Adaptive mapping with spatial summaries of sensor data

• US 8,798,840 B2
• Filed: 10/01/2012
• Issued: 08/05/2014
• Est. Priority Date: 09/30/2011
• Status: Active Grant

• Current Assignee: iRobot Corporation
• Original Assignee: iRobot Corporation
• Inventors: Fong, Philip, Eade, Ethan, Munich, Mario E.
• Primary Examiner(s): Tarcza, Thomas
• Assistant Examiner(s): GOLDMAN, RICHARD A
• Application Number:
  US13/632,997
• Publication Number:
  US 20140005933A1
• Time in Patent Office: 673 Days
• Field of Search: None
• US Class Current: 701/23
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G01C 21/3881 Tile-based structures
• CPC Class Codes: G05B 15/00 Systems controlled by a computer G05B13/00, G05B19/00 take precedence; automatic controllers with particular characteristics G05B11/00
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• 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 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: Y10S 901/00 Robots

Abstract

A system and method for mapping parameter data acquired by a robot mapping system is disclosed. Parameter data characterizing the environment is collected while the robot localizes itself within the environment using landmarks. Parameter data is recorded in a plurality of local grids, i.e., sub-maps associated with the robot position and orientation when the data was collected. The robot is configured to generate new grids or reuse existing grids depending on the robot'"'"'s current pose, the pose associated with other grids, and the uncertainty of these relative pose estimates. The pose estimates associated with the grids are updated over time as the robot refines its estimates of the locations of landmarks from which determines its pose in the environment. Occupancy maps or other global parameter maps may be generated by rendering local grids into a comprehensive map indicating the parameter data in a global reference frame extending the dimensions of the environment.

Claims

1. A method of mapping parameters acquired by a robotic system in an environment, the method comprising:

driving the robotic system in the environment;

measuring a first set of parameters that characterize the environment;

estimating a first current pose of the robotic system;

defining a first anchor node representing an estimate of the first current pose, wherein the first anchor node is one of a plurality of anchor nodes;

generating a first grid associated with the first anchor node, wherein the first grid comprises a map of the first set of measured parameters, wherein the first set of measured parameters are mapped relative to the first pose;

after driving a determined period of time, determining an estimate of a second current pose of the robotic system;

determining an uncertainty between the estimate of the second current pose and the first current pose; and

if the uncertainty is greater than a first threshold, then;

a) defining a second anchor node representing to the estimate of the second current pose of the robotic system; and

b) generating a second grid associated with the second anchor node, wherein the second grid comprises a map of a second set of measured parameters mapped relative to the second current pose.

2. The method of claim 1, further comprising merging grids associated with the plurality of anchor nodes, wherein merging comprises:

determining an uncertainty between an estimate of each pose of the plurality of anchor nodes and every other pose of the plurality of anchor nodes;

determining an uncertainty between the estimates of two of the plurality of anchor nodes; and

if the uncertainty between estimates of poses of two anchor nodes is below a second threshold, then combining the grids associated with the two anchor nodes into a single grid associated with a single anchor node.

3. The method of claim 2, wherein the uncertainty between estimates of poses is based on a covariance matrix of relative pose estimates.

4. The method of claim 1, wherein estimating the first current pose comprises:

identifying a plurality of landmarks in the environment;

determining locations of the plurality of landmarks with respect to a global reference frame associated with the environment;

determining the first current pose of the robotic system with respect to a global reference frame based on the locations of the plurality of landmarks.

5. The method of claim 1, further comprising:

identifying a plurality of landmarks in the environment; and

determining locations of the plurality of landmarks.

6. The method of claim 5, further comprising:

updating the poses associated with the plurality of anchor nodes based on the locations of the plurality of landmarks; and

generating an occupancy map from a plurality of grids, wherein locations of the plurality of grids are based on locations of respective anchor nodes.

7. The method of claim 1, wherein the first set of parameters being mapped comprises occupancy data.

8. The method of claim 7, wherein the occupancy data indicates locations of obstacles in the environment.

9. The method of claim 1, wherein the first set of parameters being mapped indicate the locations of dirt in the environment.

16. The method of claim 1, wherein the method is performed at least in part by a computing system residing on the robotic system.

17. The method of claim 1, wherein the method is performed at least in part by the robotic system, the robotic system comprising hardware, using a sensor processor, a parameter processor, a localization module, a parameter mapping module, and a navigation module.

10. A method of mapping parameters acquired by a mobile mapping system in an environment, the method comprising:

driving the mapping system in an environment;

measuring parameter data that characterizes the environment;

mapping the measured parameter data to a plurality of grids, each grid being associated with one of a plurality of pose estimates;

determining an uncertainty between each pose estimate and every other one of the plurality of pose estimates; and

if the uncertainty between two of the plurality of pose estimates is below a second threshold, then combining the grids associated with the two pose estimates into a spatial summary grid associated with a pose estimate.

11. The method of claim 10, further comprising:

rendering a plurality of the spatial summary grids into a global parameter map.

12. The method of claim 11, wherein at least one of the spatial summary grids comprises a map of parameter data in proximity to a location given by an associated pose estimate.

13. The method of claim 12, wherein at least one of the spatial summary grids comprises a Cartesian coordinate system different than the global parameter map.

14. The method of claim 10, wherein the spatial summary grid consists of a single grid, wherein the single grid comprises parameter data from at least two grids associated with different pose estimates.

15. The method of claim 14, wherein parameter data is represented in at least one spatial summary grid using one or more polygons.

18. The method of claim 10, wherein the method is performed at least in part by a computing system residing on the robotic system.

19. The method of claim 10, wherein the method is performed at least in part by the mobile mapping system, the mobile mapping system comprising hardware, using a sensor processor, a parameter processor, a localization module, a parameter mapping module, and a navigation module.