Abstract: A method in a navigational controller includes: controlling a ceiling-facing camera of a mobile automation apparatus to capture a stream of images of a facility ceiling; activating a primary localization mode including: (i) detecting primary features in the captured image stream; and (ii) updating, based on the primary features, an estimated pose of the mobile automation apparatus and a confidence level corresponding to the estimated pose; determining whether the confidence level exceeds a confidence threshold; when the confidence level does not exceed the threshold, switching to a secondary localization mode including: (i) detecting secondary features in the captured image stream; (ii) updating the estimated pose and the confidence level based on the secondary features; and (iii) searching the image stream for the primary features; and responsive to detecting the primary features in the image stream, re-activating the primary localization mode.

Abstract: A method for dynamic loop closure in a mobile automation apparatus includes: obtaining mapping trajectory data defining a plurality of trajectory segments traversing a facility to be mapped; controlling a locomotive mechanism of the apparatus to traverse a current segment; generating a sequence of keyframes for the current segment using sensor data captured via a navigational sensor of the apparatus; and, for each keyframe: determining an estimated apparatus pose based on the sensor data and a preceding estimated pose corresponding to a preceding keyframe; and, determining a noise metric defining a level of uncertainty associated with the estimated pose relative to the preceding estimated pose; determining, for a selected keyframe, an accumulated noise metric based on the noise metrics for the selected keyframe and each previous keyframe; and when the accumulated noise metric exceeds a threshold, updating the mapping trajectory data to insert a repetition of one of the segments.

Abstract: A method of detecting an edge of a support surface in an imaging controller includes: obtaining image data captured by an image sensor and a plurality of depth measurements captured by a depth sensor, the image data and the plurality of depth measurements corresponding to an area containing the support surface; detecting preliminary edges in the image data; applying a Hough transform to the preliminary edges to determine Hough lines representing candidate edges of the support surface; segmenting the plurality of depth measurements to assign classes to each pixel, each class defined by one of a plurality of seed pixels, wherein the plurality of seed pixels are identified from the depth measurements based on the Hough lines; and detecting the edge of the support surface by selecting a class of pixels and applying a line-fitting model to the selected class to obtain an estimated edge of the support surface.

Abstract: A method of detecting an end of an aisle of shelf modules in an imaging controller of a mobile automation apparatus, includes: obtaining image data captured by an image sensor and a plurality of depth measurements captured by a depth sensor, the image data and the depth measurements corresponding to an area containing a portion of the aisle of shelf modules; obtaining locomotive data of the apparatus; generating a dynamic trust region based on the locomotive data; detecting an edge segment based on the image data and the plurality of depth measurements, the edge segment representing an edge of a support surface; and when the edge segment is located at least partially in the dynamic trust region, updating an estimated end of the aisle based on the detected edge segment.

Abstract: A method in a navigational controller includes: controlling a ceiling-facing camera of a mobile automation apparatus to capture a stream of images of a facility ceiling; activating a primary localization mode including: (i) detecting primary features in the captured image stream; and (ii) updating, based on the primary features, an estimated pose of the mobile automation apparatus and a confidence level corresponding to the estimated pose; determining whether the confidence level exceeds a confidence threshold; when the confidence level does not exceed the threshold, switching to a secondary localization mode including: (i) detecting secondary features in the captured image stream; (ii) updating the estimated pose and the confidence level based on the secondary features; and (iii) searching the image stream for the primary features; and responsive to detecting the primary features in the image stream, re-activating the primary localization mode.

Abstract: A method of detecting an end of an aisle of shelf modules in an imaging controller of a mobile automation apparatus, includes: obtaining image data captured by an image sensor and a plurality of depth measurements captured by a depth sensor, the image data and the depth measurements corresponding to an area containing a portion of the aisle of shelf modules; obtaining locomotive data of the apparatus; generating a dynamic trust region based on the locomotive data; detecting an edge segment based on the image data and the plurality of depth measurements, the edge segment representing an edge of a support surface; and when the edge segment is located at least partially in the dynamic trust region, updating an estimated end of the aisle based on the detected edge segment.

Abstract: A method of detecting an edge of a support surface in an imaging controller includes: obtaining image data captured by an image sensor and a plurality of depth measurements captured by a depth sensor, the image data and the plurality of depth measurements corresponding to an area containing the support surface; detecting preliminary edges in the image data; applying a Hough transform to the preliminary edges to determine Hough lines representing candidate edges of the support surface; segmenting the plurality of depth measurements to assign classes to each pixel, each class defined by one of a plurality of seed pixels, wherein the plurality of seed pixels are identified from the depth measurements based on the Hough lines; and detecting the edge of the support surface by selecting a class of pixels and applying a line-fitting model to the selected class to obtain an estimated edge of the support surface.

Abstract: A method for dynamic loop closure in a mobile automation apparatus includes: obtaining mapping trajectory data defining a plurality of trajectory segments traversing a facility to be mapped; controlling a locomotive mechanism of the apparatus to traverse a current segment; generating a sequence of keyframes for the current segment using sensor data captured via a navigational sensor of the apparatus; and, for each keyframe: determining an estimated apparatus pose based on the sensor data and a preceding estimated pose corresponding to a preceding keyframe; and, determining a noise metric defining a level of uncertainty associated with the estimated pose relative to the preceding estimated pose; determining, for a selected keyframe, an accumulated noise metric based on the noise metrics for the selected keyframe and each previous keyframe; and when the accumulated noise metric exceeds a threshold, updating the mapping trajectory data to insert a repetition of one of the segments.

Abstract: A method for dynamic target feature mapping in a mobile automation apparatus includes, at a navigational controller of the apparatus: obtaining mapping trajectory data defining a trajectory traversing a facility to be mapped; controlling a locomotive mechanism of the apparatus to traverse the trajectory; generating a sequence of keyframes and corresponding estimated mobile automation apparatus poses in a facility frame of reference during traversal of the trajectory, using a navigational sensor of the mobile automation apparatus; simultaneously with generating a target-associated one of the keyframes, detecting a target feature using an environmental sensor of the mobile automation apparatus; storing a relative target location of the target feature, defined relative to the estimated pose of the target-associated keyframe; generating a map of the facility based on the sequence of keyframes; and storing a final target location for the target feature, defined in the facility frame of reference.