Embodied Cognitive Robotics and the learning of sensorimotor schemes

Abstract

Embodied Cognitive Robotics focuses its attention on the design of artificial agents capable of performing cognitive tasks autonomously. A central issue in this consists in studying process by which agents learn through interaction with their environment. Embodied Cognitive Robotics aims to implement models of cognitive processes coming from Cognitive Sciences. The guidelines in this research area are a direct response to the shortcomings of Classical Artificial Intelligence, where high-level tasks and behaviors were studied. This article describes the work carried out in the Cognitive Robotics Laboratory at the Universidad Autónoma del Estado de Morelos (UAEM). Our work is based on the concept of low-level sensorimotor schemes coded by Internal Models, thus falling as a matter of course within the tenets of Embodied Cognition, particularly with the idea that cognition must be understood as occurring in agents that have a body with which they interact in a specific environment. It is through this interaction that learning emerges laying the ground for cognitive processes. Our research includes theoretical work laying the foundations of Embodied Cognitive Robotics, as well as work with artificial and with natural agents.

Intrinsic motivation and episodic memories for robot exploration of high-dimensional sensory spaces

“…This process is inspired by the classical idea in neuroscience about efference copy and corollary discharge (Baltieri & Buckley, 2018;Kawato, 1999;Straka et al, 2018). We are aware of more recent theories that challenged the usage of efference copies and of inverse models (Feldman, 2016;Friston, 2011;Lara et al, 2018). Future works will include reframing the predictive models of this study, getting rid of inverse models and using proprioceptive predictions to generate motor commands, as in the active inference proposal (Friston, 2010).…”

Soft-assembled human–machine perceptual systems

“…With that said, if the framework on current offer is theoretically coherent and provides routes for empirical support, then there is no a priori reason to reject machine components from integrating in soft-assembled perceptual systems (cf. Lara et al, 2018; Zech et al, 2017). The caveat is that such nonbiological components must—as stated above—preserve features of ecological and embodied systems, for example, specification of environmental information (Figure 4).…”

Grounding 4E Cognition in Mexico: introduction to special issue on spotlight on 4E Cognition research in Mexico

“…Bruno Lara and colleagues (2018) offer a richly detailed review of their empirical work on Embodied Cognitive Robotics in their Laboratory at the Autonomous University of the State of Morelos (UAEM). They focus on the design of artificial agents that are capable of performing cognitive tasks autonomously and learning through interaction with their environment.…”