CARMEN (Abstract)

Nowadays, due to progressive ageing in developed society and improvements in health care , there is an increasing number of persons with physical and or cognitive disabilities that, in the worst case, become dependent. Unfortunately, human and economic resources to support this population sector are quite limited; hence, these people lose quality of life and, ultimately, need to be institutionalized. In order to avoid related personal, social and economic problems, there has been a major effort in FP6 and FP7 to use Information and Communication Technology (ICT) to assist people with special needs. Specifically, it has been reported that loss of mobility is tightly coupled with loss of quality of life and dependency. Indeed, most assistive devices at home are basically focused on mobility assistance.

Conventional wheelchairs are the most common tool to assist people with reduced mobility. However, an important group of these people is not able to use them. Furthermore, specific conditions, e.g. post-stroke apraxia, make it impossible for some users to even cope with power wheelchairs, that require only minimal physical effort. In these cases, it has been suggested to robotize power wheelchairs, so they can help persons to remain autonomous. In our case, we have robotized a Meyra Runner wheelchair adding encoders, an external joystick, a Hokuyo laser and an industrial PC (see here technical details).

2. SHARED CONTROL

A robotic wheelchair is basically an autonomous robot that yields a proper interface to be guided by a user. In fact, it could reach any target fed by the user on its own, like any autonomous mobile robot. However, it is necessary to keep users as active as possible to avoid loss of residual skills, as reported by rehabilitation professionals, and also to increase his/her self confidence and sense of control over his/her actions. Thus, most robotic wheelchairs rely on the so called shared control paradigm, where user and robot make decisions together. Most shared control systems are based on swapping control from user to robot and viceversa either when a triggering condition is detected (e.g. door crossing, narrow corridor...) or when the user chooses to do so. The main drawback of these systems is that the user never copes with situations he/she finds complex, so he/she could end up losing any residual skill related to those situations. Besides, control switching provokes discontinuities that may cause problems for navigation algorithms. This work focuses on a new shared control approach to solve the commented problems.

3. CONTRIBUTIONS

CONTRIBUTION I: COLLABORATIVE CONTROL

This dissertation proposes a shared control mechanism that we call collaborative control. Collaborative control is a reactive scheme that can be used as low level layer in any hybrid architecture. It is based on continuously combining human and robot command vectors -returned by any navigation algorithm, in our case a Potential Field Approach (PFA)- into a single emergent one. In this combination, vectors are weighted by their respective local efficiency. Local efficiency is necessarily calculated in terms of punctual factors that can be obtained at any location in a memoryless fashion. These factors roughly correspond to the properties of a navigation function: smoothness, safety and directness.

a) vectors involved in collaborative control (VR, VH and VC for robot, human and collaborative); and b) angles involved in estimating smoothness (R), safety (G) and directness (B): local efficiency at a given location can be visually evaluated from its RGB color.

From a practical point of view, a command efficiency depends on how much the mobile would steer, how close we would gert to obstacles and how closer would be our target. This target may be provided by a deliberative layer or extrapolated from user's commands since the last curvature inflection point. In brief, the better the user drives, the larger his/her impact on the emerging trajectory. The rest is up to the robot. This system was succesfully tested with a group of 18 inpatients with different degrees of physical and cognitive disability at Fondazione Santa Lucia (FSL) under medical supervision (see metrics used to characterize our target population). Users as a whole kept an average efficiency over 80% during the whole tests, that included door crossing and corridor navigation.

a) CARMEN wheelchair; b) Casa Agevole (test environment)

Some results in these experiments, though, were quite surprising: users with better physical and cognitive skills usually performed worse than the rest. After exhaustive analysis of recorded data, it was concluded that these users actually acknowledged that the wheelchair was not doing exactly what they were commanding and fought against the system, even when their commands were clearly dangerous, like trying to collide into a wall just to prove their theory. Efficiency for these volunteers decreased in time and, in the end, they often reported that "the wheelchair was not working properly". In order to quantify this effect, a new metric was proposed: Disagreement is equal to the angle between the user's command and the emergent command. Disagreement usually has a minimum that depends on the usability of the vehicle itself -in our case it was around15-20%-, since it can not accommodate to user's commands immediately. However, in our case it was as high as 50% for some users. In order to reduce it, we decided to develop a navigation algorithm for the robot able to mimic the user's way of driving.

