Carpet drift estimation using differential sensors or visual measurements

• US 9,427,875 B2
• Filed: 11/23/2015
• Issued: 08/30/2016
• Est. Priority Date: 06/08/2012
• Status: Active Grant

• Current Assignee: iRobot Corporation
• Original Assignee: iRobot Corporation
• Inventors: Goel, Dhiraj, Eade, Ethan, Fong, Philip, Munich, Mario E.
• Primary Examiner(s): Edwards, Jerrah
• Assistant Examiner(s): MOTT, ADAM R
• Application Number:
  US14/949,002
• Publication Number:
  US 20160075032A1
• Time in Patent Office: 281 Days
• US Class Current: 1/1
• CPC Class Codes: B25J 11/0085 Cleaning
• CPC Class Codes: B25J 5/007 mounted on wheels
• CPC Class Codes: B25J 9/1628 characterised by the control loop
• CPC Class Codes: B25J 9/1664 characterised by motion, path, trajectory planning
• CPC Class Codes: B25J 9/1697 Vision controlled systems
• CPC Class Codes: G05D 1/0253 extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow determining position or orientation from images G06T7/70
• CPC Class Codes: G05D 1/0268 using internal positioning means
• CPC Class Codes: G05D 1/027 comprising intertial navigation means, e.g. azimuth detector inertial navigation G01C21/16; inertial navigation combined with non-inertial navigation instruments G01C21/165
• CPC Class Codes: G05D 1/0272 comprising means for registering the travel distance, e.g. revolutions of wheels measuring distance traversed on the ground by vehicles, e.g. using odometers G01C22/00
• CPC Class Codes: G05D 1/24 Arrangements for determining position or orientation
• CPC Class Codes: G05D 1/244 using passive navigation aids external to the vehicle, e.g. markers, reflectors or magnetic means
• CPC Class Codes: G05D 1/40 Control within particular dimensions
• CPC Class Codes: G05D 1/644 Optimisation of travel parameters, e.g. of energy consumption, journey time or distance
• CPC Class Codes: Y10S 901/01 Mobile robot

Abstract

Apparatus and methods for carpet drift estimation are disclosed. In certain implementations, a robotic device includes an actuator system to move the body across a surface. A first set of sensors can sense an actuation characteristic of the actuator system. For example, the first set of sensors can include odometry sensors for sensing wheel rotations of the actuator system. A second set of sensors can sense a motion characteristic of the body. The first set of sensors may be a different type of sensor than the second set of sensors. A controller can estimate carpet drift based at least on the actuation characteristic sensed by the first set of sensors and the motion characteristic sensed by the second set of sensors.

Claims

1. A robotic device comprising:

a camera;

an actuator system configured to move the robotic device across a surface, the actuator system comprising;

a plurality of left wheels interconnected by a left track, and

a plurality of right wheels interconnected by a right track; and

a controller coupled to the camera, wherein the controller is configured to;

extract features from two or more images captured by the camera;

match extracted features from the two or more images;

generate visual observations of motion based on a motion of matching extracted features relative to the two or more images;

estimate drift based at least on the visual observations of motion;

determine, from the estimated drift, whether the surface is carpeted or non-carpeted;

in response to determination that the surface is carpeted, generate a carpet drift vector based at least on the visual observations of motion;

generate commands, using the carpet drift vector, configured to compensate for carpet drift; and

send the generated commands to the actuator system to compensate for the carpet drift.

2. The robotic device of claim 1, wherein the controller is further configured to generate the visual observations of motion in response to a determination that a difference between the motion of the matching extracted features and a motion predicted by odometry estimates is below a threshold.

3. The robotic device of claim 1, wherein the controller is further configured to estimate the drift using a Kalman filter to process the visual observations of motion.

4. The robotic device of claim 1, wherein the visual observations of motion indicate a path angle of the robotic device.

5. The robotic device of claim 1, wherein the robotic device is configured to match the extracted features from the two or more images using epipolar matching.

6. The robotic device of claim 1, wherein matching the extracted features from the two or more images comprises a translation direction estimation and a camera rotation estimation.

7. The robotic device of claim 1, wherein the features are extracted using scale invariant feature transformation.

8. The robotic device of claim 1, further comprising a vacuum assembly and a brush comprising bristles.

9. A-robotic device comprising:

an imaging sensor;

an actuator system configured to move the robotic device across a surface, the actuator system comprising;

a plurality of left wheels interconnected by a left track, and

a plurality of right wheels interconnected by a right track; and

a controller communicatively coupled to the imaging sensor, wherein the controller is configured to;

extract features from two or more images captured by the imaging sensor;

match extracted features from the two or more images;

generate visual observations of motion based on a motion of matching extracted features relative to the two or more images;

estimate drift based at least on the visual observations of motion;

determine, from the estimated drift, whether the surface is carpeted or non-carpeted;

in response to determination that the surface is carpeted, generate a drift vector based at least on the visual observations of motion;

generate commands, using the drift vector, configured to compensate for the estimated drift; and

send the generated commands to the actuator system to compensate for the estimated drift.

10. The robotic device of claim 9, wherein the controller is further configured to generate the visual observations of motion in response to a determination that a difference between the motion of the matching extracted features and a motion predicted by odometry estimates is below a threshold.

11. The robotic device of claim 9, wherein the controller is further configured to estimate the drift using a Kalman filter to process the visual observations of motion.

12. The robotic device of claim 9, wherein the visual observations of motion indicate a path angle of the robotic device.

13. The robotic device of claim 9, wherein the robotic device is configured to match the extracted features from the two or more images using epipolar matching.

14. The robotic device of claim 9, wherein matching the extracted features from the two or more images comprises a translation direction estimation and an imaging sensor rotation estimation.

15. The robotic device of claim 9, further comprising a body, the body comprising arcuate edges.