INTRODUCTION TO INTELLIGENT ROBOTICS

WHAT ARE INTELLIGENT ROBOTS

In popular culture, the term ROBOT generally connotes some anthropomorphic (human
like) appearance. The tendency to think about robots as human like appearance may stem
from the origins of the term “ROBOT”. The word “ROBOT” came into the popular
consciousness on January25,1921,in PRAGUE with the first performance of KAREL
KAPEK’s play ,R.U.R(Rossum’s Universal Robots).In R.U.R,an unseen
inventor,Rossum,has created a race of workers made from a vat of biological parts, smart
enough to replace a human in any job.
The shift from human like mechanical creatures to whatever shape gets the job done is
due to reality .While robots are mechanical, they don’t have to be anthropomorphic or
even like animal .It should be made clear that appearance does not form a useful
definition of the robot .Therefore the definition arises is an intelligent robot is a
mechanical creature which can function autonomously.
Intelligent implies that robot does not do things in a mindless, repetitive way it is
opposite of the connotation from the factory automation.
The mechanical creature portion of the definition is an acknowledge of the fact that our
scientific technology uses mechanical building blocks, not Biological components. It also
emphasizes that a robot is not the same as a computer.
A robot may use a computer as building block, equivalent to a nervous system or brain,
but the robot is able to interact with its world move around, change it etc.

HISTORY OF ROBOTICS

In 1942, the United States embarked on a top secret project, called the Manhattan project
to build a nuclear bomb. The theory of nuclear bomb had existed for a number of years in
academic circles.
One of the first problem that the scientists and engineers encountered was handling and
Processing radioactive materials, including uranium and plutonium, in large quantities.
One of the first solutions was the GLOVE BOX .nuclear material was put in a glass box.
But this was not an acceptable solution.
Thus a force reflecting TELEMANIPULATOR, a sophisticated mechanical linkage
which translated motions on one hand of the mechanism to motions at the other hand.
A nuclear worker would insert their hands into the telemanipulator, and move it around
while watching a display of what the other end of the arm doing in the containment cell.
Telemanipulators are similar in principle to power gloves now used in computer games,
but much harder to use. The mechanical technology would not allow a perfect mapping
of hand and arm movement to the robot arm. Often the operator had to make the
awkward and non intuitive motions with their arms to get arms to get the robot arm to
perform a critical manipulation very much like working in front of a mirror .Likewise, the
telemanipulators had challenges in providing the force feedback so the operator could
feel that how hard gripper was holding an object. The lack of naturalness in controlling
the arm meant that even a simple task is going to consume a lot of time.
. Pioneer work done on this by NORBERT WIENER allowed engineers to accurately
control electrical and mechanical devices using the cybernetics.
The two most common types of robot technology that evolved for industrial use are robot
arms, called industrial manipulators, and mobile carts, called automated guided vehicles
(AGV).The control was assumed to be ballistic control, or open loop control. Automatic
guide vehicles or AGV are intended to the most flexible conveyor system possible, a
conveyor which doesn’t need a continuous belt or roller table. The industrial engineers
started working for a black factory. A black factory is a factory that has no lights turned
on because there are no workers. Computers and robots were expected to allow complete
automation of manufacturing process.
In space robotics Artificial intelligence plays a much important role. Instead of sending
men in space planetary rovers were the best possible solution to replace the astronaut .So
need of autonomous rovers arose .These automated planetary rovers would ideally have a
high degree of autonomy ,much like a trained dog. The robot would receive the
commands from earth to explore particular region. It would navigate around boulders and
would not fall into canyons and traverse steep slopes without rolling over .The robot
might even be smart enough to regulate its own energy supply ,for example by making
sure it was sheltered during the planetary nights and to stop what it was doing and
position itself for recharging its solar batteries. Study of the impact of uncertain and
incomplete information on a rover was also to be done .If the robot was moving based
on the map taken from the telescope or an overhead command module ,the map could
still contain the errors or at the wrong resolution to see certain dangers. In order to
navigate successfully ,the robot has to compute its path with the new data or risk
colliding with the rock or falling into the hole. What if the robot did something broke
totally unexpected or all the assumptions about planet were wrong ? The robot should be
able to diagnose the problem and attempt to continue to make progress over its task. Thus
a lot of research over the algorithms was to be done to make the robots work according
to the human need. Clearly ,developing a planetary rover and other robots for space
which could replace astronaut and also to assist him was going to require a concentrated
and long term-effect.