Results for volunteer 17 (severe dementia, very low physical residual skills) in collaborative mode. Efficiency in RGB is provided for human, PFA and collaborative control (left) as well as the joystick shadow in all three cases (right)

CONTRIBUTION II: USER ADAPTATION

Prediction of how a given user may drive is far from simple, much less in a population with physical and cognitive disabilities that may have a major impact in different aspects of his/her control. Hence, rather than searching for a generic user model for each specific disability, we decided to develop a learning system to personalize the robot navigation model to each user.'s particularities . The proposed learning algorithm was based on Case Based Reasoning (CBR). CBR is based on associating each distinct input pattern with a proper response, which in our case we take from the user's command to solve the situation. The case also includes the solution efficiency, calculated as commented earlier. Given any situation, CBR always returns the closest case available in the casebase, even if it differs significantly from the situation at hand. In these situations, it is necessary to mutate the output case through an adaptation function that, in our case, is derived from PFA. Specifically, our input instance includes the mobile relative position with respect to target and nearby obstacles, plus the wheelchair direction, because it is non-holonomic. Distance in our CBR implementation is based on Mahalanobis: instead of isolated case components, we compare the vector envelope so that the layout of surrounding obstacles has more weight in the results that exact distances to one particular object. The case output is either provided by the user or -if his/her efficiency is too low- by the emergent command returned by an underlying PFA-based collaborative control system. Finally, adaptation i-f necessary- relies on combining the case output with the PFA repulsor, to grant adequate obstacle avoidance at worst. Emergent motion is globally a sequence of cases that mimics the user's way of driving whenever residual skills allow it. After a while, the system converges and CBR based collaborative control becomes a combination of user's commands -reflecting his will-, CBR -reflecting his usual response to current situation- and, at worst, PFA -reflecting what the robot would do if the user can't cope with the situation at hand-. In order to avoid discontinuities when the system switches from PFA to CBR, we also allowed some temporal inertia to the system through a shifting window. This window relies on Gaussian functions applied at transitions. Emergent navigation is adapted to the user as much as possible and, indeed, a new experiment with 9 volunteers at Casa Agevole (FSL) proved that inpatients with the best physical and cognitive skills did not yield a larger Disagreement this time. Furthermore, in inpatients with very poor residual skills, the casebase eventually converged to PFA. It needs to be noted that the casebase resulting from sampling a given user's way of driving in autonomous mode is fit to create am inpatient simulator quite close to reality. This simulator was implemented to check the performance of the system in hazardous situations and untested environments

Results for inpatient 26 with CBR based collaborative control. Disagreement ( :) :| :( ) and human/robot control percentage are depicted on the bottom right)

CONTRIBUTION III: WAVE ENVELOPE MODULATION

The main drawback of CBR based collaborative navigation was that some users requiried more assistance on a general basis and not just to cope with punctual situations. These people sometimes failed to complete the proposed trajectories, either because they could not physically provide a given command or because they cognitively forgot were to go. In these cases, the system was prone to fall into local traps, i.e. places where further maneuver was impossible. In order to solve this problem, we decided to modulate the control function with a wave envelope. The envelope K(i) for the user command depends on the average efficiency of the user since its last inflection point,. The robot command is modulated by 1-K(i). This method provides some inertia to punctual changes and, besides, it increases as a whole the amount of assistance provided in areas where the user's efficiency is consistently low. Similarly, if the user is performing well in average, the amount of assistance provided is decreased as a whole and not so dependent on punctual situations. In brief, assistance is consistently provided when needed.

