Discovering Schema-Based Action Sequences Through Play in Situated Humanoid Robots

Abstract

Exercising sensorimotor and cognitive functions allows humans, including infants, to interact with the environment and objects within it. In particular, during everyday activities, infants continuously enrich their repertoire of actions, and by playing, they experimentally plan such actions in sequences to achieve desired goals. The latter, reflected as perceptual target states, are built on previously acquired experiences shaped by infants to predict their actions. Imitating this, in developmental robotics, we seek methods that allow autonomous embodied agents with no prior knowledge to acquire information about the environment. Like infants, robots that actively explore the surroundings and manipulate proximate objects are capable of learning. Their understanding of the environment develops through the discovery of actions and their association with the resulting perceptions in the world. We extend the development of Dev-PSchema, a schema-based, open-ended learning system, and examine the infant-like discovery process of new generalised skills while engaging with objects in free-play using an iCub robot. Our experiments demonstrate the capability of Dev-PSchema to utilise the newly discovered skills to solve user-defined goals beyond its past experiences. The robot can generate and evaluate sequences of interdependent high-level actions to form potential solutions and ultimately solve complex problems towards tool-use.

Alternative Object Use in Adults and Children: Embodied Cognitive Bases of Creativity

“…The critical role of action on objects for the development of creative cognition suggests that embodied and socially situated autonomous agents may significantly complement symbolic computer systems aiming to emulate creativity computationally (Pezzulo et al, 2013;Lubart et al, 2021). Of particular interest is the research in developmental and cognitive robotics, which underscores the role of embodied interactions and human scaffolding in the development of cognitive competencies in artificial agents (Fong et al, 2002;Lindblom and Ziemke, 2003;Lungarella et al, 2004;Dautenhahn, 2007;Cangelosi et al, 2015;Kumar et al, 2021). Recent works on modeling language grounding (Roy et al, 2004;Krunic et al, 2009;Shridhar et al, 2020), robotic creative (Antunes et al, 2016;Nyga et al, 2018;Nair and Chernova, 2020) and conventional tool use (Awaad et al, 2015;Chu et al, 2016;Neemeh, 2019), as well as the ability to transfer objects' functions (Agostini et al, 2015) could help to verify and test the models of the creative process and further unveil the role of visual perception, motor components and language in the genesis and development of creativity.…”

Cognitive System of a Virtual Robot Based on Perception, Memory, and Hypothesis Models for Calligraphy Writing Task

“…By combining cognitive psychology and robotics, [7][8] revealed a psychological structure with schema and chain for robots to learn simple tasks. These studies showed good effect on the application of higher-level cognitive strategies for robots.…”