A5081116913- Robotics and Automated Systems
- EEG and Brain-Computer Interfaces
- Social Robot Interaction and HRI
- Hand Gesture Recognition Systems
- Assistive Technology in Communication and Mobility
- Opportunistic and Delay-Tolerant Networks
- Gaze Tracking and Assistive Technology
- Mobile Ad Hoc Networks
- Fuzzy Logic and Control Systems
- Modular Robots and Swarm Intelligence
- Robot Manipulation and Learning
- Advanced Memory and Neural Computing
- Neural Networks and Applications
- Autism Spectrum Disorder Research
- Caching and Content Delivery
- Robotic Path Planning Algorithms
- IoT and Edge/Fog Computing
- Augmented Reality Applications
- Human Mobility and Location-Based Analysis
- AI in Service Interactions
- Human Pose and Action Recognition
- Manufacturing Process and Optimization
- Time Series Analysis and Forecasting
- Child and Animal Learning Development
- Teleoperation and Haptic Systems
Bulgarian Academy of Sciences
2013-2024
Institute of Robotics
2018-2023
Université Grenoble Alpes
2022
Technical University of Sofia
1993-2022
Kyushu Institute of Technology
2018
University of Portsmouth
2015
University of Wuppertal
2002
Conversational AI combines natural language processing (NLP) with machine and deep learning models so that people can interact in human-like manner the digital devices. The quality of social interactions be additionally improved by utilizing physical presence robot prompting context derived from robot's hardware. Therefore, we propose a modular software architecture to integrate into Socially Assistive Robots (SARs). It follows flow-based approach shared repositories direct or message-based...
Human-like interactions with robots based on Conversational AI facilitate assistance and teamwork in various contexts. Those are further enhanced by utilizing physical presence context from the robot's hardware. Robot cooperation is also especially useful, when software or hardware resources have to be shared a multi-robot system. Therefore, we propose modular architecture for that extends integration of into Socially Assistive Robots, previously suggested authors. It utilizes flow-based...
This research aims to improve the pedagogical rehabilitation of children with Special Educational Needs (SEN) based on play-like activities for orientation in space, shapes, colors and emotions. The designed EEG-based portable Brain-Computer Interface (BCI) measures features real time brain signals order analyze attentional or emotional states a child. output performance scores are used either as an input control play scenarios facilitate assessment cognitive child by special educators....
Our interest is in time series classification regarding cyber–physical systems (CPSs) with emphasis human-robot interaction. We propose an extension of the k nearest neighbor (kNN) classifier to time-series using intervals’ numbers (INs). More specifically, we partition a into windows equal length and from each window data induce distribution which represented by IN. This preserves dimension representation. All-order statistics, IN, are employed implicitly as features; moreover, parametric...
Humanoid robots have a substantial potential to serve as teaching and social assistants. However, the expectations of children from interact like humans are huge. This study presents general model for understanding natural language in human-robot interaction by applying Generative Pre-trained Transformer (GPT) models service Internet Things. Thus, physical presence robot can help fine-tuning GPT prompts derived environmental context subsequent actions embodiment outputs. The uses web or...
P300 is one of the most widely studied event-related potentials. Unfortunately, existing automatic detection schemes require computations over repetitive trials in both training and recognition phases. Several attempts have recently been endeavored towards single trial signals. However, no acceptable solution to problem found till date. In present work, we attempted address this light latency (amplitude) deflection signal. The intra- inter-personal variations inherent these features are...
The paper presents a "design and simulation of gesture"-based model to support education children with hearing problems. To engage the child's attention control their own learning according individual skills, framework is proposed for interaction an artificial hand in form game rewards correct answers. anthropomorphic hand, designed purpose 3D, both realistic able produce all fingerspelling signs international sign language. novelty present work integration biologically feasible movements...
Social robots keep proliferating. A critical challenge remains their sensible interaction with humans, especially in real world applications. Hence, computing semantics is instrumental. Recently, the Lattice Computing (LC) paradigm has been proposed a capacity to compute represented by partial order mathematical lattice data domain. In aforementioned context, this work proposes parametric LC classifier, namely Granule-based-Classifier (GbC), applicable (T,⊑) of tree structures, each which...
