In this article, we present a new scheme that approximates unknown sensorimotor models of
robots by using feedback signals only. The formulation of the uncalibrated sensor-based …

Due to their dependence on a task-specific reward function, reinforcement learning agents
are ineffective at responding to a dynamic goal or environment. This paper seeks to …

The objective of this study is to understand the learned-strategy of neural network-controlled
robots in relation to their physical learning environments by visualizing the internal layer of …

The ability to learn the sensorimotor maps of unknown environments without supervision is a
vital capability of any autonomous agent, be it biological or artificial. An accurate …

Cognitive robotics is a broad field that spans diverse areas of robotics such as human-robot
interaction (HRI), navigation, visual perception, object manipulation, physical human-robot …

How do we create machines with the ability to capture, record and recall memories of past
experience? How should these machines choose the most optimal action based on those …

Sequence similarity is a critical concept for comparing short-and long-term memory in order
to identify hidden states in partially observable Markov decision processes. While …

El robot Mecabot 5.0 corresponde a la quinta versión de robots modulares creados por el
grupo de investigación DAVINCI de la Universidad Militar Nueva Granada. Con las …