"It's one small step in the history of space flight. But it was one giant leap for computer-kind, with a state of the art artificial intelligence system being given primary command of a spacecraft."

- from NASA's DEEP SPACE 1 - REMOTE AGENT site

Artist's concept of Deep Space 1, courtesy of NASA

Introductory Readings

Satellite duo performs space pas de deux. By Kelly Young, with Will Knight. NewScientist.com news (April 19, 2006). "As if engaged in a slow-motion dance, two mated satellites used a robot arm to draw apart, then come together again several hours later on Monday. It is the first step towards the mission's ultimate goal of separating completely and docking with each other autonomously from a distance of 7 kilometres away. The $300-million Orbital Express mission -- run by the US Defense Advanced Research Projects Agency (DARPA) -- uses two satellites. One, called ASTRO (Autonomous Space Transport Robotic Operations), is designed to dock with and test repairs on another, called NextSat. The 90-day mission is meant to test autonomous operations in a spacecraft so that one day, a fix-it satellite might be deployed to fuel, inspect or even repair a wounded satellite without help from human controllers."

• Update: US achieves autonomous docking in space. By Kelly Young. New Scientist Space (May 8, 2007). "Two free-flying satellites performed the first autonomous separation and docking for the US on 5 and 6 May. The test was done without any human intervention as the craft flew nearly 500 kilometres above the planet, and could one day lead to robotic spacecraft that are able to repair damaged satellites. The ASTRO (Autonomous Space Transport Robotic Operations) and NextSat satellites together make up the Orbital Express mission. ... 'We essentially just sat back and watched,' says Fred Kennedy, Orbital Express's programme manager at the US Defense Advanced Research Projects Agency (DARPA). 'Picture-perfect and totally autonomous, save only that we decided to turn off our spotlight about halfway through to keep it from getting too hot.' ... Although this is the first autonomous docking for the US, Russia has long had autonomous technology in spacecraft."

'Scolding' software to speed planet hunt. By Zeeya Merali. New Scientist (February 27, 2008; Issue 2644: page 26; subscription req'd). "Last week, astronomers reported spotting the first multiplanet system orbiting another star, thanks to a network of robotic telescopes dotted around the world (see 'One-hit-wonder planet-spotting technique adds a new feather to its cap'). Each telescope runs software that allows it to alert the entire network as soon as it spots something interesting. The telescopes then bid for the chance to carry out follow-up observations, citing their assessment of their equipment, position and availability. ... [Alasdair] Allan and his colleagues have built a software control system (http://www.arxiv.org/abs/0802.0431) that ranks telescopes on the data they return. If a telescope fails to keep its promises, the system scolds it, instructing it to work out why it failed and to be more modest."

Google puts $30 million behind lunar robot. By Stefanie Olsen. CNET News.com (September 13, 2007). "Google on Thursday announced it has sponsored the Google Lunar X Prize, a robotic race to the moon with a purse of $30 million. The contest invites private teams from around the world to build a robotic rover capable of roaming the lunar surface for at least 500 meters and then sending video, images and data back to Earth, among other feats. The idea behind the challenge is to urge private industry to develop new robotic and virtual-presence technology to reduce the cost of space exploration. ... The contest comes at a time when NASA is working on new spacecraft and technology to take man back to the moon within the next 12 years. At a recent artificial-intelligence conference, Peter Norvig, the former head of computation at NASA's Ames facility who is now Google's director of research, suggested that the space agency is taking the more expensive approach in trying to send astronauts to the moon and that it should focus on robotics."

• Watch the Moon 2.0 Rollout Video, at YouTube and visit the Google Lunar X Prize homepage.

Intelligent Beings in Space! By Kenneth Chang. The New York Times (May 30, 2006). "Until recently, interplanetary robotic explorers have largely been marionettes of mission controllers back on Earth. The controllers sent instructions, and the spacecraft diligently executed them. But as missions go farther and become more ambitious, long-distance puppetry becomes less and less practical. If dumb spacecraft will not work, the answer is to make them smarter. Artificial intelligence will increasingly give spacecraft the ability to think for themselves. 'These technologies are already in operation on specific missions,' said Steve Chien, a computer scientist who heads the artificial intelligence group at NASA's Jet Propulsion Laboratory in Pasadena, Calif. Scientists discussed some of the recent progress last week at a meeting of the American Geophysical Union in Baltimore."

