IP Library › Granted Patent US 12,443,184
Granted Patent B2
US 12,443,184 · App. 17/553,850 · Granted Oct 14, 2025

Smart sanitation robot

Inventors: Florian Geissler (Munich, DE); Say Chuan Tan (Penang, MY); Chien Chern Yew (Penang, MY); Ying Wei Liew (Sg Ara, MY); Neslihan Kose Cihangir (Munich, DE)
Assignee: Intel Corporation
G05D1/0088A47L9/2826A47L9/2852G01D21/00G05B13/027A47L11/4011A47L2201/04A47L2201/06G05B15/02
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,443,184
App. No.
17/553,850
Granted
Oct 14, 2025
Kind
B2
Abstract

Disclosed herein are systems, devices, and methods of a sanitation system for intelligently adapting the cleaning operations of a sanitation robot. The sanitation system detects a plurality of objects in a workspace and then, for each detected object of the plurality of objects, determines a sanitation score for the detected object based on observations of the detected object over a time period. The sanitation system generates a cleaning schedule based on the sanitation score for each detected object, wherein the cleaning schedule comprises instructions for a sanitation robot to clean the plurality of objects.

Claims (35)

1. A device comprising:

a processor configured to:

detect a plurality of objects in a workspace;

determine, for each detected object of the plurality of objects, a sanitation score for the detected object based on observations of the detected object over a time period;

generate a cleaning schedule based on the sanitation score for each detected object, wherein the cleaning schedule comprises instructions for a sanitation robot to clean the plurality of objects, wherein the cleaning schedule comprises an ordered list of cleaning tasks for the plurality of objects, wherein each object of the plurality of objects is associated with a corresponding cleaning task of the ordered list of cleaning tasks;

determine, for each cleaning task, a corresponding utility value for the corresponding cleaning task, wherein the corresponding utility value is based on the sanitation score divided by an estimated time to complete the corresponding cleaning task;

order the ordered list of cleaning tasks based on the corresponding utility value for the corresponding cleaning task; and

control the sanitation robot to execute the cleaning schedule according to the ordered list of cleaning tasks.

2. The device of claim 1 , wherein the observations of the detected object comprise a frequency with which the detected object is touched over the time period.

3. The device of claim 1 , further comprising a sensor configured to collect sensor data about the workspace, wherein the sensor data is indicative of the observations.

4. The device of claim 3 , wherein the processor configured to detect the plurality of objects in the workspace comprises the processor configured to analyze the sensor data to identify the plurality of objects within the workspace.

5. The device of claim 4 , wherein processor configured to analyze the sensor data comprises the processor configured to use a neural network identify the plurality of objects.

6. The device of claim 1 , wherein the observations of each detected object of the plurality of objects are indicative of a surface type of the detected object, wherein the cleaning schedule comprises a cleaning task associated with each detected object, and wherein the processor is configured to determine the cleaning task for the detected object based on the surface type of the detected object.

7. The device of claim 1 , wherein the processor is configured to determine the sanitation score based on a predetermined sanitation score derived from a usage class of each detected object, wherein the usage class comprises at least one of a high-touch usage class or a low-touch usage class.

8. The device of claim 1 , wherein the observations of the detected object comprise a manner in which the detected object is touched over the time period, wherein the manner is indicative of at least one of a duration of a touch, an extent of area covered by the touch, or a force associated with the touch.

9. The device of claim 1 , wherein the sanitation score is proportional to a number of persons detected within the workspace during the time period.

10. The device of claim 1 , wherein the processor is configured to determine the sanitation score based on a layout of the workspace and a location of the detected object within the layout.

11. The device of claim 1 , the processor configured to determine the sanitation score based on the observations of the detected object comprises the processor configured to group the observations into a plurality of observation classes, wherein each observation class of the plurality of observation classes has an associated weighting, wherein the processor is configured to calculate the sanitation score based on a weighted sum of each observation class multiplied by the associated weighting.

12. The device of claim 1 , wherein the processor is configured to determine the cleaning schedule based on a location of each detected object within the workspace.

