Search

US-20260127433-A1 - SYSTEMS AND METHODS FOR AI BASED RECOMMENDATIONS FOR OBJECT PLACEMENT IN A HOME

US20260127433A1US 20260127433 A1US20260127433 A1US 20260127433A1US-20260127433-A1

Abstract

The following relates generally to light detection and ranging (LIDAR) and artificial intelligence (AI). In some embodiments, a system: trains a machine learning algorithm based upon preexisting data of object placement in a room; receives room data comprising dimensional data of a room; receives object data comprising: (i) dimensional data of an object; (ii) a type of the object; and/or (iii) color data of the object; and with the trained machine learning algorithm, generates a recommendation for placement of the object in the room based upon: (i) the received room data, and (ii) the received object data.

Inventors

  • Nicholas Carmelo Marotta
  • Laura Kennedy
  • JD Johnson Willingham

Assignees

  • STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

Dates

Publication Date
20260507
Application Date
20260102

Claims (20)

  1. 1 . A computer-implemented method for object placement based upon light detection and ranging (LIDAR) data and machine learning, the computer-implemented method comprising: generating, via one or more processors, room data comprising a plurality of dimensions of a room by: receiving, via the one or more processors, LIDAR data generated from a LIDAR camera; and measuring, via the one or more processors, the plurality of dimensions of the room based upon analysis of the LIDAR data; with a machine learning algorithm, generating, via the one or more processors, a recommendation for placement of the object in the room based upon: (i) the generated room data, and (ii) object data including color data of the object; receiving, via the one or more processors, an object placement in the room from a user; and displaying, via the one or more processors, both: (i) a representation of the object placement in the room from the user, and (ii) a representation of the object placement generated by the machine learning algorithm, thereby allowing the user to compare the placements.
  2. 2 . The computer-implemented method of claim 1 , wherein the recommendation is a first recommendation, and the computer-implemented method further comprises: with the machine learning algorithm, generating, via the one or more processors, a second recommendation for placement of the object in the room; and presenting, via the one or more processors, as first and second options, the first and second recommendations to the user.
  3. 3 . The computer-implemented method of claim 1 , further comprising: receiving, via the one or more processors, a placement of an item from the user in the room; wherein the recommendation for object placement in the room is further based upon the received placement of the item.
  4. 4 . The computer-implemented method of claim 1 , further comprising: building, via the one or more processors, a user profile based upon furniture placement in a home of the user; wherein the recommendation for object placement in the room is further based upon the user profile.
  5. 5 . The computer-implemented method of claim 4 , further including receiving, via the one or more processors, selections of preferred object placements from the user, wherein the user profile is further based upon the received selections of preferred object placements.
  6. 6 . The computer-implemented method of claim 1 , wherein the object data further includes: (i) dimensional data of the object; and (ii) a type of the object.
  7. 7 . The computer-implemented method of claim 1 , wherein the machine learning algorithm is a convolutional neural network.
  8. 8 . The computer-implemented method of claim 1 , further comprising: measuring, via the one or more processors, a plurality of dimensions of the object based upon analysis of the LIDAR data; wherein the object data comprises dimensional data of the object, and the dimensional data of the object comprises the plurality of dimensions of the object measured based upon the analysis of the LIDAR data.
  9. 9 . A computer system configured for object placement based upon light detection and ranging (LIDAR) data and machine learning, the computer system comprising one or more processors configured to: generate room data comprising a plurality of dimensions of a room by: LIDAR data generated from a LIDAR camera; and measuring the plurality of dimensions of the room based upon analysis of the LIDAR data; with a machine learning algorithm, generate a recommendation for placement of the object in the room based upon: (i) the generated room data, and (ii) object data including color data of the object; receive an object placement in the room from a user; and display both: (i) a representation of the object placement in the room from the user, and (ii) a representation of the object placement generated by the machine learning algorithm, thereby allowing the user to compare the placements.
  10. 10 . The computer system of claim 9 , wherein the recommendation is a first recommendation, and the one or more processors are further configured to: with the machine learning algorithm, generate a second recommendation for placement of the object in the room; and present, as first and second options, the first and second recommendations to a user.
  11. 11 . The computer system of claim 9 , further comprising: a display; wherein the one or more processors are further configured to: display, on the display, the generated recommendation for placement of the object in the room.
  12. 12 . The computer system of claim 9 , wherein a type of the object comprises: a chair; a table; a desk; a couch; a lamp; a bookshelf; a picture; or a painting.
  13. 13 . The computer system of claim 9 , wherein the one or more processors are further configured to: build a user profile; wherein the recommendation for object placement in the room is further based upon the user profile.
  14. 14 . The computer system of claim 9 , wherein the machine learning algorithm is a convolutional neural network.
