understood that other hardware and / or software components, or both, may be used with computer 1010, although these are not shown. Examples include, but are not limited to, microcode, device driver 1024, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archive storage systems.

[0126] It is understood that a computer or a program running on computer 1010 may communicate with a server implemented as server 1100 via one or more communication networks implemented as communication network 1200. Communication network 1200 may include, for example, wireless, wired, or optical fiber, as well as transmission media and network links including routers, firewalls, switches, and gateway computers. Communication network may include connections such as wired, wireless links, or optical fiber cables. Communication network can represent a global collection of networks and gateways, such as the Internet, that communicate with each other using various protocols, such as LDAP (Lightweight Directory Access Protocol), TCP / IP (Transport Control Protocol / Internet Protocol), HTTP (Hypertext Transport Protocol), and WAP (Wireless Application Protocol). Network may also include several different types of networks, such as intranets, local area networks (LANs), and wide area networks (WANs).

[0127] In one example, a computer can use a network that allows it to access websites on the World Wide Web using the Internet. In one embodiment, a computer 1010 including a mobile device can use a communication system or network 1200 that includes the Internet, or for example, a Public Switched Telephone Network (PSTN), a cellular network. The PSTN can include telephone lines, fiber optic cables, microwave transmission links, cellular networks, and communication satellites. The Internet can facilitate a number of search and text messaging technologies, for example, using a mobile phone or laptop computer to send queries to a search engine via text message (SMS), multimedia messaging service (MMS) (related to SMS), email, or a web browser. The search engine can retrieve search results, i.e., links to websites, documents, or other downloadable data corresponding to the query, and similarly, it can provide the search results to the user via the device, for example, as a web page of search results.

[0128] <Further examples and embodiments> Referring to Figure 9, an exemplary system 1500 for use with embodiments of the present disclosure is depicted. System 1500 includes several components and elements connected via a system bus 1504. At least one processor (CPU) 1510 is connected to the other components via the system bus 1504. A cache 1570, ROM (Read Only Memory) 1512, RAM (Random Access Memory) 1514, input / output (I / O) adapter 1520, sound adapter 1530, network adapter 1540, user interface adapter 1552, display adapter 1560, and display device 1562 are also operably coupled to the system bus 1504 of system 1500. An AR device 1590 may also be operably coupled to the bus 1504. An AI-enabled robot and control system 1580 may also be operably coupled to the bus 1504. Such a robot and control system 1580 may incorporate all or part of embodiments of the present disclosure and embodiments discussed herein. An artificial intelligence (AI) system 1575 or AI ecosystem may also be operably coupled to bus 1504. A power supply 1595 may also be operably connected to bus 1504 for supplying power to its components and for the functions described herein. An augmented reality (AR) device 1590 may also be operably connected to bus 1504 to provide an augmented reality output to a wearable augmented reality device, such as AR glasses or an AR headset.

[0129] One or more storage devices 1522 are operably coupled to the system bus 1504 by an I / O adapter 1520. The storage devices 1522 may be, for example, disk storage devices (e.g., magnetic disks or optical disk storage devices), solid-state magnetic devices, etc. The storage devices 1522 may be of the same type or different types. The storage devices may include, for example, a hard drive or flash memory, and may be used to store one or more programs 1524 or applications 1526. Programs and applications are shown as general-purpose components and are executable using the processor 1510. Program 1524 or application 1526, or both, may include all or part of the programs or applications discussed in this disclosure, and vice versa; i.e., Program 1524 and application 1526 may be part of other applications or programs discussed in this disclosure.

[0130] System 1500 may include a control system 170 (described in further detail herein) which is part of System 100 and can communicate with the system bus independently or as part of System 100, and thus can communicate with other components of System 1500 via the system bus. In one example, a storage device 1522 can communicate via the system bus with a control system 170 having various functions as described herein.

[0131] In one embodiment, speaker 1532 is operably coupled to system bus 1504 by sound adapter 1530. Transceiver 1542 is operably coupled to system bus 1504 by network adapter 1540. Display 1562 is operably coupled to system bus 1504 by display adapter 1560.

