# US 2026/0083291 A1 · Robot Vacuum Automation Cleaner

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0083291 A1
- Document ID: US20260083291A1
- Status: Published application
- Kind: A1
- Application number: 18/898,104
- Filed: 2024-09-26
- Published: 2026-03-26
- Earliest claimed: 2024-09-26
- Assignees: Comcast Cable Communications, LLC
- Applicants: Comcast Cable Communications, LLC
- Inventors: Aarif Muhamed; Rubakanthan Nandakumar; Ganesh Ranganathan
- Web page: https://patentgrep.com/patent/US20260083291A1

## CPC

- A47L 9/2805: {Parameters or conditions being sensed}
- A47L 9/2852: {Elements for displacement of the vacuum cleaner or the accessories therefor, e.g. wheels, casters or nozzles}
- A47L 9/2894: {Details related to signal transmission in suction cleaners}
- A47L 11/4011: {Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor}
- A47L 2201/04: Automatic control of the travelling movement; Automatic obstacle detection
- A47L 2201/06: Control of the cleaning action for autonomous devices; Automatic detection of the surface condition before, during or after cleaning
- A47L: DOMESTIC WASHING OR CLEANING (brushes A46B; cleaning quantities of bottles or of other hollow articles of one kind B08B9/00; laundry D06F); SUCTION CLEANERS IN GENERAL (cleaning in general B08)

## 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.

## Claims

### Claim 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.

### Claim 2 (depends on 1)

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.

### Claim 3 (depends on 1)

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.

### Claim 4 (depends on 1)

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.

### Claim 5 (depends on 1)

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.

### Claim 6 (depends on 1)

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.

### Claim 7 (depends on 1)

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.

### Claim 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.

### Claim 9 (depends on 8)

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.

### Claim 10 (depends on 8)

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.

### Claim 11 (depends on 8)

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.

### Claim 12 (depends on 8)

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.

### Claim 13 (depends on 12)

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.

### Claim 14 (depends on 8)

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.

### Claim 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.

### Claim 16 (depends on 15)

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.

### Claim 17 (depends on 15)

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.

### Claim 18 (depends on 15)

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.

### Claim 19 (depends on 15)

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.

### Claim 20 (depends on 15)

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.
