Inverse observation model and multiple hypothesis tracking for indoor mobile robots

Abstract

This paper presents a complete robot perception system of moving point detection and target tracking for robustly following target human in an unknown indoor dynamic environment. To detect moving points under grid-based formulation, a modified inverse observation model is proposed to overcome several frequently happened detection limitations. Next, related human-extraction techniques are proposed to filter out less possible clusters for detecting potential human target from these moving points. Finally, the multiple hypothesis tracking algorithm is implemented to deal with the data association problem for enhancing the reliability and robustness of the human tracking when measurements are noisy. Related experiments have been performed to evaluate the effectiveness of the proposed algorithm framework.