Results with joystick tied forwards and collaborative control a) unmodulated; b) modulated

New tests with 12 inpatients, once more in Casa Agevole, proved that this final implementation was the best in terms of average efficiency and Disagreement for all users, despite their cognitive and physical skills. Other parameters like total path length, time to complete it or curvature were also better in this case. Besides, the amount of help offered by the system in this case was globally lower than before, i.e. users contributed to control more than ever. In order to check the effect of modulated assistance from the user's point of view, some healthy volunteers performed new tests consisting of completing a complex trajectory blindfolded. All volunteers succeeded and commented later that the joystick was harder to push when they tried to go in a wrong direction. However, the joystick was not haptic. In fact, what the user perceives is that the wheelchair speed decreases when Disagreement grows. This effect is known as pseudo-haptic feedback and it helped them to correct their commands to go in the direction that rewarded a higher speed. We believe that this effect also helped people with severe cognitive disabilities to "remember" where they had to go, i.e. they simply went with the flow and eventually remembered where they were supposed to arrive.

Results for blindfolded user in modulated CBR-based collaborative mode

All in all, in 3 years we ran tests with more than 70 volunteering in-patients at FSL presenting different degrees of physical/cognitive disabilities and we gathered all data related to unassisted driving -with a safeguard stop layer to prevent collisions- and in the different collaborative control commented modes. The best results were returned, as commented, by the final implementation: efficiency-modulated CBR-based collaborative control with smoothed case transition. However, we tested other approaches, like modulating control depending on biometrics using a Bluetooth wearable. All results were validated by ANOVA tests and evaluated by users with a PIADS. questionnaire. In all cases, results were very positive.

The next step would be to establish an intelligent agent layer in our hybrid architecture to reconcile efficiency considerations, biometrics, medical condition and Activities of Daily Living (e.g. rehabilitation sessions, lunch time, etc), if available. This work remains open to be integrated as a higher hybrid layer, fully compatible with the proposed hybrid architecture we deployed in this dissertation (DLA).

CONTRIBUTION IV:DISABILITY PROFILE

To wrap up, since we had a large amount of data from diagnosed real users, we though that it might be possible to solve the classic cold start problem if we could build a generic user profile for each disability using these data. The profile could also be useful to modulate efficiency in a predictive way and to support diagnosis. Hence, we applied data mining techniques to our unassisted navigation data set. First, we split all faced obstacle situations into 6 classes, as proposed in (Minguez et al, 2009). This initial cluster only depends on the robot and obstacle(s) relative positions. We performed a second clustering inside each class, this time according to the relative position of target and mobile and its headning. This process returned the following 32 classes.

Disability profile for a prototype user

The medoid of each class was obtained from the average of all its elements, after weighting each of them by its efficiency. Thus, it does not correspond to the most efficient solution, but also to the most frequent one. Each of these medoids corresponds to a nuclear behavior required to solve everyday navigation situations and its efficiency is the baseline for users to solve them. It needs to be noted that this efficiency will rarely be close to 1 -our population has a spectrum of disabilities, but even healthy individuals will not be able to solve most sitiations with the highest efficiency-. This process only needs to be carried out once, as long as the population is large enough and the situations solved are representative. Afterwards, results by a given user are evaluated with respect to this model, by simply cheching wichi class the situations he/she faces belong to and what is the difference between his/her efficiency and that of the class. medoid . Absence of some classes or a very low relative efficiency to solve them has been correlated to specific problems with well known effects, like right or left hemisphere strokes, which provoke loss of skills on the contrary side of the body.

Disability profile for an user with right hemisphere ischemia: a) unassisted; b) in collaborative mode; c) difference between a and b.

In order to extract more meaningful medical data, we would need support by health professionals. However, to predict the wave envelope required for a given user to deal with a specific environment situation, we just need his/her profile and change K(i) accordingly.

