If there are bowling-ball size satellites flying in formation inside the International Space Station, where's Luke Skywalker? What may sound like a scene straight from a "Star Wars" movie is actually an experiment that will test how well spacecraft can fly in formation and then rendezvous and dock without the aid of a human pilot. Image to right: Expedition 8 Commander Michael Foale holds the SPHERES Beacon / Beacon Tester. Credit: NASA Astronaut Jeff Williams won't need the Force or a lightsaber May 18 when he unveils the first of three free-flying nano-satellites and releases it for a test flight inside the U.S. Destiny Lab. Developing autonomous formation flying and docking control algorithms is an important step in making future space missions possible.

NASA Develops Robust Artificial Intelligence for Planetary Rovers 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. Scientists at NASA Ames Research Center, in the heart of California's Silicon Valley, are developing very complex AI software that enables a higher level of robotic intelligence. In the past, very simple artificial intelligence systems on board rovers allowed them to make some simple decisions, but much smarter AI will enable these mobile robots to make many decisions now made by mission controllers. Image left: Future robotic rovers will have enough intelligence to navigate the martian landscape without detailed instructions from scientists on Earth. "Human beings make decisions in response to their environment. How do you encapsulate this behavior into a rover, or a robot, sitting on a planet millions of miles away? That's what we are working on," said Kanna Rajan, a computer scientist at NASA Ames.

When Paul Selmer lost his right leg below the knee in a hunting accident, a doctor fitted him with a standard prosthesis that required a waist belt to swing the wooden foot with each step. Selmer remembers it feeling like a "sandbag." That was 28 years ago. The gallery owner and small-aircraft pilot is now a devotee of a high-tech device called a PROPRIO foot, which utilizes sensors, artificial intelligence and microprocessors. "I marvel at how far we've come and how far we can go," said Selmer, who was unable to fly newer planes until discovering the PROPRIO.

The past few years have shown that U.S. government intelligence goes only so far. One of the biggest challenges is recognizing vital information in foreign languages -- and acting quickly on it. That's why the military would love software that can listen to TV broadcasts or phone conversations and read Web sites in Arabic and Chinese, translate them into English and summarize the key elements for humans. But each of those steps has long bedeviled computer scientists. Perfecting them and combining them -- well, that is "DARPA hard."

The real-life equivalent of Isaac Asimov's Three Laws of Robotics (which posits that robots may not harm humans, even if they are instructed to do so) is, like killer-robot technology itself, a ways off. In April, the United Nations released a report (PDF) that recommended suspending the development of autonomous weapons until their function and application is discussed more thoroughly. Last December, the Department of Defense issued a directive on weapon systems autonomy, calling for the establishment of "guidelines designed to minimize the probability and consequences of failures in autonomous and semi-autonomous weapon systems that could lead to unintended engagements." Though the Pentagon document stresses the need for human supervision of military robots, critics claim it leaves the door open for the development of autonomous lethal robots that aren't accountable to meaningful human oversight. "We already don't understand Microsoft Windows; we're certainly not going to understand something as complex as a humanlike intelligence," says Mark Gubrud, a research associate working on robotic and space weapons arms control at Princeton.

Chinese restaurant Two Panda Deli in Pasadena, California, recruited a pair of Japanese robot waiters, Tanbo R-1 and Tanbo R-2 (for $20,000 each), to deliver Chow mein to customers and bust out disco moves. Police radio interference compelled them to splatter orange chicken and whirl furiously around in circles. Complex customer requests were also often met with the terse reply: "That's not my problem." In The Terminator, Arnold Schwarzenegger stars as a cyborg killing machine from the future programmed to go back in time, find, and kill Sarah Conner in 1984 Los Angeles.

Google plans to begin testing its new prototype of a self-driving car -- which, unlike earlier models, the company hopes to operate without a backup driver -- at NASA's Ames Research Center on the grounds of Moffett Field, just a few miles from the tech company's headquarters, space agency officials said this week. Because Moffett is federal property, Google cars can drive the network of streets that crisscross the sprawling, 2,000-acre research facility without worrying about California regulations that say a human operator must be able to take control of self-driving vehicles during testing on public roads. Testing of cars without drivers could begin at Moffett early next year, according to a statement from Ames Associate Director Deborah Feng. NASA is working with Google on the project and hopes to gain useful information for its own efforts to develop unmanned drones and air traffic management systems. The Google cars are one of several projects run by the company's secretive X division, overseen by co-founder Sergey Brin. He and Google CEO Larry Page have said computer-driven cars may someday eliminate countless traffic injuries and deaths caused by human error, while also saving time, money and land devoted to parking, since they could drop off passengers and return later to pick them up.

Today: Google strikes deal with Johnson & Johnson to make robots that can assist surgeons, launching a new challenge to Sunnyvale's Intuitive Surgical. Also: Intel, Altera soar after reports of merger. Google's newest push into health care technology involves surgical robots, a partnership with a pharmaceutical giant and competition with one of Silicon Valley's largest medical-device companies. Google and a Johnson & Johnson unit announced Friday that they will be working together to make robots that can assist in surgeries, a strategic collaboration with no price tag announced. The aim of the project appears to be similar to the da Vinci robots manufactured and sold by Sunnyvale's Intuitive Surgical, the third largest public Silicon Valley company in the biotech/health care sector.

Riverain Technologies has received regulatory approval for the next-generation version of its imaging software that "suppresses" bones to help radiologists detect cancerous lung nodules. OnGuard 5.2, the latest version of the software, uses pattern recognition and machine learning technologies to essentially allow radiologists to see behind ribs and clavicles that often obscure lung abnormalities. OnGuard also circles areas that may be a lung tumor, according to the Dayton, Ohio-area company. The software's aim is to help clinicians reading chest X-rays get better views of pulmonary nodules -- spots on the lungs that can be a form of early stage cancer, but can also be benign. The new version of the software offers greater sensitivity, meaning it can better detect nodules, and better specificity, meaning it yields fewer false positives, said Steve Worrell, Riverain's chief technology officer.

This ScienceLives article was provided to LiveScience in partnership with the National Science Foundation. Nancy J. Nersessian's research is driven by the question "How do scientists think?" Nersessian's research focuses on how the cognitive and learning practices of scientists and engineers lead to creative and innovative outcomes. She is a Regents' Professor of Cognitive Science at the Georgia Institute of Technology with joint appointments in the Ivan Allen College of Liberal Arts School of Public Policy and the College of Computing School of Interactive Computing. Her research supports the insight that scientists think not only with ideas, but also with the artifacts they create to investigate nature.