A Real-Time GPU-Based Wall Detection Algorithm for Mapping and Navigation in Indoor Environments

Hadi Moradi, Eun Kwon, Dae Neung Sohn, JungHyun Han

Abstract: In robotic applications, there is a growing trend for developing human-like real-time interaction capabilities. A good example can be found in Simultaneous localization and mapping technique, where a robot or an autonomous vehicle builds up a map within an unknown environment while at the same time keeping track of its current position. Especially in indoor environments, wall detection is often a critical part of SLAM: it plays a key role in scene interpretation and 3D workspace modeling. Further, it also reduces the size of the map. This paper presents an effective and real-time approach for detecting walls in indoor environment using GPU (graphics processing unit). The experimental results show the feasibility of using GPU as a coprocessor in robotic applications.