Blog

[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.Read more

[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.Read more

[2023 – 2024] Research on developing safer and more human-like autonomous driving systems using large language models that learn human driving preferences.Read more

[2025] A novel framework enabling collaborative perception among vehicles with different models by adapting on-the-fly during inference.Read more

[2021 – 2025] We extended the open-source Autoware platform with cooperative perception and maneuver coordination features, enabling next-generation infrastructure-assisted autonomous driving.Read more

[2024 – 2025] Real-time offloading of semantic perception tasks from MR headsets to edge AI accelerators, enabling scene-level understanding and interaction in unstructured environments.Read more

[2023 – 2025] Developing a multipath framework to improve real-time media quality under fluctuating 5G network conditions by leveraging multiple mobile connections simultaneously.Read more

[2023 – 2025] Building a federated learning-based architecture for efficient and secure communication and intelligence in connected autonomous vehicles.Read more

[2021 – 2025] Building a digital twin platform that fuses large-scale geometry, precise positioning, and real-time acoustic simulation to enable responsive 3D audio in urban mixed-reality environments.Read more

[2023 – 2024] Developing a next-generation BIM-based digital twin that fuses building geometry, spatial acoustics, and semantic data for real-to-virtual integration.Read more

[2017 – 2023] A metadata framework to describe and utilize media content with spatial and temporal context, enabling interactive and reusable applications.Read more

[2019 – 2020] Designing and deploying networked RSPUs to enable infrastructure-driven cooperative perception for safe and efficient autonomous driving.Read more

[2014 – 2019] A programmable media platform enabling immersive and interactive live experiences through networked control of spatial audiovisual environments.Read more