BrainMap

Alexandru Sorici

- UNIVERSITATEA NAȚIONALĂ DE ȘTIINȚĂ ȘI TEHNOLOGIE POLITEHNICA BUCUREȘTI

Researcher | Teaching staff

Web of Science ResearcherID: not public

Expertise & keywords

AI Folk - Resource Management for Distributed AI Call name: P 1 - SP 1.1 - Proiecte de cercetare pentru stimularea tinerelor echipe independente - TE-2021
PN-III-P1-1.1-TE-2021-1422 2022 - 2024

Role in this project:

Coordinating institution: UNIVERSITATEA NAŢIONALĂ DE ŞTIINŢĂ ŞI TEHNOLOGIE POLITEHNICA BUCUREŞTI

Project partners: UNIVERSITATEA NAŢIONALĂ DE ŞTIINŢĂ ŞI TEHNOLOGIE POLITEHNICA BUCUREŞTI (RO)

Affiliation:

Project website: https://aifolk.upb.ro/

Abstract:

Într-un ecosistem de inteligență artificială distribuit, participanții au nevoie să caute, să transfere, și să împărtășească resurse legate de învățarea automată: observații, seturi de date, modele de învățare și experiențe folosind modelele respective. Aceasta asigură o distribuire a calculului peste resursele de calcul existente și o gestionare a datelor care protejează dreptul la viață privată.

Obiectivul nostru de cercetare este dezvoltarea unui model de cunoștințe și a unui protocol de interacțiune care permit unui sistem format din actori umani, software sau organizaționali să caute resursele de învățare automată de care au nevoie, să folosească aceste resurse în mod adecvat bazat pe descrierea lor, să îmbunătățească resursele și să împărtășească resursele cu alți actori. Ne bazăm în acest proiect pe experiența existentă în domeniile învățării federative (federated learning) și inteligenței artificiale de periferie (in-edge AI) și ne axăm pe două scenarii concrete: o aplicație de conducere autonomă și un scenariu de răspuns la dezastre.

Proiectului va avea ca rezultat o ontologie pentru descrierea resurselor de învățare automată, o metodologie pentru crearea căutărilor pentru resurse, un modul care implementează protocolul de interacțiune prin care actorii pot căuta, transfera și actualiza resurse de învățare automată, implementarea a două aplicații prototip folosind această abordare, și o metodologie generală de aplicare a abordării propuse în alte domenii ale IA.

Context-Aware Search and Discovery in Hypermedia-Driven Multi-Agent Environments Call name: P 1 - SP 1.1 - Proiecte de cercetare Postdoctorală - PD-2021
PN-III-P1-1.1-PD-2021-0756 2022 - 2024

Role in this project:

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA NAŢIONALĂ DE ŞTIINŢĂ ŞI TEHNOLOGIE POLITEHNICA BUCUREŞTI (RO)

Affiliation:

Project website: https://sites.google.com/view/cashmere-project/home

Abstract:

In Hypermedia driven Multi-Agent Systems (HyperAgents) the web and its architecture act like a global environment in which different types of agents (whether human or software) perform interactions and compose the functionality of web-enabled things to achieve their goals.

The main objective of the project is the development of a web-based framework facilitating context-aware search and discovery of web-enabled things in hypermedia driven environments. The requirement is to facilitate the detection and understanding of shared context between a producer and a consumer to enable corresponding discovery of and access to relevant web resources to agents operating in the web environment. Specific objectives are: (i) development of a web-based platform that can expressively model relevant context information of web things and enable a semantic-query and complex-event processing based mechanism to define and detect situations of shared context between web things and agents; (ii) development of web-based APIs that take the detection of a shared context as input and are able to facilitate the creation of authorization elements that integrate into existing access control and search technologies for web things.

Bridging the Early Diagnosis and Treatment Gap of Brain Diseases via Smart, Connected, Proactive and Evidence-based Technological Interventions Call name: P 3 - SP 3.6 - Premierea participării în Orizont 2020
PN-III-P3-3.6-H2020-2020-0186 2021 - 2023

Role in this project:

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA NAŢIONALĂ DE ŞTIINŢĂ ŞI TEHNOLOGIE POLITEHNICA BUCUREŞTI (RO)

Affiliation:

Project website: https://aimas.cs.pub.ro/alameda/

Abstract:

Our vision in ALAMEDA is to research and prototype the next generation of personalized AI healthcare support systems, aiming at addressing the needs of people with brain diseases and disorders, specifically focusing on the needs of patients’ rehabilitation treatments. ALAMEDA innovations are anchored at the integration of lifestyle retrospective data as well as new streams of patient monitoring data, via new methods during every-day activities, including sleep behaviour, deploying advanced data analytics and AI recommendation services. We focus on three particular diseases stroke, Parkinson and multiple sclerosis.

