UNIT I SCOPE OF ROBOTS AND INTELLIGENCE

1.The scope of industrial Robots

 A robot is a mechanical or virtual intelligent agent that can perform tasks

automatically or with guidance by remote control.
 A robot is usually an electro- mechanical machine that is guided by
computer and electronic programming.
 Robots hold the promise of moving and transforming materials with the
same ease as a computer program transforms data. 

Definition of industrial robot

 An industrial robot is a robot system used for manufacturing.

 Industrial robots are automated, programmable and capable of
movement. 

Industrial Applications
Industrial robots – These robots bring into play in an industrialized
manufacturing atmosphere.
 Typically, these are articulated arms particularly created for applications
like- material handling, painting, welding and others.
 The robotic process automation is one of the revolutions in the
automation industry, and it is expected to increase higher potential in
terms of utilization and staff implementation in the upcoming year. 

Domestic or household robots – Robots  which are used at home this sort of

robots consists of numerous different gears

For example- robotic pool cleaners, robotic sweepers, robotic vacuum cleaners,
robotic sewer cleaners and other robots that can perform different household
tasks.

Medical robots: Existing technologies are being combined in new ways to

streamline the efficiency of healthcare operations.
 As a result, a wide range of robots is being developed to serve in a variety
of roles within the medical environment.
 Robots specializing in human treatment include surgical robots and
rehabilitation robots. 

Military robots: Robots brought into play  in military & armed forces.

This sort of robots consists of bomb discarding robots, various shipping robots,
exploration drones. 

Need for industrial robots

 Robots can be programmed to perform dangerous, dirty and/or repetitive
tasks with consistent precision and accuracy.
 Industrial robots are increasingly used in a variety of industries and
applications.
 Industrial robots are used in a variety of applications.
Applications of industrial robots
 Arc Welding.
 Spot Welding.
 Materials Handling.
 Machine Tending.
 Painting.
 Picking, Packing and Palletizing.
 Assembly.
 Mechanical Cutting, Grinding, Deburring and Polishing.

2.Robot Intelligence
 Robot intelligence is the ability of a computer or a robot controlled by
a computer to do tasks that are usually done by humans because they
require human intelligence and discernment.
 The ability of a digital computer or computer-controlled robot to
perform tasks commonly associated with intelligent beings. 
 Robot intelligence is intelligence demonstrated by machines, as
opposed to natural intelligence viewed by animals including humans.
 The study of "intelligent agents": any system that perceives its
environment and takes actions that maximize its chance of achieving
its goals.

3.State Space Search:

 A state-space is defined as a set of all possible states of a problem.
 A state-space representation allows for the formal definition of a problem
that makes the move from the initial state to the goal state.
 Advantages of State Space Search:
1. It is very useful in AI because of it provides a set of all possible states,
operations and goals.
2. If the entire state space for a problem is given then it is possible to trace the
path from the initial to goal state and identify the sequence of operation required
for doing it.

Disadvantages of State Space Search:

1. It is not possible to visualize all states for a problem.
2. The resources of the computer system are very limited to handle huge
combinational state-space.
Water Jug problem algorithm
1. (x,y)→(4,y) // Fill the 4 gallon jug

2. (x,y)→(x,3) // Fill the 3 gallon jug

3. (x,y)→(x-d,y) // Pour some water out of the 4-gallon jug

4. (x,y)→(x,y-d) // Pour some water out of the 3-gallon jug

5. (x,y)→(0,y) // Empty the 4-gallon jug on the ground

6. (x,y)→(x,0) // Empty the 3-gallon jug on the ground

7. (x,y)→(4,y-(4-x)) // Pour water from the 3-gallon jug into the 4 gallons until
the 4-gallon jug is full

8. (x,y)→(x-(3-y),3) // Pour water from the 4-gallon jug into the 3 gallons until
the 3-gallon jug is full

9. (x,y)→(x+y,0) // Pour water all the water from the 3-gallon jug into the 4-
gallon jug

10. (x,y)→(0,x+y) // Pour water all the water from the 4-gallon jug into the 3-
gallon jug

