A voice-operated computer assistant is set to be used in space for the first time on Monday – its operators hope it proves more reliable than "HAL", the treacherous speaking computer in the movie 2001.
Called Clarissa, the program will initially talk astronauts on the International Space Station through tests of onboard water supplies. But its developers hope it will eventually be used for all computer-related work on the station.
Clarissa was designed with input from astronauts. They said it was difficult to perform the 12,000 procedures necessary to maintain the ISS and conduct scientific experiments while simultaneously reading through lengthy instruction manuals.
"Just try to analyse a water sample while scrolling through pages of a procedure manual displayed on a computer monitor while you and the computer both float in microgravity," says US astronaut Michael Fincke, who spent six months on the station in 2004.
Clarissa queries astronauts about the details of what they need to accomplish in a particular procedure, then reads through step-by-step instructions. Astronauts control the program using simple commands like "next" or more complicated phrases, such as "set challenge verify mode on steps three through fourteen".
"The idea was to have a system that would read steps to them under their control, so they could keep their hands and eyes on whatever task they were doing," says Beth Ann Hockey, a computer scientist who leads the project at NASA's Ames Research Center in Moffett Field, California, US.
That capability "will be like having another crew member aboard", says Fincke. (You can see Clarissa in action in a mp4 video hosted on this NASA page.)
“No, I meant … “
Clarissa's software runs on a laptop and astronauts interact with it using a headset, which helps screen out noise from the station. The program "listens" to everything astronauts say and analyses what to do in response using a "command grammar" of 75 commands based on a vocabulary of 260 words.
It accurately interprets those commands about 94% of the time, but if it makes a mistake, astronauts can correct it with commands like, "no, I meant … ". But because Clarissa listens to everything, early versions of the program misinterpreted whether an astronaut was giving it a command or having an unrelated conversation about 10% of the time.
So developers turned to the Xerox Research Centre Europe in Grenoble, France, and researchers there halved that error rate by using the context of phrases as a "spam-filtering system", says Manny Rayner, Clarissa's lead implementer at NASA Ames.
Clarissa's software was delivered to the station in January 2005 and on Monday, US astronaut John Phillips, currently aboard the station, will train to use the program in space.
It currently covers a handful of procedures designed to test station water for bacteria. But project managers hope the protocol can be applied to other procedures - and eventually could be used to launch any computer application. "Ultimately, we'd like speaking to your computer to be normal," Hockey told New Scientist.
That might send shivers down the spine of anyone who watched HAL turn on its human controllers in Stanley Kubrick's "2001: A Space Odyssey". But Hockey says Clarissa does not have HAL's artificial intelligence. "Clarissa is more friendly and is not going to go renegade on us," says Hockey, whose recorded voice has been borrowed by Clarissa.