Research

The Institute for Networked Cyber-Physical Systems (NCPS) is part of the School of Electrical Engineering, Computer Science, and Mathematics at the Hamburg University of Technology (TUHH).

Our work is driven by three trends:

sensors are everywhere and give near real-time insights in every aspect of the world,
AI is here to stay,
nearly everything gets programmable, see RISE-Lab.

We do - mainly data-driven - systems research on networked and intelligent systems. We are particularly passionate about the Internet of Things (IoT), Cyber-Physical Systems, Edge & Fog Computing, Edge AI and TinyML. We love to build systems and play with them (= run experiments and write papers about them). We release our results as open source and evaluate our work on large-scale testbeds, often with hundreds of nodes. Software releases of projects in which we were involved are published on GitHub (GitHub TUHH-NCPS, GitHub DS-Kiel, GitHub IoT Chalmers).

Currently, our Institute focuses on the following directions:

Deep Learning

            						Adaptive Machine Learning: Adaptive and flexible Deep Neural Networks 
Edge AI and TinyML: Resource-efficient and embedded ML
Distributed Machine Learning: split computing and federated learning 

        						

Internet of Things

            						Low-Power Wireless Networking: Bluetooth (BLE), ZigBee / 802.15.4, LoRa, UWB
Wireless Networking: 5G, 6G, 802.11
Resilient Internet of Things: Synchronous transmissions for resilient low-latency wireless networking in low-power wireless networks 

        						

Edge Computing

            						Distributed Computing: Distributed computing in dynamic and resource-constrained environments
Swarms of Autonomous Devices: Coordinating maneuvers, positioning and localization in dynamics and mobile environments
Process Mining: Mining of processes on distributed event sources

        						

Current Projects at Hamburg University of Technology

DFG Project EdgeMine, part of Research Unit: "SOURCED – Process Mining on Distributed Event Sources"

Distributed, locality-aware process mining and process mining on resource-constrained IoT devices.

Project Webseite: Sourced
Role: PI
Year(s): 2023-2027 (4 years)
Volume: about 400k Euro

Current Projects at Kiel University

KIMMCO: AI-controlled monitoring of marine microalgae as CO2 sinks

The KIMMCO project investigates how biodiversity affects the CO2 storage capacity of phytoplankton, a key factor in marine conservation. Researchers integrate data from sensors, cameras, optical measurements, and satellites, using AI to analyse these inputs and deliver near real-time insights into phytoplankton productivity and composition. The project aims to make large-scale ocean measurements more efficient, accurate, and sustainable by reducing time, ship operations, and the CO2 footprint of marine observation.

Project website
Role: Co-PI
Year(s): 2025-2027 (2.5 years)
Volume: 325k Euro

Intelligent Underwater Monitoring, part of “Helmholtz School for Marine Data Science”

Intelligent underwater monitoring systems combining distributed underwater sensor networks with cloud-based digital twins.

Helmholtz MarData
Role: Co-PI
Year(s): 2025-2028 (3 years)
Volume: 230k Euro

X-Ferry - Building Acceptance For Autonomous Transit Through Understanding

Understanding creates acceptance. This is the premise behind the new CAPTN project X-Ferry. With this research project, the CAPTN initiative is taking another step towards realizing its idea of developing a mobility chain of self-driving, safe and clean vehicles. After the Fjord Area, 5G and Flex projects, which laid the foundation for autonomous shipping in Kiel, the focus is now on explaining the technical processes and communicating with users. Initially, the focus will remain on ships. The new project will research systems that will increase the acceptance of autonomous vehicles.

Project Webseite: X-Ferry
Role: Co-PI
Year(s): 2024-2027 (3 years)
Volume: 270k Euro

An INnovative, intelligent SYSTem for coastal water monitoring using artificial intelligence (INSYST)

Data-driven prediction and event detection for underwater sensing.

Project Webseite: INSYST
Role: PI
Year(s): 2023-2026 (3 years)
Volume: 325k Euro

Completed Projects

At TUHH, Kiel University, and Chalmers University of Technology (Sweden)