A platform for embodied models of infant cognition, and its use in a model of event perception

Mark Sagar, Alecia Moser, Annette M. E. Henderson, Sam Morrison, Nathan Pages, Alireza Nejati, Wan-Ting Yeh, Jonathan Conder, Alistair Knott, Khurram Jawed, Martin Takác

Abstract: While most modelling efforts focus on particular components of the infant cognitive system studied in isolation, we have developed a model of a ‘whole baby’: a graphical simulation of a baby, whose behaviour is produced by a multi-component brain model. The novelty of the model is that it is realistic and fast enough to interact in real time with human users playing a caregiver role. This allows us to directly compare the behaviour of the simulated baby interacting with users with that of real babies interacting with parents via video chat using touchscreen devices. In this paper, we present some work in progress on the cognitive model, relating to the components involved in perceiving events, and representing events in working memory, with a focus on motion events. We also introduce our framework for recording video interactions between real parents and babies, and we describe a preliminary evaluation of our motion event model against manually identified motion events from these interactions.