A

SEMINAR REPORT ON

By P.GOPALA KRISHNA, (1203108).

CONTENTS
INTRODUCTION WHAT IS ROBOTICS? LAWS OF ROBOTS ARTIFICIAL INTELLIGENCE
Acquiring Knowledge Knowledge Representation Goal Trees Scientific Nuclear reactors Military Industrial Medical

ROBOT APPLICATIONS

WORKING PERCEPTION ACTION

Vision Speech recognition Navigation Manipulation

ADVANTAGES DISADVANTAGES CONCLUSION

Introduction
Any automatically operated machine that replaces human effort, though it may not resemble human beings in appearance or perform functions in a humanlike manner. The term is derived from the Czech word robota, meaning "forced labour" Modern use of the term stems from the play R.U.R.,(Rossums Universal Robots) written in 1920 by the Czech author Karel Capek, which depicts society as having become dependent on mechanical workers called robots that are capable of doing any kind of mental or physical work. Robotics is science of designing building and application of robots. The aim of robotics is to design an efficient robot . robot will become efficient if it can think for thinking robotics uses AI technology For manufacturing robots .robotics and AI seem to be different branches and science. Robotics concerned with mechanical and electrical devices while AI is branch of computer science which is concerned with ways of programming and designing computers to simulate human intelligent thought robot is ordered to get target.

What is Robotics?
The word "robot' was coined by Karel Capek who wrote a play entitled "R.U.R." or "Rossum's Universal Robots" back in 1921. The base for this word comes from the Czech word 'robotnik' which means 'worker'. In his play, machines modeled after humans had great power but without common human failings. In the end these machines were used for war and eventually turned against their human creators. But even before that the Greeks made movable statues that were the beginnings of what we would call robots. For the most part, the word "Robot" today means any manmade machine that can perform work or other actions normally performed by humans.

What Do Robots Do?

Most robots today are used in factories to build products such as cars and electronics. Others are used to explore underwater and even on other planets.

What are Robots Made Of?

Robots have 3 main components:

Brain - usually a computer Actuators and mechanical parts - motors, pistons, grippers, wheels, gears Sensors - vision, sound, temperature, motion, light, touch, etc.

With these three components, robots can interact and affect their environment to become useful.

Laws Of Robotics
Popular science fiction writer Isaac Asimov created the Three Laws of Robotics: 1. A robot must not injure a human being or, through inaction, allow a human being to come to harm. 2. A robot must always obey orders given to it by a human being, except where it would conflict with the first law. 3. A robot must protect it's own existence, except where it would conflict with the first or second law. Later, Asimov added this "Zeroth Law" A robot must not injure a humanity or, through inaction, allow a humanity to come to harm.

Artificial Intelligence
Artificial intelligence is study of mental faculties (powers) through use of computational models. Fundamental principles of AI is what a brain does may be thought of at some level at kind of computation. The aim of AI is to create machine which can think. What is meant by think is the capability of acquiring and applying knowledge. Acquired knowledge is done by through vision voice recognition inferences Acquiring knowledge is represented in memory by using Predicated calculus techniques By bits, intrinsic images, abstract view, object identification. To reach a goal we will use goal trees and plans. A goal tree describes a situation in which a goal can be satisfied by solving sub goals. There are more than one method available, an algorithm may have to try several before finding one that works. This brings about a such problem. All possible ways that a problem can be solved constitutes a search space backtracking, planning, coordination. It is impossible to search all the search space .as the search space increases exponentially with the possible ways. By using fundamental (primitive tasks) tasks only the goals is reached. There changes according to their domain of field concerned like home, scientific.

Applications
Scientific applications. Nuclear reactors. Military-intelligent radars, intelligent agents. Industrial. Medical. Home.

Working
The working of robot is combination of perception and action. perception involves interpreting sights, sounds, smell, touch. action includes ability navigate through the world and manipulate objects.

Perception Cognition Action

Physical
World

The above figure shows design for a complete autonomous robot. Most of AI is concerned only with cognition, the idea being that an intelligent program or developed we will simply add sensors and effectors to them. A manufacturing of sensors and effectors involves electronically, mechanical work.

The key difference between artificial intelligence and robotics is programs usually operate in computer simulated worlds. Robots must operate physical world. As a example, concerned a move in chess. An AI program can search millions of nodes in game tree without ever having to sense or to touch anything to real world. A complete chess playing robot, on the other hand must be capable of grasping pieces, visually interpreting board positions and carrying on a host of other actions.

Perception
Two important sensory channels for humans or vision and spoken language. It is through there two faculties that we gather almost all of the knowledge that drives our problem solving behaviors.

Vision:
Accurate machine vision opens of a new real of computer applications. Then applications include mobile robot navigation, complex manufacturing tasks, analysis of satellite images and medical image processing. Here, we investigate how we can transform raw camera images into useful information about the world. A video camera provides a computer with an image represented on a two-dimensional grid of intensity levels. We perform the given four operations on order of increasing complexity. 1. 2. 3. 4. Signal. Measurement analysis. Pattern recognition. Image under standing.

