AREA 2025
5th Workshop on Agents and Robots for reliable Engineered Autonomy
25th October 2025 at ECAI 2025 - Bologna
Registration @ ECAI
| Time | Activity |
|---|---|
| 09:15 - 09:30 | Opening Remarks |
| Session 1: Agent Programming & Reasoning | |
| 09:30 - 09:55 | “Selecting the Most Specific Plan in AgentSpeak Programs” — Ethan Le Trung, Babak Esfandiari |
| 09:55 - 10:20 | “A Formal Factorization Approach of Non-Deterministic Plans: Application to an Anti-Poaching Robotic Mission Scenario” — Baptiste Pelletier, Caroline P. C. Chanel, Alexandre Albore |
| 10:30 - 11:00 | Coffee Break |
| Invited Talk | |
| 11:00 - 12:00 | Alessandro Ricci — Agent Programming in the Generative AI Era Abstract: Historically, agent programming and agent-oriented programming languages have played an essential role in the engineering of agent and multi-agent systems across diverse domains — from software agents to robotics. Their main contribution has been to provide proper levels of abstraction for designing and developing agents, as well as rigorous theoretical foundations and tools to detect and prevent errors, verify behaviours and interactions. This role, however, has been challenged over the past decade. Today, the tremendous achievements in generative AI have led to the emergence of agentic AI frameworks and technologies that enable the development of LLM-based autonomous agents and multi-agent systems — apparently without the need for explicit abstractions, architectures, or programming languages. In just a few years, these technologies have achieved widespread diffusion and adoption, making 2025 the “year of AI agents.” In this invited talk, I will explore this evolving landscape and argue for novel approaches to engineering agents and multi-agent systems that, on the one hand, preserve the benefits of “Good Old-Fashioned Agent Programming” and “Good Old-Fashioned Agent-Oriented Software Engineering,” and, on the other hand, effectively harness the new capabilities brought by generative AI. |
| Session 2: Verification & Safety | |
| 12:00 - 12:25 | “Corroborative V&V for Autonomous Systems: Integrating Evidence and Discrepancy Analysis for Safety Assurance” — Dhaminda B. Abeywickrama, Christopher Bishop, Simon Watson, Frederic Wheeler, Michael Fisher, Louise A. Dennis |
| 12:30 - 14:00 | Lunch Break |
| 14:00 - 14:25 | “Towards Safe Action Policies in Multi-robot Systems with Causal Reinforcement Learning” — Giovanni Briglia, Stefano Mariani, Franco Zambonelli |
| Invited Talk | |
| 14:30 - 15:30 | Alessandro Farinelli — Safe Reinforcement Learning for Intelligent Robotic Systems Intelligent Robotic Systems are a critical asset in several application scenarios, ranging from agile manufacturing, to environmental monitoring and logistics. A crucial element for Intelligent Robotic Systems to be successfully deployed in such scenarios is the ability to adapt their behaviours to changes in the operational environments, and Reinforcement Learning (RL) is a widely used approach to achieve this. However, the adoption of RL techniques for robotics is still a major challenge mainly because undesired or dangerous behaviours, that are extremely difficult to avoid for these methods, may not be acceptable in robotic applications. In this talk we will consider the key aspects related to safety for RL in Intelligent Robotic Systems. Specifically, we will focus on the possibility of providing formal guarantees for RL methods when deployed on Intelligent Robotic Systems. In more detail, we will consider Formal Verification methods and discuss whether such approaches may have a role in RL for robotic systems and what are the main challenges associated with this. Moreover, we will discuss Neuro Symbolic approaches for Safe RL, investigating why Safe RL methods may benefit from symbolic approaches and why integrating symbolic methods in RL approaches is challenging. Finally, we will consider future research directions associated with Safe RL for Intelligent Robotic Systems, highlighting application scenarios where these methods can have a key impact. |
| 15:30 - 16:00 | Coffee Break |
| Session 3: Robotics & Perception | |
| 16:00 - 16:25 | “A wearable stereo vision-based obstacle detection system for visually impaired individuals” — Andrea Ruo, Dario Napolitano, Valeria Villani |
| 16:25 - 16:50 | “Sim-to-Real 6-DoF Pose Estimation for UAVs using Synthetic RGB-D Data” — Jan Rodziewicz-Bielewicz, Marek Wernikowski, Marcin Korzeń, Radoslaw Mantiuk |
| Session 4: Learning & Control | |
| 16:50 - 17:15 | “Conversational Text-to-SQL: A Comprehensive Survey of Paradigms, Challenges, and Future Directions” — Yufei Yang, Zewu Peng, Fangfang Zhou, Xu yao, Yuhao Zhang |
| 17:15 - 17:40 | “BC-MPPI: A Probabilistic Constraint Layer for Safe Model-Predictive Path-Integral Control” — Chidinma Ezeji, Michael Ziegltrum, Giulio Turrisi, Tommaso Belvedere, Valerio Modugno |
| 17:40 - 17:50 | Closing Remarks |
