CAMBRIDGE, Mass -- A scientific "assistant" developed by MIT researchersand colleagues is key to an experiment on sleep to be carried out onastronauts John Glenn and Chiaki Mukai during the shuttle mission scheduledfor liftoff this Thursday.
The assistant, a computerized artificial intelligence system, willhelp ensure that the astronauts properly don and activate the electrodes,wired vests, microphones and other equipment that will measure variousparameters as they sleep. Its feedback, which includes red and greensignals indicating the status of connections and trouble-shootingprocedures if something is amiss, is important because the scientists whodesigned the experiment won't be available to check the set-up. Further,the study comes at the end of a long day when there's more probability forsimple mistakes that could jeopardize data collection.
Dubbed the Principal Investigator-in-a-Box, or [PI] for short (thebrackets represent the box), the system was created to "capture thereasoning power of the scientist doing the experiment when that scientistis not physically in contact with the experiment," said Laurence R. Young,Apollo Program Professor of Astronautics and principal investigator for thesystem. He explained that although astronauts are highly trained, theycannot be experts on every experiment they conduct. [PI] helps them makedecisions that might otherwise require consultation with the machine'shuman counterpart.
For the same reasons [PI] could also be useful for studies inremote areas on Earth, and has particular relevance for long-term missionsaboard the planned International Space Station. "It would be nice to haveif you're an astronaut going to Mars and it's been six months since youlast practiced the research protocol for a given experiment," said SusanneM. Essig, a research assistant on the [PI] project and graduate student inthe Department of Aeronautics and Astronautics.
This will be the third time in space for the system. Earlier thisyear it flew aboard the Neurolab mission where it supported the firstexecution of the sleep study, led then and now by Dr. Charles A. Czeislerof Harvard Medical School and Brigham and Women's Hospital. An earlierversion of [PI] went to space in 1993. On that mission it supported anexperiment by MIT researchers and colleagues on the human balance system.
[PI] AT WORK
For two nights at the beginning of the flight and two at the end,astronauts Glenn and Mukai will don the instrumentation that will detectparameters related to their sleep and respiration. (Dr. Mukai will alsotake a capsule of melatonin, a sleep aid, to determine if it improves thequality of her sleep. Senator Glenn was disqualified from this part of theexperiment for undisclosed reasons.)
After the two are outfitted, astronauts Stephen Robinson and ScottParazynski will plug the apparatus into a digital sleep recorder that inturn will be plugged into a laptop containing [PI]. The system will thendisplay and analyze 15 signals (such as brain waves and heart rate) comingin from the astronauts. "[PI] first checks to make sure that all signalsare present. It then assesses their quality by performing statisticalanalyses on them and comparing the results of these analyses with acceptedranges for quality signals," Ms. Essig said.
"If a signal is either not present or of poor quality, a red lightassociated with that signal will flash on the laptop." The astronaut canthen click on the red light to get trouble-shooting procedures. "Once theastronauts are satisfied that the signals are ok, they disconnect from [PI]and close it down," Ms. Essig said.
HOW IT BEGAN
In early 1986 Professor Young was to have an experiment go up onthe shuttle. Then came the Challenger tragedy.
"I knew there would be a long delay before NASA flew again," hesaid, "so rather than wait, I decided to take advantage of the delay andlook into something I'd been interested in for years--expert systems."
So he took a sabbatical at Stanford at NASA's Ames Research Centerand "spent six months studying artificial intelligence in graduate-studentmode." His goal: "how can I use this new technology to do space experimentsbetter?"
[PI] grew out of that interest and a strong continuingcollaboration with researchers at Ames, currently led by Dennis Heher, andwith MIT's Professor Peter Szolovits of the Laboratory for Computer Scienceand Department of Electrical Engineering and Computer Science. Dr. AlanNatapoff, a research scientist in aeronautics and astronautics, is aco-investigator for [PI] on the current mission with Professor Szolovits.
Professor Young noted that the project has also involved severalstudents, resulting in four MIT theses so far. Most recently Luca Callinireceived a masters (1998) for his work on the system.
Professor Young is more than familiar with the space program andwith the challenges faced by astronauts. In 1993 he was alternate payloadspecialist for a mission aboard Space Shuttle Columbia.
Talking about why he became interested in applying artificialintelligence systems to space studies, he explained: "In the quiet of atraining session you can explain all the 'what ifs' to an astronaut, butunder the special conditions of a space flight all that can go out thewindow."
Further, "there are millions and millions of people who watch NASAmissions, so any comments related to a problem are going to be picked upand potentially become issues for rumor and the press. As a result, thereis a great disincentive for an astronaut to say, 'this isn't proceedinglike it did in training,' or to otherwise talk about problems. I realizedthis much more after my own crew experience."
In such a situation it's much easier to communicate with acomputer, he said, noting that "[PI] can't foresee everything, but it cando a reasonable job." In the Neurolab mission in April, the system alertedthe astronauts to anomalous signals over 100 times. "Eighty percent of thetime it was correct and changes were made," said Professor Young.
MEETING JOHN GLENN
One of the rewards of working on projects related to the spacestation is meeting astronauts. For Ms. Essig, who was involved in [PI]training sessions for the crew involved, meeting John Glenn "definitelymade my career, as opposed to just my day!" It "was also neat meeting Dr.Mukai. She's a national hero in Japan."
The [PI] work was sponsored by NASA's Ames Research Center and theNational Space Biomedical Research Institute, of which Professor Young isdirector.
NOTE TO EDITORS: Photo available. To view, seehttp://web.mit.edu/newsoffice/nr/1998/shuttle.html
The above post is reprinted from materials provided by Massachusetts Institute Of Technology. Note: Materials may be edited for content and length.
Cite This Page: