Localization and Mapping Using Physical Features

• US 20160271795A1
• Filed: 03/18/2015
• Published: 09/22/2016
• Est. Priority Date: 03/18/2015
• Status: Active Grant

• Current Assignee: iRobot Corporation
• Original Assignee: iRobot Corporation
• Inventors: Vicenti, Jasper
• Granted Patent: US 9,630,319 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A47L 2201/00 Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
• CPC Class Codes: A47L 2201/04 Automatic control of the travelling movement; Automatic obstacle detection
• CPC Class Codes: B25J 9/163 learning, adaptive, model based, rule based expert control
• CPC Class Codes: B25J 9/1664 characterised by motion, path, trajectory planning
• CPC Class Codes: B25J 9/1666 Avoiding collision or forbidden zones
• CPC Class Codes: G05D 1/0219 ensuring the processing of the whole working surface
• CPC Class Codes: G05D 1/0227 using mechanical sensing means, e.g. for sensing treated area
• CPC Class Codes: G05D 1/0238 using obstacle or wall sensors G05D1/0246 and G05D1/0289 take precedence; lidar systems designed for anti-collision purposes G01S17/93
• 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 1/246 using environment maps, e.g. simultaneous localisation and mapping [SLAM]
• CPC Class Codes: G05D 1/628 following the obstacle profile, e.g. a wall or undulated terrain
• CPC Class Codes: Y10S 901/01 Mobile robot

Abstract

A method includes maneuvering a robot in (i) a following mode in which the robot is controlled to travel along a path segment adjacent an obstacle, while recording data indicative of the path segment, and (ii) in a coverage mode in which the robot is controlled to traverse an area. The method includes generating data indicative of a layout of the area, updating data indicative of a calculated robot pose based at least on odometry, and calculating a pose confidence level. The method includes, in response to the confidence level being below a confidence limit, maneuvering the robot to a suspected location of the path segment, based on the calculated robot pose and the data indicative of the layout and, in response to detecting the path segment within a distance from the suspected location, updating the data indicative of the calculated pose and/or the layout.

Claims

1. A method of navigating an autonomous robot within an area at least partially enclosed by walls, the method comprising:

maneuvering the robot in a following mode in which the robot is controlled to travel along a path segment adjacent an obstacle, while recording data indicative of the path segment;

maneuvering the robot in a coverage mode in which the robot is controlled to traverse the area while performing a function, while

generating data indicative of a physical layout of the area, including area boundaries and obstacle perimeters detected while performing the function,

updating data indicative of a calculated robot pose, the calculated robot pose comprising a calculated location and orientation of the robot within the area, based at least on robot odometry data, and

calculating a robot pose confidence level; and

in response to the robot pose confidence level being below a predetermined confidence limit;

maneuvering the robot to a suspected location of the path segment, based on the calculated robot pose and the data indicative of the physical layout of the area; and

then,

in response to detecting the path segment adjacent the obstacle within a predetermined distance from the suspected location of the path segment, updating at least one of the data indicative of the calculated robot pose and the data indicative of the physical layout of the area, thereby updating a relative pose of the robot within the area.

2. The method of claim 1, further comprising:

selecting the suspected location of the path segment maneuvered to based on a time differential from a first traversal of the suspected location of the path segment.

3. The method of claim 1, further comprising:

selecting the suspected location of the path segment maneuvered to based on a distance differential from a first traversal of the suspected location of the path segment.

4. The method of claim 1, wherein updating the data indicative of the calculated robot pose relative to the data indicative of the physical layout of the area re-localizes two or more segments to the data indicative of the physical layout of the area.

5. The method of claim 1, wherein updating the data indicative of the calculated robot pose relative to the data indicative of the physical layout of the area re-localizes the data indicative of the robot pose to the data indicative of the physical layout of the area.

6. The method of claim 1, wherein recording the data indicative of the path segment includes collecting data from a sensor on the robot.

8. The method of claim 1, further comprising, after maneuvering the robot to the suspected location of the path segment:

maneuvering the robot in the following mode to follow the detected obstacle while recording robot pose data; and

from the recorded robot pose data, generating data indicative of a path of the robot along the detected obstacle;

and wherein updating the data indicative of calculated robot pose comprises

comparing the data indicative of the path of the robot along the detected obstacle to the data indicative of the path segment recorded in the following mode, to determine whether the path of the robot along the detected obstacle sufficiently matches the path segment recorded in the following mode; and

upon determining a sufficient match, updating either of the data indicative of calculated robot location and the data indicative of the physical layout of the area, in accordance with the sufficiently matched path segment.

9. The method of claim 1, wherein comparing the data comprises comparing at least one of path lengths, starting poses of the data, ending poses of the data, straight distances traveled, and curvatures.

10. The method of claim 1, wherein detecting the obstacle comprises physically contacting the detected obstacle.

11. The method of claim 1, wherein generating data indicative of the physical layout of the area comprises analyzing image data from a camera on the robot.

12. The method of claim 1 further comprising:

building a library of path segments in the wall following mode, and wherein in response to the robot pose confidence level falling to below the predetermined confidence limit, the robot is maneuvered to a suspected location of a path segment selected as a function of its suspected relative position with respect to the robot.

13. The method of claim 1 further comprising:

building a library of path segments based on the data indicative of the physical layout of the area, and wherein in response to the robot pose confidence level falling to below the predetermined confidence limit, the robot is maneuvered to a suspected location of a path segment from the library of path segments selected as a function of its suspected relative position with respect to the robot.

14. The method of claim 1, further comprising:

after updating either of the data indicative of calculated robot location and the data indicative of the physical layout of the area, again maneuvering the robot in the coverage mode.

15. The method of claim 1, further comprising:

in response to detecting an obstacle while maneuvering the robot in the coverage mode, initiating the following mode.

16. The method of claim 1, wherein the function comprises cleaning a floor within the area.

7. The method of claim 7, wherein the sensor is at least one of an odometer, a radiation transceiver, a bump sensor, a pressure sensor, and a proximity sensor.