4. PUBLISHED WORKS

PRELIMINARY WORKS

The reactive layer in this dissertation is inserted into a hybrid architecture, previously presented in:

1. U. Cortés, R. Annicchiarico, J. Vázquez-Salceda, C. Urdiales, L. Canamero, M. López, M. Sánchez-Marre, and C. Caltagirone, “e-tools: the use of assistive technologies to enhance disabled and senior citizens’ autonomy,” e-Health: Application of Computing Science in Medicine and Health Care (ISBN:970-36-0118-9), pp. 119–132, 2003.

2. C. Urdiales, A. Poncela, R. Annicchirico, F. Rizzi, F. Sandoval, and C. Caltagirone, A topological map for scheduled navigation in a hospital environment, pp. 228–243, 2003.

3. C. Urdiales, A. Bandera, E. J. Pérez, A. Poncela, and F. Sandoval, Hierarchical planning in a mobile robot for map learning and navigation. Physica Verlag, pp. 2165–2188, 2003.

4. U. Cortés, R. Annicchiarico, F. Campana, J. Vázquez-Salceda, C. Urdiales, L. Canamero, M. López, M. Sánchez-Marré, S. D. Vincenzo, and C. Caltagirone, “Intelligenza artificiale in medicina: progetto di una piattaforma mobile inserita in un ambiente intelligente per l’assistenza ai disabili e agli anziani,” Recenti Progressi in Medicina, vol. 95, no. 4, pp. 190–195, 2004.

5. C. Urdiales, E.J. Pérez, F. Sandoval, ”A time stamp control strategy for CBR based reactive navigation in dynamic environments with priorities”, Proc. of IEEE Int. Conf. Agent Technology (IAT’04), Beijing (China), 2004 (Nominated to best conference paper)

DISSERTATION WORKS

NATIONAL CONFERENCES

1. C. Urdiales, A. Poncela, F. Galluppi, M. Olivetti, and F. Sandoval, “Control compartido a nivel reactivo basado en eficiencia,” in Proc. of the URSI 2007 (URSI’07), Sta Cruz de Tenerife, Spain, 2007.

INTERNATIONAL CONFERENCES

1. U. Cortés, R. Annicchiarico, A. Villar, C. Barrué, C. Urdiales, and C. Caltagirone, “Refocusing e-tools: Towards a patient’s oriented vision,” in Proc. of 17th European Conference on Artificial Intelligence (ECAI’06), Trento, Italy, 2006.

2. C. Urdiales, A. Poncela, I. Sánchez-Tato, and F. Sandoval, “Efficiency based reactive shared control for collaborative human/robot navigation,” in Proc. of the IEEE Conference on Intell. Robots and Systems (IROS’07), San Diego, USA, 2007

3. I. Sánchez-Tato, J. del Toro, E. Perez, C. Urdiales, U. Cortés, R. Annicchiaricco, F. Sandoval, and C. Caltagirone, “Collaborative control for personalized mobility assistance to persons with physical/cognitive disabilities,” in Proc. of IROS-2007-Workshop on Assistive Technologies (IROS’07), San Diego, USA, 2007.

4. C. Urdiales, J. M. Peula, C. Barrué, U. Cortés, F. Sandoval, C. Caltagirone, and R. Annichiaricco, “An adaptive scheme for wheelchair navigation collaborative control,” in Proc. of Fall Symposium of Asociation for the Advancement of Artificial Intelligence (AAAI’08), Arlington, US, 2008.

5. F. Galluppi, C. Urdiales, A. Poncela, I. Sanchez-Tato, F. Sandoval, and M. Olivetti, “A study on human performance in a cooperative local navigation robotic system,” in Proc. of CoMA Workshop (WETICE’08), Roma, Italy, 2008 (Best conference paper).

6. C. Urdiales, J. M. Peula, C. Barrué, E. J. Pérez, I.Sánchez-Tato, J. del Toro, U. Cortés, F. Sandoval, R. Annicchiarico, and C. Caltagirone, “A new collaborative shared control strategy for continuous elder/robot assisted navigation,” in Proc. of Int. Conf. of Int. Society for Geronthology 2008 (ISG’08), Pisa, Italy, 2008.

