Periodic Reporting for period 1 - CybSPEED (Cyber-Physical Systems for PEdagogical Rehabilitation in Special EDucation)
Reporting period: 2017-12-01 to 2019-11-30
"The aim of the current MSCA RISE proposal CybSPEED is to advance a novel framework for analysis, modelling, synthesis and implementation of Cyber-Physical Systems for pedagogical rehabilitation in special education, based on a combination of the best of experience and achievements of the partners in the domains of brain-aware robotics, cognitive biometrics, computational intelligence and reasoning in humanoid and non-humanoid robots for education. CybSPEED Action builds on the results and insights of the recently completed project funded by EEA Grant of Bulgaria and Norway ""METEMSS: Methodologies and technologies for enhancing the motor and social skills of children with developmental problems"" (IR- BAS), on a logical projection of the EU funded project ""Social & Smart"", called “Storytelling NAO” of Spain (UPV/EHU) , on the ongoing research of the project “Special Education Robot Teaching Assistant (EduBot)” of Greece (EMaTTech) funded by the Stavros Niarchos Foudation and on the recent project Wikitherapist of The Netherlands (TiViPe.) CybSPEED Action emphasizes the intrinsic-motivational approach to learning by designing human-robot situations (games, pedagogical cases, artistic performances) and advanced interfaces (brain-computer, eye-gaze tracking and virtual reality) where children and students interact with the novel technology to enhance the underlying self-compensation and complementarity of brain encoding during learning. The CybSPEED project has established an innovation network across EU, Japan and CHile, pursuing research at three levels: 1) analysis of cognitive biometric signals, 2) modelling the learner robot interaction and 3) development of novel instruments toward an optimal design of Cyber-physical systems for improved pedagogical rehabilitation in education."
Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far
First and foremost, the consortium has achieved almost 100% of the planned research months with small deviations of the work plan, and has finished 54% of the proposed tasks. We have submitted all the planned deliverables for the first period with little average delay. Big delays were communicated in advance to the Project Officer, if were foreseeable due to the conditions of the consortium work. Explanation of delays have been provided in all deliverables suffering any delay. Aside from some inconveniences explained elsewhere, the management of the project has been smooth and without major incidents. The beneficiaries and partners have been extremely active and proactive, which is the key of the success of the project up to this point.Secondly the training, courses and conferences proposed in the project have been realized with minor o no delay. Only one training that appears in the GA can not be realized for reasons explained in section 5 of this report. One of the keys to the success of these activities has been the willing participation of the researchers from all the beneficiaries and partners, that have adjusted their agendas in order to attend.Thirdly the scientific work advances smoothly as well along with the dissemination works. We have achieved a large number of open access publications, listed elsewhere in this document (section 1.2.4) including open source software and open data, and conference presentations, some of them invited as keynote speakers. Moreover, experimental work is planed for the second period that will be providing new evidences and material for further publications and advances.Fourthly we have also been active trying to reach out to the general public. We have achieved some moderate media impact that we expect to increase in the second period, when the new experiments and results will be available. Reach out activities targeting specific audiences, such as parents, professional educators and researchers have had a moderate impact in the press and the general media.
Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)
The main expected results from IHU from the remaining time of the project are:- A theoretical framework for CPSs for pedagogical rehabilitation in special education;- CPS model for pedagogical rehabilitation in special education based on Lattice Computing (LC) and other computational modelling approaches;- Developed innovative LC models to fit cognitive biometrics signals recorded by advanced interfaces (brain-computer, eye-gaze tracking and virtual reality);- A novel method for transformation of (numerical) signals such as images to (nonnumerical) symbols toward an effective data compression for communication of robots with one another (as well as with humans) being endowed by novel synthetic sensors;-A model for representation of (nonnumerical) notions from psychology in computational models, including the notion “Gestalt”, with noticeable pedagogical effect;Designs of optimal educational scenarios toward maximising the educational outcome estimated by cognitive biometrics data such as eye tracking and EEG data. Future work by IR-BAS in the remaining period of CybSPEED will focus on the following:The societal implications will be in better understanding of the learning needs of children and provision of advanced technological support; better understanding of the professional needs of teachers and provision of advanced tools for individualised work with children; more entertaining learning environment for children, expert system support to the teaching process, reduced number of tests in class and the respective stress level on children in standard and special education.Models for CPS will be developed with emphasis on logic/reasoning techniques building on novel computational (e.g. Fuzzy Lattice Reasoning) methodology. The data, obtained from recording brain and muscle activity and eye tracking during social interaction, will be modelled with further application to the representation of knowledge gained by learning from robots. A platform for sensation restoring via virtual reality will be integrated as a novel type of human-robot interface in the overall system, based on extension of research on muscle computer interaction (muCI) and learning with limited sensor abilities. Research on life-long learning implementing deep learning techniques will be carried out with application to user preference modelling required by personalised human-robot interaction. The approach for validating educational situations (games) for children with special learning needs, describing the transition from one experiment in real-life conditions to another, not just from pilot to real-life testing, forwarded recently by IR-BAS, will be further developed.Work by CVC, UPV/EHU, UH2C, and UCH will be devoted to intelligent system design and data analysis to support the experimental results that will be provided by PRAXIS, UGA and IR-BAS researchers. Specifically we will be aiming to the modeling of the behavioral and neural responses of children with special needs and the effect of CPS on their learning performance.