KHWAJA NAVED EC-0842231409 Introduction to Robotics
Definition of a Robot
Definition of a Robot According to The Robot Institute of America (1979) : "A reprogrammable, multifunctional manipulator designed to move materials, parts, tools, or specialized devices through various programmed motions for the performance of a variety of tasks."
According to the Webster dictionary: "An automatic device that performs functions normally ascribed to humans or a machine in the form of a human (Webster, 1993)."
A Brief History of Robotics
Robotics' history is tied to so many other technological advances that today seem so trivial, we don't even think of them as robots.
How did a remote-controlled boat lead to autonomous metal puppies?
Croatian-American scientist Nikola Tesla.
Invented many things, including the alternating current system.
Remote-controlled, submersible boat was acting on radio signals.
Slaves of steel
The first person to use the word robot was a playwright, Czechoslovakian writer Karel Capek first used the word robot in his satirical play, R.U.R. (Rossum's Universal Robots).
Cover page of the first edition
World War II was a big catalyst in the development of two important robot components: artificial sensing and autonomous control.
The U.S. military created auto-control systems for mine detectors that would sit in front of a tank as it crossed enemy lines
The Germans developed guided robotic bombs that were capable of correcting their trajectory.
German robot bomb found in France
A robot in every pot
The invention of the transistor in 1948 increased the rate of electronic growth and the possibilities seemed endless.
The creation of silicon microchips reinforced that growth.
The seven-foot robot could smoke and play the piano.
Elecktro:The smoking robot
1961 General Motors installed the applied telecherics system on their assembly line. The one-armed robot unloaded die casts, cooled components and delivered them to a trim press.
In 1978 the PUMA (Programmable Universal Machine for Assembly) was introduced and quickly became the standard for commercial telecherics.
PUMA industrial robot
Early personal robots RB5X Hero 1
In 1985 Dr. Yik San Kwoh invented the robot-software interface used in the first robot-aided surgery, a stereo tactic procedure.
The surgery involves a small probe that travels into the skull.
A CT scanner is used to give a 3D picture of the brain, so that the robot can plot the best path to the tumor.
Dr. Yik San Kwoh with surgical robot
Dante II aids in the dangerous recovery of volcanic gases and samples.
These robotic arms with wheels saved countless lives defusing bombs and investigating nuclear accident sites.
Telecheric robot inspects suspicious package
Mark Tilden's BEAM robots look and act like big bugs.
Tilden builds simple robots out of discrete components and shies away from the integrated circuits most other robots use for intelligence.
Started in the early 1990s, the idea was to create inexpensive, solar-powered robots ideal for dangerous missions such as landmine detection.
A range of rovers
Sojourner, semi-autonomous robot platforms to be launched into Mars in 1996.
The problem was, it could only travel short distances.
In 2004, twin robot rovers caught the public's imagination again, sending back amazing images in journeys of kilometers, not meters.
In the late '90s there was a return to consumer-oriented robots.
One of the real robotic wonders of the late '90s was AIBO the robotic dog, made by Sony Corp.
By using sensor array, AIBO can autonomously navigate a room and play ball.
AIBO takes a spill
Quasi 2005 – Los Angeles
Quasi can make responses based on guest input and can recognize speech patterns, track faces, detect proximity, dispense candy and even perform a karaoke duet.
Softwares includes Alias Maya, BAT and so on.
Quasi - Carnegie Mellon University
Classification Of Robots ROBOTS Robot like devices: Prostheses Exoskeletons Telecherics Coordinate system based robots: Cylindrical Spherical Cartesian Human like robots: Humanoids, Androids, Actroids, Geminoids,Gynoids
Robot like devices: Prostheses:
The figure, showing a prosthetic arm actuated by artificial muscles and fit to a human, describes the long-term goals of this research in which the patient will be able to control a multi-degree of freedom robot prosthesis that provides force feedback information.
Exoskeletons are a skeletal framework to be worn by a human, specially soldiers and construction workers.
They are designed to assist and protect the wearer.
Telerobotics is the area of robotics concerned with the control of robots from a distance, chiefly using wireless connections (like Wi-Fi, Bluetooth) or tethered connections.
The figure alongside shows a mars rover.
Robots based on coordinate system:
Practical robots based on coordinate system:
Human like robots: Humanoid Android
The Honda Humanoid
Different Humanoids By Honda
The Uncanny Valley:
Degree of freedom:
Sense organs in robots(The sensors): SENSORS Tactile sensors Proximity and range sensors Sensor based systems
Tactile sensors: PIE-ZO ELECTRIC SENSORS RESISTIVE SENSORS TACTILE ARRAY SENSORS TOUCH SENSORS FORCE SENSORS TACTILE SENSORS
Charles Darwin first identified the process of natural selection in his monumental work “ The Origin of Species”.
Inspired by this natural process of ‘survival of the fittest’, evolutionary algorithms (EAs) attempt to find a solution to a problem using simulated evolution in a computer.
Types of EAs:
There are two types of EAs:
Genetic Algo (GA): It involves manipulating a fixed-length bit string. The bit string represents a solution to the problem being solved; it is up to the programmer to determine the meaning of the string.
Genetic Programming (GP): It involves generating expression trees as used by languages such as LISP and SCHEME.
With genetic programming, actual programs can be created and then executed.
Applying EAs to Robotic Navigation
EAs have been used to get a robot to learn how to adapt to its limited capabilities. Using GP in this way is termed evolutionary learning.
In most of the EA applications, two distinct steps occur: an initial training period is conducted by running the EA on a training set, followed by the execution of the best-fit solution.
With Continuous and Embedded Learning , the two steps are linked and operated concurrently while the robot is performing its task.
The figure shows an outline of this approach where the key components are:
Learning continues indefinitely, allowing adaptation to sensory failure.
Learning is done on a simulation model.
The simulation model is updated to reflect changes in the real robot or environment
In an experiment, a robot was given the task of navigating to the opposite side of a room through a passage in a wall starting from one wall and heading in a random direction from -90 degrees to 90 degrees, with 0 pointing directly to the opposite wall.
With no evolution and all sensors functioning, the robot was able to navigate successfully about 25% of the time.
After 50 generations of evolution, the robot's success rate increased to about 61%.
With three sensors on the right side of the robot disabled after 50 generations, the success rate dropped to about 42%, but increased over 50 more generations to about 63%.
The results of the experiment show that a robot using CEL can not only learn how to improve its navigation abilities by itself, but also re-learn how to navigate after suffering the loss of some sensory capability
Living on Their Own:
Ecosystem-like settings are interesting from an alife perspective.
Within ecosystems, the main goal of a robot is self-preservation.
Resources, especially energy, are limited in time and space.
Consequently, robots must compete for them.
Thus competition forms the basis of all robot interactions in the system.
When trying to re-create biological phenomena, it makes sense to look at the biological world for some good initial pointers.
For instance, the study of robotic locomotion is aided by observing and imitating biological systems such as a spider.
A robot is limited when using wheels (very un-biological) in rough terrains, whereas a biologically inspired robot would have legs like that of a spider for maneuvering around and over obstacles
Implementation of knowledge:
Line following robot:
Line follower is a machine that can follow a path.
The path can be visible like a black line on a white surface (or vice-versa) or it can be invisible like a magnetic field.
Practical applications of a line follower involve automated cars running on roads with embedded magnets; guidance system for industrial robots moving on shop floor etc.