1. Signal processing: Enhancing the image, either for human consumption or an input to another program. 2. Measurement analysis: For images containing a single object, determining the twodimensional extent of the object depicted. 3. Pattern recognition: For single-object images ,classifying the object in a category drawn from a finite set of possibilities. 4. Image under standing: For images containing many objects, locating the objects in the image, classifying them and building a three-dimensional model of the scene. The problem in understanding an image are 2D image of 3D objects.

An image in two-dimensional, while the world is threedimensional.

Some information is necessary loosen when an image is created.

One image may contain several objects and some object s may partially overlap others. The value of a single pixel is affected by many different phenomena, including the color of the object, the source of the light ,the angle and distance of the camera, the pollution in the air etc. It is hard to disentangle these effects.

By using low-level image features such as shadows and texture we can interpret the image. Having multiple images of the same of object can also be helpful for recovering 3D structure. Other image factors we might want to consider are shading, intensity, reflectance and color to interpret images.

SHADOW VISION High level knowledge is also important for interpreting, visual data. For ex: consider the object at the center of (fig*) while no lowlevel image features can sell as what the object is the objects surroundings provide us with top down expectations. These are critical to for interpreting visual scenes.

12 A13C 14
fig a. fig b.

Speech Recognition:
Spoken language is a more natural form of communication in many human computer interfaces. Design issues concerned with speech systems.

Speaker dependence vs. speaker independence: - A speaker independent system can linker to any speaker and translate the sounds to written text. Speaker independence in difficult to achieve. Continuous vs. isolated word speech: - Interpreting isolated speech is easier one. But the ability to recognize continuous speech is very important, however, since humans have difficulty speaking in isolated words. Real time vs. off time processing: - In interactive applications a sentence be translated in to text on it in being spoken, while in other situations, it is permissible to spend minutes in computation. Large vs. small vocabulary: - Recognizing utterances that are confirmed to small vocabulary words is easier than working with large vocabularies.

Action
Intelligence puts mobility to effective use. Here we investigate the nature of mobility (ability to move) in terms of how robots navigate through the world and manipulate objects.

Navigation:
Navigation means moving around the world: Planning router, reaching desired destinations with out bumping in to things, and so forth. Navigational problems are complex. For example suppose that there are obstacles in the robots path, on in figure. The problem of path planning is to plot a continuous set of points connecting the initial position f the robot to its desired position. If the robot in to small as to be considered a point, the problem can be solved stright forwardly by constructing a visibility graph. Let S be the set consisting of the initial and find positions as well as the vertices of all obstacles. To form the visibility graph, we connect every pair of points in S that are visible from one another, as shown in the figure. We can then search the graph to find the optimal path for the robot.

Manipulation (To operate or control by skilled use of

hands):
Robots have simple repetitive tasks like bolting and fitting automobile parts, but these robots are highly task-specific. If in a Lang slading goal in Robotics to built robots that can be programmed to carry out a wide variety of tasks. The general manipulation problem addressed by Robot is pick and place, in which a robot must grasp an object and move it to a specific location. There are two main tasks. 1. Grasping 2. Placing.

Grasping:- Some of path planning can be used to move he arm towards the object. Then we wide the gripper as in fig and graph it. Placing it can be done by using two ways Navie and Clever.

Advantages Of Robotics
The advantages are obvious - robots can do things we humans just don't want to do, and usually do it cheaper. Robots can do things more precise than humans and allow progress in medical science and other useful advances.

Disadvantages of Robotics
Yes there are problems. As with any machine, robots can break and even cause disaster. They are powerful machines that we allow to control certain things. When something goes wrong, terrible things can happen. Luckily, this is rare because robotic systems are designed with many safety features that limit the harm they can do. There's also the problem of evil people using robots for evil purposes. This is true today with other forms of technology such as weapons, and biological material. Of course, robots could be used in future wars. This could be good or bad. If humans perform their aggressive acts by sending machines out to fight other machines, that would be better than sending humans out to fight other humans. Teams of robots could be used to defend a country against attacks while limiting human casualties. Either way, human nature is the flawed component that's here to stay.

The Future Of Robotics

The population of robots is growing rapidly. This growth is lead by Japan that has almost twice as many robots as the USA. All estimates suggest that robots will play an ever-increasing role in modern society. They will continue to be used in tasks were danger, repetition, cost, and precision prevents humans from performing.

Conclusion
Some people are concerned that robots will reduce the number of jobs and kick people out of their jobs. This is almost never the case. The net affect of advanced technology such as robots (or cars, electric drills and other machines) is that humans become more productive. Robotics is an engineering field, which uses AI techniques to build intelligent robots for the purpose of efficiency. The research of Robotics and AI would lead to a manufacturing of Robots that will be used in every industry. In future, if the robotics will be used in constructive way than in destructive way then it needs very peaceful to mankind.