Prof Michael Richardson (Macquarie University)

Title: Modelling the Behavioural Dynamics of Multi-agent Coordination: Dynamical Primitives, Machine Learning, and Generative AI

Abstract:

Effective multi-agent interaction and teamwork depends on individuals’ ability to coordinate their movements, actions, and decisions in dynamic environments. Expert performance is often distinguished by the flexibility and efficiency with which individuals determine who, how, and when to act. In this talk, I will present ongoing work exploring multimodal modelling and analysis techniques that integrate dynamical motor primitives, advanced machine learning, and generative AI—including large language models—to examine, predict, and enhance human perceptual-motor behaviour and decision-making in team-based tasks. By leveraging multiple data modalities, from movement trajectories to linguistic interactions, these techniques provide deeper insights into the underlying mechanisms of human coordination. They also inform the development of interactive artificial agents capable of real-time adaptation, anticipation, and intervention to optimize team and joint-action performance.

Bio:

Professor Richardson is a cognitive scientist and director of research in the School of Psychological Sciences at Macquarie University. His research is directed towards modelling the dynamics of human perception, action, and cognition for the development of human-machine systems. He has expertise in social and multi-agent interaction and coordination, computational, dynamical, and complex systems modelling, and machine-learning and AI.