2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)

The oblique effect, observed in both humans and animals, refers to the phenomenon of differential perceptual performance in visual recognition tasks that involve horizontal and vertical, vs. diagonal patterns. Furthermore, differences have been found in the visual cortical organization for the horizontal and vertical vs. diagonal representations. However, why such structural differences leading to... View full abstract»

We present a model for the autonomous learning of active binocular vision using a recently developed biomechanical model of the human oculomotor system. The model is formulated in the Active Efficient Coding (AEC) framework, a recent generalization of classic efficient coding theories to active perception. The model simultaneously learns how to efficiently encode binocular images and how to genera... View full abstract»

We present a self-calibrating binocular vision system that autonomously learns how to encode the visual input and how to move its eyes. The model combines the learning of disparity representations and vergence eye movements through Active Efficient Coding (AEC) and the learning of saccades to interesting targets through two novel attention models. The first model is an extension of the Attention b... View full abstract»

The brain integrates information from multiple sensory modalities to form a coherent and robust perceptual experience in complex environments. This ability is progressively acquired and fine-tuned during developmental stages in a multisensory environment. A rich set of neural mechanisms supports the integration and segregation of multimodal stimuli, providing the means to efficiently solve conflic... View full abstract»

Guiding the action selection mechanism of an autonomous agent for learning control behaviors is a crucial issue in reinforcement learning. While classical approaches to reinforcement learning seem to be deeply dependent on external feedback, intrinsically motivated approaches are more natural and follow the principles of infant sensorimotor development. In this work, we investigate the role of inc... View full abstract»

A class of specialized neurons, called lobula plate tangential cells (LPTCs) has been shown to respond strongly to wide-field motion. The classic model, elementary motion detector (EMD) and its improved model, two-quadrant detector (TQD) have been proposed to simulate LPTCs. Although EMD and TQD can percept background motion, their outputs are so cluttered that it is difficult to discriminate actu... View full abstract»

Action recognition is a multi-faceted challenge that requires solving three principal challenges in its design: Synchronization, Segmentation and Uncertainty, all of which have specific implications to classification performance and possible solutions to mitigate these implications. We subsequently use observations carried out during the training of an action recognition system to generalize to th... View full abstract»

In this paper, we introduce a technique to learn sensory-motor sequences in multiple consecutive stages, where one stage bootstraps sequences serving as training data for the subsequent stage. By introducing multiple interaction stages and recording the generated sensory-motor sequences of a preceding interaction stage, we obtain a system capable of self-generation of training data to increase the... View full abstract»

In this work, we present an approach to imitation learning and flexible execution of dual-arm structured tasks. The proposed framework exploits imitation learning and attentional supervision to learn both a set of motion primitives and the associated tasks structure. During the teaching phase, attentional supervision allows the teacher to exploit attention manipulation, like object and verbal cuei... View full abstract»

In this paper we discuss the enactive self from a computational point of view and study the suitability of current methods to instantiate it onto robots. As an assumption, we consider any cognitive agent as an autonomous system that constructs its identity by continuous interaction with the environment. We start examining algorithms to learn the body-schema and to enable tool-extension, and we fin... View full abstract»

In this paper, we propose the concept of sensorimotor tappings, a new graphical technique that explicitly represents relations between the time steps of an agent's sensorimotor loop and a single training step of an adaptive internal model. In the simplest case this is a relation linking two time steps. In realistic cases these relations can extend over several time steps and over different sensory... View full abstract»

How is perception of depth and shape built from sensorimotor interactions with the environment? We address this question by proposing a computational model validated on an iCub robot. First we face the problem of how we can obtain haptic and visual samples from different surfaces using the iCub robot. Then we perform a surface classification experiment to assess which are the more informative feat... View full abstract»

In this paper, we investigate the possibility of human physical activity recognition in a robot game scenario. Being able to recognize types of activity is essential to enable robot behavior adaptation to support player engagement. Also, the introduction of this recognition system will allow for development of better models for prediction, planning and problem solving in PIRGs that can foster huma... View full abstract»

In this paper, we propose a novel framework for detecting and identifying cylindrical shapes, commonly found in daily contexts, using multi-modal visual information provided by RBG-D cameras. The current state-of-the-art methods for cylinder detection are based on RANSAC and Hough transforms which estimate cylinder parameters using 3D point cloud information. However, the presence of distracting n... View full abstract»

We have been observing how infants between 3 and 21 months react when a vibrotactile stimulation (a buzzer) is applied to different parts of their bodies. Responses included in particular movement of the stimulated body part and successful reaching for and removal of the buzzer. Overall, there is a pronounced developmental progression from general to specific movement patterns, especially in the f... View full abstract»