Adaptive mapping with spatial summaries of sensor data
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.
1. A method of mapping an environment, the method comprising:
receiving landmark information corresponding to an environment from at least one first robot;
generating a first map of parameters that include the landmark information, wherein the first map of parameters are measured by the at least one first robot and are mapped to the first map relative to a first estimated pose of the at least one first robot;
receiving a second map of parameters measured by at least one second robot different from the at least one first robot and mapped to the second map relative to a second estimated pose of the at least one second robot;
determining an uncertainty value between the first estimated pose and the second estimated pose; and
operating the at least one first robot to traverse the environment based on a combination of the first map of parameters measured by the at least one first robot and the second map of parameters measured by the at least one second robot in response to the uncertainty value satisfying a condition.
2. The method according to claim 1 , wherein the first map of parameters is generated based on the at least one first robot performing operations comprising:
estimating a first current pose of the at least one first robot in the environment based on the parameters measured by the at least one first robot, wherein the parameters measured by the at least one first robot include obstacles and clear spaces;
defining a first local origin that represents an estimate of the first current pose; and
generating the first map of the parameters measured by the at least one first robot, wherein the parameters measured by the at least one first robot are mapped relative to the first local origin.
3. The method according to claim 2 , wherein receiving the second map comprises receiving updated map information that is generated based on the parameters measured by the at least one second robot.
4. The method according to claim 1 , wherein receiving the second map comprises receiving a plurality of sub-maps from respective two or more robots, and further comprising generating a single map from the plurality of sub-maps.
5. The method according to claim 1 , further comprising:
receiving positioning information corresponding to the at least one second robot.
6. The method according to claim 1 , further comprising:
transmitting the landmark information or the first map to two or more robots other than the at least one first robot.
7. The method according to claim 1 , wherein receiving the second map comprises receiving respective landmark information or respective maps of parameters from two or more robots different from the at least one first robot.
8. The method according to claim 1 , wherein the landmark information comprises first landmark information corresponding to a portion of the environment traversed by the at least one first robot, and wherein the second map comprises second landmark information corresponding to a portion of the environment traversed by the at least one second robot.
9. The method according to claim 8 , wherein the first map comprises a first sub-map and the second map comprises a second sub-map, and further comprising:
generating a global parameter map that includes data corresponding to the first sub-map and data corresponding to the second sub-map.
10. The method according to claim 1 , wherein the first map comprises a spatial summary including a combination of at least some of the parameters measured by the at least one first robot at different poses in the environment.
11. The method according to claim 10 , wherein the combination of the at least some of the parameters measured at the different poses is associated with a same anchor node, and wherein the same anchor node comprises one of the different poses or a new pose created by combining the different poses.
12. The method according to claim 10 , wherein the spatial summary is based on an uncertainty value between estimates of respective poses of the at least one first robot being below a threshold value.
13. The method according to claim 1 , wherein at least one of the first map or the second map comprises two-dimensional coordinates.
14. The method according to claim 1 , wherein at least one of the first map or the second map includes three-dimensional map data.
15. The method according to claim 2 , wherein estimating the first current pose of the at least one first robot based on the parameters measured by the at least one first robot is performed using sensor data corresponding to the obstacles and the clear spaces within the environment.
16. The method according to claim 15 , wherein data corresponding to the obstacles within the environment are detected by a bump sensor or a visual sensor.
17. The method according to claim 2 , further comprising:
generating a spatial summary that is based on the first map and the second map, wherein the spatial summary is associated with a local origin that is different from the first local origin.
18. A method of mapping an environment, the method comprising:
receiving landmark information corresponding to an environment from a plurality of robots comprising first and second robots, wherein the landmark information comprises first landmark information for a first portion of the environment traversed by the first robot, and second landmark information for a second portion of the environment traversed by the second robot;
transmitting a first map of parameters that include the first landmark information and that are measured by the first robot to the second robot, wherein the first map of parameters are mapped to the first map relative to a first estimated pose of the first robot;
transmitting a second map of parameters that include the second landmark information and that are measured by the second robot to the first robot, wherein the second map of parameters are mapped to the second map relative to a second estimated pose of the second robot;
determining an uncertainty value between the first estimated pose and the second estimated pose; and
in response to the uncertainty value satisfying a condition, operating the first robot to traverse the environment based at least on the second map of parameters, or operating the second robot to traverse the environment based at least on the first map of parameters.
19. The method according to claim 18 , further comprising:
transmitting, to the second robot, first positioning information corresponding to navigation of the first robot in the environment; and
transmitting, to the first robot, second positioning information corresponding to navigation of the second robot in the environment.
20. The method according to claim 18 , wherein the first map comprises a first sub-map and the second map comprises a second sub-map, and further comprising:
generating a global parameter map that includes data corresponding to the first sub-map and data corresponding to the second sub-map,
wherein transmitting the first map and transmitting the second map comprises transmitting the global parameter map to the first and second robots.
21. The method of claim 1 , wherein operating the at least one first robot to traverse the environment is based at least on the second map of parameters in response to the uncertainty value between the first and second estimated poses exceeding a threshold.