Artificial Intelligence to Boost Space-Probe Efficiency. By Richard A. Lovett. National Geographic News (May 30, 2006). "In a shift some hail as a revolution in space technology, scientists are reprogramming existing space probes to make more decisions on their own. Experts say artificial intelligence will help unmenned spacecraft work more efficiently and send better data back to Earth. ... Steve A. Chien, a JPL computer scientist and AGU panel speaker, said that the new approach, called onboard autonomy, is already in use on the Earth Observing-1 spacecraft, or EO-1. ... For more than a year, the satellite has been programmed to make its own decisions. If the unit spots a volcanic eruption, EO-1 reprograms its mission and zooms its cameras in for a closer look. Likewise, if the satellite detects a flood, EO-1 takes pictures as soon as possible. The upgrade, Chien says, has increased the satellite's scientific contribution a hundredfold, while cutting operating costs by more than a million U.S. dollars a year."

Mars robots to get smart upgrade. By Jonathan Amos. BBC News (May 28, 2006). "The US space agency's rovers will get a software upgrade to allow them to make 'intelligent' decisions in the study of Martian clouds and dust devils. The new algorithms will give the robots' computers the onboard ability to search through their images to find pictures that feature these phenomena. Only the most significant data will then be sent to Earth, maximising the scientific return from the missions. Nasa says its robotic craft will become increasingly autonomous in the future. ... Leaving the robots to 'get on with it' -- to do the decision-making -- is the way ahead, Nasa believes. The agency's Mars Odyssey orbiter, which has been mapping the Red Planet since 2001, will get new autonomous flight software later this year. ... [Ralph Lorenz] said self-reliant spacecraft would open up new science opportunities on far-distant missions, where probes might be out of contact with Earth for hours or even days at a time."

• Update: Mars rovers are taught new tricks - Nasa is testing a "smart" upgrade to its robotic rovers on Mars. BBC News (January 2, 2007). "Space agency scientists have begun testing four new skills included in flight software that has been uploaded to the rovers' onboard computers. The two American rovers, Spirit and Opportunity, are approaching their third year on the Martian surface. One of the new capabilities is designed to allow the rovers to make 'intelligent' decisions in the study of Martian clouds and dust devils."

Space station gets HAL-like computer. By Maggie McKee. NewScientist.com news (June 27, 2005). "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 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'."

• Also see this related article

Into the deep - Robots explore Earth's hidden depths: An intelligent, unmanned submarine is exploring Earth's most inhospitable places. Next stop: Jupiter's moons. By Danny Bradbury. The Independent Online Edition (April 25, 2007). "Next month, an 'autonomous explorer robot' (AER) named DepthX will face its biggest challenge. The US team behind the AER proved the machine's worth in February when they sent it to the bottom of a well-charted sinkhole in Mexico. ... In the next few weeks, researchers will send it to the bottom of El Zacatón, in the Mexican state of Tamaulipas. No one knows how deep this mysterious hole is;.... The word that makes DepthX special is 'autonomous'. The robot is designed to operate under its own steam, making decisions for itself without the help of researchers. It is already going where no one has gone before on this planet, but this autonomy will become even more important when robots are sent to explore other worlds. The long distances involved in space travel make it difficult to guide a robot based on what it tells people about its environment. 'Mars is fairly close to Earth right now, but one-way communication still takes 20 minutes,' says Wolfgang Fink, head of the Visual and Autonomous Exploration Systems Research Laboratory at the California Institute of Technology (Caltech). 'If you were to go to Titan [one of Saturn's moons], then you're dealing with over an hour.' Nasa scientists spend painstaking hours instructing guided explorers, but building a robot that can guide itself is the next logical step. In the meantime, while galactic plans are hatched, a mission to Antarctica's Lake Bonney is another good example of why autonomy is important. ... Robotic navigation is typically done using two techniques: dead reckoning and mapping. ... Robot explorers in space * MARS ROVERS ... * INTERPLANETARY GLOBAL NAVIGATION SATELLITE SYSTEMS ... * AUTONOMOUS NANOTECHNOLOGY SWARMS (Ants) ... * TIER-SCALABLE RECONNAISSANCE."

