REFLECT: Biocybernetic control with multiple loops

It has been said that every cloud has a silver lining and the only positive from chronic jet lag (Kiel and I arrived in Vancouver yesterday for the CHI workshop) is that it does give you a chance to catch up with overdue tasks.  This is a post I’d been meaning to write for several weeks about my involvement in the REFLECT project.

For the last three years, our group at LJMU have been working on a collaborative project called REFLECT funded by the EU Commission under the Future and Emerging Technology Initiative.  This project was centred around the concept of “reflective software” that responds implicitly to changes in user needs and in real-time.  A variety of physiological sensors are applied to the user in order to inform this kind of reflective adaptation.  So far, this is regular fare for anyone who’s read this blog before, being a standard set-up for a biocybernetic adaptation system.

One of the many things that makes the work on REFLECT project interesting is that we constructed several biocybernetic loops designed to run as autonomous units working in parallel.  Our partners at Philips Research led research into the mood music player where physiological monitoring of mood was used to drive the selection of music.  Our group at LJMU collaborated with colleagues at the University of Groningen to develop a cognitive monitor designed to help the user in the case of information overload.  The University of Pavia developed a loop to detect physical discomfort by monitoring changes in posture; these data were used to adapt a seat using inflatable pads to keep the user comfortable.  These systems were researched, prototypes were put together and they were integrated in the most stylish way possible thanks to our partners at Ferrari working with the Ludwig-Maximilians-University of Munich in conjunction with the Fraunhofer Institute for Computer Architecture and Software Technology, who also coordinated the project.

Three weeks ago, I traveled to Maranello for the final project review where these systems had been integrated into a Ferrari California car for the purposes of demonstration.  The project meeting was very positive (the review went well) but it was also a sad occasion – because we all enjoyed working together on this project very much.

Aside from the usual technical challenges of creating real-time analysis and adaptation for the individual loops, the REFLECT system posed some interesting questions for the development of biocybernetic adaptation in an extended context.  In other words, what happens when we have multiple loops with distinct goal states (in our case, sustain positive mood, prevent information overload, keep the driver comfortable) running in parallel?  If we want our systems to have an overt influence on the user, in this case a driver, we have to regard him or her as a limited capacity receiver.

First of all, there is the question of priority – which is the most important loop?  The obvious choice for this context is the cognitive loop because that is principally concerned with the prevention of accidents.  The mood music player comes a close second, this system is about promoting emotional well being but I think it’s safe to assume that the prevention of driver anger can contribute to traffic safety.  Secondly how to manage real-time adaptation from different systems – if we have several types of intervention, it may be disconcerting if too many things happen at once; we may need to coordinate the presentation of adaptation between each loop.

In our case, the goals of each loop were broadly in alignment – we wanted to promote the safety, well being and comfort of the driver.  However, it is possible for loops to pull the user in different directions.  Imagine a gaming system with two loops, one designed to sustain engagement by adapting task load to maintain challenge and another designed to detect fatigue and to suggest appropriate rest breaks.  The former is designed to promote enjoyment, the second is the joy killer, the loop designed to protect the player from themselves.  It’s an interesting dilemma for the designer – leaving aside, the thorny issue of whether computers should protect people from themselves.

The official website for the REFLECT project is here; there is also a nice summary of the project here on the Perada website.  Myself and Nikola Serbedzija (but mainly Nikola) have speculated about how this concept might be extended in the future with respect to personalisation – see our 2009 paper available here.

Finally I wanted to say thanks to everyone I’ve worked with on REFLECT over the last 3 years: Nikola, Alessandro, Amadeo, Joyce, Marjolein, Dick, Chris, Andreas, Christian, Martin, Gilbert, Gian, Andrea & Marko, it’s been a pleasure.


1 thought on “REFLECT: Biocybernetic control with multiple loops

  1. Pingback: Physiological Computing : Physiological Game Interaction and Psychophysiological Evaluation in Research and Industry

Comments are closed.