[0132] In another embodiment, one or more user input devices 1550 are operably coupled to the system bus 1504 by a user interface adapter 1552. The user input devices 1550 can be, for example, a keyboard, mouse, keypad, image capture device, motion sensing device, microphone, or a device incorporating at least two functions of a prior device. It is also possible to use other types of input devices while maintaining the spirit of the present invention. The user input devices 1550 may be of the same type or different types. The user input devices 1550 are used to input and output information to and from the system 1500.

[0133] <Other embodiments and examples> The present invention may be a system, method, or computer program product or combination thereof, integrated at any possible level of technical detail. The computer program product may include a computer-readable storage medium storing computer-readable program instructions for causing a processor to perform aspects of the present invention.

[0134] A computer-readable storage medium can be a tangible device capable of holding and storing instructions used by an instruction execution device. Examples of computer-readable storage media may be electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or appropriate combinations thereof. More specific examples of computer-readable storage media include portable computer diskettes, hard disks, RAM, ROM, EPROM (or flash memory), SRAM, CD-ROM, DVD, memory stick, floppy disk, punch cards, or grooved raised structures, and mechanically encoded devices on which instructions are recorded, and appropriate combinations thereof. Computer-readable storage devices as used herein should not be interpreted as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through optical fiber cables), or electrical signals transmitted through wires.

[0135] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computer device / processor. Alternatively, they can be downloaded to an external computer or external storage device via a network (e.g., the Internet, LAN, WAN, or wireless network, or a combination thereof). The network may include copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers or edge servers, or a combination thereof. A network adapter card or network interface within each computer device / processor receives computer-readable program instructions from the network and transfers them for storage in a computer-readable storage medium in the respective computer device / processor.

[0136] The computer-readable program instructions for performing the operation of the present invention may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuits, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk and C++, and procedural programming languages ​​such as the "C" programming language or similar programming languages. The computer-readable program instructions can be executed as a standalone software package, either entirely on the user's computer or partially on the user's computer. Alternatively, they can be executed partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network, including LANs and WANs, or it may be connected to an external computer (for example, via the Internet using an Internet service provider). In some embodiments, electronic circuits, including, for example, programmable logic circuits, field-programmable gate arrays (FPGAs), and programmable logic arrays (PLAs), can execute computer-readable program instructions by utilizing state information of computer-readable program instructions in order to customize the electronic circuits for the purpose of performing aspects of the present invention.

[0137] Each aspect of the present invention is described herein with reference to flowcharts or block diagrams, or both, of methods, apparatus (systems), and computer program products according to embodiments of the present invention. Each block in a flowchart or block diagram, or both, and combinations of multiple blocks in a flowchart or block diagram, or both, are executable by computer-readable program instructions.

[0138] The above computer-readable program instructions may be provided to a processor of a general-purpose computer, a dedicated computer, or other programmable data processing device for the purpose of producing a machine. This creates a means for these instructions, executed via the processor of such computer or other programmable data processing device, to perform functions / operations identified in one or more blocks in a flowchart or block diagram, or both. The above computer-readable program instructions may further be stored in a computer-readable storage medium that can be instructed to function in a particular manner to a computer, a programmable data processing device, or other device, or a combination thereof. This constitutes a product in which the computer-readable storage medium containing the instructions includes instructions for performing functions / operations identified in one or more blocks in a flowchart or block diagram, or both.

[0139] Alternatively, a computer execution process may be generated by loading computer-readable program instructions into a computer, another programmable device, or other device, and having a series of operational steps executed on that computer, other programmable device, or other device. This ensures that the instructions executed on the computer, other programmable device, or other device perform functions / operations identified in one or more blocks in a flowchart, block diagram, or both.

[0140] The flowcharts and block diagrams in the drawings of this disclosure illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of instructions, containing one or more executable instructions for performing a particular logical function. In some other implementations, the functions shown within a block may be executed in an order different from the order shown in each figure. For example, two consecutively shown blocks may actually be achieved as a single process, executed simultaneously or substantially simultaneously, executed in a partially or entirely overlapping manner in time, or, in some cases, executed in reverse order, depending on the functions involved. Each block in a block diagram or flowchart or both, and combinations of multiple blocks in a block diagram or flowchart or both, can be executed by a dedicated hardware-based system that performs a particular function or operation, or by a combination of dedicated hardware and computer instructions.

[0141] <Additional aspects and examples> While this disclosure includes a detailed description of cloud computing, it should be understood that the implementation of the teachings described herein is not limited to cloud computing environments. Rather, embodiments of the present invention can be implemented in any other type of computing environment that is currently known or will be developed in the future.