WORK OVER ROBOTICS

WHAT ARE ROBOTIC PARADIGMS?

A paradigm is a philosophy or set of assumptions and or techniques which characterize

an approach to a class of problems.
There are currently three paradigms for organizing intelligence in robots, hierarchical,
reactive, and hybrid deliberative/reactive. The paradigms are described in two ways.
1.By the relationship between the three commonly accepted primitives of robotics :
SENSE, PLAN, ACT.
If function is taking in information from the robot’s sensors and producing an output
useful by other functions, then the function lies in the SENSE category.
If function is taking in information either from sensors or its own knowledge and
producing one or more tasks for the robot to perform, that is the PLAN category.
Functions which produce output commands to motor actuators fall into ACT (turn 123
degree, clockwise).
By the way sensory data is processed and distributed through the system.
How much aperson or robot or animal is influenced by what senses. So it is often difficult
To adequately describe a paradigm with just a box labeled SENSE. In some paradigms,
sensor information is restricted to being used is a specific, or dedicated, way for each
function of a robot in that case processing is local to each function. Other paradigms
expect all sensor information to be first processed into one global world model and then
subsets of the model distributed to the other functions as needed.

THREE PARADIGMS OF ROBOTICS

THE HIERARCHICAL PARADIGM: it is the oldest paradigm and was prevalent

from1967-1990.Under it, the robot operates in atop down fashion, heavy on planning. this
was based on an introspective view of how people think.
For ex: A person wants to reach the door for him it is not the matter of planning and he
will be doing it very normally i.e. there will not be a correct assessment of a thought
process. Under the Hierarchical Paradigm, the robot senses the world, plans the next
action and then acts(SENSE,PLAN,ACT).Then it sense the world, plans acts. At each
step robot explicitly plans the next move. The other distinguished feature of the
HIERARCHICALPARADIGM is that all the sensing data tends to be gathered into one
global world model, a single representation that the planner can use and can be routed to
the actions. Constructing generic global world models turns out to be very hard and
brittle due to the frame problem and the need for a closed world assumption.
THE REACTIVE PARADIGM: It was a reaction to the Hierarchical Paradigm and led to
exciting advances in robotics. It was heavily used in robotics starting in 1988 and
continuing through 1992. It is still used but since 1992 there has been a tendency towards
the hybrid architectures. The reactive paradigm was made possible out of two trends.
One was a popular movement among AI researchers to investigate biology and cognitive
psychology in order to living examples of intelligence. Another was rapidly decreasing
cost of computer hardware coupled with the increase in computing power. As a result,
researchers could emulate frog and insect behavior with robots costing less $500 versus
the $100,000s shakey, the first mobile robot, cost.
The reactive paradigm through out planning all together. It is a SENSE-ACT(S-A) type
organization. Whereas hierarchical paradigm assumes the input to an ACT will always be
the result of a PLAN the reactive paradigm assumes that the input to an ACT will always
be the direct output of a sensor, SENSE.
The robot has multiple instances of SENSE-ACT COUPLINGS. These couplings are
concurrent processes called behaviors which take local sensing data and compute the best
action to take independently of what the other processing are doing.
One behavior can direct the robot to” move forward 15 meters”(ACT on drive motors) to
reach the goal(SENSE the goal) while another behavior can say “turn 90 degree” (ACT
on steer motors) to avoid a collision with an object dead ahead (SENSE obstacles).The
robot will do a combination of both the behaviors, swerving off course temporarily at a
45 degree to avoid the collision .
While the reactive paradigms produced exciting results and clever robot insect
demonstrations, it became clear that throwing away planning was too extreme for general
purpose robots.
HYBRID DELIBERATIVE PARADIGM: The reactive paradigm serves the basis for the
HYBRID DELIBERATIVE /REACTIVE PARADIGM.
The hybrid paradigm emerged in 1990 and continues to be the current area of research.
Under the hybrid paradigm the robot first plans (deliberates)how to best decompose a
task into subtasks (also called “mission planning”) and what are the suitable behaviors to
accomplish each subtask etc.
Then the behavior starts executing as per the Reactive Paradigm. This type of
organization is PLAN, SENSE-ACT (P, S-A), Planning is done at one step and then
sensing and acting is done together. Sensing organization in the hybrid paradigm is also
A mixture of hierarchical and reactive styles sensor data gets routed to each behavior that
needs that sensor, but is also available to the planner for construction of a task oriented
global world model. The planner may also “eavesdrop” on the sensing done by each
behavior identifies obstacles that could than be put into a map of the world by the
planner each function performs computations at its own rate deliberative planning , which
is generally computationally expensive may update every five seconds ,while the reactive
behaviors often execute at 1/60 second. Many robots run at 80 cm/sec.

