PAIS Invited Speakers
Grigorios Antoniou
Leeds Beckett University, UK
AI for Mental Health Diagnostics
Abstract: In this talk, we cover our work on using AI as a clinical decision support tool for mental conditions, with a focus on adult ADHD, adult ASD and suicidology. These works are done collaboratively with the one of UK’s NHS Trusts and have resulted in developing new technological solutions.
In addition, we also review the development and potential use of domain- specific ontologies and discuss potential uses of Large Language Models. Finally, we present opportunities and challenges of Neuro symbolic AI.
Bio: Grigoris Antoniou is Professor of AI at Leeds Beckett University, UK. His research interests lie in semantic technologies, particularly knowledge representation and reasoning and semantics for big data, and its application to health, law and smart cities. He has published over 200 technical papers in scientific journals and conferences. His research has attracted over 15,000 citations. He is member of the European Academy of Sciences and Arts, Fellow of IEEE, Fellow of the European Association for Artificial Intelligence and Fellow of the Asia-Pacific AI Association.
Roni Stern
Ben Gurion University of the Negev, Israel
Multi-Agent Pathfinding in Automatic Warehouses – An Overview After 15 Years of Research
Abstract: Multi-Agent Path Finding (MAPF) has evolved from a theoretical combinatorial search problem into a foundational technology for real-world deployed systems. In this talk, I will focus on one such application: large-scale automated warehouses, where fleets of robots transport goods efficiently and safely. We will begin with the classical MAPF problem formulation, in which multiple agents navigate a shared space without collisions, and briefly review key algorithmic approaches to solving it. I will then describe the automated warehouse application in more detail and highlight the gaps between the MAPF-like challenges encountered there and the classical MAPF definition. We will examine existing approaches to bridging these gaps, including lifelong planning, robustness to failures, and techniques for mitigating uncertainty. The talk will conclude with open questions and promising research directions for advancing MAPF in practical, dynamic environments.
Bio: Roni Stern received his Ph.D in 2011. He is a full professor of computer science at Ben-Gurion University, Israel. In the past, he was a Principal Scientist at the Palo Alto Research Center (PARC) and the president of the Symposium on Combinatorial Search (SoCS). His research interests include single- and multi-agent planning, learning domain models, automated diagnosis, and applying AI for Software Engineering. Roni is currently the head of the Software Engineering Program at BGU and leading the Anomaly Detection and Diagnosis lab and the Search, Planning, and Learning lab at BGU. He has been working on Multi-Agent Path Finding since 2010 and his contributions the field have received several awards including the AIJ prominent paper award.