[0142] Cloud computing is a service delivery model that enables convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal administrative effort or interaction with service providers. This cloud model may include at least five characteristics, at least three service models, and at least four implementation models.

[0143] The characteristics are as follows:

[0144] On-demand self-service: Cloud consumers can unilaterally prepare computing power, such as server time and network storage, automatically as needed, without requiring human interaction with service providers.

[0145] Broad network access: Computing power is available over the network and accessible through standard mechanisms. This facilitates utilization by heterogeneous thin or thick client platforms (e.g., mobile phones, laptops, PDAs).

[0146] Resource pooling: A provider's computing resources are pooled and delivered to multiple consumers using a multi-tenant model. Various physical and virtual resources are dynamically allocated and reallocated as needed. Generally, consumers have a sense of location independence because they do not manage or know the exact location of the resources provided. However, consumers may be able to identify the location at a higher level of abstraction (e.g., country, state, data center).

[0147] Rapid Elasticity: Computing power can be prepared quickly and flexibly, allowing it to scale out automatically and immediately, and to be quickly released and scale in immediately. To consumers, the computing power available for preparation often appears unlimited and can be purchased in any quantity at any time.

[0148] Measured Services: Cloud systems leverage metric capabilities at a certain level of abstraction, appropriate for the type of service (e.g., storage, processing, bandwidth, active user accounts), to automatically control and optimize resource usage. Resource usage can be monitored, controlled, and reported, providing transparency to both service providers and consumers.

[0149] The service model is as follows:

[0150] Software as a Service (SaaS): The functionality offered to consumers is the ability to use the provider's applications running on a cloud infrastructure. These applications can be accessed from various client devices via thin client interfaces such as web browsers (e.g., webmail). Consumers do not manage or control the underlying cloud infrastructure, including the network, servers, operating systems, storage, or even individual application functions, except for configuring a limited number of user-specific applications.

[0151] Platform as a Service (PaaS): The functionality offered to consumers is the ability to deploy applications they have created or acquired to cloud infrastructure using programming languages ​​and tools supported by the provider. Consumers do not manage or control the underlying cloud infrastructure, including networks, servers, operating systems, and storage, but they can control the deployed applications and, in some cases, the configuration of their hosting environment.

[0152] Infrastructure as a Service (IaaS): The functionality provided to consumers is to prepare processors, storage, networking, and other basic computing resources that enable consumers to deploy and run any software, including operating systems and applications. Consumers do not manage or control the underlying cloud infrastructure, but they can control the operating system, storage, and deployed applications, and in some cases, partially control certain network components (e.g., host firewalls).

[0153] The deployment model is as follows:

[0154] Private Cloud: This cloud infrastructure is operated exclusively for a specific organization. This cloud infrastructure can be managed by that organization or a third party and can reside on-premises or off-premises.

[0155] Community Cloud: This cloud infrastructure is shared by multiple organizations to support a specific community with common interests (e.g., mission, security requirements, policies, and compliance). This cloud infrastructure can be managed by the organization or a third party and can reside on-premises or off-premises.

[0156] Public Cloud: This cloud infrastructure is provided to a large number of people or large industry groups and is owned by organizations that sell cloud services.

[0157] Hybrid Cloud: This cloud infrastructure combines two or more cloud models (private, community, or public). While maintaining the unique entities of each model, they are bound together by standards or individual technologies to achieve data and application portability (e.g., cloud bursting for load balancing across clouds).

[0158] Cloud computing environments are service-oriented environments that emphasize statelessness, low coupling, modularity, and semantic interoperability. At the core of cloud computing is the infrastructure, which includes a network of interconnected nodes.

[0159] Here, Figure 10 shows an exemplary cloud computing environment 2050. As illustrated, the cloud computing environment 2050 includes one or more cloud computing nodes 2010. Local computer devices used by cloud consumers (e.g., PDA or mobile phone 2054A, desktop computer 2054B, laptop computer 2054C, or automotive computer system 2054N, or a combination thereof) can communicate with these nodes. The nodes 2010 can communicate with each other. The nodes 2010 can be grouped physically or virtually (not shown) in one or more networks, such as the private, community, public, or hybrid clouds or a combination thereof. This allows the cloud computing environment 2050 to provide infrastructure, platforms, or software as a service, or a combination thereof, without requiring cloud consumers to maintain resources on their local computer devices. Please note that the types of computer devices 2054A-N shown in Figure 10 are merely examples, and the computing node 2010 and the cloud computing environment 2050 can communicate with any type of electronic device via any type of network, a network addressable connection (e.g., using a web browser), or both.

