IP Library › Granted Patent US 10,310,510
Granted Patent B2
US 10,310,510 · App. 15/538,002 · Granted Jun 4, 2019

Robotic vehicle grass structure detection

Inventors: Björn Mannefred (Jönköping, SE); Stefan Grufman (Bankeryd, SE); Anders Mattsson (Ulricehamn, SE)
Assignee: HUSQVARNA AB
G05D1/0246A01B69/008A01D34/008G05D1/0274G06K9/00791G06K9/4609G05D2201/0208
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 10,310,510
App. No.
15/538,002
Granted
Jun 4, 2019
Kind
B2
Abstract

A robotic vehicle may be configured to incorporate multiple sensors to make the robotic vehicle capable of detecting grass by measuring edge data and/or frequency data. In this regard, in some cases, the robotic vehicle may include an onboard positioning module, a detection module, and a mapping module that may work together to give the robotic vehicle a comprehensive understanding of its current location and of the features or objects located in its environment. Moreover, the robotic vehicle may include sensors that enable the modules to collect and process data that can be used to identify grass on a parcel on which the robotic vehicle operates.

Claims (58)

1. A method comprising:

receiving image data and corresponding position data captured by a robotic vehicle traversing a parcel;

comparing the image data with parameters known to identify grass; and

classifying the image data as grass when the image data meets the structural parameters indicative of grass,

wherein comparing the image data with structural parameters indicative of grass comprises:

transforming the image data from the spatial domain to the frequency domain;

performing low pass or high pass filtering on the image data; and

transforming the image data back into the spatial domain.

2. The method of claim 1 , wherein comparing the image data with structural parameters indicative of grass comprises:

measuring at least one of vertical or horizontal edges in the image data;

filtering out the edges that are shorter than a predetermined length known to identify grass; and

identifying the edges that are longer than a predetermined length known to identify grass as not belonging to grass.

3. The method of claim 1 , wherein comparing the image data with structural parameters indicative of grass comprises:

extracting edge features extending in a first direction;

extracting edge features extending in a second direction orthogonal to the first direction;

determining distances between edges in each of the first direction and the second direction; and

making a decision as to grass structure detection.

4. The method of claim 3 , wherein the first direction is horizontal and the second direction is vertical.

5. The method of claim 1 , wherein the robotic vehicle comprises:

a sensor network comprising one or more sensors configured to detect conditions proximate to the robotic vehicle; and

a detection module configured to detect objects proximate to the robotic vehicle using contact-less detection.

6. The method of claim 5 , wherein the sensor network comprises at least one of an inertial measurement unit (IMU), a real time kinematic (RTK)—GPS receiver, a grass detector, or a 2.5D sensor.

7. The method of claim 6 , wherein the detection module is configured to receive grass detection information from at least one of the grass detector or 2.5D sensor.

8. The method of claim 5 , wherein the sensor network further comprises a camera.

9. The method of claim 8 , wherein the camera provides images of objects to the detection module to compare the images with parameters known to identify grass.

10. The method of claim 5 , wherein the robotic vehicle further comprises:

a mapping module configured to generate a map regarding a parcel on which the robotic vehicle operates;

a positioning module configured to determine robotic vehicle position; and

one or more functional components configured to execute a lawn care function.

11. The method of claim 1 , further comprising:

generating the map of the parcel based on data received; and

enabling an operator to interact with the map to view one or more content items associated with respective positions.

12. The method of claim 11 , wherein generating the map of the parcel comprises incorporating input from multiple sensors of the sensor network to determine current position of the robotic vehicle and grass detection information at the current position of the robotic vehicle.

13. The method of claim 11 , wherein the map comprises zones of the parcel in which each of the zones is defined by a corresponding geographic description and corresponding grass detection information.

14. A robotic vehicle, comprising:

a sensor network comprising one or more sensors configured to detect conditions proximate to the robotic vehicle;

a detection module configured to detect objects proximate to the robotic vehicle using contact-less detection, and

processing circuitry configured for:

receiving image data and corresponding position data captured by a robotic vehicle traversing a parcel;

comparing the image data with parameters known to identify grass; and

classifying the image data as grass when the image data meets the parameters known to identify grass,

wherein comparing the image data with parameters known to identify grass comprises:

transforming the image data from the spatial domain to the frequency domain;

performing low pass or high pass filtering on the image data; and

transforming the image data back into the spatial domain.

15. The robotic vehicle of claim 14 , wherein comparing the image data with parameters known to identify grass comprises:

measuring at least one of vertical or horizontal edges in the image data;

filtering out the edges that are shorter than a predetermined length known to identify grass; and

identifying the edges that are longer than a predetermined length known to identify grass as not belonging to grass.

16. The robotic vehicle of claim 15 , wherein comparing the image data with structural parameters indicative of grass comprises:

extracting edge features extending in a first direction;

extracting edge features extending in a second direction orthogonal to the first direction;

determining distances between edges in each of the first direction and the second direction; and

making a decision as to grass structure detection.

17. The robotic vehicle of claim 16 , wherein the first direction is horizontal and the second direction is vertical.

18. The robotic vehicle of claim 14 , wherein the sensor network comprises at least one of an inertial measurement unit (IMU), a real time kinematic (RTK)—GPS receiver, a grass detector, or a 2.5D sensor.

19. The robotic vehicle of claim 18 , wherein the detection module is configured to receive grass detection information from at least one of the grass detector or 2.5D sensor.

20. The robotic vehicle of claim 18 , wherein the sensor network further comprises a camera.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 2, 2017
From: MANNEFRED, BJÖRN; GRUFMAN, STEFAN; MATTSSON, ANDERS
To: HUSQVARNA AB
Reel/Frame 044014/0127 →
Continuity (3)
Provisional Application 62095315 · Dec 22, 2014
Provisional Application 62097312 · Dec 29, 2014
Related Publication 20170344020A1 · Nov 30, 2017
Cited By (14)
US 12,239,055 US 12,296,694 US 12,369,509 US 12,425,197 US 12,443,180 US 12,472,611 US 12,510,892 US 12,564,130 US 12,593,748 US 12,653,097 US 12,677,737 US 12,690,518 US 12,696,838 US 12,714,019