7. C. Urdiales, J. Peula, M. Fdez-Carmona, R. Annicchiaricco, F. Sandoval, and C. Caltagirone, “Adaptive collaborative assistance for wheelchair driving via CBR learning,” in Proc. of 2009 IEEE Conf. on Robotics for Rehabilitation (ICORR’09), Kyoto, Japan, 2009.

8. L. Duran, M. Fernandez-Carmona, C. Urdiales, J. Peula, and F. Sandoval, “Conventional joystick vs wiimote for holonomic wheelchair control,” in Proc. of Int. Workshop on Artificial Neural Networks (IWANN’09), Salamanca, Spain, 2009.

9. M. Fernandez-Carmona, B. Fernandez-Espejo, J. Peula, C. Urdiales, and F. Sandoval, “Efficiency based collaborative controlmodulated by biometrics for wheelchair assisted navigation,” in Proc. of 2009 IEEE Conf. on Robotics for Rehabilitation (ICORR’09), Kyoto, Japan, 2009.

10. C. Urdiales, J. Peula, U. Cortés, C. Barrue, B. Fernández-Espejo, R. Annichiaricco, F. Sandoval, and C. Caltagirone, “A metrics review for performance evaluation on assisted wheelchair navigation,” in Proc. of Int. Workshop on Artificial Neural Networks (IWANN’09), Salamanca, Spain, 2009.

11. C. Urdiales, M. Fernández-Carmona, J. Peula, R. Annicchiaricco, F. Sandoval, and C. Caltagirone, “Efficiency based modulation for wheelchair driving collaborative control,” in Proc. of 2010 IEEE Conf. on Robotics for Rehabilitation (ICRA’10) (nominated best paper), Anchorage, USA, 2010.

12. C. Urdiales, M. Fdez-Carmona, J. Peula, R. Annichiaricco, F. Sandoval, and C. Caltagirone, “A collaborative control scheme for haptics-based blind wheelchair driving,” in Proc. of 2010 National Robotic Conference, Karpacz, Poland, 2010 (invited paper).

13. G. Peinado, C. Urdiales, J.M. Peula, M. Fdez-Carmona, R. Annicchiaricco, F. Sandoval and C. Caltagirone “Navigation skills based profiling for collaborative wheelchair control”, 2011 IEEE Conf. on Robotics for Rehabilitation (ICRA’11) Shangai, China, 2011 (accepted).

INTERNATIONAL JOURNALS

1. C. Urdiales and U. Cortés, “Situated robotics: from learning to teaching by imitation,” Cognitive Processing, vol. 6, no. 3, pp. 196–201, 2005.

2. C. Urdiales, E. Pérez, J.Vázquez-Salceda, M.Sánchez-Marré, and F. Sandoval, “A purely reactive navigation scheme for dynamic environments using case-based reasoning,” Autonomous Robots, vol. 39, no. 5, pp. 67–78, 2006.

3. R. Vázquez-Martin, E. Pérez, C. Urdiales, J. del Toro, and F. Sandoval, “Hybrid navigation guidance for intelligent mobiles,” IEEE ITS Society Newsletter, vol. 4, no. 8, pp. 24–30, 2006.

4. F. Galluppi, C. Urdiales, F. Sandoval and M. Olivetti, "A study on a shared control navigation system: human/robot collaboration for assisting people in mobility, Cognitive Processing, 10(2), pp.215-218, 2009

5. Poncela, A., Urdiales, C., Pérez-Rodríguez, E. J. & Sandoval, F., "A new efficiency-weighted strategy for continuous human/robot cooperation in navigation". IEEE Trans. on Systems, Man and Cybernetics-Part A: Systems and Humans, Vol. 39, No. 3, 2009

6. U. Cortés, R. Annicchiarico, C. Urdiales, A. B. Martínez, C. Barrue, and C. Caltagirone, “Assistive technologies for the new generation of senior citizens. the SHARE-IT approach,” International Journal of Computers in Healthcare, vol. 1, no. 1, 2010.

