Search

More new humanoid applications of robots

“Honda has marched to the forefront of robotics with the world’s first two-legged robot capable of dynamic walking. Honda is designing ASIMO [Advanced Step in Innovative MObility] to play various challenging roles in our society. Extraordinary hurdles in artificial intelligence have already been overcome to expand ASIMO’s capabilities. Now ASIMO is able to recognize human gestures and postures, as well as ambient surroundings, and even has the ability to take independent action based on self-acquired information,” according to a statement made by Honda.

The Honda presentation goes on to say that, “ASIMO sees you and remembers your face. It maneuvers adroitly around people and objects. The robot also hears you and responds obediently; and when ASIMO talks, you’re hearing a friendly voice that has captured hearts around the world.”

People keep finding new uses for robots. Think about how robots solder tiny wires to semiconductor chips and “pick and place” robots insert integrated circuits onto printed circuit boards used in all kinds of electronics. Robots also make and package drugs, textiles, and foods. Certain dangerous jobs are best done by robots. Guided remotely using video cameras, there are mini-androids that investigate and defuse bombs.

In fact, there are Mini-Andros that are used by bomb squads across the country to locate and dispose of bombs. About three feet long, the Mini-Andros look something like small armored tanks with eight wheels on four “legs” that extend for climbing stairs. Their movable arms can lift objects weighing up to 15 pounds and place them in bomb-proof boxes. Detachable accessories let the Mini-Andros break windows, see in the dark, and defuse or detonate bombs directly, either by blasting them with water, firing at them with a shotgun, or placing other smaller bombs nearby.

Robots can also go into dangerously polluted environments, like chemical spills or radioactive “hot zones” in nuclear power plants. Some spider-like robots are designed to explore areas with extreme radiation that would kill a human. The need for such a robot was made clear during the Chernobyl nuclear reactor accident in 1986. An explosion and fire released dangerous radioactive material into the air which made rescue and containment work nearly impossible.

Some robots “see” using ultrasonic sound, much the same way bats do. These robots typically emit 40 kilohertz sound waves (too high for humans to hear), then detect the echoes. Measuring the time delay from when the sound pulse goes out and then when it returns gives an accurate measure of the distance to an object and this navigation technique even functions in the dark. Touch sensors also help otherwise blind robots navigate. Feelers, contact switches and bump sensors let a robot know when it has made contact with walls or objects. Piezoelectric material is often used in touch sensors because such crystals respond to pressure with a small electric voltage. They can detect vibration, impact, and even heat.

Position sensors make it possible to teach a robot to do something (like spray-paint a car) by leading it through the motions. Sensors on the robot’s joints save information about the changing series of positions. The robot “remembers” this information and repeats the motions exactly. Sensors for radio signals and electric and magnetic fields are especially useful in robotics. Radio signals let robots communicate with each other from distances. Robotic lawnmowers use electromagnetic sensors to stay within the bounds of the yard.

Smell and taste in robots are not yet as refined as that of humans, nor do they need to be. Robotic sensors can detect specific gases including gases that humans can not smell. One of the most important uses of smelling robots is in airports, detecting fumes from explosives hidden in luggage and shoes.

Can robots talk?

Speech recognition systems have come a long way in the last decade. There are already systems that let you “type” into a computer with your voice and some telephone menus use speech recognition systems to let you make your selections verbally.

Processing language is complicated, however, thanks to the different accents and cadences people speak with, and the fact that many words and word fragments sound alike. Think about such words as “there, their,” and “they’re,” or how some accents can change the pronunciation of a word entirely. That’s why—at least for now—speech recognition systems work best when the vocabulary is limited to a few set commands.

Having a robot “talk back” is much simpler; voice synthesizers that convert text into speech only need a programmed list of pronunciation rules to speak intelligibly.

The road to universal robots

Research scientist Hans Moravec sees a four-stage evolution towards universal robots—robots with human-level intelligence flexible enough to do a broad range of tasks. Key to this evolution is a steady increase in computer power, defined in terms of millions of instructions per second, or MIPS.

