prof. Michal Pěchouček presents Understanding future technologies through agent-based simulation

Current world is driven by data and superb analytical capability provided by
state-of-the-art machine learning research. We assume that there exist classes
of important prediction problems related to interaction among autonomous
rational entities, for which statistical data analysis is not sufficient enough
(such as understanding of future operation of drones in urban environment or
massive deployment of autonomous vehicles in existing car traffic).

We propose to complement modern data analysis with state-of-the-art procedural
and decentralised computational modelling methods referred as agent-based
simulation. We argue that agent-based simulation can help us to understand and
solve the problems of a near future for which there are no empirical data yet
available. During the research and technology talk we will discuss concepts,
results as much as deployment visions and open problems and challenges of
agent-based simulation.