Method, system and apparatus for end of aisle detection

1. A method of detecting an end of an aisle of shelf modules in an imaging controller of a mobile automation apparatus, the method comprising:

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.

2. The method of claim 1 , wherein updating the estimated end of the aisle comprises:

obtaining an accumulated segment representing an edge of the aisle;

extending the accumulated segment to include the detected edge segment; and

identifying an endpoint of the extended accumulated segment as the estimated end of the aisle.

3. The method of claim 1 , wherein the locomotive data comprises one or more of: a velocity of the apparatus, a confidence level of a pose of the apparatus, and a yaw of the apparatus relative to an edge of the aisle.

4. The method of claim 3 , wherein generating the dynamic trust region comprises:

increasing a first dimension of the dynamic trust region in an inverse correlation to the velocity of the apparatus; and

increasing the first dimension of the dynamic trust region in a direct correlation to the confidence level of the pose of the apparatus.

5. The method of claim 4 , wherein the dynamic trust region is a right rhombic prism, and wherein the first dimension is a width of the right rhombic prism.

6. The method of claim 1 , wherein generating the dynamic trust region comprises:

obtaining an accumulated segment representing an edge of the aisle; and

locating the dynamic trust region at an endpoint of the accumulated segment.

7. The method of claim 1 , further comprising detecting an end-of-aisle feature to generate a second estimated end of the aisle.

8. The method of claim 7 , wherein detecting the end-of-aisle feature comprises:

detecting preliminary edges in the image data;

applying a filter to the preliminary edges to increase a thickness of the preliminary edges;

detecting Hough lines based on the preliminary edges;

growing vertical segments based on the filtered preliminary edges, using the Hough lines as seeds;

determining when one of the vertical segments is within a predefined threshold height; and

when the determination is positive, identifying the vertical segment as the end-of-aisle feature.

9. The method of claim 1 , further comprising:

determining a distance of the apparatus to the estimated end of the aisle; and

when the distance is less than a threshold distance, generating an indication that the apparatus is approaching the end of the aisle.

10. A mobile automation apparatus comprising:

a locomotive assembly;

an image sensor and a depth sensor; and

an imaging controller configured to:

obtain 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 an aisle of shelf modules;

obtain locomotive data of the apparatus;

generate a dynamic trust region based on the locomotive data;

detect 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, update an estimated end of the aisle based on the detected edge segment.

11. The mobile automation apparatus of claim 10 , wherein the imaging controller is configured to update the estimated end of the aisle by:

obtaining an accumulated segment representing an edge of the aisle;

extending the accumulated segment to include the detected edge segment; and

identifying an endpoint of the extended accumulated segment as the estimated end of the aisle.

12. The mobile automation apparatus of claim 10 , wherein the locomotive data comprises one or more of: a velocity of the apparatus, a confidence level of a pose of the apparatus, and a yaw of the apparatus relative to an edge of the aisle.

13. The mobile automation apparatus of claim 12 , wherein the imaging controller is configured to generate the dynamic trust region by:

increasing a first dimension of the dynamic trust region in an inverse correlation to the velocity of the apparatus; and

increasing the first dimension of the dynamic trust region in a direct correlation to the confidence level of the pose of the apparatus.

14. The mobile automation apparatus of claim 13 , wherein the dynamic trust region is a right rhombic prism, and wherein the first dimension is a width of the right rhombic prism.

15. The mobile automation apparatus of claim 10 , wherein the imaging controller is configured to generate the dynamic trust region by:

obtaining an accumulated segment representing an edge of the aisle; and

locating the dynamic trust region at an endpoint of the accumulated segment.

16. The mobile automation apparatus of claim 10 , wherein the imaging controller is further configured to detect an end-of-aisle feature to generate a second estimated end of the aisle.

17. The mobile automation apparatus of claim 16 , wherein the imaging controller is configured to detect the end-of-aisle feature by:

detecting preliminary edges in the image data;

applying a filter to the preliminary edges to increase a thickness of the preliminary edges;

detecting Hough lines based on the preliminary edges;

growing vertical segments based on the filtered preliminary edges, using the Hough lines as seeds;

determining when one of the vertical segments is within a predefined threshold height; and

when the determination is positive, identifying the vertical segment as the end-of-aisle feature.

18. The mobile automation apparatus of claim 10 , wherein the imaging controller is further configured to:

determining a distance of the apparatus to the estimated end of the aisle; and

when the distance is less than a threshold distance, generating an indication that the apparatus is approaching the end of the aisle.