Remote Agent, the first artificial intelligence software in history to command a spacecraft, recently was named co-winner of NASA's 1999 Software of the Year award. Remote Agent shared the honor with Genoa, a software package that can predict aging and failure of materials, including those used in airplanes, cars, engines and bridges.
Award winners, judged on innovation, impact and usability, were selected from a field of 50 entries representing more than 150 corporations, universities and government laboratories.
NASA scientists say the Remote Agent artificial intelligence used on NASA's Deep Space 1 is the precursor for self-aware, self-controlled and self-operated robots, exploring rovers and intelligent machines.
Over three days last May, Remote Agent controlled Deep Space 1, a feat previously accomplished only in science fiction. The software package took command of Deep Space 1 during a flight experiment, and the artificial intelligence more than met expectations. The software detected, diagnosed and fixed problems, showing that it can make decisions to keep a mission on track.
"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 NASA's Jet Propulsion Laboratory, Pasadena, CA.
"The Remote Agent approach to spacecraft autonomy signals the dawn of a new era in space exploration," said Dr. Pandu Nayak, deputy manager of Remote Agent development the NASA Ames Research Center, Moffett Field, CA. "Remote Agent will enable new classes of missions and more effective use of existing resources, and it will enable today's ground operations teams to operate significantly more missions." Remote Agent and its components are already being considered for a variety of NASA missions, he said.
Experts from JPL and Ames pooled their expertise to conduct the Remote Agent experiment, designed to push the limits of spacecraft autonomy. Their efforts proved that this sophisticated artificial intelligence software is capable of commanding the spacecraft with "high-level" goals, such as "communicate with the Earth on the agreed-upon schedule" or "fire the main engine as needed to stay on the desired trajectory."
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 abilities. During one of the simulated failures, the spacecraft's camera appeared to be stuck in the "on" position. In response, Remote Agent formulated and executed a new plan that accounted for the fact that the camera could not be turned off, thus impacting total spacecraft power availability.
An Internet web page contains the log of events from Deep Space 1 during the ambitious artificial intelligence test: http://rax.arc.nasa.gov
Launched October 24, 1998, Deep Space 1 has validated 12 new technologies, including Remote Agent, so scientists can confidently use them during science missions of the 21st century. The project has exceeded all of its technology validation success criteria.
The other software co-winner, is Genoa, a Progressive Failure Analysis Software System developed at the NASA Glenn Research Center at Lewis Field in Cleveland, OH. Genoa is used to model aging and failure in structural materials, including high-tech alloys and ceramics.
The event is cosponsored by the NASA Inventions and Contributions Board and the NASA Chief Information Officer. NASA officials will officially present the awards at special ceremonies later this year. Information about the winning team and other finalists is available from: http://www.hq.nasa.gov/office/codei/swy99win.html
Remote Agent was developed at JPL and at the NASA Ames Research Center. Deep Space 1 is managed for NASA's Office of Space Science, Washington, DC, by JPL, a division of the California Institute of Technology. JPL is a division of the California Institute of Technology, Pasadena, CA.
News Media Contact818-354-5011