eSLAM—Self Localisation and Mapping Using Embodied Data

Abstract

Autonomous mobile robots have the potential to change our everyday life. Unresolved challenges which span a large spectrum of artificial intelligence research need to be answered to progress further towards this vision. This article addresses the problem of robot localisation and mapping, which plays a vital role for robot autonomy in unknown environments. An analysis of the potential for using embodied data is performed, and the notion of direct and indirect embodied data is introduced. Further, the implications of embodied data for an embodied SLAM algorithm are investigated and set into a robotic context.