[0160] Here, Figure 11 shows the set of functional abstraction layers provided by the cloud computing environment 2050 (Figure 10). It should be understood that the components, layers, and functions shown in Figure 11 are illustrative only, and embodiments of the present invention are not limited to these. As illustrated, the following layers and corresponding functions are provided.

[0161] The hardware and software layer 2060 includes hardware and software components. Examples of hardware components include a mainframe 2061, a reduced instruction set computer (RISC) architecture-based server 2062, server 2063, blade server 2064, storage device 2065, and network and network components 2066. In some embodiments, the software components include network application server software 2067 and database software 2068.

[0162] The virtualization layer 2070 provides an abstraction layer. From this layer, for example, the following virtual entities can be provided: virtual servers 2071, virtual storage 2072, virtual networks 2073 including virtual private networks, virtual applications and operating systems 2074, and virtual clients 2075.

[0163] For example, the management layer 2080 can provide the following functions: Resource preparation 2081 enables the dynamic procurement of computing and other resources used to perform tasks within the cloud computing environment. Metering and pricing 2082 enables cost tracking as resources are used within the cloud computing environment and billing or invoicing for the consumption of these resources. For example, these resources may include application software licenses. Security enables not only protection of data and other resources but also identification and verification of cloud consumers and tasks. User portal 2083 provides consumers and system administrators with access to the cloud computing environment. Service level management 2084 enables the allocation and management of cloud computing resources to ensure that requested service levels are met. Service Level Assurance (SLA) planning and execution 2085 enables the pre-arrangement and procurement of cloud computing resources that are expected to be needed in the future in accordance with the SLA.

[0164] Workload layer 2090 provides examples of the capabilities available in a cloud computing environment. Examples of workloads and capabilities available from this layer include mapping and navigation 2091, software development and lifecycle management 2092, virtual classroom education delivery 2093, data analytics processing 2094, transaction processing 2095, and management of AI-enabled robotic devices 2096 (e.g., management of roaming robotic devices using control systems).

Claims

1. A computer implementation method for an autonomous roaming robot device that dynamically adjusts sensors and models to perform actions using artificial intelligence (AI), The roaming robot device's computer receives asset data from one or more sensors among a plurality of sensors on the robot device in response to the identification of the asset at a location using the one or more sensors, wherein the robot device has received instructions from the control system to inspect the location or the item at the location. Using the computer of the robot device, the received data and the historical data of the asset are analyzed in order to refer to inspection instructions and inspection history related to the asset. Using the computer of the robot device, based on the analysis of the data, Selecting one of the aforementioned multiple sensors, Based on the identification of the assets and the analysis of the data, the AI ​​model is loaded using the computer of the robotic device. Using the selected sensors, an asset inspection based on the AI ​​model is performed to generate asset inspection data. Methods that include...

2. To analyze the applicability of multiple AI models to the aforementioned assets, Based on the identification of the asset, the analysis of the data, and the analysis of the plurality of AI models, select the AI ​​model from the plurality of models. Using the computer of the robot device, load the selected AI model. Using the selected AI model and the selected sensor, the asset inspection is performed using the selected AI model and the selected sensor. The method according to claim 1, further comprising:

3. The method according to claim 1, wherein the AI ​​model includes an asset inspection protocol.

4. Using the computer of the robot device, select one of the multiple sensors in order to perform an inspection of the asset based on the AI ​​model, Using the selected sensors, perform an asset inspection of the asset based on the AI ​​model in order to generate asset inspection data. The method according to claim 1, further comprising:

5. Based on the aforementioned asset inspection data, a decision is made regarding the aforementioned asset. To transmit the aforementioned action to the control system, The method according to claim 1, further comprising:

6. The method according to claim 3, wherein the inspection protocol includes an inspection type and an inspection action specific to the inspection type.

