Michael Pieroni

Towards a synthetic tutor assistant: The EASEL project and its architecture

Robots are gradually but steadily being introduced in our daily lives. A paramount application is that of education, where robots can assume the role of a tutor, a peer or simply a tool to help learners in a specific knowledge domain. Such endeavor posits specific challenges: affective social behavior, proper modelling of the learner’s progress, discrimination of the learner’s utterances, expressions and mental states, which, in turn, require an integrated architecture combining perception, cognition and action. In this paper we present an attempt to improve the current state of robots in the educational domain by introducing the EASEL EU project. Specifically, we introduce the EASEL’s unified robot architecture, an innovative Synthetic Tutor Assistant (STA) whose goal is to interactively guide learners in a science-based learning paradigm, allowing us to achieve such rich multimodal interactions.

Preliminary implementation of context-aware attention system for humanoid robots

A context-aware attention system is fundamental for regulating the robot behaviour in a social interaction since it enables social robots to actively select the right environmental stimuli at the right time during a multiparty social interaction. This contribution presents a modular context-aware attention system which drives the robot gaze. It is composed by two modules: the scene analyzer module manages incoming data flow and provides a human-like understanding of the information coming from the surrounding environment; the attention module allows the robot to select the most important target in the perceived scene on the base of a computational model. After describing the motivation, we report the proposed system and the preliminary test.

The EASEL Project: Towards Educational Human-Robot Symbiotic Interaction

This paper presents the EU EASEL project, which explores the potential impact and relevance of a robot in educational settings. We present the project objectives and the theorectical background on which the project builds, briefly introduce the EASEL technological developments, and end with a summary of what we have learned from the evaluation studies carried out in the project so far.

Design and Evaluation of a Unique Social Perception System for Human–Robot Interaction

Robot’s perception is essential for performing high-level tasks such as understanding, learning, and in general, human–robot interaction (HRI). For this reason, different perception systems have been proposed for different robotic platforms in order to detect high-level features such as facial expressions and body gestures. However, due to the variety of robotics software architectures and hardware platforms, these highly customized solutions are hardly interchangeable and adaptable to different HRI contexts. In addition, most of the developed systems have one issue in common: they detect features without awareness of the real-world contexts (e.g., detection of environmental sound assuming that it belongs to a person who is speaking, or treating a face printed on a sheet of paper as belonging to a real subject). This paper presents a novel social perception system (SPS) that has been designed to address the previous issues. SPS is an out-of-the-box system that can be integrated into different robotic platforms irrespective of hardware and software specifications. SPS detects, tracks, and delivers in real-time to robots, a wide range of human- and environment- relevant features with the awareness of their real-world contexts. We tested SPS in a typical scenario of HRI for the following purposes: to demonstrate the system capability in detecting several high-level perceptual features as well as to test the system capability to be integrated into different robotics platforms. Results show the promising capability of the system in perceiving real world in different social robotics platforms, as tested in two humanoid robots, i.e., FACE and ZENO.

Damasio's Somatic Marker for Social Robotics: Preliminary Implementation and Test

How experienced emotional states, induced by the events that emerge in our context, influence our behaviour? Are they an obstacle or a helpful assistant for our reasoning process? Antonio Damasio gave exhaustive answers to these questions through his studies on patients with brain injuries. He demonstrated how the emotions guide decision-making and he has identified a region of the brain which has a fundamental role in this process. Antoine Bechara devised a test to validate the proper functioning of that cortical region of the brain. Inspired from Damasios theories we developed a mechanism in an artificial agent that enables it to represent emotional states and to exploit them for biasing its decisions. We also implement the card gambling task that Bechara used on his patients as a validating test. Finally we put our artificial agent through this test for 100 trials. The results of this experiment are analysed and discussed highlighting the demonstrated efficiency of the implemented somatic marker mechanism and the potential impact of this system in the field of social robotics.

Grand challenges in bionics

“Bionics” as an inter-science discipline offi-cially dates back to 1958 when Major J. E. Steele coined the term making reference to a research program at the Wright-Patterson Air Force Base in Dayton, OH, USA. Steele (1960) used the term bionics to mean “a like-life system that copies some functions and characteristics of a natural system.”A similar term,

Electrically tunable soft solid lens inspired by reptile and bird accommodation

Electrically tunable lenses are conceived as deformable adaptive optical components able to change focus without motor-controlled translations of stiff lenses. In order to achieve large tuning ranges, large deformations are needed. This requires new technologies for the actuation of highly stretchable lenses. This paper presents a configuration to obtain compact tunable lenses entirely made of soft solid matter (elastomers). This was achieved by combining the advantages of dielectric elastomer actuation (DEA) with a design inspired by the accommodation of reptiles and birds. An annular DEA was used to radially deform a central solid-body lens. Using an acrylic elastomer membrane, a silicone lens and a simple fabrication method, we assembled a tunable lens capable of focal length variations up to 55%, driven by an actuator four times larger than the lens. As compared to DEA-based liquid lenses, the novel architecture halves the required driving voltages, simplifies the fabrication process and allows for a higher versatility in design. These new lenses might find application in systems requiring large variations of focus with low power consumption, silent operation, low weight, shock tolerance, minimized axial encumbrance and minimized changes of performance against vibrations and variations in temperature.

P2SF: Physically-based Point Spread Function for digital image processing

P2SF is a tool aimed at estimating the spatially variant point spread function based on the ray-tracing computation of the pupil function. Only 6 parameters are required to describe a monochromatic PSF.