Method for efficient operation of mobile robotic devices

• US 10,882,186 B1
• Filed: 05/10/2018
• Issued: 01/05/2021
• Est. Priority Date: 05/11/2017
• Status: Active Grant

• Current Assignee: Ai Incorprated
• Original Assignee: Ai Incorprated
• Inventors: Ebrahimi Afrouzi, Ali, Zhang, Chen
• Primary Examiner(s): Figueroa, Jaime
• Application Number:
  US15/976,853
• Time in Patent Office: 971 Days
• Field of Search: 700245, 700255
• CPC Class Codes: B25J 11/0085 Cleaning
• CPC Class Codes: B25J 9/1666 Avoiding collision or forbidden zones
• CPC Class Codes: G05D 1/0217 in accordance with energy consumption, time reduction or distance reduction criteria
• CPC Class Codes: G05D 1/0221 involving a learning process
• CPC Class Codes: Y10S 901/01 Mobile robot
• CPC Class Codes: Y10S 901/02 Arm motion controller

Abstract

A method for efficient navigational and work duty planning for mobile robotic devices. A mobile robotic device will autonomously create a plan for navigation and work duty functions based on data compiled regarding various considerations in the work environment. These factors include what type of work surface is being operated on, whether dynamic obstacles are present in the work environment or not and the like factors.

Claims

1. A method for a mobile robotic cleaning devices to autonomously plan work duties in a work environment in a most efficient manner possible, the method comprising:

accessing historical data stored from prior work cycles, the historical data being indicative of a type of work surface and a presence or absence of dynamic obstacles in a given work area;

processing probabilities based on the historical data as to a most efficient navigational route and operational work duties for the mobile robotic cleaning device to partake in with one or more processors of the mobile robotic cleaning device;

enacting the most efficient navigational route and operational work duties by the mobile robotic cleaning device;

capturing new data by one or more sensors of the mobile robotic cleaning device while enacting the navigational route and operational work duties within the work environment;

processing new data with the one or more processors of the mobile robotic cleaning device;

assessing a penalty score for a work area within the work environment when a dynamic obstacle is detected in the work area with the one or more processors; and

enacting a new most efficient navigational route and operational work duties by the mobile robotic cleaning device when discrepancies exist between the new data and the historical data.

2. The method of claim 1 wherein the one or more processors of the mobile robotic cleaning device autonomously determines that the most efficient cleaning manner is to clean one work surface type at a time before cleaning a different work surface type.

3. The method of claim 2 wherein the mobile robotic cleaning device thereafter cleans one work surface type at a time completely before cleaning a second work surface type.

4. The method of claim 1 wherein the one or more processors of the mobile robotic cleaning device monitors the presence or absence of dynamic obstacles in the work environment.

5. The method of claim 4 wherein when a dynamic obstacle is detected, the one or more processors of the mobile robotic cleaning device collects data regarding the location this encounter occurred at, the time this encounter took place, the date of the encounter, and type of dynamic obstacle encountered.

6. The method of claim 1 wherein the one or more processors of the mobile robotic cleaning device autonomously determines to perform work duties in a different work area upon detecting the presence of a dynamic obstacle in a given work area.

7. The method of claim 1 wherein the one or more processors of the mobile robotic cleaning device autonomously determines based on processed probabilities that it is likely to encounter a dynamic obstacle in a work area and should therefore perform work duties in a different area where a presence of a dynamic obstacle is unlikely.

8. The method of claim 7 wherein after cleaning the work area the mobile robotic cleaning device thereafter checks other work areas where there have been a historical presence of a dynamic obstacle to determine when to clean those work areas.

9. The method of claim 1 wherein when a penalty score is assessed for the work area, the mobile robotic device will not conduct work duties or navigate to that area until the penalty score has reached a predetermined threshold.

10. The method of claim 1 wherein the penalty score assessed for the work area decreases at a fixed rate over a fixed time interval.

11. The method of claim 1 wherein the penalty score assessed for the work area decreases every time the mobile robotic device performs work duties in a different work area.

12. The method of claim 1 wherein the one or more processors of the mobile robotic cleaning device creates an internal map of the work environment with specific markers on the map marking the location of different work surface types and dynamic obstacles detected during operation.

13. The method of claim 1 wherein the new data consists of the mobile robotic cleaning device autonomously learning the boundaries or edges between different work surface types during operation.

14. The method of claim 13 wherein the one or more processors of the mobile robotic cleaning device learns the boundaries or edges between different work surface types from other mobile robotic devices.

15. The method of claim 1 wherein the layout of an entire work area contributes to the consideration of a mobile robotic cleaning device determining what constitutes the most efficient navigational route and operational work duties.

16. The method of claim 1 wherein the amount of battery power left is a contributing factor to the one or more processors of a mobile robotic cleaning device determining what constitutes the most efficient navigational route and operational work duties.

17. The method of claim 1 wherein the one or more processors of the mobile robotic cleaning device learns of a presence of a current dynamic obstacle in a work area from data shared by another mobile robotic device.

18. The method of claim 1 wherein the one or more processors of the mobile robotic cleaning device learns of a historical presence of a dynamic obstacle in a work area from historical data shared by another mobile robotic device.

19. The method of claim 1 wherein the mobile robotic device is a mobile robotic device other than a mobile robotic cleaning device.

20. The method of claim 1 wherein the penalty score quantifies the preference of cleaning the work area, wherein the preference is based on at least the presence of dynamic obstacles within the work area.