The Autonomous Edge - Intelligence Embedded in Industrial Applications

The Autonomous Edge - Intelligence Embedded in Industrial Applications

Communications and Networking

The Autonomous Edge - Intelligence Embedded in Industrial Applications

Editors:
Ovidiu Vermesan, SINTEF, Norway Fetze Pijlman, Signify, Netherlands

ISBN: 9788743815259 (Hardback) e-ISBN: 9788743815266

Available: June 2026

doi: https://doi.org/10.13052/rp-9788743815266


The Autonomous Edge – Intelligence Embedded in Industrial Applications explores the technological transformation taking place at the intersection of artificial intelligence, edge computing, autonomous systems, and industrial applications. Bringing together contributions from researchers and practitioners across multiple disciplines, the book presents a comprehensive perspective on how intelligence is increasingly moving from centralised cloud infrastructures directly into vehicles, robots, manufacturing systems, smart cities, critical infrastructures, and embedded devices.

The chapters examine how next-generation edge AI systems are being designed to operate under strict constraints involving latency, energy consumption, privacy, safety, reliability, and real-time responsiveness. The book covers a wide spectrum of technologies, including AI-defined vehicles, continual learning, lightweight neural networks, vision transformers, graph neural networks, digital twins, semantic mapping, multimodal perception, and distributed AI pipelines optimised for deployment on edge hardware.

A central theme throughout the book is the transition from isolated edge AI models toward integrated, adaptive, and autonomous edge intelligence architectures. The presented solutions combine advances in hardware acceleration, embedded edge AI optimisation, communication infrastructures, explainable edge AI, and real-time processing to enable practical deployment in demanding industrial environments. Applications range from autonomous systems, mobility and smart manufacturing to cybersecurity, environmental monitoring, urban safety, and hydrogen infrastructure management.

The book addresses broader challenges associated with autonomous systems, including transparency, liability, ethical decision-making, robustness, and trustworthiness. By combining theoretical foundations with implementation experiences and experimental validations, the chapters provide both scientific insight and practical guidance for researchers, engineers, architects, and decision-makers working on the next generation of intelligent industrial systems at the edge.

Positioned at the convergence of edge AI, autonomous systems, and industrial digitalisation, the book offers a forward-looking view of how distributed intelligence is reshaping the physical world and enabling a new generation of adaptive, efficient, and edge autonomous industrial applications.
Autonomous edge AI systems, edge AI technologies, software-defined vehicles, AI-defined-vehicles, edge AI technology stack, micro-edge, deep-edge, and meta-edge, artificial intelligence (AI), edge AI accelerators, deep learning (DL), machine learning (ML), federated learning (FL), edge AI trustworthiness, AI explainability (XAI), AI interpretability (IAI), edge AI applications.

Chapter 1: The AI-Defined Vehicle: Navigating the Convergence of AI and Autonomous Systems
by Ovidiu Vermesan, Valerio Frascolla, Patrick Pype, Vahid Hashemi


2

Chapter 2: From Complexity to Efficiency: Pruning Vision Transformers in Practice
by Martyna Poreba, Ahmed Soulmani, Victor Bercy, Michal Szczepanski


1

Chapter 3: GStreamer Plugin for RDMA Offload on BlueField-3 for Edge Applications
by Raphael Frantz, Romain Pouillard, Idelfonso Tafur Monroy, Juan Jose Vegas Olmos, Salvatore Di Girolamo


1

Chapter 4: On-Device Continual Learning for Unsupervised Visual Anomaly Detection in Dynamic Manufacturing
by Haoyu Ren, Kay Köhle, Kirill Dorofeev, Darko Anicic


2

Chapter 5: In-GPU GNN-based Intrusion Detection System
by Ahmed Salah Tawfik Ibrahim, Emilio Paolini, Filippo Cugini, Francesco Paolucci


1

Chapter 6: Vision-language Embeddings in Large Scale LiDAR SLAM for Terrain Segmentation
by Peteris Racinskis, Janis Arents, Modris Greitans


3

Chapter 7: Investigating Target Class Influence on Neural Network Compressibility for Energy-Autonomous Avian Monitoring
by Nina Brolich, Simon Geis, Maximilian Kasper, Alexander Barnhill, Axel Plinge, Dominik Seuß


2

Chapter 8: When a model is not Enough: A Complementary AI Pipeline for Ultra-Safe PCBA Defect Detection
by Alberto Faro, Francesco Cancelliere, Robin Faro, Raffaele Mineo


2

Chapter 9: Towards Automated Liability Determination for Autonomous Vehicles in Road Accidents
by Rohit Bohara, Omkar Joglekar, Mirko Ross, Rob van Kranenburg


1

Chapter 10: Edge-Optimized Modular Architecture for Real-Time Vehicle Re-Identification
by Tomass Zutis, Dimitrios Georgiadis, Tassos Kanelos, Janis Judvaitis, Peteris Racinskis, Konstantina Karathanasopoulou, George Dimitrakopoulos, Janis Arents, Modris Greitans

Chapter 11: Edge Deployment of Multi-Task Vision Models for Smart City Infrastructures
by Carmelo Scribano, Mohammad Mahdi, Filippo Muzzini, Nedyalko Prisadnikov, Yuqian Fu, Micaela Verucchi, Ignacio Sanudo Olmedo, Danda Pani Paudel, Luc Van Gool


1

Chapter 12: Experiences in Deploying a Weapon Detector in a Smart City
by Juan Daniel Muñoz, Hugo Albandea Merino, Jesus Ruiz-Santaquiteria, Oscar Deniz, Micaela Verucchi


2

Chapter 13: A 3D Simulation Framework for Behavior Cloning on Edge AI-Enabled E-Scooters in Smart Cities
by Artemis Stefanidou, Eleni Tsaousi, Elena Politi, Ihsan Can Yalabuk, Emrecan Bati, Burak Tüfekçi, George Dimitrakopoulos


1