In this study we propose a designed, developed and validated by experiments Speech Language Therapy (SLT) system to provide SLT intervention for children with communication disorders. order help the services in different educational social context, has potential work Internet of Things (IoT). It can wire assistive devices, APIs, online agents meet child individual needs intervention. Humanoid NAO-type robot, Emotiv EPOC+ brain headset, emotionally-expressive robot EmoSan Kinect depth sensor...
Robots of the future will socialize with humans. Human-robot interaction (HRI) by a vision-based gesture interface helps to personalize communication humans in various contexts - from support their daily life social skills training children developmental problems. We are especially interested hand HRI and propose recognition system based on novel online extraction classification scheme, which is lightweight can be used mobile robot. An Lightweight Evolving Fuzzy Clustering Method categorize...
Abstract The paper presents enhancements and innovative solutions of the proposed in [3] algorithms for fingers tracking hand gesture recognition based on new defined features describing gestures exploiting new-tracked tip thumb joints from Kinect v2 sensor. Dynamic Time Warping (DTW) algorithm is used recognition. We increased its accuracy, scale rotational invariance by defining 3D featuring angles training a database. positions fingertips are extracted depth sensor data calculation...
A method for extraction of fuzzy rules from numerical input-output data is proposed. The main idea consists in separation the input space into activation rectangles, corresponding to different output intervals. generation and membership functions based on these whereas an appropriate inference mechanism formalises synthesis system could be used function approximation, classification control purposes. An illustrative example implementation traffic given.
Ambient Intelligence (AmI) joins together the fields of ubiquitous computing and communications, context awareness, intelligent user interfaces. Energy, fault-tolerance, mobility are newly added dimensions AmI. Within AmI concept mobile ad hoc networks (MANETs) for “anytime anywhere” is likely to play larger roles in future which people surrounded supported by small context-aware, cooperative, nonobtrusive devices that will aid our everyday life. The connection between knowledge generation...
For the sake of enhancement non-verbal communication between humans, head motion counterpart is highly important to guess acceptance level and affinity. The paper presents a new emotion-expressive robot focusing on emotional reactions represented in motion, which movements are realized by parallel kind based Gough-Stewart platform. Several workspaces this have been analyzed order establish capability reproduce human head. Our goal an affective interaction robot, including coupling through...
The paper presents a linear control system framework for design of technology-based games pedagogical rehabilitation children with special learning needs as central component the proposed cyber-physical inclusive education. novelty is in explicitly addressing issue quantitatively estimating improvement desired direction during process. An advantage approach its applicability to small groups playing diverse sets without loss generalisability system's model assumptions. Statistically justified...
The recently developed Kinect sensor has opened a new horizon to Human-Computer Interface (HCI) and its native connection with Microsoft's product line of Xbox 360 One video game consoles makes completely hands-free control in next generation gaming. Games that requires lot degree freedoms, especially the driving car racing games is best suitable be driven by gestures, as use simple buttons does not scale increased number assistive, comfort, infotainment functions. In this paper, we propose...
In the ad-hoc info ware project, we develop a delay tolerant event notification service for sparse mobile networks emergency and rescue operations. most solutions, subscriptions are formed with crisp values or value ranges. Filtering mechanisms do not take into account more expressive in terms of approximate predicates complex aggregating relations among them. However, scenarios subscribers' interests often have gradual nature subjective measure. Therefore, design an intelligent system...
BACKGROUND: Rapid technological development has been opening new possibilities for children with disabilities. In particular, robots can enable and create opportunities in therapy, rehabilitation, education, or leisure. OBJECTIVE: The aim of this article is to share experiences, challenges learned lessons by the authors, all them experience conducting research field robotics disabilities, propose future directions development. METHODS: result several consensus meetings establish priorities...
Abstract The paper presents an initial step towards employing the advantages of educational theatre and implementing them into social robotics in order to enhance emotional skills a child at same time augment robots with actors’ talent. Emotional child-robot interaction helps catch quickly child’s attention information perception during learning verbalization children communication disorders. An innovative approach for through art by transferring talents socially assistive is presented...
The subscription language is an important design decision for distributed event notification services (DENS). In order to minimize resource consumption and enable applications use rich complex languages only when they are really needed, we have developed a DENS that separates the concerns of delivering subscriptions notifications from specification filtering, i.e., language. To resolve conflict between independence in strict decoupling publishers subscribers through DENS, request each new...