A robust method for elevator operation in semi-outdoor environment for mobile robot transportation system in life science laboratories

A new robust method is developed for elevator operation in semi-outdoor environment for mobile robot transportation systems in life science laboratories. Elevator operation includes the entry button detection, floor button recognition, and reading of current floor information. Different techniques have been employed for the elevator operation including HSL color representation, adaptive binary threshold filter, and optical character recognition. In addition to these techniques an enhancement function has been developed to combat the direct sunlight effect in the Kinect vision sensor. Button panel landmarks were adopted to minimize the false positive measurements in internal button detection. The implemented system approves an efficient performance with a high success rate under different light conditions.