ARCHITECTURE PRINCIPLE

Since a major objective in robotics is to learn how to build them, an important skill to
develop is evaluating whether or not a previously developed architecture (or large chunks
of it) will suit the current application. This skill will save both times spent on reinventing
the wheel and avoid subtle problems that other people have encountered and solved
.evaluation requires a set of criteria. The set that will be used in this book is adapted from
behavior based robotics.

1. SUPPORT FOR MODULARITY: does it show good software engineering principles?

2. NICHE TARGETABILITY: how well does it work for the intended application?
3. EASE OF PORTABILITY TO OTHER DOMAINS: how well would it work for other
applications or other robots.
4. ROBUSTNESS: where is the system vulnerable, and how does it try to reduce the
vulnerability?
DESCRIPTION ABOUT VARIOUS ROBOTS USED FOR RESEARCH AND
EXPLORATION PURPOSES:

GENGHIS, legged robot was built by Colin Angle, IS ROBOTICS which imitates an
insect.The fundamentals over which it was based are reflexive behavior, stimulus
response, and reactive behavior.
BEHAVIOR
SENSOR INPUT PATTERN OF MOTOR ACTION

POLLY: Ian Horswill designed the software and camera system for POLLY specifically
to explore vision and the relationship to the environment using subsumption .this
approach is called LIGHTWEIGHT VISION.
POLLY, VISUALLY GUIDED ROBOT USED BLACK AND WHITE CAMERA.

SNAKE: one of the biggest changes in robotic platforms is the recent move towards
polymorphism, literally shape-shifting robots. Snake like robots constitute an important
class of shape shifters. these robots have high number of joints and are difficult to
control.
INKTUN VGTV is also an example of polymorphic tracked vehicle.
KISMET: An example of the research over the physically expressive interface, where the
robot literally has a face and changes expresses with mood.
HUMANOID ROBOT: The hardest form of a mobile robotis humanoid robot. The two
factors on which Humanoid Robot is based are intelligence and mobility.

IMAGES FROM MARS SPIRIT ASTEROID

A NAVIGATION INTO THE HARDWARE DESIGNING OF ROBOTS:

