Speaker: Rafael C. Cardoso (University of Aberdeen, UK)
Abstract: Neuro-Symbolic Artificial Intelligence (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. In this seminar, I will give a brief overview of these two applications areas, and then 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.
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. He also holds honorary senior research associate positions at both the University of Liverpool and the University of Manchester. Dr. Cardoso earned his Master's and Doctorate degrees in Computer Science from PUCRS in 2014 and 2018, respectively, and a Bachelor's degree in Computer Science from Universidade Franciscana in 2012. His research interests encompass multi-agent systems, multi-agent planning, hybrid AI, and the integration of formal verification in software development. He actively contributes to the academic community, serving on program committees for international conferences such as AAAI, IJCAI, AAMAS, and ECAI.