Apparatus and method for localizing mobile robot

• US 8,380,384 B2
• Filed: 03/20/2009
• Issued: 02/19/2013
• Est. Priority Date: 09/12/2008
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Lee, Su-Jinn, Jeong, Woo-Yeon
• Primary Examiner(s): Trammell, James
• Assistant Examiner(s): Shafi, Muhammad
• Application Number:
  US12/382,681
• Publication Number:
  US 20100070125A1
• Time in Patent Office: 1,432 Days
• Field of Search: 700/245, 700/259, 700/253, 700/258, 700/262, 701/28, 701/23, 901/1, 901/47, 901/50, 348/61, 348/E7.086, 702/181, 702/153, 345/474
• US Class Current: 701/28
• 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 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06T 7/73 using feature-based methods

Abstract

An apparatus and method for localizing a mobile robot are provided. The method includes building a forward image map including features extracted according to position at which the mobile robot takes forward images and feature descriptors of the extracted features, and localizing the mobile robot on the basis of features extracted from a newly input forward image and the built forward image map.

Claims

1. An apparatus for localizing a mobile robot, comprising:

a forward image map processor for building a forward image map including features extracted from forward images captured by the mobile robot according to a position at which the forward images are taken and feature descriptors of the extracted features, wherein the forward images include an image captured from a space ahead of a direction in which the robot is traveling; and

a localizer for, when a new forward image is input, localizing the mobile robot on the basis of a feature extracted from the new forward image and the forward image map, and for setting particles, which are samples indicating virtual positions of the mobile robot, giving weights to the particles on the basis of the estimated position, and re-sampling the particles on the basis of the weights given to the particles to localize the mobile robot and increasing weights of particles existing within a specific range from the estimated position of the mobile robot and having an angle difference of a specific value or less from a heading angle of the mobile robot when giving weights to the particles on the basis of the estimated position.

2. The apparatus of claim 1, wherein the forward image map processor searches the forward image map for a feature of the previous forward images matching the feature extracted from the new forward image and information on a position at which a previous forward image including the matching feature is taken, and calculates an estimated position of the mobile robot using the search result.

3. The apparatus of claim 1, wherein the forward image map processor updates the forward image map when the mobile robot moves a specific distance.

4. The apparatus of claim 1, wherein the features extracted from the forward images are extracted regardless of scale.

5. The apparatus of claim 1, wherein the forward image map processor compares a size of the searched feature of the previous forward image with a size of the feature extracted from the new forward image and corrects the estimated position of the mobile robot, and the localizer gives weights to the particles on the basis of the corrected estimated position.

6. The apparatus of claim 1, further comprising:

a ceiling simultaneous localization and mapping (SLAM) performer for performing localization and map building on the basis of ceiling images,

wherein the ceiling SLAM performer includes;

a ceiling feature processor for extracting features from the ceiling images and generating feature descriptors of the extracted features; and

a ceiling image map builder for building a ceiling image map on the basis of the extracted ceiling image features and the feature descriptors of the extracted features.

7. The apparatus of claim 6, wherein the ceiling SLAM performer searches the ceiling image map for a ceiling image feature matching a feature extracted from a newly input ceiling image and calculates an estimated position of the mobile robot using the search result, and the localizer gives weights to particles on the basis of the estimated position of the mobile robot calculated from the feature of the forward image and the estimated position of the mobile robot calculated from the feature of the ceiling image.

8. The apparatus of claim 7, wherein when the localizer gives the weights to the particles, a range of particles to which weights are given on the basis of the estimated position of the mobile robot calculated from the feature of the forward image is larger than a range of particles to which weights are given on the basis of the estimated position of the mobile robot calculated from the feature of the ceiling image.

9. The apparatus of claim 7, wherein the localizer increases weights of particles included in an intersection set of particles to which weights are given on the basis of the estimated position of the mobile robot calculated from the feature of the forward image and particles to which weights are given on the basis of the estimated position of the mobile robot calculated from the feature of the ceiling image.

10. The apparatus of claim 6, wherein the forward image map processor builds the forward image map on the basis of the estimated position of the mobile robot calculated on the basis of the ceiling image map built by the ceiling SLAM performer.

11. A method of localizing a mobile robot comprising a processor, the method comprising:

building, under control of the processor, a forward image map including features extracted from forward images captured by the mobile robot according to a position at which the forward images are taken and feature descriptors of the extracted features, wherein the forward images include an image captured from a space ahead of a direction in which the robot is traveling; and

when a new forward image is input, localizing the mobile robot on the basis of a feature extracted from the new forward image and the forward image map, and setting particles, which are samples indicating virtual positions of the mobile robot, giving weights to the particles on the basis of the estimated position, and re-sampling the particles on the basis of the weights given to the particles to localize the mobile robot and increasing weights of particles existing within a specific range from the estimated position of the mobile robot and having an angle difference of a specific value or less from a heading angle of the mobile robot when giving weights to the particles on the basis of the estimated position.

12. The method of claim 11, wherein the localizing of the mobile robot includes:

searching the forward image map for a feature of the previous forward images matching the feature extracted from the new forward image and information on a position at which a previous forward image including the searched feature was taken; and

calculating an estimated position of the mobile robot using the search result.

13. The method of claim 11, wherein the building of the forward image map comprises updating the forward image map when the mobile robot moves a specific distance.

14. The method of claim 11, wherein the features extracted from the forward images are extracted regardless of scale.

15. The method of claim 11, further comprising:

extracting features from ceiling images and generating feature descriptors of the extracted features; and

building a ceiling image map on the basis of the features extracted from the ceiling images,

wherein the localizing of the mobile robot further includes;

searching the ceiling image map for a ceiling image feature matching a feature extracted from an input ceiling image, and calculating an estimated position of the mobile robot using the search result; and

giving weights to the particles on the basis of the estimated position of the mobile robot calculated from the feature of the forward image and the estimated position of the mobile robot calculated from the feature of the ceiling image.

16. The method of claim 15, wherein building a forward image map comprises building the forward image map on the basis of the estimated position of the mobile robot estimated on the basis of the built ceiling image map.