This interdisciplinary project lies at the intersection of AI, Cognitive Psychology, and Linguistics. It explores several adaptive machine learning methods which can give insight into the interaction between human and machine. The ultimate goal is open and natural communication between humans and AI that should result in mutual trust, cooperation and coordination possibilities between both. To do so, we attempt to create a natural setting that allows machine learning algorithms to learn complex human- and social characteristics.

At first, we model social interactions with Multi-Agent Based Simulations in which there is evolution and reinforcement learning. The focus of these simulations will lie on synchronisation, coordination, and cooperation between the agents. It is in turn possible to extend the experiment with human input. As such, we hope to make inferences about the acquisition and evolution of the complex social- and communicative abilities that humans have. Results will be used to develop the intended natural human-machine interaction. Possible future research has a strong focus on the combination of AI and social cognition, reinforcement learning, self-organisation, and cultural transmission.