[gtranslate]teste
International Lecture
Multi-Agent Intention Recognition and Progression
Prof. Brian Logan (University of Aberdeen, UK & Universiteit Utrecht, NL)
Abstract: For an agent in a multi-agent environment, it is often beneficial to be able to predict what other agents will do next when deciding how to act. For example, to offer effective assistance in a disaster-response scenario, a search and rescue robot must recognise the activities of humans and other agents with only minimal or no communication. Previous work in multi-agent intention scheduling assumes ‘a priori’ knowledge of the current goals of other agents. In this talk, I will present IGR, an approach to multi-agent intention scheduling in which an agent uses online goal recognition to identify the goals currently being pursued by other agents while acting in pursuit of its own goals. I will explain how IGR can be incorporated into an MCTS-based intention scheduler, and present results from a range of scenarios which demonstrate that IGR agents are able to rapidly recognise the goals of other agents, even when the other agents are pursuing multiple goals concurrently, allowing IGR agents to achieve performance similar to agents which know the goals of other agents ‘a priori’.
Short Bio: Before moving to Utrecht, Professor Brian Logan was an associate professor at the School of Computer Science at the University of Nottingham, where he still has an honorary position (Special Professor). Before that, he was a lecturer in Artificial Intelligence in the School of Computer Science at the University of Birmingham. Professor Brian Logan has also worked at the Martin Centre for Architectural and Urban Studies on architectural CAD systems, the Computer Laboratory at the University of Cambridge on computational models of belief revision, and the Department of Artificial Intelligence at the University of Edinburgh on design support systems.
National Lecture 1
Autonomous Agents and Multiagent Systems:
Perspectives on (quite) a quarter of a century of AAMAS
Prof. Jaime Simão Sichman (USP)
Abstract: In this talk, I will present an historical perspective of AAMAS conference, trying to answer the following questions: (i) How has this scientific field changed over time? (ii) What features of AAMAS research have remained constant throughout? (iii) What impact did we have as a field? What opportunities have been missed? (iv) What does the future hold for AAMAS? What kind of challenges should the community focus on?
Short Bio: Jaime Simão Sichman has obtained his PhD degree in Computer Engineering from the Institut National Polytechnique de Grenoble (INPG), France, with an European label joint with Istituto di Psicologia del CNR, Rome, Italy. His main research focus is multi-agent systems, more particularly in subjects like social reasoning, organizational reasoning, multi-agent-based simulation, reputation and trust, and interoperability in agent systems. He has advised/co-advised 23 MsC, 14 PhD, and several undergraduate students. He has published more than 160 papers in national and international conferences and journals. He is member of the editorial board of the Journal of Artificial Societies and Social Simulation (JASSS), the Knowledge Engineering Review (KER), the Computational and Mathematical Organization Theory (CMOT) and Autonomous Agents and Multi-Agent Systems (JAAMAS). He has organized several national and international conferences and workshops: in particular he was the AAMAS Tutorial Chair (2007), Program Co-Chair (2009), Local Organization Chair (2017), Workshop Co-Chair (2020) and AAMAS General Co-Chair (2024). In Brazil, he was the SBIA/IBERAMIA General Chair (2000), Program Co-Chair (2006) and the WESAAC Local Chair (2013). He is a member of the Board of Directors of the International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). He was the coordinator of the Artificial Intelligence Special Interest Group (CEIA) of the Brazilian Computer Society (SBC), and was also a member of the Societys Council. Between 2010 and 2013, he was the Director of the Electronic Computing Center (CCE) of the University of São Paulo (USP). He was indicated as a member of the Association of Computing Machinery (ACM) Distinguished Speaker Program in 2012. Curently, he is a Full Professor of the Computer Engineering and Digital Systems Department (PCS) of the Escola Politécnica (EP) at the Universidade de São Paulo (USP). Slides
National Lecture 2
Neuro-Symbolic BDI Agents
Prof. Rafael C. Cardoso (University of Aberdeen, UK)
Abstract: In this talk, I will give a brief overview of my past research on symbolic Artificial Intelligence (AI) and then I will discuss my future research direction on Neuro-Symbolic AI. Neuro-Symbolic AI studies the combination of machine learning techniques (e.g., neural networks, deep learning) and symbolic AI approaches (e.g., rule-based systems, cognitive/rational agents). Due to recent advancements in both research areas, Neuro-Symbolic AI has seen a resurgence in recent years where it has been applied to tackle complex applications such as robotics and self-driving vehicles. I will focus on my recent work of combining Belief-Desire-Intention (BDI) agents with pre-trained machine learning models for joint high-level control of self-driving vehicles in the CARLA simulator.
Short Bio: Rafael C. Cardoso is a Lecturer in the Department of Computing Science at the University of Aberdeen (UK), and a member of the Agents at Aberdeen (A3) research group and the Autonomy and Verification Network. He is also an Honorary Senior Research Associate at both the University of Liverpool (UK) and the University of Manchester (UK). Rafael obtained his Master and Doctorate degrees in Computer Science from PUCRS (2014 and 2018 resp.), and Bachelor’s degree in Computer Science from Universidade Franciscana (2012). His main research themes include cross-cutting research on multi-agent systems, AI planning, verification and validation, and neuro-symbolic AI. Rafael is a member of the program committee in several top-ranked international conferences such as AAAI, IJCAI, AAMAS and ECAI, where he also publishes his work. He is one of the main organisers of the AREA workshop and has organised other workshops such as EMAS and contests such as the International Intention Progression Competition.