Robot Vacuum Automation Cleaner

Abstract

Camera(s) from a premise may capture video feeds and may send to a computer device for analysis and cleaning tasks. The computer device may classify target objects from the video feeds and may generate cleaning tasks to clean up the target objects. The computer device may select one of a plurality of robot vacuums and send the cleaning tasks to the selected robot vacuum.

What is claimed is: 
     
         1 . A method comprising: 
 receiving, by a computing device, at least one video feed;   scheduling, based on identified objects in the at least one video feed, at least one cleaning device to perform cleaning tasks associated with the identified objects; and   based on detecting a person in the at least one video feed, sending a message to cause the at least one cleaning device to suspend a cleaning task associated with at least one of the identified objects.   
     
     
         2 . The method of  claim 1 , further comprising: 
 determining locations of the identified objects in the at least one video feed;   determining, based on the locations of the identified objects, a corresponding distance between each of the identified objects and the at least one cleaning device;   determining, based on the corresponding distance, a route for causing the at least one cleaning device to move to locations of the identified objects; and    sending a second message to the at least one cleaning device, wherein the second message indicates a cleaning task and the determined route.   
     
     
         3 . The method of  claim 1 , further comprising: 
 identifying, based on the at least one video feed, a floor,   wherein the sending is further based on a distance between the at least one identified object and the floor in the at least one video feed.   
     
     
         4 . The method of  claim 1 , further comprising: 
 resuming the cleaning task associated with the at least one identified object based on determining that the at least one identified object has been placed on a floor in the video feed.   
     
     
         5 . The method of  claim 1 , wherein the sending is further based on a distance between the at least one identified object and the person in the at least one video feed. 
     
     
         6 . The method of  claim 1 , further comprising: 
 resuming the cleaning task based on a distance between two identified objects in the at least one video feed.   
     
     
         7 . The method of  claim 1 , wherein the sending is further based on a distance between two identified objects in the at least one video feed. 
     
     
         8 . A method comprising: 
 receiving, by a computer device, at least one video feed;   determining locations of identified objects in the at least one video feed;   determining, based on the locations of the identified objects, a corresponding distance between each of the identified objects and a cleaning device;   determining, based on the corresponding distance, a route for causing the cleaning device to move to locations of the identified objects; and    sending a first message to the cleaning device, wherein the first message indicates a cleaning task and the determined route.   
     
     
         9 . The method of  claim 8 , wherein determining the locations of the identified objects further comprises: 
 determining a location of at least one camera;   determining relative locations of the identified objects associated with the location of the at least one camera; and   determining, based on the relative locations of the identified objects, the locations of the identified objects.   
     
     
         10 . The method of  claim 8 , wherein determining the route further comprises: 
 determining, based on the corresponding distance between each of the identified objects and the cleaning device, a path for moving from a current location of the cleaning device to a location of one of the identified objects.   
     
     
         11 . The method of  claim 8 , further comprising: 
 determining that a second identified object in the at least one video feed intersects the determined route;   calculating a new route, wherein the new route is calculated to avoid the second identified object; and    sending a second message to the cleaning device, wherein the second message indicates the new route.   
     
     
         12 . The method of  claim 8 , wherein each of the identified objects is identified based on: 
 generating at least one first region proposal associated with the at least one video feed;   extracting, based on the at least one first region proposal, at least one first feature associated with each of the identified objects; and   classifying, based on the at least one first feature, each of the identified objects.   
     
     
         13 . The method of  claim 12 , wherein classifying each of the identified objects further comprises: 
 generating at least one second region proposal associated with the at least one video feed;   extracting, based on at least one second region proposal, at least one second feature associated with each of the identified objects;    classifying, based on the at least one second feature, a second object; and   determining whether each of the identified objects is within a proximity of the second object.   
     
     
         14 . The method of  claim 8 , wherein the identified objects are identified based on: 
 selecting at least one machine learning model; and   identifying, based on the selected machine learning model, the identified objects.   
     
     
         15 . A method comprising: 
 receiving, by a computing device, a first message, wherein the first message indicates a cleaning task and a location of a first identified object;   receiving a second message, wherein the second message indicates a status of the cleaning task associated with the first identified object; and   suspending or resuming, based on the status, the cleaning task.   
     
     
         16 . The method of  claim 15 , wherein the first message indicates the first identified object as at least one of solid or liquid object; and 
       the cleaning task comprises a vacuum action, wherein the first message indicates the first identified object as the solid object; or  
       the cleaning task comprises a mopping action, wherein the first message indicates the first identified object as the liquid object. 
     
     
         17 . The method of  claim 15 , wherein resuming the clean task comprises: 
 releasing at least one type of cleaning solution; and   performing a mopping action after a time period from spraying the at least one type of cleaning solution.   
     
     
         18 . The method of  claim 15 , suspending, based on the status indicating a suspended status, the cleaning task; and  
       wherein the suspended status is based on: 
 a distance between the first identified object and a second identified object being less than a threshold distance. 
 
     
     
         19 . The method of  claim 15 , resuming, based on the status indicating a resume status, the cleaning task; and wherein the resume status is based on: 
 a distance between the first identified object and a second identified object being more than a threshold distance.   
     
     
         20 . The method of  claim 15 , wherein resuming the clean task comprises: 
 performing the cleaning task; and   sending a third message, wherein the third message indicates a result of the cleaning task.