Repository hosted by TU Delft Library

Home · Contact · About · Disclaimer ·

Modelling Human Movements with Turing Learning

Publication files not online:

Author: Zonta, A. · Smit, S.K. · Haasdijk, E. · Eiben, A.E.
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source:Sundaram, S., Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018, 8th IEEE Symposium Series on Computational Intelligence, SSCI 2018, 18 November 2018 through 21 November 2018, 2254-2261
Identifier: 865803
ISBN: 9781538692769
Article number: 8628691
Keywords: Co-evolution · Collective movements · Generative models · Human movements · Machine learning · Artificial intelligence · Deep learning · Learning systems · Generative model · Human behaviours · Human nature · Human-like trajectory · Learning models · Behavioral research


Modelling human behaviour is still an ongoing challenge that spaces between several fields like social science, artificial intelligence, and philosophy. Since the research of a metric able to define all the aspect of the human nature is still an ambitious task, most current studies use concepts like social forces or handwritten rules for modelling. Following the growing trend behind a new branch of Artificial Intelligence called Generative AI, this paper presents the application of Turing Learning on the problem of modelling human movements. Turing Learning is a generative model that uses evolutionary algorithms as a way to learn behaviours without the need for predefined metrics and, using deep learning models, it is able to produce human-like trajectories. We show how the system is able to infer the behaviours of the trajectories in the ETH dataset, forecasting the next points with the truthfulness of being a possible human movement. © 2018 IEEE.