Solution:
Gallons in the 4-Gallon jug Gallons in the 3-Gallon jug Rule Applie
0 0 2
0 3 9
3 0 2
 3 3 7
4 2 5
0 2 9
2 0

4.Use of Predicate
Predicate: Properties of objects that we are interested in; can be true or false.
 Mobile robots are remarkable cases of highly developed technology and
systems.
 The robot community has developed a complex analysis to meet the
increased demands of the control challenges pertaining to the movement
of robots.
 The robot operating system (ROS) is used for the communication
between the robot and its control system.
 Robotic systems of the transportation and manipulation types are key
points of manufacturing and other automated systems.
 The intelligence of robots is defined by their ability to observe the
workspaces, to analyze them, to make decisions concerning the problems,
and to execute transportation movements/manipulations to reach the
proposed goals in industrials areas.
Agent-Based Systems and Role of Robots
 The open architecture of multi-agent systems (MAS) has become the
basic direction of distributed artificial intelligence development.
 These agents are considered as self-controlled software objects with self-
estimation systems and independent problem-solving tools for their own
needs.
The conceptual agent model consists of four components:
• Perception - which is a source for information about the external world;
• Effector - which is the agent’s interface to change the world or the agent’s
community;
• Communication system - which is the tool for information exchange
between other members of the agent’s community; • aims, which are the list of
goals for the agent’s execution.
5.Logic and Means-Ends Analysis
  Means-Ends Analysis is problem-solving techniques used in Artificial
intelligence for limiting search in AI programs.
 It is a mixture of Backward and forward search technique.
 The MEA technique was first introduced in 1961 by Allen Newell,
and Herbert A. Simon in their problem-solving computer program,
which was named as General Problem Solver (GPS).
 The MEA analysis process centered on the evaluation of the
difference between the current state and goal state.

How means-ends analysis Works:

The means-ends analysis process can be applied recursively for a problem.

It is a strategy to control search in problem-solving.

Following are the main Steps which describes the working of MEA technique
for solving a problem.

 First, evaluate the difference between Initial State and final State.
 Select the various operators which can be applied for each difference.
 Apply the operator at each difference, which reduces the difference
between the current state and goal state.

Algorithm for Means-Ends Analysis:

Let's we take Current state as CURRENT and Goal State as GOAL, then
following are the steps for the MEA algorithm.

 Step 1: Compare CURRENT to GOAL, if there are no differences

between both then return Success and Exit.
 Step 2: Else, select the most significant difference and reduce it by
doing the following steps until the success or failure occurs.
 If(First-Part<------MEA(CURRENT,O-START)
And
(LAST-Part <----- MEA (O-Result, GOAL), are successful, then
signal Success and return the result of combining FIRST-PART, O,
and LAST-PART.
Example of Mean-Ends Analysis:

Let's take an example where we know the initial state and goal state as given
below. In this problem, we need to get the goal state by finding differences
between the initial state and goal state and applying operators.

Solution:

To solve the above problem, we will first find the differences between initial
states and goal states, and for each difference, we will generate a new state and
will apply the operators. The operators we have for this problem are:

o Move
o Delete
o Expand

1. Evaluating the initial state: In the first step, we will evaluate the initial state
and will compare the initial and Goal state to find the differences between both
states.

2. Applying Delete operator: As we can check the first difference is that in

goal state there is no dot symbol which is present in the initial state, so, first we
will apply the Delete operator to remove this dot.
3. Applying Move Operator: After applying the Delete operator, the new state
occurs which we will again compare with goal state. After comparing these
states, there is another difference that is the square is outside the circle, so, we
will apply the Move Operator.

4. Applying Expand Operator: Now a new state is generated in the third step,

and we will compare this state with the goal state. After comparing the states
there is still one difference which is the size of the square, so, we will
apply Expand operator, and finally, it will generate the goal state.

6.Problem solving

 Robotics is a unique field from the perspective of a student in education.

 Critical thinking and problem solving can be so hard to teach students
because of how inter-disciplinary they are: not just mathematical or
linguistic or psychological or scientific.
 Robotics has a similar sense in which the contents of a robotics course
will be so many different things, with the analytical, mathematical side
 existing alongside the physicalized manifestation of the outcome of the
work. 
 Problem solving requires a solution.
 In the same way, robotics, which is a complex and difficult field, with a
whole range of possible paths which can be taken at any one time, is a
field which demands perseverance to make it to the end of a problem and
to get the outcome you want.
 By engaging in robotics, students are able to evolve this part of the
problem-solving skill set as well.

