Granted Patent B2

US 12,186,907 · App. 17/452,247 · Granted Jan 7, 2025

Inventors: Jenny S. Li (Cary, NC); Raghu Ramaswamy (Bangalore, IN); Nirmit V Desai (Yorktown Heights, NY); Dhiraj Joshi (Edison, NJ); Satish Rajani (Dewas, IN); Nancy Anne Greco (Lagrangeville, NY); Shiva G (Nagar, IN); Aakash Praliya (Kota, IN); Wei-Han Lee (White Plains, NY); Luis Angel Bathen (Placentia, CA); Tova Roth (Woodmere, NY); Sujoy Kumar Roy Chowdhury (Kolkata, IN); Prakriti Pritmani (Ahmedabad, IN); Kay Murphy (Nebo, NC); Shilpa Shenai (Bengaluru, IN); Arun Yashwant Ingale (Pune, IN); Ajjay Ratnakar (Bangalore, IN); Gwilym Benjamin Lee Newton (Winchester, GB)

Assignee: International Business Machines Corporation

B25J9/163B25J9/162B25J13/082B25J13/089

Abstract

Claims (68)

1. A computer-implemented method for an autonomous roaming robotic device to dynamically adjust sensors and models for implementing actions using artificial intelligence (AI), comprising:

receiving data regarding an asset at a computer of a roaming robotic device from one or more sensors of a plurality of sensors on the robotic device, in response to an identification of the asset at a location using the one or more sensors, the robotic device having instructions, received from a control system, to inspect the location or items at the location;

analyzing the received data and historical data for the asset, using the computer of the robotic device, to reference relevant inspection instructions and an inspection history for the asset;

selecting a sensor of the plurality of sensors, using the computer of the robotic device, based on the analysis of the received data and the historical data;

loading an AI model using the computer of the robotic device, based on the identification of the asset and the analysis of the data and the historical data; and

conducting an asset inspection based on the AI model using the selected sensor to generate asset inspection data.

2. The method of claim 1 , further comprising:

analyzing a plurality of AI models for applicability to the asset;

selecting the AI model of the plurality of models based on the identification of the asset and the analysis of the data and the analysis of the plurality of AI models;

loading the selected AI model using the computer of the robotic device; and

using the selected AI model and the selected sensor, the conducting of the asset inspection being performed.

3. The method of claim 1 , wherein the AI model includes an inspection protocol for the asset.

4. The method of claim 1 , further comprising:

selecting a sensor of the plurality of sensors, using the computer of the robotic device, for conducting an inspection of the asset based on the AI model; and

performing an asset inspection using the selected sensor to generate asset inspection data, based on the AI model for the asset.

5. The method of claim 1 , further comprising:

determining an action with respect to the asset based on the asset inspection data; and

communicating the action to the control system.

6. The method of claim 1 , wherein the inspection protocol includes an inspection type, and an inspection action particular to the inspection type.

7. The method of claim 1 , further comprising:

analyzing the asset inspection data from the asset inspection using the computer of the robotic device; and

determining a next action based on the analysis of the asset inspection data.

8. The method of claim 7 , further comprising:

initiating the next action at the robotic device, the next action including a second sensor of the plurality of sensors on the robotic device.

9. The method of claim 8 , further comprising:

enabling a third sensor of the plurality of sensors based on a type of the asset;

loading a related AI model input for the type of the asset for the generation of the AI model;

capturing the 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 next action at the robotic device, the next action including a second sensor of the plurality of sensors on the robotic device.

10. The method of claim 1 , further comprising:

identifying a plurality of assets for inspection by the robotic device;

identifying an AI model from a plurality of AI models corresponding to each of the plurality of identified assets;

receiving data regarding each of the assets, respectively;

analyzing the received data for each of the assets, respectively;

selecting a sensor for each of the assets, respectively;

loading an AI model for each of the assets, respectively; and

conducting an asset inspection for each of the assets, respectively.

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

12. The method of claim 1 , wherein the computer of the robotic device initiates the conducting of the asset inspection based on an inspection protocol derived from the AI model, the conducting of the asset inspection by the robotic device being in response to the computer of the robotic device.

13. The method of claim 1 , wherein the computer of the robotic device initiates the performance of the conducting of the asset inspection in response to the AI model.

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

15. The method of claim 1 , further comprising:

identifying a second asset at the location using the one or more sensors of the plurality of sensors on the roaming robotic device;

receiving data at the computer of the robotic device from the one or more sensors regarding the second asset, in response to the identification of the second asset at the location;

analyzing the second data using the computer wherein the analysis includes using historical data for the second asset;

generating another AI model based on the identification of the second asset, using the analysis of the second data;

analyzing the another AI model to generate a second inspection protocol for the second asset;

selecting a second sensor from the plurality of sensors for initiating the inspection of the second asset based on the second inspection protocol;

perform a second asset inspection using the selected second sensor to generate second asset inspection data;

determining a second action with respect to the second asset based on the second asset inspection data; and

communicating the second action to the control system.

16. The method of claim 1 , wherein the action includes an alert regarding the asset.

17. The method of claim 1 , wherein the action including a communication to a device of a person.

18. The method of claim 1 , wherein the action including a maintenance activity for the asset.

19. A system for an autonomous roaming robotic device to dynamically adjust sensors and models for implementing actions using artificial intelligence (AI), which comprises:

a computer system comprising; a computer processor, a computer-readable storage medium, and program instructions stored on the computer-readable storage medium being executable by the processor, to cause the computer system to perform the following functions to;

receive data regarding an asset at a computer of a roaming robotic device from one or more sensors of a plurality of sensors on the robotic device, in response to an identification of the asset at a location using the one or more sensors, the robotic device having instructions, received from a control system, to inspect the location or items at the location;

analyze the received data and historical data for the asset, using the computer of the robotic device, to reference relevant inspection instructions and an inspection history for the asset;

select a sensor of the plurality of sensors, using the computer of the robotic device, based on the analysis of the received data and the historical data;

load an AI model using the computer of the robotic device, based on the identification of the asset and the analysis of the data and the historical data; and

conduct an asset inspection based on the AI model using the selected sensor to generate asset inspection data.

20. A computer program product for an autonomous roaming robotic device to dynamically adjust sensors and models for implementing actions using artificial intelligence (AI), the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform functions, by the computer, comprising the functions to;

receive data regarding an asset at a computer of a roaming robotic device from one or more sensors of a plurality of sensors on the robotic device, in response to an identification of the asset at a location using the one or more sensors, the robotic device having instructions, received from a control system, to inspect the location or items at the location;

analyze the received data and historical data for the asset, using the computer of the robotic device, to reference relevant inspection instructions and an inspection history for the asset;

select a sensor of the plurality of sensors, using the computer of the robotic device, based on the analysis of the received data and the historical data;

load an AI model using the computer of the robotic device, based on the identification of the asset and the analysis of the data and the historical data; and

conduct an asset inspection based on the AI model using the selected sensor to generate asset inspection data.

Assignments (1)

Continuity (1)

References Cited (18)