7. C. Urdiales, B. Fernández-Espejo, R. Annicchiaricco, F. Sandoval, and C. Caltagirone, “Biometric modulated collaborative control for a robotic mobile platform,” IEEE Trans. on Neural Systems and Rehabilitation Eng., 18(4), 2010.

8. C. Urdiales, J. Peula, C. Barrue, E. Perez, I. Sanchez-Tato, J. del Toro, F. Galluppi, U. Cortés, R. Annichiaricco, C. Caltagirone, and F. Sandoval, “A new multi-criteria optimization strategy for shared control in wheelchair assisted navigation,” Autonomous Robots, 30(2), pp. 179-197, 2011.

9. C. Urdiales, M. Fdez-Carmona, J. Peula, U. Cortés, R. Annichiaricco, C. Caltagirone and F. Sandoval, “Wheelchair collaborative control for disabled users navigating indoors,” Submitted to Artificial Intelligence in Medicine (accepted).

10. J. Peula, C. Urdiales, I. Herrero, M. Fdez-Carmona, and F. Sandoval, “Case base reasoning based emulation of persons with disabilities for wheelchair navigation,” Submitted to Artificial Intelligence in Medicine (under review).

11. C. Urdiales, "The bare necessities: adaptive assistance for wheelchair control" Submitted to AI-Communications (accepted).

12. C. Urdiales, M. Fdez-Carmona, J. Peula, R. Annichiaricco, F. Sandoval, and C. Caltagirone, "Adaptive assistance for wheelchair navigation based on efficiency modulated shared control", Submitted to IEEE Trans. on Neural Systems and Rehabilitation Eng. (under review)

BOOK CHAPTERS

1. B. Fernández-Espejo, A. Poncela, C. Urdiales, and F. Sandoval, “Collaborative emergent navigation based on biometric weighted shared control,” in Proc. of the IWANN 2007, LNCS 4507, San Sebastian, Spain, pp. 814–821, 2007.

2. U. Cortés, C. Urdiales, R. Annicchiarico, C. Barrue , A. B. Martinez, and C. Caltagirone, Assistive Wheelchair Navigation: A Cognitive View. Springer Berlin / Heidelberg, pp. 165–187, 2007.

5. OUTCOMES

During the development of this dissertation, the following products were produced:

CARMEN robotized wheelchair (Open Hardware)
Collaborative control architecture (Creative Commons)
Learning by experience approach to reactively acquire driving profiles
Baseline disability profile (benchmarking)
Raw data with results from more than 70 diagnosed inpatients from FSL
State of the art on commercial devices and robotic wheelchairs (prices included)

6. MOBILITY

RESEARCH VISITS

Fondazione Santa Lucia, Roma:

One-week visits each 4 months for testing (2007-2009)

Compulsory stay for European PhD (2010)

Open bilateral cooperation agreement subscribed with our research group as direct result from this work

KEMLg, Barcelona:

Artificial Intelligence PhD courses

Visits for advisor's supervision

Collaboration in coordinated research projects

PUNCTUAL VISITS

Fundación ESCLAT (España)

Fundación Matía (España)

Fundación Ana Aslan (Romania) (cooperation in SHARE-it project)

Dr Seth Teller, MIT, Massachussets

Dr Simon Parsons, NYC University (New York)

Dr Thomas Roefl, DFKI (Bremen) (cooperation in SHARE-it project)

Dr Koon Guan Seah, A*Star (Singapur)

Dr Krzystoff Tchon, University of Wroclaw (Poland) (bilateral cooperation agreement signed with the University)

INVITED TALKS

• Robotica aplicada al servicio de personas con discapacidad (Charla en la FIB, UPC), April 2006 (eng. Robotics applied to assist persons with disabilities)

• Wireless technology for medical applications, (Nuove Tecnologie per il supporto e la riabilitazione del disabile), Rome, May 2006

