MEDIA RELATIONS OFFICE
JET PROPULSION LABORATORY
CALIFORNIA INSTITUTE OF TECHNOLOGY
NATIONAL AERONAUTICS AND SPACE ADMINISTRATION
PASADENA, CALIF. 91109 TELEPHONE (818) 354-5011
Contact: John G. Watson, JPL, (818) 354-5011
John Bluck, NASA Ames Research Center, (650) 604-5026
FOR IMMEDIATE RELEASE
June 7, 1999
REMOTE AGENT EXPERIMENT MEETS ALL OBJECTIVES
As scientists and science fiction buffs alike have long
suspected, artificial intelligence software can indeed operate a
spacecraft millions of miles from Earth.
During the week of May 17, experts from NASA's Ames Research
Center and Jet Propulsion Laboratory (JPL) pooled their expertise
to conduct Remote Agent, an experiment designed to push the
limits of spacecraft autonomy. Their efforts, involving
commanding of NASA's Deep Space 1 spacecraft, proved that this
sophisticated artificial intelligence software is capable of
achieving high-level goals by issuing spacecraft commands.
Perhaps more importantly, however, they demonstrated that Remote
Agent can also play doctor, diagnosing its own problems and
developing effective action plans to regain its own good health.
The latter attribute proved unexpectedly handy less than 24
hours into the experiment, when the synthetic intelligence
succeeded in firing Deep Space 1's ion engine on but failed to
turn it back off. With 70 percent of objectives met and the
experiment paused starting the afternoon of May 18, it was clear
that some type of computer bug had settled in and caused this
glitch -- but what, exactly, was the problem?
In an impressive show of its own strength, Remote Agent
itself provided all the clues for scientists to diagnose and
resolve the situation precisely.
"Remote Agent showed us how powerful it is by providing a
list of possible reasons for the bug," said computer scientist
Nicola Muscettola at NASA's Ames Research Center, Moffett Field,
CA, where much of the Remote Agent code was written. Scientists
found that the bug was related to a timing error when two parts
of the program were exchanging information -- easy to fix
permanently in coming months, and safe for completing tests the
week of May 17 without immediate modifications. "After defining
the bug, our experiment team was confident we could complete the
flight test. We asked Remote Agent to develop a new plan and
then to fly Deep Space 1 solo for six more hours."
The happy end result: In 29 hours starting at 11 a.m. on
Monday, May 17, and in six hours on Friday, May 21, the remote
agent team met 100 percent of their experiment objectives.
"We ran the program about 3,000 times on Earth before the
space test, and this bug never appeared," Muscettola said. "The
sudden occurrence of this bug is an example of why we tested the
software during space flight instead of only on the ground."
"If had not been for Remote Agent's ability to do onboard
planning, we would not have been able to complete the tests so
quickly. It would have taken days for the ground team to come up
with a new plan," said Dr. Pandu Nayak, deputy manager of Remote
Agent development at Ames.
To demonstrate Remote Agent's versatility, the tests threw
unique challenges in the software's path. Scientists created
four simulated failures designed to test Remote Agent's mettle to
On May 17, the spacecraft's camera appeared to be stuck in
the "on" position. Remote Agent craftily responded by formulating
and executing a new plan that accounted for the fact that the
camera could not be turned off, thus impacting total spacecraft
Then, on May 21, "when the artificial intelligence detected
that an electronics unit had 'failed,' the software fixed the
unit by reactivating it, not unlike rebooting a personal computer
after the screen freezes," said Dr. Marc Rayman, Deep Space 1
deputy mission manager and chief mission engineer at JPL,
Pasadena, CA. "Next, a sensor 'failed,' and Remote Agent
correctly recognized the sensor was the problem, not the device
it was sensing. This pair of problems is akin to finding that
the engine warning light has come on in your car. The light can
mean one of two things: either the engine has a problem, or the
sensor that triggers the light has a problem. In each case,
Remote Agent correctly distinguished which situation it was in."
The final simulated failure was a thruster stuck in the
"off" position, which Remote Agent detected and for which it
compensated by switching to a different set of thrusters.
"This technology will allow us to pursue Solar System
exploration missions that only a few years ago would have been
considered too elaborate, too costly or too dependent on teams of
Earth-bound controllers," said Dr. Doug Bernard, Remote Agent
manager at JPL.
An Internet web page contains a log of events on Deep Space
1 during the ambitious artificial intelligence test:
Launched October 24, 1998, Deep Space 1 is validating 12 new
technologies, including Remote Agent, so scientists can
confidently use them during science missions of the 21st century.
The spacecraft team expects testing of all technologies will be
complete in June, except for one final autonomous navigation
system test scheduled to take place in late July during an
encounter with asteroid 1992 KD. Deep Space 1, part of the New
Millennium Program, is managed for NASA's Office of Space
Science, Washington, DC, by JPL, a division of the California
Institute of Technology, Pasadena, CA.