Constantine Stephanidis

Asterios Leonidis, Maria Korozi, Vassilis Kouroumalis et al.

This work aims to investigate how the amenities offered by Intelligent Environments can be used to shape new types of useful, exciting and fulfilling experiences while watching sports or movies. Towards this direction, two ambient media players were developed aspiring to offer live access to secondary information via the available displays of an Intelligent Living Room, and to appropriately exploit the technological equipment so as to support natural interaction. Expert-based evaluation experiments revealed some factors that can influence the overall experience significantly, without hindering the viewers' immersion to the main media.

Georgios Th. Papadopoulos, Asterios Leonidis, Margherita Antona et al.

Learning from Demonstration (LfD) has been established as the dominant paradigm for efficiently transferring skills from human teachers to robots. In this context, the Federated Learning (FL) conceptualization has very recently been introduced for developing large-scale human-robot collaborative environments, targeting to robustly address, among others, the critical challenges of multi-agent learning and long-term autonomy. In the current work, the latter scheme is further extended and enhanced, by designing and integrating a novel user profile formulation for providing a fine-grained representation of the exhibited human behavior, adopting a Deep Learning (DL)-based formalism. In particular, a hierarchically organized set of key information sources is considered, including: a) User attributes (e.g. demographic, anthropomorphic, educational, etc.), b) User state (e.g. fatigue detection, stress detection, emotion recognition, etc.) and c) Psychophysiological measurements (e.g. gaze, electrodermal activity, heart rate, etc.) related data. Then, a combination of Long Short-Term Memory (LSTM) and stacked autoencoders, with appropriately defined neural network architectures, is employed for the modelling step. The overall designed scheme enables both short- and long-term analysis/interpretation of the human behavior (as observed during the feedback capturing sessions), so as to adaptively adjust the importance of the collected feedback samples when aggregating information originating from the same and different human teachers, respectively.

Georgios Th. Papadopoulos, Margherita Antona, Constantine Stephanidis

Learning from Demonstration (LfD) constitutes one of the most robust methodologies for constructing efficient cognitive robotic systems. Despite the large body of research works already reported, current key technological challenges include those of multi-agent learning and long-term autonomy. Towards this direction, a novel cognitive architecture for multi-agent LfD robotic learning is introduced, targeting to enable the reliable deployment of open, scalable and expandable robotic systems in large-scale and complex environments. In particular, the designed architecture capitalizes on the recent advances in the Artificial Intelligence (AI) field, by establishing a Federated Learning (FL)-based framework for incarnating a multi-human multi-robot collaborative learning environment. The fundamental conceptualization relies on employing multiple AI-empowered cognitive processes (implementing various robotic tasks) that operate at the edge nodes of a network of robotic platforms, while global AI models (underpinning the aforementioned robotic tasks) are collectively created and shared among the network, by elegantly combining information from a large number of human-robot interaction instances. Regarding pivotal novelties, the designed cognitive architecture a) introduces a new FL-based formalism that extends the conventional LfD learning paradigm to support large-scale multi-agent operational settings, b) elaborates previous FL-based self-learning robotic schemes so as to incorporate the human in the learning loop and c) consolidates the fundamental principles of FL with additional sophisticated AI-enabled learning methodologies for modelling the multi-level inter-dependencies among the robotic tasks. The applicability of the proposed framework is explained using an example of a real-world industrial case study for agile production-based Critical Raw Materials (CRM) recovery.

Paul Zikas, George Papagiannakis, Nick Lydatakis et al.

Virtual reality (VR) has re-emerged as a low-cost, highly accessible consumer product, and training on simulators is rapidly becoming standard in many industrial sectors. However, the available systems are either focusing on gaming context, featuring limited capabilities or they support only content creation of virtual environments without any rapid prototyping and modification. In this project, we propose a code-free, visual scripting platform to replicate gamified training scenarios through rapid prototyping and VR software design patterns. We implemented and compared two authoring tools: a) visual scripting and b) VR editor for the rapid reconstruction of VR training scenarios. Our visual scripting module is capable to generate training applications utilizing a node-based scripting system whereas the VR editor gives user/developer the ability to customize and populate new VR training scenarios directly from the virtual environment. We also introduce action prototypes, a new software design pattern suitable to replicate behavioral tasks for VR experiences. In addition, we present the training scenegraph architecture as the main model to represent training scenarios on a modular, dynamic and highly adaptive acyclic graph based on a structured educational curriculum. Finally, a user-based evaluation of the proposed solution indicated that users - regardless of their programming expertise - can effectively use the tools to create and modify training scenarios in VR.