Core project
MAPLE-RF: Localization with Partial Maps
Efficient neural posterior inference for RF source localization while a robot has explored only part of its environment.
•
1 min read
Core project
MAGNETAR: Joint RF Pose Inference
Multipath-guided joint posteriors over transmitter position and heading, calibrated from simulation and evaluated on a 10-GHz robotic RF testbed.
•
1 min read
LOCUS-DT: Localization via Observation-Conditioned Uncertainty Scoring with Digital Twins
LOCUS-DT matches measured multipath to candidate ray-tracing signatures and recovers structured transmitter-location posteriors.
Beyond Point Estimates: Likelihood-Based Full-Posterior Wireless Localization
MC-CLE learns full spatial posteriors from sparse AoA/SNR measurements, preserving multipath ambiguity beyond Gaussian point-error models.
Core project
LOCUS-DT: Digital-Twin Posterior Localization
Observation-conditioned scoring of measured multipath against ray-traced location hypotheses for site-agnostic spatial posterior inference.
•
1 min read
Core project
MC-CLE: Full-Posterior Wireless Localization
Candidate-wise neural likelihood estimation from sparse AoA and SNR measurements, preserving directional and multimodal uncertainty beyond point estimates.
•
1 min read
Secondary project
Multi-Band UE Coordination Under Mobility
UE-centric multi-cell multi-band handset digital twins for closed-loop array, band, and rate prediction under mobility.
•
1 min read
Secondary project
Wireless-Guided Indoor Navigation
Ray-tracing digital-twin priors and physics-informed reinforcement learning for zero-shot indoor navigation.
•
1 min read
Core project
Robotic RF Localization & Experimental Systems
A 10-GHz robotic RF testbed connecting channel sounding, mobile sensing, localization, and SLAM-based navigation experiments.
•
1 min read