• Wireless Network Technology and Sensor Networks (ENGAGE (2nd European Union - Southeast Asia ICT Research Collaboration Conference )), Jakarta, September 2006

• RFID based Adaptive non-intrusive Monitorization for TeleCare, (ENGAGE (3rd European Union - Southeast Asia ICT Research Collaboration Conference )), Bangkok, January 2007

• Sharing-it: A collaborative environment to learn and enhance Assistive Technologies learn and enhance Assistive Technologies (ENGAGE (3rd European Union - Southeast Asia ICT Research Collaboration Conference )), Bangkok, January 2007

• A shared control strategy for continuous mobility eAssistance collaboration, (ENGAGE (3rd European Union - Southeast Asia ICT Research Collaboration Conference )), Penang, February 2007

• The SHARE-IT project, (The International Course and Workshop on Bioethical Aspects Related to the Ambient Assisted Living for Patients with Cognitive and or Physical Disabilities), Bucharest, Romania, November 2009

• Collaborative control for assistive navigation, (11-th National Conference on Robotics), Karpacz, Poland, September 2010

7. DISSEMINATION

Dissertation dissemination blog: Social Assistive Robots (http://socialassistiverobots.blogspot.com/)
Invited talk "Robots: de los automatas al asistente inteligente" (X ciclo de conferencias "Presente y futuro de la ciencia y la tecnología 2007" Conferencia del Area de Cultura del Ayuntamiento de Málaga), Málaga, Marzo 2007 (eng. Robots: from automata to intelligent assistive robots (Present and future of technology 2007; organized by Malaga City Council))
Creation of a new interactive on-line VRML representation of the history of robotics
Design and painting of the poster "History of the bots" for exhibitions in Malaga and Granada (Spain)
Participation by invitation in the exhibits "Los nuevos esclavos cibernéticos" (Parque de las Ciencias (Granada) y Principia (Málaga) (eng. The new cybernetic slaves (Park of sciences (Granada) and museum of science (Málaga))
Frequent interviews in non-specialized magazines, e.g Bulevar, newspapers, e.g. Sur, el Mundo, Qué, el Observador, scientific dissemination magazines Uciencia ... (more press clips)
Interviews in radio programs: Onda Cero in Perfiles and Partiendo de Cero
TV interviews: Canal Sur in dissemination shows (Tesis) and daily news

8. PARTICIPATION IN RELATED PROJECTS

More information on ISIS group web page

As main researcher:

ASSIST (Arquitectura de servicios inteligente de soporte a personas con necesidades especiales) (TEC2006-11689-C03-01/TCM.)(eng. Intelligence services architecture for persons with special needs)
Arquitectura de servicios inteligente de soporte a la independencia mediante robots (TEC2008-06734-C02-01/TEC) (eng. Intelligent support services for independent life based on robots)
MIND (Abordaje multidisciplinar de la enfermedad de Alzheimer) (Contrato 8.06/5.58.3145-1 (GEROZERLAN)) (eng. Multidisciplinary approach to Alzheimer: clinical aspects)
MIND II (Abordaje multidisciplinar de la enfermedad de Alzheimer) (Contrato 8.06/5.58.3145-2 (BILBOMATICA)) (eng. Multidisciplinary approach to Alzheimer: Ambient Intelligence)
ARMONIA (Contrato Plan Avanza (Novasoft) (Ref. to be assigned) (eng. Ambient Intelligence support architecture for independent living)

As Work Package leader:

SHARE-IT (Supported Human Autonomy for Recovery and Enhancement of Cognitive and Motor Habilitéis using Information Technologies.)(IST-045088. Ref. 8.06.UE/59.6027)

As researcher:

