Boundary definition system for a robotic vehicle

• US 9,497,901 B2
• Filed: 08/12/2013
• Issued: 11/22/2016
• Est. Priority Date: 08/14/2012
• Status: Active Grant

• Current Assignee: Husqvarna AB (HUSQVARNA)
• Original Assignee: Husqvarna AB (HUSQVARNA)
• Inventors: Willgert, Mikael
• Primary Examiner(s): Shafi, Muhammad
• Application Number:
  US14/420,963
• Publication Number:
  US 20150201555A1
• Time in Patent Office: 1,198 Days
• Field of Search: 701/26, 3185681-5682, 700/245, 700/243, 700/248, 700/261
• US Class Current: 1/1
• CPC Class Codes: A01D 34/008 for automated or remotely controlled operation
• CPC Class Codes: G05D 1/0221 involving a learning process
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30

Abstract

A method for defining boundaries for a work area of a robotic vehicle may include receiving map data descriptive of a parcel of land and receiving information indicative of at least one reference object disposed on the parcel. The at least one reference object may have corresponding information for defining boundaries for a work area on the parcel associated therewith. The work area may define an area to be worked by a robotic vehicle. The method may further include determining the boundaries responsive to detection of the at least one reference object, and operating the robotic vehicle to remain within the area defined by the boundaries.

Claims

1. A method comprising:

receiving, at processing circuitry associated with a robotic vehicle, map data descriptive of a parcel of land;

receiving, at the processing circuitry, information indicative of at least one reference object disposed on the parcel, the at least one reference object having corresponding information for defining boundaries for a work area on the parcel associated therewith, the work area defining an area to be worked by the robotic vehicle, wherein receiving information indicative of the at least one reference object comprises detecting the at least one reference object via a sensor disposed on the robotic vehicle;

determining, by the processing circuitry, the boundaries responsive to detection of the at least one reference object, wherein the boundaries are defined relative to known locations of the at least one reference object on the parcel of land; and

causing, by the processing circuitry, operation of the robotic vehicle only within the area defined by the boundaries, during the automated performance of a yard maintenance task.

2. The method of claim 1, wherein detecting the at least one reference object via the sensor comprises detecting an invisible marking using the sensor.

3. The method of claim 1, wherein the sensor comprises a camera, and wherein detecting the at least one reference object via the sensor comprises detecting a visible marking using the camera.

4. The method of claim 1, wherein receiving information indicative of the at least one reference object comprises detecting one of a plurality of reference objects, each of the reference objects being disposed to define a segment endpoint for a polygonal shaped work area.

5. The method of claim 1, wherein receiving information indicative of the at least one reference object comprises detecting an object and determining whether the object is one of a plurality of reference objects based on comparing a characteristic of the object detected to a known characteristic of the reference objects.

6. The method of claim 1, wherein determining the boundaries responsive to detection of the at least one reference object comprises identifying the at least one reference object based on unique indicia of the at least one reference object and retrieving the information for defining boundaries for the work area relative to the at least one reference object.

7. The method of claim 6, wherein the unique indicia is associated with a sequential number defining an order of boundary segment endpoints, or wherein the unique indicia is associated with type information indicating a boundary type associated with the at least one reference object.

8. The method of claim 6, wherein determining the boundaries further includes determining a position of the robotic vehicle relative to the at least one reference object using triangulation or stereo view.

9. The method of claim 6, wherein the boundary type is an external boundary or an internal exclusion area boundary.

10. The method of claim 1, wherein operating the robotic vehicle to remain within the area defined by the boundaries comprises:

directing vehicle operation responsive to repeated detections of the boundaries to avoid the boundaries based on corresponding repeated detections of reference objects;

or

operating the robotic vehicle to learn boundary locations based on reference object location and, thereafter, operating the robotic vehicle using learned boundary locations subsequent to removal of reference objects.

11. A robotic vehicle comprising processing circuitry configured to:

receive map data descriptive of a parcel of land;

receive information indicative of at least one reference object disposed on the parcel, the at least one reference object having corresponding information for defining boundaries for a work area on the parcel associated therewith, the work area defining an area to be worked by the robotic vehicle, wherein receiving information indicative of the at least one reference object comprises detecting the at least one reference object via a sensor disposed on the robotic vehicle;

determine the boundaries responsive to detection of the at least one reference object, wherein the boundaries are defined relative to known locations of the at least one reference object on the parcel of land; and

cause operation of the robotic vehicle only within the area defined by the boundaries, during the automated performance of a yard maintenance task.

12. The robotic vehicle of claim 11, wherein detecting the at least one reference object via the sensor comprises detecting an invisible marking using the sensor.

13. The robotic vehicle of claim 11, wherein the sensor comprises a camera, and wherein detecting the at least one reference object via the sensor comprises detecting a visible marking using the camera.

14. The robotic vehicle of claim 11, wherein receiving information indicative of the at least one reference object comprises:

detecting one of a plurality of reference objects, each of the reference objects being disposed to define a segment endpoint for a polygonal shaped work area;

or

detecting an object and determining whether the object is one of a plurality of reference objects based on comparing a characteristic of the object detected to a known characteristic of the reference objects.

15. The robotic vehicle of claim 11, wherein determining the boundaries responsive to detection of the at least one reference object comprises identifying the at least one reference object based on unique indicia of the at least one reference object and retrieving the information for defining boundaries for the work area relative to the at least one reference object.

16. The robotic vehicle of claim 15, wherein the unique indicia is associated with a sequential number defining an order of boundary segment endpoints, or wherein the unique indicia is associated with type information indicating a boundary type associated with the at least one reference object.

17. The robotic vehicle of claim 15, wherein determining the boundaries further includes determining a position of the robotic vehicle relative to the at least one reference object using triangulation or stereo view.

18. The robotic vehicle of claim 11, wherein the robotic vehicle is a robotic mower or a watering robot.