Localization by learning of wave-signal distributions

摘要

A robot having a signal sensor configured to measure a signal, a motion sensor configured to measure a relative change in pose, a local correlation component configured to correlate the signal with the position and/or orientation of the robot in a local region including the robot's current position, and a localization component configured to apply a filter to estimate the position and optionally the orientation of the robot based at least on a location reported by the motion sensor, a signal detected by the signal sensor, and the signal predicted by the local correlation component. The local correlation component and/or the localization component may take into account rotational variability of the signal sensor and other parameters related to time and pose dependent variability in how the signal and motion sensor perform. Each estimated pose may be used to formulate new or updated navigational or operational instructions for the robot.

主权项

1. A method for determining a pose (location and orientation) of a mobile device, the method comprising:
dividing a representation of a substantially planar operating environment into a first plurality of cells, wherein a given cell in the first plurality of cells is defined by a set of three or more nodes having respective locations; associating at least a first node with properties comprising a location and at least one parameter related to a detected signal detected by the mobile device; computing, while the mobile device is at an actual pose in a first cell, an estimated value of at least one property of the signal at an estimated pose of the mobile device, the computing based at least in part on an estimated location of the estimated pose and one or more of the respective properties associated with two or more of the nodes defining the first cell, wherein computing the estimated value is based at least in part on the estimated orientation of the estimated pose and a rotational variation parameter; and revising the estimated pose based at least in part on: the estimated pose, the estimated value of the signal property, and a value of the signal property measured at the actual pose.