13. The device of claim 12 , wherein the processor is configured to determine the cleaning schedule based on an object class of each detected object, wherein the object class describes an object type of the detected object.

14. The device of claim 1 , wherein the device comprises a server that is remote to the sanitation robot.

15. A non-transitory computer readable medium, including instructions which, if executed, cause a processor to:

detect a plurality of objects in a workspace;

determine, for each detected object of the plurality of objects, a sanitation score for the detected object based on observations of the detected object over a time period;

generate a cleaning schedule based on the sanitation score for each detected object, wherein the cleaning schedule comprises instructions for a sanitation robot to clean the plurality of objects, wherein the cleaning schedule comprises an ordered list of cleaning tasks for the plurality of objects, wherein each object of the plurality of objects is associated with a corresponding cleaning task of the ordered list of cleaning tasks;

determine, for each cleaning task, a corresponding utility value for the corresponding cleaning task, wherein the corresponding utility value is based on the sanitation score divided by an estimated time to complete the corresponding cleaning task;

order the ordered list of cleaning tasks based on the corresponding utility value for the corresponding cleaning task; and

control the sanitation robot to execute the cleaning schedule according to the ordered list of cleaning tasks.

16. The non-transitory computer readable medium of claim 15 , wherein the processor is configured to order the ordered list of cleaning tasks based on a difference between a location of each detected object and a location of the sanitation robot within the workspace.

17. The non-transitory computer readable medium of claim 15 , wherein the processor is configured to remove a cleaning task from the ordered list of cleaning tasks based on a safety observation at a location of the cleaning task.

18. The device of claim 1 , wherein the processor configured control the sanitation robot to execute the cleaning schedule according to the ordered list of cleaning tasks comprises the processor configured to control the sanitation robot to:

execute a first cleaning task in the ordered list of cleaning tasks;

redetermine, for each cleaning task, the corresponding utility value for the corresponding cleaning task;

reorder the ordered list based on the corresponding utility value for the corresponding cleaning task; and

preempt execution of the first cleaning task with execution of an other cleaning task of the ordered list based on the corresponding utility value of the other cleaning task being higher than the utility value of the first cleaning task.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 10, 2022
From: GEISSLER, FLORIAN; TAN, SAY CHUAN; YEW, CHIEN CHERN; LIEW, YING WEI; KOSE CIHANGIR, NESLIHAN
To: INTEL CORPORATION
Reel/Frame 059216/0428 →
Continuity (1)
Related Publication 20220107642A1 · Apr 7, 2022
References Cited (16)
US 20180272540A1 · Cronin · 2018 [cited by examiner]
US 20190029486A1 · Suvarna et al. · 2019 [cited by applicant]
US 20190064815A1 · Haynes · 2019 [cited by examiner]
US 20200100639A1 · Ullmann · 2020 [cited by examiner]
US 20210346543A1 · Brooks · 2021 [cited by examiner]
US 20220287530A1 · Xi · 2022 [cited by examiner]
US 20240118714A1 · Ebrahimi Afrouzi · 2024 [cited by examiner]
US 20250000320A1 · Sun · 2025 [cited by examiner]
CN 109602343A · 2019 [cited by applicant]
CN 111568314A · 2020 [cited by applicant]
CN 111657798A · 2020 [cited by applicant]
European Search Report issued for the corresponding European patent application No. 22200262.8, dated Jul. 5, 2023, 9 pages (for informational purposes only). [cited by applicant]
A. Abdalwhab et al., “Zero-Shot Object Detection for Indoor Robots” International Joint Conference on Neural Networks, IEEE, Jul. 14-19, 2019, Budapest, Hungary. [cited by applicant]
Y. W. Chao et al., “Learning to Detect Human-Object Interactions” 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, 10 pages. [cited by applicant]
D. Zmaranda et al., “Using Fixed Priority Pre-emptive Scheduling in Real-Time Systems” International Journal of Computers, Communications & Control (IJCCC) , Apr. 2011, vol. VI, No. 1, pp. 187-195. [cited by applicant]
Fraunhofer, “Desinfection robot: Value crated by linnking up to building data”, Recearch News, May 3, 2021, 3 pages. [cited by applicant]