Self-Trained, Map-Free AR Return Navigation With Confidence-Weighted Trajectory Reconstruction

Abstract

People with autism spectrum disorder (ASD) or dementia, young children, and visitors lost in crowded venues often need guidance back to a safe origin. Conventional map-based navigation serves this need poorly. We present a self-trained, map-free augmented-reality (AR) navigation system. It records a route as the user first walks it and later guides the user back with egocentric cues, with no pre-built map or installed infrastructure. Map-free means that the route is the user’s own recorded walk, not that the system avoids satellites. Two separate methods cover the two positioning regimes. Outdoors, where satellite fixes are corrupted by heavy multipath, we propose Confidence-Weighted Trajectory Reconstruction (CWTR), which scores each fix by reported accuracy, kinematic plausibility, and temporal spacing. A confidence-driven robust Kalman smoother then gates and down-weights outliers. In simulation, the proposed method reduces the reconstruction error by up to 78% over raw fixes and increasingly outperforms fixed-gain and adaptively gated robust Kalman baselines as multipath worsens. Recorded GPS shows that the gains are regime-dependent: under benign reception the method matches the simpler filters, while in a dense field campaign in Al-Madinah it flagged unusable traces instead of producing a fictitious route. Its main benefit is route stability—low trajectory jitter and hence stable AR cue placement—rather than better end-point accuracy. In indoor environments, where satellite reception fails, the deployed iPhone app uses only the camera and inertial sensors to record a route once and later guide the user along it with floor-registered cues. It reaches decimeter-level end-point accuracy without satellite positioning. A confidence-gated disorientation detector separates positioning-induced irregularities from behavior-induced irregularities. The evidence validates the reconstruction, detector, and deployed app on navigation data; human-subject evaluation with the motivating populations remains future work.