Egang: Data Driver

On The Cover/Top Stories
Data Driver
09.04.06

Sebastian Thrun is very clear on the future. "Forty-two thousand people in the U.S. die in traffic accidents every year," he says. "Down the road, I know cars will drive themselves. It's just right!" Robots don't get drunk, fall asleep or talk on the phone. If we turn highways into "invisible rail systems," he says, we can combine the convenience of a car with the safety of a train.

This vision has been a futurist phantasm since the 1950s, but Thrun and a car named Stanley are bringing the age of the autoroad a bit closer. Stanley is a Volkswagen Touareg built by Thrun, 39, who teaches computer science at Stanford, and his graduate students. In October 2005 Stanley drove itself to a rookie victory in the Grand Challenge, a 131-mile race across the Mojave Desert. First prize: $2 million. Race sponsor, tellingly: the U.S. Department of Defense.

In the same race a year earlier none of the 15 robotic entrants even finished. Thrun entered the race last fall largely out of frustration at these results; he had just arrived at Stanford from Carnegie Mellon's Robotics Institute. Researchers there had spent years coming up with some of the fundamental principles for building robotic vehicles. Analyzing tons of data was key: They packed cars with ever more sensors to navigate the world around them.

But Thrun knew that sometimes the data points are simply wrong. He had built a robotic tour guide for the Smithsonian National Museum of American History in 1998, and the contraption got confused when people waved at it. Thrun taught his bots to stop trusting all data equally and instead assign some probability to its utility and accuracy.

"The robot has to figure out: Is this data a wall? Could it be a kid? Could it be a shadow or a trick?" Thrun says.

Stanley sports five global-positioning antennas, six Pentium M computers, five laser range finders and a video camera. To train Stanley's brains, Thrun and his crew drove it 1,000 miles over desert terrain to reveal what conditions drivers deem critical and what they ignore. A bad bump jostling Stanley's sensors might accidentally produce data indicating a wall ahead even if the road is clear. Stanley learned to downplay such data and stay attuned to more significant obstacles.

To win the race in October Stanley took six hours and 54 minutes; Carnegie Mellon's car needed another 11 minutes to finish. Best of all, Thrun says, 5 contestants finished (of 23 total). "We all won. The robotics community won." The next Grand Challenge is in November 2007, with a 60-mile romp through a city yet to be named. Contestants will have to avoid static obstacles and, most important, one another. Thrun will be ready with a new Volkswagen Passat. "To make robots really useful," he says, "they will have to deal with traffic."

http://www.forbes.com/free_forbes/2006/0904/102.html?boxes=custom

--##--

Sphere: Related Content

Egang: Emobots

On The Cover/Top Stories
Emobots
09.04.06

Caleb Chung wants pleo to perform. "Come on," he coaxes the rubbery toy dinosaur, stroking its nose. Pleo blinks its large eyes, stretches, wags its tail and totters a few steps--then yawns and curls up for a nap.

Life is exhausting when you're a prototype robotic toy, just months away from your debut. It's even more exhausting for principal inventor Chung, 49, and his three dozen colleagues at Ugobe Inc., who are trying to create a "designer life form," a creature that can elicit the same cooing and warm fuzzy feelings as a new puppy.

So far, so good. When Chung showed off Pleo earlier this year at a tech conference, 200 people sang "Happy Birthday" to the robot. Since then thousands have e-mailed Ugobe pleading to be among the first to pay $250 for a Pleo. They need patience: Pleo, first planned for the holidays, won't emerge until March.

Pleo is a technical marvel, but all the wizardry is invisible, designed to create a personality. Chung knows how to prompt feelings without using words. He was a street mime; he played an orangutan on TV; he taught himself to make mechanized puppets and toys. In the 1980s he made a playful dinosaur for Mattel, but the company nixed the idea as too expensive. Chung later cocreated Furby, the big-eared fuzz ball that sold 50 million units. He retired comfortably but hankered to build a robotic dino pet.

