Wireless Indoor Navigation & SLAM
I develop ray-tracing wireless digital twins and PIRL (physics-informed reinforcement learning) methods that use simulated propagation as a transferable prior for zero-shot indoor navigation, wireless SLAM, and symbolic-prior robot policies. This line is being extended toward physical localization and navigation experiments with TurtleBot4 and Jackal UGV platforms, FR3 channel-sounding hardware, and controlled navigation scenarios.
This figure links posterior RF belief maps with indoor navigation, showing how uncertainty-aware localization can support zero-shot wireless robot policies.
The rollout animation shows a navigation policy using wireless belief maps as spatial guidance during indoor search.
Related papers
- Zero-Shot Wireless Indoor Navigation through Physics-Informed Reinforcement Learning (ICRA 2024)
- Digital Twin-Enhanced Wireless Indoor Navigation: Achieving Efficient Environment Sensing with Zero-Shot Reinforcement Learning (IEEE OJ-COMS 2025)
- Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigation (RLC 2025 Spotlight)
Haozhe Lei (Graduate Student Member, IEEE) is a Ph.D. candidate in Electrical and Computer Engineering at New York University, advised by Professor Sundeep Rangan in NYU WIRELESS. He received the B.E. degree in electrical engineering and automation from China Agricultural University in 2019 and the M.S. degree in computer engineering from NYU in 2022. His research develops uncertainty-aware wireless intelligence for embodied autonomy and adaptive 6G systems, combining algorithms, digital twins, and physical testbeds to transform sparse RF and multimodal observations into calibrated spatial beliefs and closed-loop decisions.
His current work includes MC-CLE and LOCUS-DT for posterior RF localization, PIRL and wireless digital-twin priors for zero-shot robot navigation, MCMB-HDT for closed-loop multi-band handset adaptation, and object-centric graph memory for multimodal spatial reasoning. He also builds FR3/mmWave RFSoC/Pi-Radio channel-sounding systems with TurtleBot4 and Jackal UGV platforms. He received the 2023 Ernst Weber Fellowship from the NYU Tandon School of Engineering.