Systems and methods for filtering potentially unreliable visual data for visual simultaneous localization and mapping

• US 7,272,467 B2
• Filed: 12/17/2003
• Issued: 09/18/2007
• Est. Priority Date: 12/17/2002
• Status: Active Grant

• Current Assignee: iRobot Corporation
• Original Assignee: Evolution Robotics Inc. (iRobot Corporation)
• Inventors: Di Bernardo, Enrico, Pirjanian, Paolo, Karlsson, L. Niklas, Goncalves, Luis Filipe Domingues
• Primary Examiner(s): Black; Thomas
• Assistant Examiner(s): Marc; McDieunel
• Application Number:
  US10/739,919
• Publication Number:
  US 20040167667A1
• Time in Patent Office: 1,371 Days
• Field of Search: 700/245
• US Class Current: 700/245
• CPC Class Codes: G01C 21/12 executed aboard the object being navigated; Dead reckoning
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• 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 1/0234 using optical markers or beacons optical beacons per se G01S1/70
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/0242 using non-visible light signals, e.g. IR or UV signals
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0248 in combination with a laser lasers per se H01S
• 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 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G05D 1/0278 using satellite positioning signals, e.g. GPS
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 7/55 from multiple images
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: Y10S 901/01 Mobile robot
• CPC Class Codes: Y10S 901/46 Sensing device
• CPC Class Codes: Y10S 901/47 Optical
• CPC Class Codes: Y10S 901/50 Miscellaneous

Abstract

Apparatus and methods that use a visual sensor and dead reckoning sensors to process Simultaneous Localization and Mapping (SLAM). These techniques can be used in robot navigation. Advantageously, such visual techniques can be used to autonomously generate and update a map. Unlike with laser rangefinders, the visual techniques are economically practical in a wide range of applications and can be used in relatively dynamic environments, such as environments in which people move. One embodiment further advantageously uses multiple particles to maintain multiple hypotheses with respect to localization and mapping. Further advantageously, one embodiment maintains the particles in a relatively computationally-efficient manner, thereby permitting the SLAM processes to be performed in software using relatively inexpensive microprocessor-based computer systems.

Claims

1. A method of identifying a potentially unreliable visual measurement for navigation, the method comprising:

determining that one or more features in an image match with one or more features from at least one previously identified landmark, where the determination of the matching one or more features is performed by a visually-based automated process;

analyzing one or more quality metrics associated with the match between the one or more features of the image and the at least one previously identified landmark; and

automatically determining that the visual measurement is potentially unreliable at least partly based on the analysis of the one or more quality metrics.

2. The method as defined in claim 1, wherein automatically determining that the visual measurement is potentially unreliable further comprises determining whether to use the match at least partly based on the one or more quality metrics.

3. The method as defined in claim 1, wherein the method is used by a robot for robot navigation.

4. The method as defined in claim 1, wherein determining that one or more features in the image match further comprises receiving an indication from a visual front end that one or more features in the image match.

5. The method as defined in claim 1, wherein analyzing one or more quality metrics further comprises:

receiving an indication related to a quality of the match; and

comparing the indication to a predetermined threshold.

6. The method as defined in claim 5, wherein the indication relates to a count of a number of features that match between the image and the previously-identified landmark, and wherein automatically determining that the measurement is potentially unreliable further comprises determining that the measurement is potentially unreliable when the number of features that match does not exceed a predetermined number.

7. The method as defined in claim 5, wherein the indication relates to a root-mean-square (RMS) projection error between (i) a set of the 2-dimensional projected features of the previously-observed landmark as projected after a calculation of a hypothetical relative device pose and (ii) a set of the 2-dimensional features of the image, and wherein automatically determining that the measurement is potentially unreliable further comprises determining that the measurement is potentially unreliable when the RMS projection error exceeds a predetermined number.

8. The method as defined in claim 5, wherein the method is used by a mobile device for navigation, wherein:

the mobile device is configured to travel along a surface;

the indication relates to a computation of a slope of the surface;

the slope corresponds to a measurement of vertical displacement per unit of measured horizontal translation; and

wherein automatically determining that the measurement is potentially unreliable further comprises determining that the measurement is potentially unreliable when the slope of the surface exceeds a predetermined number.

9. The method as defined in claim 8, wherein the slope equals:

$\mathrm{slope}=<br><br>\frac{\mathrm{\Delta <br><br>}<br><br><br><br>z}{\sqrt{{\left(\mathrm{\Delta <br><br>}<br><br><br><br>x\right)}^2+{\left(\mathrm{\Delta <br><br>}<br><br><br><br>y\right)}^2}}<br><br>.$