An Optimal Anchor Deployment Method for UWB Localization Based on Particle Swarm Optimization

With the advancement of fully mechanized coal mining, demand for high precision localization in underground environments has grown substantially, as both autonomous equipment and human operators rely on accurate positional data for safety and efficiency. Ultra wideband (UWB) technology is a preferred solution in Global Navigation Satellite System (GNSS) denied settings due to its high ranging accuracy and strong multipath resistance. However, non-line-of-sight (NLoS) propagation caused by obstacles and spatially varying accuracy requirements remain key challenges. This study proposes an adaptive UWB anchor deployment framework that integrates bidirectional long short term memory (BiLSTM) based region prediction, Cramér–Rao lower bound (CRLB) based accuracy modeling, and particle swarm optimization (PSO). Monte Carlo simulations using real world datasets under both line-of-sight (LoS) and mixed LoS/NLoS conditions were conducted, with performance evaluated via the root error bound (REB). Results show that the method achieves median REB reductions of 23.94% in LoS and 21.36% in mixed environments, while significantly enhancing stability. The optimization adapts anchor placement to predicted regions of interest and avoids obstacle affected areas, achieving better convergence and robustness than static layouts. These findings demonstrate that the proposed framework offers a practical and scalable solution for reliable high precision localization in complex underground scenarios.