Anchor Pair Selection in TDOA Positioning Systems by Door Transition Error Minimization
Marcin Kolakowski, Jozef Modelski
TL;DR
The paper tackles accuracy degradation in indoor UWB TDOA positioning caused by NLoS and body shadowing when anchor infrastructure is limited. It introduces a zone-based adaptive anchor-pair selection method that calibrates anchor sets by minimizing door-transition errors, using historical trajectories and automatically detected door locations. Localization is performed with an Extended Kalman Filter, with TDOA measurements chosen in a feedback loop conditioned on the current zone and user heading, and door detection is implemented via a RetinaNet-based detector. Experimental results in a furnished apartment (6 anchors) demonstrate a mean trajectory error of $0.32\,\mathrm{m}$, representing a meaningful improvement over fixed anchor configurations and supporting practical viability for residential indoor localization.
Abstract
This paper presents an adaptive anchor pairs selection algorithm for UWB (ultra-wideband) TDOA-based (Time Difference of Arrival) indoor positioning systems. The method assumes dividing the system operation area into zones. The most favorable anchor pairs are selected by minimizing the positioning errors in doorways leading to these zones where possible users' locations are limited to small, narrow areas. The sets are determined separately for going in and out of the zone to take users' body shadowing into account. The determined anchor pairs are then used to calculate TDOA values and localize the user moving around the apartment with an Extended Kalman Filter based algorithm. The method was tested experimentally in a furnished apartment. The results have shown that the adaptive selection of the anchor pairs leads to an increase in the user's localization accuracy. The median trajectory error was about 0.32 m.