Method of Improving WiFi SLAM based on Spatial and Temporal Coherence

The paper addresses the revisiting (loop closing) problem of simultaneous localization and mapping (SLAM) by investigating spatio-temporal coherence in inertial and perceptual inputs to improve the robustness and convergence of SLAM. The basic idea is to find out coherent subsequences of confidence in trajectory to ensure against error-prone correspondences. It is achieved by leveraging fuzzy matching based on local trajectory structure and measurement similarity. Our approach does not rely on any global features or propagation modeling, which can be unreliable in the presence of gross errors and result in divergence. Apart from WiFi SLAM, our approach can also be capable of improving generic SLAM problems by leveraging spatio-temporal coherence. The experiments show that our approach can significantly reduce the ambiguity in WiFi fingerprinting, and subsequently lead to performance improvement in terms of mapping and localization.