Robust NLOS discrimination for range-based acoustic pose tracking

Indoor localization is a field in research with many competing technologies using different kinds of media. A common challenge faced by most systems is dealing with Non-Line-of-Sight (NLOS) conditions. We are addressing this issue with focus on sound in the frequency range above 20 kHz, as we encountered severe occurrence of outliers due to multipath propagation, by reflections, and from occlusion. The proper discrimination of erroneous signals is of special concern during initialization time of the tracking system. During run time, the computationally demanding process can be spared, if motion is modelled and stochastic filtering techniques are applied. This paper depicts solutions for both cases, and demonstrates that a combined use of static and dynamic localization methods delivers increased robustness at an affordable computational cost.