Inventory management

A system comprising:

• a first robotic device comprising a camera configured to capture image data;
• a second robotic device;
• and
• a computing system configured to:
• determine, for each position of a plurality of selectable positions of the camera, a value of one or more on-item visual identifiers expected to be within a field of view of the camera while the camera is positioned at the position and the first robotic device navigates along a first route within an environment;
• select, from the plurality of selectable positions, a position for the camera on the first robotic device based on the determined value of the one or more on-item visual identifiers expected to be within the field of view of the camera for each position of the plurality of selectable positions;
• receive image data captured by the camera positioned at the selected position while the first robotic device navigates along the first route within the environment;
• analyze the image data to detect an on-item visual identifier corresponding to an inventory item in the environment;
• determine a location of the inventory item corresponding to the detected on-item visual identifier based on the image data;
• based on a comparison of the determined location of the inventory item to an expected location of the inventory item, detect a difference between the expected location and the determined location;
• and
• responsive to detecting the difference between the expected location and the determined location, dispatch a second robotic device to the determined location.

A non-transitory computer-readable medium having stored therein instructions, that when executed by a computing device, cause the computing device to perform functions comprising:

• determining, for each position of a plurality of selectable positions of a camera on a robotic device, a value of one or more on-item visual identifiers expected to be within a field of view of the camera while the camera is positioned at the position and the robotic device navigates along a first route within an environment;
• selecting, from the plurality of selectable positions, a position for the camera on the robotic device based on the determined value of the one or more on-item visual identifiers expected to be within the field of view of the camera for each position of the plurality of selectable positions;
• receiving image data captured by the camera positioned at the selected position while the first robotic device navigates along the first route within the environment;
• analyzing the image data to detect an on-item visual identifier corresponding to an inventory item in the environment;
• determining a location of the inventory item corresponding to the detected on-item visual identifier based on the image data;
• based on a comparison of the determined location of the inventory item to an expected location of the inventory item, detecting a difference between the expected location and the determined location;
• and
• responsive to detecting the difference between the expected location and the determined location, dispatching a second robotic device to the determined location.