More from NASA:

• Artificial Intelligence Group at the Jet Propulsion Laboratory (JPL). "The Artificial Intelligence Group performs basic research in the areas of Artificial Intelligence Planning and Scheduling, with applications to science analysis, spacecraft commanding, deep space network operations, and space transportation systems."
• DART. Marshall Space Flight Center. "The Demonstration for Autonomous Rendezvous Technology, or DART, is a flight demonstrator vehicle designed to test technologies required to locate and rendezvous with other spacecraft. The DART mission is unique in that all of the operations will be autonomous - there will be no astronaut onboard at the controls, only computers programmed to perform functions."
  • Beaming Up a Software Doctor. Astrobiology Magazine (October 10, 2004).
• NASA Develops Robust Artificial Intelligence for Planetary Rovers. By John Bluck. NASA.gov. (August 10, 2004). "NASA is planning to add a strong dose of artificial intelligence (AI) to planetary rovers to make them much more self-reliant, capable of making basic decisions during a mission."
• Autonomous Sciencecraft Experiment (ASE). From NASA's Artificial Intelligence Group at the Jet Propulsion Laboratory. "Since the dawn of the space age, unmanned spacecraft have flown blind with little or no ability to make autonomous decisions based on the content of the data they collect. The Autonomous Sciencecraft Experiment (ASE) will fly onboard the Earth Orbiter 1 mission in 2003. The ASE software uses onboard continuous planning, robust task and goal-based execution, and onboard machine learning and pattern recognition to radically increase science return by enabling intelligent downlink selection and autonomous retargeting. This software will demonstrate the potential for space missions to use onboard decision-making to detect, analyze, and respond to science events, and to downlink only the highest value science data."
• MAPGEN. From NASA Ames Research Center. "MAPGEN (Mixed Initiative Activity Planning Generator) is a ground-based decision support system for MER mission operations and science teams that begins to give content to the notion of autonomous planetary exploration. MAPGEN is called a mixed initiative planner. The essence is in human interaction with the advanced planning software. While the routine plan generation process is handled by the machine, the user brings unique knowledge and experience to bear to produce qualitatively good plans, said MAPGEN project lead Kanna Rajan. The paradigm is to enable the person using the software to critique a plan that the system automatically produces and ensure that resulting plans are viable within mission and flight rules."
  • Read this interview with "principal investigator and project lead for the Mars Mission’s on-ground software effort, Kanna Rajan."
  • Also see: Mixed-Initiative Planning in Space Mission Operations. By John L. Bresina and Paul H. Morris. AI Magazine 28(2): Summer 2007, 75. Abstract: "The MAPGEN system represents a successful mission infusion of mixed-initiative planning technology. MAPGEN was deployed as a mission-critical component of the ground operations system for the Mars Exploration Rover mission. Each day, the ground-planning personnel employ MAPGEN to collaboratively plan the activities of the Spirit and Opportunity rovers, with the objective of achieving as much science as possible while ensuring rover safety and keeping within the limitations of the rovers’ resources. The Mars Exploration Rover mission has now been operating for more than two years, and MAPGEN continues to be employed for activity plan generation for the Spirit and Opportunity rovers. During the multiyear deployment effort and subsequent mission operations experience, we have learned valuable lessons regarding application of mixed-initiative planning technology to mission operations. These lessons have spawned new research in mixed-initiative planning and have influenced the design of a new ground operations system, called M-SLICE, that is baselined for the Mars Science Laboratory mission. In this article, we discuss the mixed-initiative aspects of the MAPGEN system, focusing on the task, control, and awareness issues."
• Deep Space 1's REMOTE AGENT. "Known as Remote Agent, the software operated NASA's Deep Space 1 spacecraft and its futuristic ion engine during two experiments that started on Monday, May 17, 1999. For two days Remote Agent ran on the on-board computer more than 60,000,000 miles (96,500,000 kilometers) from earth. The tests were a step toward robotic explorers of the 21st century that are less costly, more capable and more independent from ground control."
• Artificial Intelligence Software to Command Mission. Space Daily (May 29, 2001). "NASA software that thinks for itself and makes decisions without help from ground controllers will fly as the brains of triplet satellites in 2002. The software builds on previous efforts to use artificial intelligence to control a spacecraft (such as NASA's Remote Agent experiment, which controlled the Deep Space 1 spacecraft during portions of several days in 1999). However, this new software uses more advanced technology to respond more quickly to events and will command a mission continuously for a period of approximately three months. The Continuous Activity Scheduling, Planning Execution and Replanning (CASPER) software will guide a constellation of three identical miniature satellites, each weighing less than 15 kilograms (33 pounds)."
• NASA's Intelligent Systems Division: Technical Research Areas: Autonomous Systems and Robotics... Collaborative & Assistant Systems ... Discovery and Systems Health ... Robust Software Engineering.
• NASA's Robotic Explorers
• NASA software programs available for commercial applications and development: Artificial Intelligence and Expert Systems.
• Student FAQs from their Robotics Education Project.