PLATEA (Plataforma inalámbrica de banda ancha para monitorización y teleasistencia domiciliaria) ((PETRI). Ref.: 95-1005.OP) (eng. Wireless wide band platform for monitorization and home tele-assistance)
Plataforma inalámbrica de banda ancha para monitorización y teleasistencia domiciliaria (Contrato 8.06/58.2436 (CITIC)) (eng. Wireless platform for monitorization and home tele-assistance)
Investigación en tecnología y arquitectura de sensores inteligentes (Contrato 8.06/58.2537 (CETECOM)) (eng. Research on intelligent sensors technology and architecture)
AmIVital (Contrato 8.06/5.58.2767 (TID)) (eng. Ambient Intelligence: sensors and services)
AmIVital II (Contrato 8.06/5.58.2768 (Telvent)) (eng. Ambient Intelligence: biometrics)
SIAD (Proyecto de Excelencia JA) (eng. Autonomous robots for Assisted Living)
TELEADM (Teleasistencia Avanzada, Domótica y Multimedia) (Contrato 8.06/5.58.2758 (TID)) (eng. Advanced teleassistance, domotics and multimedia)

Networking:

Red de Agentes Físicos (REDAF) (TIN2006-27679-E) (eng. Physical agents network)
EURON (EUropean RObotics research Network)
eVIA (Plataforma Tecnológica Española de tecnologías para la vida independiente y la accesibilidad.) (eng. Spanish Technological Platform for indenpendent living and accesibility)

9. OTHERS

- This dissertation has been accepted for publication as book by Springer Verlag under the title "Assistive technology for the aging society" as part of the series "Intelligent Systems Reference Library"

- The paper “A study on human performance in a cooperative local navigation robotic system,” (WETICE’08) was awarded as best of the conference and papers ”A time stamp control strategy for CBR based reactive navigation in dynamic environments with priorities” (IAT'04) and "Efficiency based modulation for wheelchair driving collaborative control" (ICRA'10) were nominated for awards.

-Two patents have been claimed (under process) in 2008:

• Claros Moreno, D., Domínguez Durán, M. Á., del Toro Lasanta, J. C., Urdiales, C. & Sandoval Hernández, F. (2008). System for Locating Minors in Large Retail Facilities (P200703081).[Más] [Versión en línea]

• Fernández Carmona, M. Urdiales, C. del Toro Lasanta, J. C., Sandoval Hernández, F. & Fernández Espejo, B. (2008). RFID-Based Object Tracking for the Visually Impaired (P20070379) [Más]

- I have supervised 14 student projects since 2006, including two national awards (Dña. Blanca Fdez-Espejo and D. Gerardo Reveriego Sierra) given by INDRA (2007) and INFOGLOBAL (2009) by COIT, respectively. Even though none is included in this dissertation, most of them were based on its results, e.g. driving a wheelchair with a Wiimote, integrating KNX/EIB in DLA, etc.

- Supervision of ERASMUS Mr Franceco Galluppi's master thesis and co-publication of several works in conferences and journals.

- Organization of the following international workshops:

• "Assistive Technologies and e-Health" (IWANN’07)

• "Ageing well in the Knowledge Society (AKS)" (IWANN’09)

- Participation by invitation in the following summer courses:

• Tecnología aplicada a la movilidad asistida para personas con discapacidad motora (Curso de Nuevas Tecnologıas al Servicio de las Personas con dependencias, cursos de verano de la UNIA-06), Malaga, Julio 2006 (eng. Assisted mobility Technologies for people with motory challenges)

• Tecnologías asistenciales para apoyo al envejecimiento (Curso organizado por el KEMLg, UPC), Abril-Mayo, 2007 (eng. Assistive technology to support the elderly)

• Apoyo a la autonomía personal y mejora de las habilidades motoras y cognitivas (Curso de Inteligencia Ambiental para Apoyo a la Salud y a la Vida Independiente, Universidad de Granada: Cursos de verano), Julio 2008 (eng. Assistance for personal autonomy and rehabilitation of cognitve/motory skills)

- Co-editor of the book Agent technology and eHealth (Cortes, Annicchiarico and Urdiales eds.), Whitestein Series in Sofware Agent Technologies and Automatic Computing, 2008

- Associated editor of JoPha journal (ISSN:1888-0258)

Google Sites

Report abuse