Mower with object detection system

• US 9,563,204 B2
• Filed: 08/12/2013
• Issued: 02/07/2017
• 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): Hilgendorf, Dale W
• Application Number:
  US14/420,912
• Publication Number:
  US 20150220086A1
• Time in Patent Office: 1,275 Days
• 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 1/0231 using optical position detecting means position-fixing by using electromagnetic waves other than radio waves, e.g. optical position detecting means G01S5/16
• CPC Class Codes: G05D 1/0238 using obstacle or wall sensors G05D1/0246 and G05D1/0289 take precedence; lidar systems designed for anti-collision purposes G01S17/93

Abstract

A method for processing object detection-related information may include receiving information indicative of an encounter between a robotic vehicle and an object responsive to communication received from a sensor of the robotic vehicle while the robotic vehicle transits a parcel, determining a location of the robotic vehicle at a time corresponding to occurrence of the encounter, determining whether the location corresponds to a location associated with a known object associated with the parcel, and classifying the object as an unknown object based on the location not corresponding to the location associated with the known object.

Claims

1. A method comprising:

receiving information indicative of an encounter between a robotic vehicle and an object responsive to communication received from a sensor of the robotic vehicle while the robotic vehicle transits a parcel;

determining a location of the robotic vehicle at a time corresponding to occurrence of the encounter;

determining whether the location corresponds to a location associated with a known object associated with the parcel;

classifying the object as an unknown object based on the location not corresponding to the location associated with the known object, and

defining a safety distance for the object based on a classification of the object,

wherein defining the safety distance comprises defining a first safety distance for the object if the object is classified as the known object and defining a larger second safety distance for the object if the object is classified as the unknown object.

2. The method of claim 1, further comprising storing the location in association with the encounter in response to the object being classified as the unknown object.

3. The method of claim 2, further comprising, in response to a plurality of encounters at a same location, classifying a previously unknown object as a fixed object.

4. The method of claim 2, further comprising, in response to more than one encounter at a same location within a given period of time, classifying a previously unknown object as a fixed object.

5. The method of claim 2, further comprising, in response to operator input, classifying a previously unknown object as a fixed object.

6. The method of claim 2, wherein storing the location comprises storing the location locally at the robotic vehicle or remotely.

7. The method of claim 6, further comprising enabling an operator to delete the stored location.

8. The method of claim 1, wherein determining the location comprises determining the location using one or more of global positioning system, inertial navigation, optical flow, radio navigation, and visual location techniques.

9. The method of claim 1, wherein the sensor comprises a camera, a radar device, a laser scanner, or an ultrasonic sensor.

10. The method of claim 1, wherein determining the location comprises determining the location relative to a map stored at the robotic vehicle.

11. A robotic vehicle comprising processing circuitry configured to:

receive information indicative of an encounter between a robotic vehicle and an object responsive to communication received from a sensor of the robotic vehicle while the robotic vehicle transits a parcel;

determine a location of the robotic vehicle at a time corresponding to occurrence of the encounter;

determine whether the location corresponds to a location associated with a known object associated with the parcel;

classify the object as an unknown object based on the location not corresponding to the location associated with the known object, and

define a safety distance for the object based on a classification of the object,

wherein defining the safety distance comprises defining a first safety distance for the object if the object is classified as the known object and defining a larger second safety distance for the object if the object is classified as the unknown object.

12. The robotic vehicle of claim 11, further comprising storing the location in association with the encounter in response to the object being classified as the unknown object.

13. The robotic vehicle of claim 12, further comprising, in response to a plurality of encounters at a same location, classifying a previously unknown object as a fixed object.

14. The robotic vehicle of claim 12, further comprising, in response to more than one encounter at a same location within a given period of time, classifying a previously unknown object as a fixed object.

15. The robotic vehicle of claim 12, further comprising, in response to operator input, classifying a previously unknown object as a fixed object.

16. The robotic vehicle of claim 12, wherein storing the location comprises storing the location locally at the robotic vehicle or remotely.