0%
open source
v2x
[2023 – 2026] Developing a robust, channel-adaptive vehicular localization and tracking system utilizing mmWave MIMO, RIS, and OTFS technologies for environments where GPS is unavailable.
digital twins extended reality
[2025 – 2028] Investigating Spatial ID as a standardized, multi-resolution spatial indexing layer that enables interoperable urban data systems, real-time querying, and large-scale spatial computing applications.
digital twins
[2023 – 2025] This project seeks to establish a scientifically framework for Level-4 autonomous flight of unmanned aerial vehicles (UAVs). Unlike traditional methods limited to static, spatial path planning, this research integrates 4D spatiotemporal representations, predictive world-models, safety-constrained reinforcement learning, and GPS-independent Vision-Language(-Action) (VLM/VLA) modules. The resulting system aims to achieve safe, efficient, and flexible navigation in dynamic, uncertain environments while addressing regulatory certification requirements.
open data
The URT-Kashiwa Dataset (Unprotected Right Turn, Kashiwa Campus) is a collection of driving scenario recordings focused on unprotected right turns, a challenging maneuver for autonomous vehicles (equivalent to unprotected left turns in Europe). The dataset was collected at the Kashiwa Campus of the University of Tokyo using the Pixkit 3.0 platform, and includes interactions with one pedestrian and one opponent vehicle across 16 different routes. © 2025 Tsukada Laboratory (T-Lab), The University of Tokyo Contributors: Ehsan Javanmardi, Dongyang Li, Manabu Tsukada
