# US 10,310,510 B2 · Robotic vehicle grass structure detection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,310,510 B2
- Document ID: US10310510B2
- Status: Granted
- Kind: B2
- Application number: 15/538,002
- Filed: 2015-10-20
- Published: 2017-11-30
- Granted: 2019-06-04
- Earliest claimed: 2014-12-22
- Assignees: Husqvarna AB
- Applicants: Husqvarna AB
- Inventors: Björn Mannefred; Stefan Grufman; Anders Mattsson
- Web page: https://patentgrep.com/patent/US10310510B2

## CPC

- G05D 1/0246: {using a video camera in combination with image processing means}
- A01B 69/008: {automatic}
- A01D 34/008: {for automated or remotely controlled operation}
- G05D 1/0274: {using mapping information stored in a memory device (navigation using map-matching G01C21/30)}
- G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- A01B: SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL (making or covering furrows or holes for sowing, planting or manuring A01C5/00; mowers convertible to soil working apparatus or capable of soil working A01D42/04; mowers combined with soil working implements A01D43/12; soil working for engineering purposes E01, E02, E21)
- A01D: HARVESTING; MOWING
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## 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

### Claim 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.

### Claim 2 (depends on 1)

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.

### Claim 3 (depends on 1)

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.

### Claim 4 (depends on 3)

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

### Claim 5 (depends on 1)

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.

### Claim 6 (depends on 5)

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.

### Claim 7 (depends on 6)

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.

### Claim 8 (depends on 5)

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

### Claim 9 (depends on 8)

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.

### Claim 10 (depends on 5)

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.

### Claim 11 (depends on 1)

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.

### Claim 12 (depends on 11)

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.

### Claim 13 (depends on 11)

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.

### Claim 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.

### Claim 15 (depends on 14)

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.

### Claim 16 (depends on 15)

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.

### Claim 17 (depends on 16)

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

### Claim 18 (depends on 14)

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.

### Claim 19 (depends on 18)

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.

### Claim 20 (depends on 18)

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