Daring encounter with asteroid. BBC News (November 3, 2005). "A Japanese spacecraft is about to make a close encounter with an asteroid in a mission to recover space dust. The Hayabusa probe is stationed over a giant asteroid some 300 million km from Earth. ... The Japanese Aerospace Exploration Agency (Jaxa) probe carries the 10cm-tall Minerva robot that will bounce across the asteroid, collecting temperature readings and images. ... The landings will be controlled autonomously by the spacecraft's software."

• More information about Hayabusa's mission is available from the Japanese Aerospace Exploration Agency (Jaxa).

Halfway to Mars - How a hardy band of researchers braved freezing nights, bad food, and high winds in the Chilean desert to test the next generation of planetary rovers. By Jean Kumagai. IEEE Spectrum Online (March 2006). "[David] Wettergreen, an associate research professor at Carnegie Mellon University's Robotics Institute, in Pittsburgh, and his team have been roughing it here in the Atacama since August, and they'll remain until November, just as South America's spring gives way to summer. They've come to test out new concepts and designs for the next generation of planetary rover, because this place, more than any other on Earth, approximates the barren, arid rockiness of the Red Planet. Testing the rover means pushing the technology to its limits, and sometimes beyond. The robot is so unusual and so new that breaking down is, for now, anyway, what it's supposed to do. 'A hundred percent success means we're not really trying hard enough,' Wettergreen says. It isn't the most elegant-looking machine ever built. Weighing in at 180 kilograms, the rover, dubbed Zoë, looks something like a motorized, overgrown ice cream cart. But it is beautiful in the one way that really matters to planetary scientists: unlike all the rovers built thus far, Zoë can roam autonomously. ... The rover can even make some rudimentary decisions about what terrain to explore. In a set of experiments conducted in Chile, Zoë successfully determined which tests to run at a given location."

• Visit the CMU Field Robotic Center Zoë Web site.

European Space Shuttle Glides To Success. Deutsche Welle / DW-World.de (May 9, 2004). "Space researchers in Bremen came a step closer this weekend to the creation of Europe's first reusable, unmanned space shuttle. The so-called Phoenix craft, a prototype of the future Hopper space glider, landed safely at a testing ground after reaching speeds of 450 kilometers per hour in northern Sweden on Saturday. ... The German-designed prototype was carried to a height of 2,400 meters by a helicopter. It then glided back to earth without the use of a motor and without controls from the ground. An onboard computer equipped with GPS guided the Phoenix to a perfect landing. ... A craft with artificial intelligence? But what really set the Phoenix mission apart from others was the fact that it steered itself. An onboard computer controlled the navigation of the craft by processing data from radar, laser-distance measurements and satellite navigation, which it then used to determine small changes of direction and altitude until it made its landing."

A new robot makes a leap in brainpower. By Faye Flam. Philadelphia Inquirer / available from Philly.com (January 15, 2004). "A new robot is as good as human scientists at creating and evaluating experiments, its British creators said yesterday. The announcement, on the same day President Bush revealed his plan for sending astronauts to Mars, added fuel to an old debate: Why send humans into space if robots could do the job?"

Robot Telescopes Comb the Skies.  By Lakshmi Sandhana. Wired News (September 21, 2004). "British astronomers have just begun to operate RoboNet-1.0, a global network of the world's biggest robotic telescopes, controlled by intelligent software to effectively act as one giant eye that can be focused anywhere in the sky within a minute. It's a dream come true for the astronomers at Liverpool John Moores University who pioneered the development of a fully automated intelligent robotic network. They developed the network to allow astronomers to follow up unpredictable events or appearances of objects in the sky as rapidly as possible, something that isn't ordinarily possible with a single telescope at a fixed position. ... ESTAR, a joint project of Liverpool John Moores University and Exeter University, developed intelligent autonomous software programs, known as agents, that will function as the brains of the network. Acting as 'virtual astronomers,' the agents will collect and analyze data 24 hours a day, alerting their flesh-and-blood counterparts only when they catch sight of something noteworthy."

