Socially compliant behaviour modelling for artificial systems and small groups of teachers and learners
Sahba Zojaji is a Marie-Curie PhD fellow of Computer Science at the KTH University, Sweden. He received his M.Sc. in Computer Engineering-Artificial Intelligence & Robotics from Iran University of Science & Technology (IUST) in 2011. After his ten-year career as an engineer and researcher in different companies and universities in Iran, Sahba joined the LITIS laboratory in 2016, where he accepted a research engineer position at INSA of Rouen Normandy, France. He focused on Embodied Conversational Agents, story-telling and Child-agent multi-modal interaction during his over two years work for LITIS Lab. Eventually, he started his PhD at KTH Royal Institute of Technology from first of November 2018.
His research interests include Human-Computer Interaction, humanoid and social agents, affective computing and educational technology.
You can find more information about him in his personal web-page.
Kungliga Tekniska Högskolan (KTH)
Christopher Peters (KTH), in association with Mohamed Chetouani, Catherine Pelachaud (UPMC) and Chloé Clavel (IMT)
IMT; UPMC; SBR
While many modern education scenarios involving robots and agents involve the participants (teachers and children) moving to and accommodating the robot, a vision for future training scenarios is that robots will be capable of moving to groups of learners and teachers in order to accommodate them. This requires systems that are capable of not only navigating, but also positioning and introducing themselves appropriately in order to engage in interaction i.e. they must be socially compliant. For example, artificial systems should join a group in a suitable manner, minimising intrusions to a group that is engaged in an ongoing pedagogical scenario, and do so by finding a suitable position for themselves in a formation of conversation partners, maintaining appropriate social and sensory distances. The central aspect in this ESR project will be to develop socially compliant small group behaviours for robots and agents tailored to small groups of learners and teachers. This will be accomplished through procedural models and machine-learning approaches based on data corpora from human-human and human-machine interactions and through the use of experiments involving human participants and groups of virtual replicas in virtual reality.
Completed draft of PhD dissertation, algorithms and tools for modelling compliant behaviours between mobile systems and small groups, peer-reviewed publications, international journal and conference publications