A leading robotics competition held in June, several multi-million-dollar robots and even the simplest tasks, struggled to climb a flight of stairs; With impeccable comic timing, even what looks like some toppled over. But a few of these funny pratfalls robots' instruments, motors, and other components has resulted in catastrophic damage.
Fortunately, for klutzes robot, researchers are exploring ways to enable robots to fall more gracefully and safely. Robots are used in more complex environments, such as the important dynamic at work, and legs that move the wheels of the test engineers.
Georgia Tech researchers on the way down to an arm or a leg sticking out of the way to break a fall, take inspiration from. "When you fall down, you try to dissipate energy," Karen Liu, now works at Disney Research Pittsburgh Sehoon her graduate student Ha, a professor of computer science at Georgia Tech, who carried out the work. "Every time you make contact with the ground, some of the energy is dissipated."
Liu Ha unbalanced and that hits the ground with less force robot that can find its body to bend into a protocol that is planned. Fall algorithm calculates how to create the momentum necessary to disperse a number of points of contact with the ground.
A conference in Germany last month, Georgia Tech, a small robot that Bioloid GP pair tested the algorithm, and a large humanoid Atlas described simulations. The latter advanced on foot and is now owned by Google, which specializes in making machines for the company Boston Dynamics developed. Atlas robots are used in many teams that participated in the June events. In the event, DARPA Robotics Challenge, television operated robots, driving a golf cart on a series of doors opened, and perform a series of tasks, including operating a power drill that was bet.
DARPA's event, "Why robots and Humans- see (primarily a stricken nuclear plant when assisting a robot in the event of problems, to simulate the material, but this is no ordinary human context of work aimed robots remaining challenges highlighted DARPA 'The Challenge") battles.
Matt DeDonato, who led a team from Worcester Polytechnic Institute at the DARPA event, says that most participants were more focused on staying upright than working out better ways to fall, especially because each fall incurred a hefty time penalty.
To minimize damage, the Atlas robot operated by his team, in collaboration with researchers from CMU, would power down its actuators and go limp when it detected a fall.
But DeDonato, whose team managed to keep the robot upright throughout the DARPA event, says the area needs to be explored as more robots become commercialized. “You are guaranteed to fall over sometimes,” he says.
Marc Raibert, founder of Boston Dynamics, now part of Google, and a pioneer in legged robotics, says his team started thinking about how to protect a falling robot while developing a four-legged machine called BigDog.
The first idea was to have the limbs seize up when a fall was detected. “That caused the limbs to act as long levers that apply large forces to the joints when the limbs strike the ground,” he says. “We actually broke some legs clean off the robot, so we reprogrammed BigDog to relax its joints during a fall. All the robots we build now do something like that when they detect that they have lost their balance.”
Lui and his team if they fall into the ways in which robots have to avoid hurting the population is interested in passing. This is very unlikely to come to a person in a way that may be related to balance, he says.
The approach developed so far is limited, however, by the sensing capabilities and the computational power of most robots. For their experiments, the Georgia Tech team used an accelerometer in the head of the physical robot as well as external motion-capture cameras. Liu notes that the complexity of calculating how best to fall explains why so many animals, including humans, have a nervous system, which reacts automatically.
"We have the reflexes, that's why," says Liu. "We think of robots building something like a nervous system."
Post a Comment