General Circuit
Pinout
 RESEARCH AND NAVIGATION

The Mars Pathfinder

Sojo
urner Rover, a lightweight machine on wheels, accomplished a revolutionary feat on
the surface of Mars. For the first time, a thinking robot equipped with sophisticated laser
eyes and automated programming reacted to unplanned events on the surface of another
planet. After a few days on the Martian surface the NASA controllers turned on
Sojourner's hazard avoidance system and asked it to start making some of its own
decisions. This hazard avoidance system set the rover apart from all other machines that
have explored space. Sojourner made trips between designated points without the benefit
of detailed information to warn it of obstacles along the way Sojourner moved slowly at
one and one half feet per minute and stopped a lot along the way to sense the terrain and
process information, but there was no hurry on Mars which is not visited very often.
Sojourner was carried to Mars by Pathfinder which launched on December 4, 1996 and
reached Mars on July 4, 1997, directly entering the planet's atmosphere and bouncing on
inflated airbags. Sojourner was designed by a large NASA team lead by Jacob Matijevic
and Donna Shirley. Sojouner traveled a total of about 100 meters (328 feet) in 230
commanded maneuvers, performed more than 16 chemical analyses of rocks and soil,
carried out soil mechanics and technology experiments, and explored about 250 square
meters (2691 square feet) of the Martian surface. During the mission, the spacecraft
relayed an unprecedented 2.3 gigabits of data, including 16,500 images from the lander's
camera, 550 images from the rover camera, 16 chemical analyses of rocks and soil, and
8.5 million measurements of atmospheric pressure, temperature and wind. The flight
team lost communication with the Sojouner September 27, after 83 days of daily
commanding and data return. In all, the small 10.5 kilogram (23 lb) Sojouner operated 12
times its expected lifetime of seven days. Mars Pathfinder Sojourner Rover .Sojourner
weighed only 23 pounds, and explored about 250 square meters of Martian surface.
Sojourner collected 16,500 images from the lander's camera. Today Sojourner sleeps on
the surface of Mars, waiting to be retrieved someday.
 Asteroid 37452 Spirit .The asteroid Spirit travels in a path that is tilted 8 degrees from
the plane of the solar system.
Though they've never seen an asteroid, NASA's two robotic geologists have contributed
so much to planetary exploration during their journeys across Mars that two asteroids
have now been named after them. The rovers are the first planetary missions to be so
honored.
The asteroids, named Spirit and Opportunity after NASA's Mars Exploration Rovers,
were discovered on Sept. 24, 1960 by Ingrid van Houten-Groeneveld, Cees J. van
Houten, and Tom Gehrels. The trio spotted the moving masses of rock on photographic
plates of the night sky taken with telescopes at Caltech's Palomar Observatory.
Both rovers have now been exploring Mars for almost three times as long as originally
expected.

Thousands of Years of Immortality

It took more than 40 years to name the asteroids Spirit and Opportunity because both are
quite faint. International Astronomical Union rules require asteroids to be observed
during four separate cycles around the Earth and sun before they become eligible for
numbering and naming. The more observations, the more precisely scientists can
calculate the orbit.
Spirit has a diameter of 4 kilometers to 9 kilometers (2.5 miles to 5.6 miles) and
Opportunity has a diameter of 3 kilometers to 7 kilometers (1.9 miles to 4.4 miles).
Van Houten-Groeneveld, who lives in the Netherlands, proposed the name recently after
the asteroids were assigned an official number in 2002.

Both asteroids take 7.9 years to complete one orbit around the sun between Mars and the
mammoth gaseous planet Jupiter. Neither follows a path that crosses the orbit of other
planets and neither will be knocked out of orbit by the immense gravitational force of
Jupiter. They belong to a small group of asteroids known as the Hilda group that have a
3:2 orbital resonance with Jupiter. This means that each time Jupiter completes two orbits
around the sun, the asteroids complete three.
The honor renders the two Mars rovers immortal in the sense that the asteroids are in
stable orbits that will last for thousands of years.