• Also see: Smart software watches the skies - Intelligent agents may sound like something out of The Matrix, but smart programs are helping astronomers find out more about the Universe. BBC (October 15, 2003). "'What is so important here is that we have developed an intelligent observing system,' said Dr Alasdair Allan of the University of Exeter. 'It thinks and reacts for itself, deciding whether something it has discovered is interesting enough to need more observations. If more observations are needed, it just goes ahead and gets them.' ... 'The Agents can detect and respond to the rapidly changing universe faster than any human, and make decisions to observe an object much faster than would otherwise be possible,' explained Dr Allan."
• Visit eStar.

Virtual Astronomy Claims Largest Space Rock Ever. By Robert Roy Britt. SPACE.com (August 24, 2001). "'Many people think that so-called virtual astronomy is going to be the next big thing,' [David Jewitt] said. 'The idea is that, in the future, certain kinds of science will be done by digging into huge databases using intelligent algorithms instead of going directly to the telescope as we do now. What that will do is open up the time domain of astronomy: we'll see everything that moves or varies in any way.'"

Automatic Astronomy - New Robotic Telescopes See and Think. By Robert Roy Britt. Space.com (June 4, 2003). "If an asteroid is discovered tonight and found to be on a collision course with Earth, you may have a robot to thank for the warning. If a star blinks for a nanosecond, you won't notice it, but a robot might, and it will deduce that an object no bigger than this city, roaming the solar system in Pluto's realm, has just passed in front of a distant star. A surprisingly cheap new crop of thinking and seeing machines work alone, scanning the heavens every night, from dusk to dawn with no coffee breaks, looking for objects that humans have so far failed to find. ... More than a dozen teams from around the world, all involved in creating fully autonomous, semi-intelligent observatories, met here last week at a meeting of the American Astronomical Society (AAS) to present new findings and swap ideas."

Brainy 'Bots - NASA's own "Bionic Woman" is applying artificial intelligence to teach robots how to behave a little more like human explorers. By Annie Strickler and Patrick Barry. Science at NASA (May 29, 2001). "[T]he ultimate goal for Ayanna and her colleagues is 'putting a robot on Mars and walking away, leaving it to work without direct human interaction.'"

Machines that Think. Artificial Intelligence Webcast from the Jet Propulsion Laboratory (June 29, 2001). "The show is hosted by Alice Wessen, JPL Technology Outreach Lead. The guests will be autonomous software specialists Barbara Engelhardt and Russell Knight, FIDO rover lead system engineer Dr. Edward Tunstel, and Machine Vision Group Supervisor Dr. Larry Matthies."

General Readings

The Future of AI in Space. Bi Steve Chien, Richard Doyle, Ashley Gerard Davies, Ari Jónsson, and Ralph Lorenz. IEEE Intelligent Systems 21(4): July/August 2006, 64-69. "Two key flight technology experiments--the Remote Agent Experiment (RAX) and the Autonomous Sciencecraft Experiment (ASE)--validated appropriate uses of AI-based capabilities in future robotic and human exploration of the Moon, Mars, and beyond. A survey of future missions describes some of them."

PI in a Box: A Knowledge-Based System for Space Science Experimentation. By Richard Franier, Nicholas Groleau, Lyman Hazelton, Silvano Colombano, Michael Compton, Irving Statler, Peter Szolovits, and Laurence Young. AI Magazine 15(1): Spring 1994, 39-56. "The principal investigator (PI)-IN-A-BOX knowledge based system helps astronauts perform science experiments in space. These experiments are typically costly to devise and build and often are difficult to perform. Further, the space laboratory environment is unique; ever changing; hectic; and, therefore, stressful. The environment requires quick, correct reactions to events over a wide range of experiments and disciplines, including ones distant from an astronaut’s main science specialty. This environment suggests the use of advanced techniques for data collection, analysis, and decision making to maximize the value of the research performed. PI-IN-A-BOX aids astronauts with quick-look data collection, reduction, and analysis as well as equipment diagnosis and troubleshooting, procedural reminders, and suggestions for high-value departures from the preplanned experiment protocol. The astronauts have direct access to the system, which is hosted on a portable computer in the Space Lab module. The system is in use on the ground for mission training and was used in flight during the October 1993 space life sciences 2 (SLS-2) shuttle mission."

