Autonomous robotic monitor for alerting of hazards

Patent metadata

Field	Value
Publication number	US-10933528-B2
Application number	US-201816028591-A
Country	US
Kind code	B2
Filing date	Jul 6, 2018
Priority date	Jul 6, 2018
Publication date	Mar 2, 2021
Grant date	Mar 2, 2021

Abstract

A computer-implemented method includes detecting, by one or more sensors of a robot, one or more characteristics of a current point on a surface on which the robot travels. A feature vector is constructed to describe the current point on the surface on which the robot travels, based on the one or more characteristics. The feature vector is mapped to a confidence level that a hazard exists at the current point on the surface. It is determined that the confidence level meets a threshold confidence. An alert is issued in association with the current point on the surface, based on the confidence level meeting the threshold confidence.

First claim

What is claimed is:

1. A method for a robot comprising:
detecting, by the robot, one or more characteristics of a current point on a surface on which the robot travels using one or more sensors of the robot; and
determining, by the robot, a hazard on the surface on which the robot travels, the determining comprising:
constructing a feature vector describing the current point on the surface on which the robot travels, based on the one or more characteristics;
mapping the feature vector to a confidence level that the hazard exists at the current point on the surface;
determining that the confidence level meets a threshold confidence; and
issuing an alert associated with the current point on the surface, based on the confidence level meeting the threshold confidence; and

remediating, by the robot, the hazard associated with the alert.

2. The method of claim 1 , wherein mapping the feature vector to the confidence level comprises training a classifier to map feature vectors to confidence levels.

3. The method of claim 1 , further comprising:
assigning a sensitivity level to the current point on the surface; and
activating, at the current point on the surface, an additional sensor of the robot, based on the sensitivity level assigned to the current point on the surface.

4. The method of claim 1 , further comprising:
assigning a sensitivity level to the current point on the surface; and
determining a frequency at which the robot returns to the current point on the surface, based at least in part on the sensitivity level assigned to the current point on the surface.

5. The method of claim 1 , wherein issuing the alert comprises placing, by the robot, a physical object on the surface.

6. The method of claim 5 , wherein issuing the alert further comprises requesting that one or more other robots place one or more other physical objects on the surface.

7. The method of claim 1 , wherein issuing the alert comprises generating a heatmap indicating a plurality of confidence levels of a plurality of points across the surface.

8. The method of claim 1 , wherein the robot is a retrofitted cleaning robot.

9. An autonomous robot comprising:
one or more sensors, the autonomous robot having computer-readable instructions configured to:
detect one or more characteristics of a current point on a surface on which the autonomous robot travels using the one or more sensors; and
determine a hazard on the surface on which the autonomous robot travels, the determine comprising:
construct a feature vector describing the current point on the surface on which the autonomous robot travels, based on the one or more characteristics;
map the feature vector to a confidence level that a hazard exists at the current point on the surface;
determine that the confidence level meets a threshold confidence; and
issue an alert associated with the current point on the surface, based on the confidence level meeting the threshold confidence.

10. The autonomous robot of claim 9 , wherein, to map the feature vector to the confidence level, the computer-readable instructions further cause the one or more processors to train a classifier to map feature vectors to confidence levels.

11. The autonomous robot of claim 9 , wherein the computer-readable instructions further cause the one or more processors to:
assign a sensitivity level to the current point on the surface; and
activate, at the current point on the surface, an additional sensor of the autonomous robot, based on the sensitivity level assigned to the current point on the surface.

12. The autonomous robot of claim 9 , wherein the computer-readable instructions further cause the one or more processors to:
assign a sensitivity level to the current point on the surface; and
determine a frequency at which the autonomous robot returns to the current point on the surface, based at least in part on the sensitivity level assigned to the current point on the surface.

13. The autonomous robot of claim 9 , wherein, to issue the alert, the computer-readable instructions further cause the one or more processors to place a physical object on the surface.

14. The autonomous robot of claim 9 , wherein, to issue the alert, the computer-readable instructions further cause the one or more processors to generate a heatmap indicating a plurality of confidence levels of a plurality of points across the surface.

15. A computer-program product for detecting hazards, the computer-program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:
detecting one or more characteristics of a current point on a surface on which the robot travels using one or more sensors of a robot; and
determining a hazard on the surface on which the robot travels, the determining comprising:
constructing a feature vector describing the current point on the surface on which the robot travels, based on the one or more characteristics;
mapping the feature vector to a confidence level that a hazard exists at the current point on the surface;
determining that the confidence level meets a threshold confidence; and
issuing an alert associated with the current point on the surface, based on the confidence level meeting the threshold confidence.

16. The computer-program product of claim 15 , wherein mapping the feature vector to the confidence level comprises training a classifier to map feature vectors to confidence levels.

17. The computer-program product of claim 15 , the method further comprising:
assigning a sensitivity level to the current point on the surface; and
activating, at the current point on the surface, an additional sensor of the robot, based on the sensitivity level assigned to the current point on the surface.

18. The computer-program product of claim 15 , the method further comprising:
assigning a sensitivity level to the current point on the surface; and
determining a frequency at which the robot returns to the current point on the surface, based at least in part on the sensitivity level assigned to the current point on the surface.

19. The computer-program product of claim 15 , wherein issuing the alert comprises placing, by the robot, a physical object on the surface.

20. The computer-program product of claim 15 , wherein issuing the alert comprises generating a heatmap indicating a plurality of confidence levels of a plurality of points across the surface.

Assignees

• IBM

Inventors

• Gordon Michael S
• Kozloski James R
• Kundu Ashish
• Pickover Clifford A

Classifications

• G08B21/20

  responsive to moisture · CPC title

• B25J11/008

  Manipulators for service tasks · CPC title

• G08B21/182

  Level alarms, e.g. alarms responsive to variables exceeding a threshold · CPC title

• G08B21/24

  Reminder alarms, e.g. anti-loss alarms · CPC title

• B25J9/1666 Primary

  Avoiding collision or forbidden zones · CPC title