People detection and tracking for social robots and autonomous cars Call name: P 2 - SP 2.1 - Proiect experimental - demonstrativ
PN-III-P2-2.1-PED-2019-4995 2020 - 2022

Role in this project:

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Affiliation: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Project website: https://aimas.cs.pub.ro/petra

Abstract:

Detecting, tracking, and recognizing people is a valuable capability for machines. However, these tasks are quite difficult to be achieved autonomously and, although significant results have been obtained, they are still a major technological challenge. People tracking, unlike other recognition and interpretation tasks, is difficult both from the point of view of the recognition and prediction of trajectory, and from the one of the identification of the ground truth.

The main objective of the PETRA project is the development of a software platform enabling the development of applications requiring people detection and tracking in real environments. The design and implementation of the platform and the set of supported algorithms for people detection and tracking will be such that they can be easily used and integrated in tasks performed by social robots in closed spaces, and also in tasks in open spaces, such as is the case for pedestrian detection and tracking. The scientific and technological challenge of the project is to start from our current developments on people detection and tracking in the contexts of user-robot interaction and autonomous driving, and develop and implement novel solutions based on deep learning approaches. Especially for people tracking, this is a significant challenge, less explored in the current state-of-the art, and aiming at improving results performances.

One of the main focuses of the project is to extensively test the implementations towards several difficult benchmarks, but also on our own data sets, and strive to achieve results better than current state-of-the-art.

The Robots and the Society: Cognitive Systems for Personal Robots and Autonomous Vehicles Call name: P 1 - SP 1.2 - Proiecte complexe realizate in consorții CDI
PN-III-P1-1.2-PCCDI-2017-0734 2018 - 2021

Role in this project:

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO); INSTITUTUL DE CERCETARI PENTRU INTELIGENTA ARTIFICIALA ,,MIHAI DRAGANESCU'' (RO); INSTITUTUL DE MATEMATICA "SIMION STOILOW" AL ACADEMIEI ROMANE (RO); UNIVERSITATEA TEHNICA DIN CLUJ - NAPOCA (RO); UNIVERSITATEA "DUNAREA DE JOS" (RO)

Affiliation: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Project website: http://aimas.cs.pub.ro/robin/

Abstract:

ROBIN is a user-centered project designing software systems and services for the use of robots in an interconnected digital society, and enables companies to develop complex, intelligent and ready-to-use products and services for these users, as well as for the society as a whole. The project covers a diverse range of robots: assistive robots for the support of people with special needs, social robots for interaction with store customers, and software robots that can be installed on intelligent vehicles to achieve autonomous car driving. The project combines advanced techniques and technologies of artificial intelligence, human-robot interaction, interactions with a pervasive intelligent environment, and Cloud processing.

ROBIN-Social develops integrated and easily configurable solutions for the personalization of assistive and social robots, with a cognitive and autonomous character.

ROBIN-Car develops computer vision methods, which resolves a large and sophisticated plethora of tasks for automated driving, and a prototype system which will be tested on an electrical vehicle.

ROBIN-Context creates a support platform for the semantic representation and efficient management of data that becomes context in scenarios of personalized robotic assistance and AADS.

ROBIN-Dialog develops a set of scenarios for micro-worlds and the technology for the Romanian language processing to achieve situational dialogs in these micro-worlds.

ROBIN-Cloud builds a support platform for collecting data coming from the sensors of robotic systems and IoT systems that offers Cloud Edge and Cloud Robotics computing.

The complex project, through the interaction of its developed components, brings significant contributions in fundamental research, applied research, innovation, and technological transfer, offers advanced scientific and technical services, and contributes to the enhancement of the institutional capacity of the 4 partners in the consortium.

