A robot in one embodiment includes a navigation system, a manipulation unit, a visual recognition unit, and a processing unit. The visual recognition unit includes at least one detector configured to acquire presence information of humans within at least a portion of the area. The processing unit is operably coupled to the navigation system, manipulation unit, and visual recognition unit, and is configured to determine a presence of a human within at least one predetermined range of the robot using the presence information from the visual recognition unit, determine at least one control action responsive to determining the presence of the human within the at least one predetermined range, and control at least one of the navigation system or manipulation unit to implement the at least one control action.