SOFIA’s Choice: An AI Approach to Scheduling Airborne Astronomy Observations. By Jeremy Frank, Michael A. K. Gross, and Elif Kürklü. In Proceedings of the Sixteenth Innovative Applications of Artificial Intelligence Conference (2004), 828 - 835. Menlo Park, Calif.: AAAI Press. Abstract: "We describe an innovative solution to the problem of scheduling astronomy observations for the Stratospheric Ob-servatory for Infrared Astronomy, an airborne observatory. The problem contains complex constraints relating the feasi-bility of an astronomical observation to the position and time at which the observation begins, telescope elevation limits and available fuel. Solving the problem requires making discrete choices (e.g. selection and sequencing of observa-tions) and continuous ones (e.g. takeoff time and setting up observations by repositioning the aircraft). The problem also includes optimization criteria such as maximizing observing time while simultaneously minimizing total flight time. We describe a method to search for good flight plans that satisfy all constraints. This novel approach combines heuristic search, biased stochastic sampling, continuous optimization techniques, and well-founded approximations that eliminate feasible solutions but greatly reduce computation time."

Advanced Automation for Space Missions. Edited by Robert A. Freitas, Jr. and William P. Gilbreath. Proceedings of the 1980 NASA/ASEE Summer Study (NASA Conference Publication 2255). Portions of the report are available online, including the Introduction: "This document is the final report of a study on the feasibility of using machine intelligence, including automation and robotics, in future space missions. The 10-week study was conducted during the summer of 1980 by 18 educators from universities throughout the United States who worked with 15 NASA program engineers. The specific study objectives were to identify and analyze several representative missions that would require extensive applications of machine intelligence, and then to identify technologies that must be developed to accomplish these types of missions." Some of the other sections available online are Survey of Artificial Intelligence and History of NASA Automation Activities.

Medicine on Mars - How sick can you get during three years in deep space? By Jerome Groopman. The New Yorker (February 14, 2000: pages 36 - 41; available at the author's web site). "There might also be a 'virtual mentor': a computerized database whose artificial intelligence will assist the onboard physician in diagnosis and treatment. 'For example, astronaut John Doe has a fever, and pain in his right lower abdomen,' [Jon] Bowersox says. 'The virtual mentor instructs the doctor to perform an ultrasound, with voice and image overlay, all the while comparing the new ultrasound data with baseline data. Appendicitis, which is the likely diagnosis, would be best treated with intensive antibiotics, given the difficulties of operating in zero G. Surgery is a last resort.' When surgery could not be avoided, it would be performed by the doctor, coached by the virtual mentor and aided by robotics."

SPIKE: Intelligent Scheduling of Hubble Space Telescope Observations. By Mark D. Johnson and Glenn E. Miller, Space Telescope Science Institute. In Intelligent Scheduling, ed. M. Fox and M. Zweben, San Francisco: Morgan-Kaufmann, 1994, pp 391-422. "The HST scheduling problem ranks among the largest and most complex scheduling problems faced on a continuing basis: some 10,000 to 30,000 observations are scheduled per year and each is subject to a large number of operational and scientific constraints."

• For more information, visit the SPIKE homepage.

Raptor Science. Los Almos Research Quarterly (Fall 2003). "RAPTOR can do more than respond to satellite alerts. Equipped with sophisticated computer intelligence, it is the first robotic observatory system that can find and study transient optical events on its own. It is also the only robotic observatory system with stereovision, which allows it to discern between transient optical events and nearby space junk, as well as to detect 'killer' asteroids. ... To capture a transient optical event, RAPTOR must 'think' and act fast. The system has one minute to decide if any one of up to 250,000 objects in a wide-field image is a transient optical event. In contrast, other robotic observatory systems capture transient optical events by chance or by responding to satellite alerts or to commands from humans, who are much slower and less precise than RAPTOR. To detect a new object in a wide-field image, RAPTOR compares the position and brightness of each object in the image with those of known objects identified in previous scans."

The AI Program at the National Aeronautics and Space Administration: Lessons Learned During the First Seven Years. By Melvin D. Montemerlo. AI magazine 13(4): Winter 1992, 49-62. "This article is a slightly modified version of an invited address that was given at the Eighth IEEE Conference on Artificial Intelligence for Applications in Monterey, California, on 2 March 1992."

Darwinian Design. Survival of the Fittest Spacecraft - evolving better spacecraft through artificial intelligence. NASA Space Science News (April 7, 1999). "Survival of the fittest, when applied to computer design, is one of the ingredients for artificial intelligence. 'What it boils down to is trying to get computers to recognize patterns and react,' says [David] Noever. 'We treat the designing choices of a mission like a biologist treats a genetic chromosome. We can cut and splice missions together with remarkable speed, compete them against each other, and then multiply the survivors.'"

