Toward Autonomous Multi-floor Exploration: Ascending Stairway Localization and Modeling

Abstract

Abstract : Localization and modeling of stairways by mobile robots can enable multi-floor exploration for those platforms capable of stair traversal. No system yet presented is capable of localizing a stairway on a map and estimating its properties, two functions that would enable stairways to be considered as traversable terrain in a path planning algorithm. We propose a system for detecting and modeling an ascending stairway while performing simultaneous localization and mapping. We design a generative model of a stairway as a single object and localize it with respect to the map, as well as estimate the dimensions of its steps. Modeling the stairway as a whole will enable exploration of higher floors of a building by allowing the stairway to be incorporated into path planning by considering it as a portal to new frontiers. Our system consists of two parts: a computationally efficient detector that leverages geometric cues from depth imagery to detect sets of ascending stairs, and a stairway modeler that uses multiple detections to infer the location and parameters of a stairway that is discovered during exploration. We demonstrate the performance of this system when deployed on several mobile platforms.