Invited Talks

Abstract: Hierarchical plan validation gets a sequence of actions and determines if it is a valid hierarchical plan, that is, it is executable and can be obtained by decomposing some task. If the plan is valid, then a proof in the form of the task decomposition structure can be released. However, if the plan is not valid, plan validators simply state this. This is where plan correction may help by suggesting modifications to invalid plans, such as inserting or deleting actions, to make them valid hierarchical plans. Although the original motivation for plan correction was to enhance plan validation, the concept proved to apply to various other problems, including plan recognition, plan repair, and even planning itself.

The talk illustrates a journey from plan validation to plan correction, advocating plan correction as a general concept that encompasses various hierarchical planning tasks. As a future research direction, it suggests that a similar approach can be applied to planning domain models to obtain truly autonomous planning agents capable of learning and maintaining models of own behavior.

Short Bio: Prof. Roman Barták, Ph.D. is a Professor of Computer Science at Charles University in Prague, where he coordinates graduate and doctoral programs in Artificial Intelligence and Theoretical Computer Science. His research focuses on artificial intelligence, particularly automated planning and scheduling, constraint satisfaction, and knowledge representation. He has coordinated numerous national and European research projects and has extensive experience in industrial applications of AI and optimization. Prof. Barták has authored more than 170 research papers and regularly serves on the program committees of major international AI conferences, including IJCAI, AAAI, ECAI, ICAPS, and CP. He is a senior member of ACM, an AAAI Fellow, and a EurAI Fellow.

Goal Recognition in Automated Planning

Abstract: Goal Recognition is the task of inferring an agent’s goal from a sequence of observations. It has been studied in a wide range of real-world domains, including human–robot interaction, smart homes, autonomous driving, and surveillance. In this talk, we will explore how Goal Recognition has been addressed within the Automated Planning community, highlighting the different assumptions and methodologies that have shaped the field. Building on these foundations, we will then discuss the emergence of reinforcement learning and deep learning approaches. Finally, we will look at possible future directions for the field, particularly in light of the recent breakthrough of Large Language Models and their growing impact across Artificial Intelligence.

Short Bios: 

Dr. Mattia Chiari is a Research Fellow at the University of Brescia, Italy. He received his Ph.D. in Computer Science from the University of Brescia in 2024. His research lies at the intersection of Automated Planning and Machine Learning, with a particular focus on Goal Recognition, sequential decision making, and neuro-symbolic AI. His work spans topics such as deep learning for goal recognition, planning with large language models, and learning-based approaches for real-world planning applications.

Dr. Luca Putelli is an Assistant Professor at the University of Brescia (Italy) where he received his Ph.D. in Information Engineering in 2021. His main research interests are Natural Language Processing and Explainable AI, with a particular focus on real-world applications, semantics, word representation and fairness in Transformer-based models. He also works in neuro-symbolic AI, where he has contributed to the creation of several deep learning models applied to automated planning, in particular for goal recognition and plan generation with Large Language Models.