Autonomous Edge – Intelligence Embedded in Industrial Applications

Dr. Ovidiu Vermesan holds a Ph.D. degree in microelectronics and a Master of International Business (MIB) degree. He is Chief Scientist at SINTEF Digital, Oslo, Norway. His research interests are intelligent systems integration, mixed-signal embedded electronics, analogue neural networks, edge artificial intelligence and cognitive communication systems. Dr. Vermesan received SINTEF’s 2003 award for research excellence for his work on implementing a biometric sensor system. He is currently working on projects addressing nanoelectronics, integrated sensor/actuator systems, communication, cyber-physical systems (CPSs) and the Industrial Internet of Things (IIoT), with applications in green mobility, energy, autonomous systems, and smart cities. He has authored or co-authored over 100 technical articles and conference papers. He is actively involved in the activities of the European partnership for Key Digital Technologies (KDT) Joint Undertaking (JU), now the Chips JU. He has coordinated and managed various national, EU and other international projects related to smart sensor systems, integrated electronics, electromobility and intelligent autonomous systems such as E3Car, POLLUX, CASTOR, IoE, MIRANDELA, IoF2020, AUTOPILOT, AutoDrive, ArchitectECA2030, AI4DI, AI4CSM. Dr. Vermesan actively participates in national, Horizon Europe and other international initiatives by coordinating and managing various projects. He is a member of the Alliance for AI, IoT and Edge Continuum Innovation (AIOTI) board. He is currently the coordinator of the Edge AI Technologies for the Optimised Performance Embedded Processing (EdgeAI) project.Dr. Fetze Pijlman is a principal scientist in artificial intelligence at Signify Research, bringing over 20 years of experience in translating complex technological challenges into impactful real-world applications. His primary focus lies at the forefront of edge AI and connected IoT systems. He has been deeply involved in the European EdgeAI project, serving as a project leader for initiatives involving computer vision, radar, and RF sensing, while also leading the Dutch consortium on edge AI. His hands-on work includes the exploration and development of distributed AI and autonomous AI-agents tailored for large-scale sensor networks and edge devices. Furthermore, he is a key stakeholder in the NWO FIND project, driving collaborative academic research on foundation models for industry. He has extensive expertise in analysing and forecasting time series of events, successfully applying reinforcement learning, variational Bayes, and statistical modelling to enable self-learning wireless mesh networks for human activity recognition. Holding a Ph.D. in theoretical subatomic physics from the Vrije Universiteit Amsterdam, Dr. Pijlman applies this analytical rigor in his dual role as a hands-on algorithm architect and project leader, driving innovation across intelligent, distributed edge ecosystems.

• 1. The AI-defined Vehicle: Navigating the Convergence of AI and Autonomous Systems 2. From Complexity to Efficiency: Pruning Vision Transformers in Practice 3. GStreamer Plugin for RDMA Offload on BlueField-3 for Edge 4. On-device Continual Learning for Unsupervised Visual Anomaly Detection in Dynamic Manufacturing 5. In-GPU GNN-based Intrusion Detection System 6. Vision-language Embeddings in Large Scale LiDAR SLAM for Terrain Segmentation 7. Investigating Target Class Influence on Neural Network Compressibility for Energy-autonomous Avian Monitoring 8. When a Model is Not Enough: A Complementary AI Pipeline for Ultra-safe PCBA Defect Detection 9. Towards Automated Liability Determination for Autonomous Vehicles in Road Accidents 10. Edge-optimized Modular Architecture for Real-time Vehicle Re-identification 11. Edge Deployment of Multi-task Vision Models for Smart City Infrastructures 12. Experiences in Deploying a Weapon Detector in a Smart City 13. A 3D Simulation Framework for Behavior Cloning on Edge AI-enabled E-scooters in Smart Cities 14. Edge-AI Ready Lightweight Digital Twin for Anomaly Prediction: A Case Study on Hydrogen Refueling Station Data