Robots Walk With Close-to-human Efficiency

WASHINGTON, D.C. -- Robots that walk like human beings are common in science
fiction but not so easy to make in real life. The most famous current example, the Honda
Asimo, moves smoothly but on large, flat feet. And compared with a person, it consumes
much more energy.
Three powered walking robots: (a) The Cornell biped (b) The Delft biped (c) The MIT
learning biped.
Purdue University is leading a four-year project to enable humanoid robots to move
more like people and adapt quickly to new situations so that they can complete a variety
of tasks they weren't .
Berkeley Researchers Developing Robotic Exoskeleton That Can Enhance Human
Strength And Endurance .The mere thought of hauling a 70-pound pack across miles of
rugged terrain or up 50 flights of stairs is enough to evoke a grimace in even the burliest
individuals.
But researchers at Cornell University, the Massachusetts Institute of Technology (MIT)
and Holland's Delft University of Technology have built robots that seem to more closely
mimic the human gait -- and the Cornell robot matches human efficiency. The
researchers' inspiration: simple walking toys that fascinated children in the 19th century.
The Cornell robot consumes an amount of energy per unit weight and distance
comparable to a human walker. In contrast, they estimate that the Honda Asimo uses at
least 10 times as much energy as a human. The MIT and Delft robots, though not built
deliberately to be energy-efficient, also use much less energy than the Asimo. More
important, the researchers say, is that their robots provide a more realistic model of how
humans walk.
Cornell's robot equals human efficiency, because it uses energy only to push off, while
other robots needlessly use energy to absorb work, for example in moving the limbs
forward more slowly than they would naturally swing under gravity power. "In other
robots the motors are fighting themselves”.
Researchers at each of the three universities have built walking robots, differing slightly
but based on the same principle. They are an extension of several years of research into
"passive-dynamic walkers" that walk down a shallow slope, very much like simple
walking toys that have been around since the 1800s and developed more scientifically
starting in 1988. These downhill walkers were developed further in Ruina's lab, leading
to a two-legged version with articulated knees built by Wisse during a visit to Cornell.
Collins further refined that and then built the first Cornell powered model, while Wisse
returned to Delft and developed other unpowered and powered robots.
For the robots being described in Science , the researchers at all three institutions have
simply substituted small motors for gravity power. The research followed the example of
the Wright Brothers, who carefully researched gliders, then simply added a motor to
achieve powered flight.
The robot work was done primarily to study the biomechanics of human locomotion, but
it could have applications in practical robotics. Collins, now at the University of
Michigan, already is applying some of what he has learned to the design of a powered
prosthetic foot for amputees. "It's not exactly the same thing, but certainly the mode of
thought comes from thinking about robots". Information gained from studying walking
robots should be of use to the rehabilitation community.. The researchers note in their
Science paper that gravity-powered walkers have been considered irrelevant to human
walking by some because humans don't always walk downhill, but that these new
machines demonstrate that there is nothing special about gravity as a power source.
Gravity-powered walking toys work by swaying from side to side, allowing first one foot
and then the other to swing forward. Human beings minimize the swaying and bend their
knees to allow the moving foot to clear the ground, and two of the three new robots do
the same. All three robots have arms synchronized to swing with the opposite leg for
balance.
The Cornell robot supplies power to the ankles to push off. When the forward foot hits
the ground, a simple microchip controller tells the rear foot to push off. During the
forward swing of each leg a small motor stretches a spring, which is finally released to
provide the push.
The Delft robot uses a pneumatic push at the hip, and the MIT robot uses electric motors
that directly move the ankle. Control programs in the Cornell and Delft robots are
extremely simple, while the MIT robot uses a learning program that allows the robot to
teach itself to walk, which it can do in about 600 steps.

The fact these robots can walk with a humanlike gait with very simple control programs
"suggests that steady-state human walking might require only simple control as well”.
“The success of human mimicry demonstrated here … strongly suggests an intimate
relationship between body architecture and control in human walking."

SUGGESTIONS AND CONCLUSIONS

Scientists believe that computers might become powerful enough to understand human
speech and duplicate human reasoning.
This in turn suggests that computers might mimic the capabilities of animals and human
sufficiently.
The planetary survives for long periods with only simple instructions from earth.
The space program has been developing new intelligence through robots.
NASA also introduces the notion that AI ROBOTS would of course be mobile, rather
than strapped to a factory floor, and would have to integrate all forms of AI
(UNDERSTANDING SPEECH,PLANNING,REASONING,REPRESENTING THE
WORLD,LEARNING) into one program –a daunting task which is to be accomplished.