  15. 15 . A computer system configured for object placement based upon light detection and ranging (LIDAR) data and machine learning, comprising: one or more processors; and a non-transitory program memory coupled to the one or more processors and storing executable instructions that when executed by the one or more processors cause the computer system to: generate room data comprising a plurality of dimensions of a room by: receiving LIDAR data generated from a LIDAR camera; and measuring the plurality of dimensions of the room based upon analysis of the LIDAR data; with a machine learning algorithm, generate a recommendation for placement of the object in the room based upon: (i) the generated room data, and (ii) object data including color data of the object. receive an object placement in the room from a user; and display both: (i) a representation of the object placement in the room from the user, and (ii) a representation of the object placement generated by the machine learning algorithm.
  16. 16 . The computer system of claim 15 , wherein the recommendation is a first recommendation, and wherein the executable instructions further cause the computer system to: with the machine learning algorithm, generate a second recommendation for placement of the object in the room; and present, as first and second options, the first and second recommendations to a user.
  17. 17 . The computer system of claim 15 , wherein the executable instructions further cause the computer system to: build a user profile based upon furniture placement in a home of a user; wherein the recommendation for object placement in the room is further based upon the user profile.
  18. 18 . The computer system of claim 15 , wherein the room data further comprises color data of the room, and a window placement in the room.
  19. 19 . The computer system of claim 15 , wherein the generated plurality of dimensions of the room includes a length of the room, a width of the room, and a height of the room.
  20. 20 . The computer system of claim 15 , wherein the machine learning algorithm is a convolutional neural network.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. patent application Ser. No. 17/240,999 (filed April 26, 2021) which claims the benefit of U.S. Provisional Application No. 63/016,168 (filed April 27, 2020); U.S. Provisional Application No. 63/025,600 (filed May 15, 2020); and U.S. Provisional Application No. 63/027,201 (filed May 19, 2020), the entirety of each of which is incorporated by reference herein. FIELD The present disclosure generally relates to light detection and ranging (LIDAR) technology and artificial intelligence (AI). More specifically, the following relates to LIDAR technology and AI based 3-dimensional (3D) models, navigation systems, and visualization systems. BACKGROUND LIDAR is a technology that measures distance to a target by illuminating the target (e.g., using laser light) and then measuring the reflected light with a sensor (e.g., measuring the time of flight from the laser signal source to its return to the sensor). Digital 3D representations of the target may then be made using differences in laser return times and wavelengths. LIDAR may be used to measure distances (e.g., the distance from a LIDAR camera to an object, the distance between objects, and so forth). SUMMARY The present embodiments may be related to LIDAR technology, and to AI. Broadly speaking, some embodiments relate to: (i) LIDAR technology based 3D home models for visualizing proposed changes to a home; (ii) LIDAR technology based 3D home models for representation of the home; (iii) LIDAR technology based viewing of objects to be placed in a building; (iv) AI based recommendations for placement of belongings in a residence; (v) LIDAR technology based visualization of landscape design; (vi) LIDAR technology based visualization of utility lines; (vii) LIDAR technology based commercial inventory mapping; (viii) LIDAR technology and AI based floor plan generation; and (ix) LIDAR technology and AI based visualization of directions to interior rooms. In accordance with the described embodiments, the disclosure herein generally addresses, inter alia, systems and methods for visualizing proposed changes to a home. A server may receive light detection and ranging (LIDAR) data generated from a LIDAR camera, measure a plurality of dimensions of a room of the home based upon processor analysis of the LIDAR data, build a 3D model of the room based upon the measured plurality of dimensions, receive an indication of a proposed change to the room, modify the 3D model to include the proposed change to the room, and display a representation of the modified 3D model. In one aspect, a computer-implemented method for visualizing proposed changes to a home may be provided. The computer-implemented method may include, via one or more local or remote processors, transceivers, sensors, and/or servers, (1) receiving light detection and ranging (LIDAR) data generated from a LIDAR camera; (2) measuring a plurality of dimensions of the home based upon processor analysis of the LIDAR data; (3) building a 3D model of the home based upon the measured plurality of dimensions; (4) receiving an indication of a proposed change to the; (5) modifying the 3D model to include the proposed change to the room; and/or (6) displaying a representation of the modified 3D model. The method may include additional, less, or alternate actions, including that discussed elsewhere herein. Further in accordance with the described embodiments, the disclosure herein generally addresses, inter alia, systems and methods for representation of property. A server may receive light detection and ranging (LIDAR) data generated from a LIDAR camera, measure plurality of dimensions of the home based upon processor analysis of the LIDAR data, build a 3D model of the home based upon the measured plurality of dimensions, and display a representation of the 3D model by visually navigating through the 3D model. In another aspect, a computer-implemented method for representation of property may be provided. The computer-implemented method may include, via one or more local or remote processors, transceivers, sensors, and/or servers, (1) receiving light detection and ranging (LIDAR) data generated from a LIDAR camera; (2) measuring a plurality of dimensions of the home based upon processor analysis of the LIDAR data; (3) building a 3D model of the home based upon the measured plurality of dimensions; and/or (4) displaying a representation of the 3D model by visually navigating through the 3D model. The method may include additional, less, or alternate actions, including that discussed elsewhere herein. Further in accordance with the described embodiments, the disclosure herein generally addresses, inter alia, systems and methods for viewing potential placement of an object. A server may receive light detection and ranging (LIDAR) data generated from a LIDAR camera, measure a plurality of dimensions of the object based upon processor analysis of the L