Immobots Take Control. By Wade Roush. Technology Review (December 2002/January 2003). "From photocopiers to space probes, machines injected with robotic self-awareness are reliable problem solvers. ... Deep Space One had something Mars Polar Lander lacked: an onboard robot able to think autonomously and handle the unexpected. Using its engineering knowledge, the robot tried to repair the switch by toggling it on and off. When this failed, it devised a successful plan to complete the navigation maneuver, and the craft proceeded unharmed."

HAL Gets Straight A's. SpaceDaily (June 16, 1999). "As scientists and science fiction buffs alike have long suspected, artificial intelligence software can indeed operate a spacecraft millions of miles from Earth."

Who should explore space, man or machine? By Richard Stenger. CNN (February 19, 2003). "The loss of seven space shuttle astronauts this month again brought home the serious risk that humans face into the hostile environs beyond our sheltered planet, reviving the question of whether exploring the heavens should be left to unmanned missions." [Note: more articles about this topic can be found in our February 2003 news archive.]

Related Resources

"The eSTAR Project is a programme to build an intelligent robotic telescope network. It is a joint project between the Astrophysics Research Institute at Liverpool John Moores University and the Astrophysics Rearch Group of the School of Physics at the University of Exeter."

• "The eSTAR agent software is open-source, and the team hopes that other astronomers will be able to create their own agents to carry out their observational tasks." - from Autopilot Telescopes Ease Gazing. By Michelle Delio. Wired News (November 5, 2003).

FLAIRS-2001:The 14th International FLAIRS Conference. In cooperation with the Intelligent Systems Technical Committee of the The American Institute of Aeronautics and Astronautics Presents Special Track: Artificial Intelligence in Aerospace. Key West, FL May 21-23, 2001.

Los Alamos Thinking Telescope Project. "Humans simply do not have the attention span, memory, or reaction time required to recognize fast transients and rapidly respond. Autonomous robotic instrumentation with the ability to extract pertinent information from the data stream in real time will therefore be essential for recognizing transients and commanding rapid follow-up observations while the ephemeral behavior is still present. The development and integration of three technologies: (1) robotic telescope networks; (2) machine learning; and (3) advanced database technology, can enable the construction of smart robotic telescopes, which we loosely call 'thinking' telescopes, capable of mining the sky in real time."

• Meet RAPTOR, a component of the Thinking Telescope Project. "Scientific Goal: RAPTOR will detect celestial optical transients automatically and autonomously follow-up on them before they fade away."

NASA's Intelligent Systems Division: Technical Research Areas: Autonomous Systems and Robotics ... Collaborative & Assistant Systems ... Discovery and Systems Health ... Robust Software Engineering.

"NASA's Intelligent Systems Project supports research in intelligent, self-monitoring, adaptive, and usable systems. It will drive revolutionary advances in human+machine system intelligence for NASA's next century of aerospace science, exploration, and transportation."

• "The Automated Reasoning (AR) subproject of NASA's Intelligent Systems Project supports and manages research in technologies that make decisions with limited operator intervention."
• "The Human-Centered Computing (HCC) subproject of NASA's Intelligent Systems Project develops means of optimizing the performance of mixed human/automation systems. HCC research will enable development of adaptive systems that amplify human cognitive, perceptual, and motor capabilities -- in space, in mission control operations, and in air traffic management, safety, and security systems."
• "The Intelligent Data Understanding (IDU) subproject of NASA's Intelligent Systems Project develops techniques for transforming data into scientific understanding."

NASA Quest: "a rich resource for educators, kids and space enthusiasts who are interested in meeting and learning about NASA people and the national space program."

• Also be sure to check out these other educational resources from NASA.

Space Technology Hall of Fame, established by the Space Foundation in cooperation with NASA: "honoring those who quietly transform technology originally deveveloped for space exploration into products that help improve the quality of life here on Earth."

• Space Foundation press release (March 8, 2006): "The Space Foundation today announced that the iRobot PackBot Tactical Mobile Robot and Novariant AutoFarm RTK AutoSteer are the 2006 inductees into the prestigious Space Technology Hall of Fame."