The Robots and the Society: Cognitive Systems for Personal Robots and Autonomous Vehicles Call name:
PN-III/ Nr. ctr. 72PCCDI/01.03.2018 2018 - 2020

Role in this project: Key expert

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Affiliation: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Project website:

Abstract:

Artificially intelligent ecosystem for self-management and sustainable quality of life in AAL Call name: P 3 - SP 3.5 - Programul "Active and Assisted Living"
AAL-CAMI 2015 - 2018

Role in this project: Key expert

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO); CENTRUL IT PENTRU STIINTA SI TEHNOLOGIE S.R.L. (RO)

Affiliation: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Project website: http://www.camiproject.eu/

Abstract:

CAMI is offering a fully integrated AAL solution by providing services for health management, home management and wellbeing (including socialization, and reduced mobility support). CAMI builds an artificial intelligence ecosystem, which allows seamless integration of any number of ambient and wearable sensors with a mobile robotic platform endowed with multimodal interaction (touch, voice, person detection), including a telepresence robot with manipulatory capabilities.

The services offered by CAMI ecosystem address both healthy individuals as well as those with age-related impairments. CAMI solution will reconcile the increased demand for care in the current aging society with limited resources by supporting an efficient and sustainable care system.

Performant Services for Client Assistance Based on Robotic Platforms Call name: P 2 - SP 2.1 - Transfer de cunoaștere la agentul economic „Bridge Grant”
PN-III-P2-2.1-BG-2016-0425 2016 - 2018

Role in this project:

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO); CENTRUL IT PENTRU STIINTA SI TEHNOLOGIE S.R.L. (RO)

Affiliation: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Project website: http://aimas.cs.pub.ro/sparc

Abstract:

Robots have started to have a tremendous impact in economy and society through cost reduction of operations, increase of quality and conditions of work, assistance of people with special needs and, recently, client support and assistance in different domains.

The available technology at CITST on which this project is based, is the Tiago robot manufactured by Pal Robotics. Tiago is a mobile platform with manipulation, perception, manipulation and grasping abilities, and speech synthesis and understanding,. Tiago is an almost humanoid robot with a height of 146 cm and a weight of 75kg. CITST wants to exploit this robotic technology as a service offer for its potential clients. The envisaged scenarios are product promotion and/or clients’ assistance in public places such as malls, museums, exhibitions, etc. If a certain company wants to promote a product or offer robotic assistance to its clients, CITST will personalize and adapt the actions of the robot to achieve the desired tasks or scenarios, and will lease the robot to this company. In this context, the main goal of this project is the design and implementation of a robotic platform to achieve integrated planning of Tiago tasks, command of the execution of defined tasks and monitoring of robots actions. Based on this platform, the robot activity must be easily configurable according to given scenarios and must allow multi-modal interactions with the client.

The successful achievement of the project objectives will have a significant impact for the CITST company. The immediate technical impact of the project is to offer the company an easy way to define and configure the robot for client support in different contexts. The possible future impact is to increase the number and nature of CITST robotic services with services that are autonomous, flexible and reliable, including services for persons with special needs.

A Context Management Middleware Servicing Ambient Intelligence Applications Call name: P 2 - SP 2.1 - Proiect experimental - demonstrativ
PN-III-P2-2.1-PED-2016-1753 2017 - 2018

Role in this project:

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Affiliation: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Project website: http://aimas.cs.pub.ro/consert

Abstract:

Ambient Intelligence (AmI) has nowadays matured enough to become the focus of industry-level projects and European support directives.

A foundational subdomain of AmI is that of context management and context-aware computing (provide applications and users with the right information, at the right time, and in the right way).

Context Management covers many research aspects from knowledge representation and reasoning issues to information management concerns. A clear separation of concerns between the main application functionality and contextual adaptation is needed.

Thus, the objective of this project is the creation of an open source context management middleware solution presenting rich features that alleviate context-aware application development.

Work is based on an existing platform called CONSERT, recently developed in the AIMAS research group of UPB. The current project improves upon CONSERT with: (1) performance improvement and modularisation of the reasoning engine to support applications of variable complexity requirements, (2) development of an integrated development environment (IDE) for context modeling and deployment to facilitate context-aware application programming based on the CONSERT Middleware, (3) advanced options for OSGi and Docker based deployments of CONSERT processing units to address dynamic change of context within an application (e.g. change of location, change of activity), and (4) development of two test applications: Smart Meeting Support for activity monitoring of students and teachers on a campus, and Smart Home User Support for adequate dynamic configuration of services offered in an ambient intelligence environment to assist users at home.

An open web-platform (CONSERT Store) will be setup where software components and configurations of CONSERT processing units can be shared by developers.

FILE DESCRIPTION	DOCUMENT
List of research grants as project coordinator or partner team leader
Significant R&D projects for enterprises, as project manager
R&D activities in enterprises
Peer-review activity for international programs/projects