Moravec describes computer intelligence in terms of animal intelligence. For example, a typical home computer has 1000 MIPS of power, about the brain power equivalent of an insect. Among Moravec’s predictions, outlined below, is that robots will achieve human-level intelligence (100,000,000 MIPS) in 2040.


Year: 2010

Processing power: 3,000 MIPS

Intelligence equivalent: lizard

Robots will have basic navigation skills and could be used for cleaning or delivery and take on expanded roles in factories.

Year: 2020

Processing power: 100,000 MIPS
Intelligence equivalent: mouse

Robots will be able to learn on the job, adapting their own programs to perform more successfully. Robots will do the same jobs as before, but more reliably and flexibly.

Year: 2030

Processing power: 3,000,000 MIPS

Intelligence equivalent: monkey

Robots will demonstrate world modeling: a general understanding of objects and what they are for, and of living things and how to interact with them. For example, a robot will “know” what an egg is and know that it must be picked up gently. Simulations will allow robots to practice and perfect new tasks before attempting them. Robot servants will be able to “read” the moods of the people around them.

Year: 2040

Processing power: 100,000,000 MIPS

Intelligence equivalent: human

Robots will be able to speak and understand speech, think creatively, and anticipate the results of their actions far in advance. With reasoning power at or beyond the human level, robots will be generally as competent as people.

“Robomenagerie,” vanguard of biomimetics, a strange field in which scientists reverse-engineer nature's greatest accomplishments

The idea is to copy Mother Nature’s tricks—things like a lobster’s ability to navigate pounding surf or a bat’s sonar that allows it to find mosquitoes in the dark. There is a trend for engineers and researchers to move in the direction of microrobotics; in other words, the idea is to use many little robots to do the work of one big robot or even a human. Military agencies like the idea of sending robobeasts to do things far too dangerouis for humans; such tasks as, clearing land mines or inspecting nuclear reactors in submarines.

The best example of the microrobotic trend is seen in NASA, which has embraced the “smaller, faster, cheaper” philosophy of sending lots of little space probes to do the work of one big space probe.

Some examples of microrobotic creatures are the following: robofly, robolobster (being built at Northeastern University), and robopike (which swims in a tank at the Massachusetts Institute of Technology). Robofly is envisioned as having a body made of paper-thin stainless steel and its wings of Mylar, which looks and feels a lot like Saran Wrap. Robofly is scheduled to be powered by the sun, and a tiny device called a piezoelectric actuator that will flap its four puny wings. One of robofly’s missions will be to fly through the rubble of an earthquake searching for survivors or even being a spy to keep tabs on terrorists or wandering spouses.

“Robotics,” another word that enriches our language

The term “robotics” refers to the study and use of robots. The term was coined and first used by the Russian-born American scientist and writer Isaac Asimov (born January 2, 1920, died Aprril 6, 1992). Asimov wrote prodigiously on a wide variety of subjects. He was best known for his many works of science fiction. The most famous include I Robot, (1950); The Foundation Trilogy, (1951-52); Foundation’s Edge, (1982); and The Gods Themselves, (1972).

Asimov first used the word robotics in Runaround, a short story published in 1942. I, Robot, a collection of several of these stories, was published in 1950. Asimov also proposed his three “Laws of Robotics”, and he later added a “zeroth law”.

Law Zero: A robot may not injure humanity, or, through inaction, allow humanity to come to harm.

Law One: A robot may not injure a human being, or, through inaction, allow a human being to come to harm, unless this would violate a higher order law.

Law Two: A robot must obey orders given it by human beings, except where such orders would conflict with a higher order law.

Law Three: A robot must protect its own existence as long as such protection does not conflict with a higher order law.

Robotics is now defined as a branch of engineering that involves the conception, design, manufacture, and operation of robots. This field overlaps with electronics, computer science, artificial intelligence, mechatronics, nanotechnology, and bioengineering.

Back to part 2 of robots                 Take me to part 4 of robots
if (isMyPost) { }