Simulating the Emergence of Early Physical and Social Interactions : A Developmental Route through Low Level Visuomotor Learning

Abstract

International audienceIn this paper, we propose a bio-inspired and developmental neural model allowing a robot, after learning its own dynamics during a babbling phase, to gain imitative and shape recognition abilities leading to early attempts for physical and social interactions. We use a motor controller based on oscillators. During the babbling step, the robot learn to associate its motor primitives (oscillators) to the visual optical flow induced by its own arm. It also statically learn to recognize its arm by selecting moving local view (feature points) in the visual field. We demonstrate in real indoor experiments that, using this same model, early physical (reaching objects) and social (immediate imitation) interactions can emerge through visual ambiguities induced by the external visual stimuli

Emotional modulation of peripersonal space as a way to represent reachable and comfort areas

“…We use an algorithm for points of interest (PoI) extraction by convolving the gradient images with a DoG filter. These PoI are categorized as visual signatures and associated with the objects to learn (See [20] for more details). Our system also learns a set of landmarks that should not be associated with none of the objects in order to be robust to background "noise".…”

A Modular Dynamic Sensorimotor Model for Affordances Learning, Sequences Planning, and Tool-Use

“…The camera is used to recognise and localise the arm, the tools and the target on the image. This is achieved by the use of a previously developed bio-inspired object recognition algorithm, based on local points of interests (see [82]). It gives the robot a 12-neuron vector, 4 for the presence of the different objects and 8 for their positions on the X and Y axes.…”

Building brains that communicate like machines

“…In this line of thinking, computational models have been built and used to improve human robot interaction and communication, in particular through the notion of learning by imitation (Breazeal & Scassellati 2002;Lopes & Santos-Victor 2007). Furthermore, some studies embedded machines with computational models using an adequate action-perception loop and showed that some complex social competencies such as immediate imitation (present in early human development) could emerge through sensorimotor ambiguities as proposed in Gaussier et al (1998), Nagai et al (2011, and Braud et al (2014). This kind of model allows future machines to better generalize their learning and to acquire new social skills.…”