Working with a friend, Chung came up with software that animates a four-legged robot with balanced, smooth motions. Soon entrepreneur Robert Christopher signed up to be chief executive of a new company, which he named "Ugobe" (as in, "You go be what you want to be"). They have raised $2.7 million from investors so far and bank on getting another $8 million in September.

In Boise, Idaho Chung and a dozen collaborators have modeled Pleo after a plant-eating baby camarasaurus from the Jurassic period. Pleo has an operating system, a microcontroller, 14 motors (one for each joint) and 31 sensors to detect changes in light, sound and motion. Skin has slowed Pleo's arrival; Chung wants the rubbery material to fit snugly yet move naturally.

Pleo's coolest feature is software that lets it react to stimuli and its environment in a thousand different ways. Touching its head can startle a young Pleo, make an older Pleo wag its tail playfully--and annoy a hungry one. Owners will be able to download new behaviors from the Web or write their own code. Young Pleos might even pick up habits or catch a cold by hanging out with other Pleos, sharing data via infrared links. "Our job is to create a relationship between Pleo and a person," Chung says. "You'll interact with it, share an emotional language with it. Then you can play."

http://www.forbes.com/free_forbes/2006/0904/098.html?boxes=custom

--##--

Sphere: Related Content

Egang: Stickybot

On The Cover/Top Stories
The Stickybot
09.04.06

Cockroaches inspire Robert J. Full. So do crabs, geckos and a closetful of other creepy creatures. Not that he likes them. "I think they're disgusting!" says Full, a professor at UC, Berkeley. "But how do they move like they do?"

This biologist believes he can best nature. He has spent his life scrutinizing the ways many-legged animals scamper over bumpy terrain and scoot up a wall or even glass. Working with Mark Cutkosky of Stanford University and other mechanical engineers, Full designs robots that use these principles. "We don't want to copy nature," Full says. "That's a totally mistaken idea. Nature inspires us."

In April Full, 48, and Cutkosky, 49, unveiled their most recent bio-inspired robot, the two-foot long "Stickybot," which strides up a window much like a gecko but at 1.5 inches a second. "Everybody wants to know if Stickybot can do windows," Cutkosky says. "I just want robots that can look for cracks in the Bay Bridge."

Stickybot is the result of a decadelong collaboration between Full and Cutkosky. When they met, Full already was a leader in unraveling the principles of animal locomotion. He has measured the force of cockroaches' footsteps and the stiffness of their legs. (The legs of most creatures, insect or human, work like a pogo stick; the stiffness of the "spring"--the muscle--strongly influences their speed.)

"Cockroaches can run even faster by standing on their rear legs and running like bipeds." Full says.

Working with Irobot (see p. 94), Full developed a crablike machine that walks on land and underwater. With researchers at the University of Pennsylvania, he built a six-legged robot the size of a shoebox; it traverses rocky trails without tipping over. Pixar tapped Full for help in giving characters in A Bug's Life more personality through motion.

Cutkosky, meanwhile, had been making a name for himself by developing dexterous robotic hands. He became an expert in bonelike structures built by layering materials with different properties, a technique called shape-deposition manufacturing. Instead of making a robot's limbs with solid plastic, Cutkosky can make them, for instance, with an elastic core and a tough outer shell.

The duo has made various families of robots, each with their own talents. Some, inspired by cockroaches, sport six legs and can clamber over rocks. The speediest of these moves at 2.7 yards per second.

Getting robots to climb walls is a tougher challenge. "Even five years ago I would have had no clue how to build Stickybot," Cutkosky says. A dozen motors and embedded tendons made of fabric and cables let Stickybot maneuver each of its four legs and 16 toes independently.

Those toes are the real marvel. Geckos can cling to glass by a single toe because each has millions of fibers so tiny they stick to surfaces through weak molecular forces. Stickybot does the same, using hundreds of tiny tapered stalks measuring 10 microns (that's four ten-thousandths of an inch) at the tip. Because the tips are sharply angled, Stickybot's toes stick going in one direction and peel off easily when pulled the other way. Stickybot, funded in part by the Defense Advanced Research Projects Agency, could get stickier still. More sensors and motors would let it sense when it is about to fall off a wall or when it needs to rotate its feet, as geckos do, to climb down.

http://www.forbes.com/free_forbes/2006/0904/104.html?boxes=custom

--##--

Sphere: Related Content

Egang: The Robots Are Coming!