7.Robot Learning

Definition

Robot learning consists of a multitude of machine learning approaches,

particularly reinforcement learning, inverse reinforcement learning, and
regression methods, that have been adapted sufficiently to domain so that
they allow learning in complex robot systems such as helicopters, flapping-
wing flight, legged robots, anthropomorphic arms and humanoid robots.

Robot Learning Systems

As learning has found many backdoor entrances to robotics, this section can
only scratch the surface. However, robot learning has clearly been successful
in several areas: (i) Model Learning, (ii) Imitation and Apprenticeship
Learning, (iii) Reinforcement Learning as well as in various other topics.

Model Learning

 Model learning is the machine learning counterpart to classical system

identification.
 However, while the classical approaches heavily relies on the structure
of physically-based models, specification of the relevant state
variables and hand-tuned approximations of unknown nonlinearities.
 Model learning approaches avoid many of these labor-intensive steps
and the entire process to be more easily automated.
  Machine learning and system identification approaches often assume
an observable state of the system to estimate the mapping from inputs
to outputs of the system.

Two types of models are commonly learned, i.e., forward, and inverse
models.

 Forward models predict the behavior of the system based either on the
current state or a history of preceeding observations.
 Inverse models attempt to predict the input to a system in order to
achieve a desired output in the next step, i.e., it uses the model of the
system to directly generate control signals.

Imitation and Apprenticeship Learning

 In imitation learning also known as behavioural cloning, the robot

system directly estimates a policy from a teachers presentation, and,
subsequently, the robot system reproduces the task using this policy.
 A key advantage of this approach is that it can often learn a task
successfully from few demonstrations.
 In areas where human demonstrations are straightforward to obtain,
e.g., for learning racket sports, manipulation, drumming on
anthropomorphic systems, direct imitation learning often proved to be
an appropriate approach.

Robot Reinforcement Learning

 The ability to self-improve with respect to an arbitrary reward

function, i.e., reinforcement learning, is essential for robot systems to
become more autonomous.
 Here, the system learns about its policy by interacting with its
environment and receiving scores (i.e, rewards or costs) for the quality
of its performance.

8.Robot Task Planning

 A task planner would transform the task level specifications into
manipulator level specifications.
  The task planner must have a description of the objects being
manipulated, the task environment, the robot carrying out the task, the
initial state of the environment, and the desired final state.
 The output of task planner would be the robot program to achieve the
desired final state when executed in the specified initial state.
There are 3 phases in task planning
i)Modeling
ii)Task specification
iii)Manipulator program synthesis
Modeling
There are 2 types of representation
1. Boundary representation
2. Sweep representation
Boundary representation
 BREP describes only the oriented surface of a solid as a data structure
composed of vertices, edges, and faces.
 A face is represented in a Boundary representation by its bounding edges
and vertices.
 Thus, a Boundary representation consists of three primitive topological
entities: faces (2-dimensional entities), edges (1-dimensional entities) and
vertices (0-dimensional entities).
Sweep representation
 Sweep representations are used to construct three dimensional objects
from two dimensional shape .
 There are two ways to achieve sweep: Translational sweep and Rotational
sweep.
 In translational sweeps, the 2D shape is swept along a linear path normal
to the plane of the area to construct three dimensional object.
 For rotational sweeps, we can move along a circular path through any
angular distance from 0° to 360°.
Task specification
Tasks are actually defined by sequences of states of the world model.
There are 3 methods by specifying configurations
i)Using a CAD system to position models of the objects at the desired
configurations.
ii)Using the robot itself to specify robot configurations and to locate features of
the objects
iii)Using symbolic spatial relationships among object features to constrain
configurations of objects.
Manipulator program synthesis
 It is the crucial phase of task planning.
 The major steps involved in this phase are
i)grasp planning
ii)motion planning
iii)error detection
 The output of the synthesis phase is a program composed of grasp
commands, several kinds of motion specifications, error tests.