Hankuk University of Foreign Studies

Notice — PASS Lab. was formerly the Embedded Software Engineering (ESE) Laboratory. In March 2027 the department is renamed the Department of AI Robotics; until then it remains the Department of Information and Communications Engineering.

Welcome to the Physical AI System Software (PASS) Laboratory, Department of AI Robotics, Hankuk University of Foreign Studies, Korea.

We build the system software that sits between a learned model and a machine that has to move: partitioning models across on-device accelerators, guaranteeing timing for workloads of mixed criticality, and orchestrating both with cloud-native infrastructure. See Research for the three axes we work on.

News

  • March 2027 — The department is renamed the Department of AI and Robotics Engineering, and the laboratory becomes PASS Lab.
  • June 2026 — MCKube: a holistic mixed-criticality orchestration system in Kubernetes appears in the Journal of Systems Architecture. doi:10.1016/j.sysarc.2026.103904
  • January 2026 — A Protocol-Agnostic and Automated Approach to Bi-directional Inter-Domain Communication in Software-Defined Vehicles appears in the International Journal of Automotive Technology. doi:10.1007/s12239-025-00375-w
  • May 2025 — DNNPipe: Dynamic programming-based optimal DNN partitioning for pipelined inference on IoT networks appears in the Journal of Systems Architecture, open access. doi:10.1016/j.sysarc.2025.103462
  • July 2024 — Our work on dynamic mapping of mixed-criticality applications is presented at IEEE ICDCS 2024, Jersey City. doi:10.1109/ICDCS60910.2024.00154