Related AI Topics Pages

• Applications
• Autonomous Vehicles
• Robots
• Science Fiction

Other References Offline

Bonasso, R. Peter, David Kortenkamp, NASA Johnson Space Center, et al. 1997. Using a Robot Control Architecture to Automate Space Shuttle Operations. In Proceedings of the Ninth Annual Conference on Innovative applications of Artificial Intelligence, ed. Senator, Ted and Bruce Buchanan, 949-956. Menlo, CA: AAAI. This paper describes preliminary results from using an AI robot control software architecture, known as 3T, as the software framework for a procedure tracking system for the space shuttle Remote Manipulator System (RMS). The system, called 3TPT, is designed to track the expected steps of the crew as they carry out RMS operations, detecting malfunctions in the RMS system fro failures or improper configurations as well as improper or incomplete procedures by the crew.

Carlson, Shawn. Algorithm of the Gods. Scientific American, March 1997. "To find the one way of ordering the galaxies for a search that put the absolute least strain on the telescope, we would have had to check every possible ordering. Unfortunately, this job could not be accomplished even by all the world's supercomputers working day and night for sextillions of years.... Fortunately, computer scientists have devised an algorithm that can find such solutions to many seemingly impossible problems."

Chien, S., A. Govindjee, T. Estlin, et al. 1997. Automated Generation of Tracking Plans for a Network of Communications Antennas. In Proceedings of the Ninth Annual Conference on Innovative Applications of Artificial Intelligence, ed. Ted Senator and Bruce Buchanan, 963-970. Menlo Park, CA: AAAI. Describes the Deep Space Network Antenna Operations Planner (DPLAN): a system that automatically generates antenna tracking plans for a set of highly sensitive radio science and telecommunications antennas. A prototype of the DPLAN system was successfully demonstrated in February 1995 at NASA's experimental DSN station, DSS-13, on a series of Voyager tracks. Based on this successful demonstration, DPLAN will become operational as part of the arger Network Monitor and Control (NMC) upgrade underway projected to save NASA over $9 million per year in operations costs.

Loftin, R. Bowen, Lui Wang, Paul Baffes, et al. 1989. An Intelligent Training System for Space Shuttle Flight Controllers. In Proceedings of the First Annual Conference on Innovative Applications of Artificial Intelligence, ed. Schorr, Herbert and Alain Rappaport, 15-25. Menlo Park, CA: AAAI.

Miller, David P., Anne Wright, Randy Sargent, et al. 1997. Attitude and Position Control Using Real-Time Color Tracking. In Proceedings of the Ninth Annual Conference on Innovative Applications of Artificial Intelligence, ed. Senator, Ted and Bruce Buchanan, 1026-1031. Menlo Park, CA: AAAI. A variety of positioning methods and sensors have been developed over the years. Most methods rely on active sensors (such as sonars or lasers) which have range and power restrictions, or rely on computationally complex (and often slow) methods such as recovering positions from stereo or optical flow. This paper describes a system that can determine a robot's position and orientation, in all six degrees of freedom, relative to a simple passive target. The system can determine its position relative to the target from a single image frame, and process the image and calculate the position faster than a camera's frame rate (60Hz). It uses a standard, uncalibrated color video camera as its sensor. The system runs on an inexpensive microprocessor (a Motorola68332) leaving many cycles left over. By careful design of the target and the vision processing hardware and software, we are able to selectively perceive only the relevant parts of the target, simplifying and speeding necessary computations. The system is being developed for autonomous spacecraft station keeping and docking.

Muratore, John F., Roy A. Heindel, Terri B. Murphy, Arthur N. Rasmussen, and Robert Z. McFarland. 1989. Applications of Artificial Intelligence to Space Shuttle Mission Control. In Proceedings of the First Annual Conference on Innovative Applications of Artificial Intelligence, ed. Schorr, Herbert and Alain Rappaport. Menlo Park, CA: AAAI.

Quan, A.G., U.M. Schwuttke, J.S. Herstein, et al. 1995. Automated Consultation for the Diagnosis of Interplanetary Telecommunications. In Proceeding of the Seventh Innovative Applications of Artificial Intelligence Conference, 136-145. Menlo, CA: AAAI.

Schwuttke, U. M., A. G. Quan, R. Angelino, et al. 1992. Marvel: A Distributed Real-Time Monitoring and Analysis Application. In Proceedings of the Fourth Annual Conference on Innovative Applications of Artificial Intelligence, ed. Scott, A. Carlisle and Phillip Klahr, 89-106. Menlo Park, CA: AAAI.