7. Using the computer of the robot device, the asset inspection data obtained from the asset inspection is analyzed. Based on the analysis of the asset inspection data, the following actions will be determined: The method according to claim 1, further comprising:

8. Initiating the following action in the robot device, the following action includes detection by a second sensor among the plurality of sensors on the robot device. The method according to claim 7, further comprising:

9. Based on the type of the aforementioned asset, the third sensor among the plurality of sensors is enabled, For the generation of the aforementioned AI model, the input to the AI ​​model related to the aforementioned type of asset is loaded, The inspection data is captured by the third sensor, In order to determine another action based on the aforementioned asset inspection data, the inspection data is analyzed, The robot device initiates the following action, the following action includes initiating the second sensor among the plurality of sensors on the robot device. The method according to claim 8, further comprising:

10. Identifying multiple assets for inspection by the aforementioned robotic device, Identifying an AI model from multiple AI models corresponding to each of the identified assets, To receive data relating to each of the aforementioned assets, Analyze the received data for each of the aforementioned assets, Selecting each of the sensors of the aforementioned asset, Loading each of the aforementioned AI models, Each of the aforementioned assets shall be inspected separately, The method according to claim 1, further comprising:

11. The method according to claim 1, wherein the selection of the sensor is performed by the computer of the robot device without instructions from the control system regarding the selection.

12. The computer of the robot device initiates the execution of the asset inspection based on an inspection protocol derived from the AI ​​model, and the execution of the asset inspection by the robot device is in response to the computer of the robot device, as described in claim 1. The method.

13. The method according to claim 1, wherein the computer of the robot device starts the performance of the asset inspection in response to the AI ​​model.

14. The method according to claim 1, wherein the selection of the sensor and the execution of the asset inspection are not initiated in response to the control system.

15. Using one or more of the multiple sensors of the roaming robot device, to identify a second asset located at the location, The computer of the robot device receives data from one or more sensors relating to the second asset in response to the identification of the second asset at the location. Analyzing second data using the aforementioned computer, wherein the analysis includes using historical data of the second asset. Using the analysis of the second data, generate another AI model based on the identification of the second asset, To generate a second inspection protocol for the second asset, the other AI model is analyzed, Based on the second inspection protocol, in order to initiate the inspection of the second asset, Selecting a second sensor from the aforementioned plurality of sensors, Using the selected second sensor, a second asset inspection is performed to generate second asset inspection data. Based on the second asset inspection data, a second action regarding the second asset is determined, To transmit the second action to the control system, The method according to claim 1, further comprising:

16. The method according to claim 1, wherein the action includes an alert relating to the asset.

17. The method according to claim 1, wherein the action includes communication to the device.

18. The method according to claim 1, wherein the action includes maintenance activities for the asset.

19. A system for an autonomous roaming robot device that dynamically adjusts sensors and models to perform actions using artificial intelligence (AI), The system includes a computer system, the computer system includes a computer processor, a computer-readable storage medium, and program instructions stored on the computer-readable storage medium, the program instructions are processed by the processor, The computer system is executable to perform a function, and the function is The roaming robot device's computer receives asset data from one or more sensors among a plurality of sensors on the robot device in response to the identification of the asset at a location using the one or more sensors, wherein the robot device has received instructions from the control system to inspect the location or the item at the location. Using the computer of the robot device, the received data and the historical data of the asset are analyzed in order to refer to inspection instructions and inspection history related to the asset. Using the computer of the robot device, based on the analysis of the data, Selecting one of the aforementioned multiple sensors, Based on the identification of the assets and the analysis of the data, the AI ​​model is loaded using the computer of the robotic device. Using the selected sensors, an asset inspection based on the AI ​​model is performed to generate asset inspection data. A system that includes this.

20. Receiving asset data from one or more sensors among a plurality of sensors on the robot device, in response to the identification of the asset at a location using the one or more sensors, wherein the robot device has instructions received from the control system to inspect the location or the item at the location. Using the computer of the robot device, the received data and the historical data of the asset are analyzed in order to refer to inspection instructions and inspection history related to the asset. Using the computer of the robot device, based on the analysis of the data, Selecting one of the aforementioned multiple sensors, Based on the identification of the assets and the analysis of the data, the AI ​​model is loaded using the computer of the robotic device. Using the selected sensors, an asset inspection based on the AI ​​model is performed to generate asset inspection data. A computer program that causes a processor to execute something.

Images