1st International Workshop on Engineering Autonomous Systems Intelligence (EASI)
held in conjunction with
Verona, Italy | June 8-12, 2026
Read More
Autonomous Systems (AS), such as robots, self-driving cars, and body sensor networks,
whether enabled with Artificial Intelligence (AI) or not, are increasingly pervasive in our
daily lives. They are rapidly transforming domains such as transportation, manufacturing, the
built environment, and healthcare. Their effectiveness depends heavily on Information
Systems (IS), which provide the information, infrastructures, and coordination mechanisms
that enable autonomy.
In this context, AS act and generate massive streams of real-time data (sensor readings,
environmental feedback, performance metrics). IS process and analyze this data, supporting
decisions for both AS and human operators or users. Together, AS and IS form a continuous
feedback loop where the AS act and produce data, and IS interpret the data to provide
feedback to enable AS adaptation. Notably, this loop is more and more embedded within
socio-technical systems, where humans and technology continuously interact to fulfill
stakeholder requirements. Furthermore, AI is increasingly integrated within such loops,
offering new solutions for autonomy and automation. This tight coupling, along with the
proliferation of Large Language Models (LLMs) and Large Multimodal Models (LMMs),
raises new challenges, such as ensuring trustworthy data governance, protecting systems
from cyber threats, ensuring sustainable goals, addressing ethical concerns in
decision-making, and aligning autonomy with organizational and social contexts.
This workshop aims to explore the synergy of AS and IS, focusing on how autonomy and
information processes can be jointly designed, integrated, and governed in complex
environments. We aim to bring together diverse research communities, including
autonomous systems, information systems, artificial intelligence, software engineering, and
business process management, to foster a holistic understanding of the challenges and
opportunities of AS-IS connection.
The main topics include, but are not limited to:
| Time | Session | Duration |
|---|---|---|
| Chair: TBA | ||
| 14:00-14:05 | Welcome | 5 min |
| 14:05-15:00 |
Keynote: Francesco Leotta, Sapienza Università di Roma (Italy) Autonomous Systems in Smart Manufacturing see abstractSmart manufacturing is evolving from conventional automation toward intelligent, adaptive, and increasingly autonomous industrial ecosystems. This keynote explores how autonomous systems are transforming modern manufacturing and logistics through the integration of artificial intelligence, robotics, industrial IoT, digital twins, and multi-agent coordination. Drawing from recent industrial developments the talk will discuss how autonomous decision-making, perception, planning, and human–robot collaboration are reshaping factory operations.
|
40 + 15 Q&A |
| 15:00-15:30 |
Paper Presentation: Ofir Manor, Ortal Lavi, Ahmed M. Elmisery, Igor Podoski, Ewa Seroczynska and Andrés Murillo. Towards a Cyber Threat Operationalization Engine see abstractWith new adversarial threats reported every day, it has become imperative to harden existing systems against them as fast as possible. Cyber Threat Intelligence (CTI) reports describe adversarial behaviour in narrative form, but operationalizing these reports into network-specific, executable emulations remains labour-intensive and slow, delaying validation and mitigation. Nevertheless, existing tooling rarely provides a direct path from narrative CTI to runnable, topology-aware emulation artefacts, forcing experts to manually translate reports into environment-specific actions, which delays vulnerability mitigation and exposes organizations to cyber threat actors. We present a work-in-progress Cyber Threat Operationalization Engine that transforms a CTI report into (i) ATT&CK-labelled behaviours, (ii) a network-constrained representation of a feasible attack path derived via logic-based attack-graph reasoning, and (iii) an executable emulation plan instantiated in MITRE CALDERA and executed safely inside an isolated, emulated “CyberTwin” network. Our design leverages established components: ATT\&CK, CALDERA, Multi-host, multi-stage Vulnerability Analysis Language (MulVAL), and Graphical Network Simulator 3 (GNS3) — while using an agentic orchestration layer to connect CTI-derived intent to concrete actions on a specific topology. We focus on the representation and compilation of adversarial behaviour into attack-graph form and discuss practical challenges toward autonomy, including topology uncertainty, and the gap between abstract techniques and runnable emulation artefacts. A case study based on the Cutting Edge campaign was also introduced to demonstrate the feasibility of the proposed framework.
|
20 + 10 Q&A |
| 15:30-16:00 | Coffee Break | 30 min |
| Chair: TBA | ||
| 16:00-16:30 |
Paper Presentation: Flavio Corradini, Barbara Re, Lorenzo Rossi, Massimiliano Sampaolo and Mattia Scattu. Knowledge Graphs as a Semantic Layer for Understanding Robotic Video see abstractRobotic systems are increasingly deployed in industrial environments, where understanding and analyzing their operations is essential for monitoring and optimizing automated processes. Techniques such as process mining offer powerful tools for analyzing operational workflows, but they require structured representations of activities that are difficult to extract from raw sensory data. Among available data sources, video streams capture the temporal evolution of robotic actions, yet interpreting robotic behavior directly from video remains challenging.
In this paper, we propose the use of knowledge graphs as a semantic layer to support the interpretation of robotic video streams. The proposed approach separates visual perception from semantic reasoning through a modular architecture. A perception module extracts structured observations from video frames, while a knowledge graph encodes domain knowledge about the robotic environment, including objects, states, and possible interactions. This semantic layer supports the reasoning process used to interpret robot actions observed in the video.
The resulting framework enables the extraction of structured representations of robotic activities from video streams, supporting event-based descriptions of robot behavior that can be used for process analysis.
|
20 + 10 Q&A |
| 16:30-16:50 |
Paper Presentation: Elena Hoemann, Akshay Anilkumar Girija, Johann Maximilian Christensen, Yannick Kees, Florian Krone, Thomas Liebert, Ryan Mut, Gerald Sauter, Thomas Stefani, Frank Köster and Sven Hallerbach. Towards a Domain-Agnostic Safety-by-Design AI Engineering Pipeline see abstractAI-based applications already revolutionize our everyday lives; however, it remains unclear how to assess their safety given their black-box nature. Certifying them for safety-critical applications is thus still under current research. Therefore, we developed the Safe AI Pipeline (SAIPi) as an example of a safety-by-design approach to the engineering of AI systems. The pipeline contains several tools for data, model, and monitoring design, fulfilling requirements such as data completeness and model accuracy. MNIST is used as an exemplary showcase and proof of concept for developing deep learning models. We completed an entire iteration of the pipeline, which demonstrates how to engineer an AI system in a safe, iterative way. Future work will improve the tool and pipeline and increase the complexity of use cases.
|
15 + 5 Q&A |
All dates are Anywhere on Earth (AoE)
The papers must be submitted via EasyChair,
selecting the 1st International Workshop on Engineering Autonomous Systems Intelligence track.
Papers must conform to the Springer LNCS/LNBIP format
and should not exceed 12 pages for full papers and 6 pages for short papers (including references).
The proceedings of the conference workshops will be published as one volume in the Springer LNBIP series.
At least one author of each accepted paper must register and participate in the workshop. Please visit the main conference website for more information.
Track email address: easi-2026@easychair.org
Gran Sasso Science Institute, Italy
sara.pettinari@gssi.it
University of Fribourg, Switzerland
iva.vasic@unifr.ch
Hasselt University, Belgium
yannis.bertrand@uhasselt.be