COVER: EGANG 2006
Magazine issue date: Sept. 4, 2006

The robots are on the move--leaping, scrambling, rolling, flying, climbing. They are figuring out how to get here on their own. They come to help us, protect us, amuse us--and some even do floors.

Since Czech playwright Karel Capek popularized the term ("robota" means "forced labor" in Czech) in 1921, we have imagined what robots could do. But reality fell short of our plans: Honda Motor trotted out its Asimo in 2000, but for now it's been relegated to temping as a receptionist at Honda and doing eight shows a week at Disneyland. The majority of the world's robots are bolted to a spot on a factory floor, sentenced to a repetitive choreography of welding, stamping and cutting.

No more. In our eighth annual E-Gang (our group of tech innovators to watch), we present the masters of robotic innovation--entrepreneurs and researchers who are fusing advances in biomechanics, software, sensor technology, materials science and computing to create new generations of robotic assistants.

Learning has been key, both for robots and for their designers. Carnegie Mellon's Robotics Institute has been an incubator for much of the current work on robots. Rodney Brooks of the Massachusetts Institute of Technology nudged the whole field forward in early 1990s when he showed how robots could make faster decisions by responding to sensory data from their immediate environment rather than relying on complex sets of rules.

The pioneers we've highlighted in this report work in diverse corners of the robotics arena. Some people have devoted their lives to developing robots, such as Colin Angle and Helen Greiner, who founded iRobot with their academic adviser, Rodney Brooks. In the medical world, Russell Taylor has contributed to innovations in surgical robots for decades.

Others are relative newcomers. Sebastian Thrun, from Stanford University, burst into the headlines last year by winning a U.S. Defense Department race of autonomous vehicles through the desert. But he brings with him the legacy of Carnegie Mellon. So, too, does Mark Cutkoski (also of Stanford), who collaborated with an insightful biologist, Robert Full of the University of California, Berkeley. Although Full did not set out to become a robotics expert, his basic research discoveries about how creatures--from cockroaches to people--move has become a cornerstone of much work.

Soren Lund at Lego is helping bring what was once considered esoteric engineering into the hands of enthusiasts everywhere in the world. Yoshiyuki Sankai, at the University of Tsukuba in Japan, proudly continues Japan's long tradition of innovative--and surprising--humanoid robots. And Caleb Chung and his colleagues at the startup UGobe remind us to celebrate the playfulness and creativity that has also been a hallmark of robotics over the years.

The market is still small: $6 billion a year for industrial robots, according to the International Federation of Robots.(That doesn't include the software, peripherals and systems needed to support robots. Add those elements in, and the value of the market jumps to $18 billion.) Data on the size of the nascent business of service robots--robots that clean or protect or entertain--are sketchier, but the growth predictions are dizzying: the IFR, in cooperation with the United Nations Economic Commission for Europe, expects to see 7 million service robots sold by 2008.

In the U.S., the Defense Department has been the big spender for robots, seeking machines that can protect soldiers' lives. But interest is simmering in the venture community--a signal that profits lie ahead. Big players are muscling in, too. In May, Microsoft announced that it had a new research program under way, aimed at developing an operating system and software development tools for robots.

Tandy Trower, general manager of Microsoft's robotics group, says robotics today reminds him of the early days of the PC--chock-full of ideas, opportunities and too many different operating systems.

Unlike PCs, however, robots are calling on the ingenuity of people from wildly diverse backgrounds: biologists are teaching robots to move, entertainers are teaching them how to amuse us, statisticians are teaching them when to ignore data, computer scientists are teaching them how to think, and materials scientists are inventing new composites that make them light on their feet.

Robots are about to be unshackled from forced labor. Expect them everywhere.

http://www.forbes.com/egang/2006/08/17/robot-egang-history_06egang_cz_ec_0817robotintro.html

--##--

Sphere: Related Content