Upload
er-rahul-abhishek
View
93
Download
4
Embed Size (px)
Citation preview
Learning of Robots by Using & Sharing The Cloud Computing Techniques
Pratik 3
rd Year IT Branch
MITS Engineering College Rayagada, Odisha
Rahul Abhishek 3
rd Year IT Branch
MITS Engineering College Rayagada, Odisha
rahulmithu.abhishek
@gmail.com
Payal Sinha 3
rd Year IT Branch
MITS Engineering College Rayagada, Odisha
ABSTRACT Robots are shaping a new era in the technology, many
algorithms has been developed for their learning which
they can apply to find the solution for the problems that
they are facing. That is, we have tried to provide them a
basic intelligence (like recognition, collision avoidance, etc.). But besides that basic intelligence we are interested
in developing an intelligent system in which robots will
use their experiences and share it with each other just like
humans, who have got all its intelligence by his
experience and imaginations and sharing it with each
other. To implement this intelligent system we can use a
local server (word interchangeable to database) that will
be restricted to a robot only and a Cloud (global) server
where the authorized robots can upload their experiences
which can be used by every robot (which is authorized to
that server) to solve their problems.
Keywords Artificial Intelligence (AI), Robotics, (Global
Server(cloud Computing), Local Server, Memory
function.
1. INTRODUCTION
1.1 What is Robot?
The term “Robot” is coined by Karl Capek in his play R.U.R (Rossum’s Universal Robots), which opened in
Prague in 1921. Robot is Czech word for forced labour
Robots are reprogrammable, multifunctional manipulator
design to move material, parts, tools, or specialized
devices through various programmed motions for the
performance of a variety of test or we can say that a robot
is a simple device who can move itself They have sensors
to perceive their environment and effectors to assert
physical forces on it. Since robots has proven that they are
now the part of human life and provide benefits to us and
for getting these benefits we need some human like
intelligence in them and it can be obtained by AI.
1.2. Robots Theory A robot consists of various electronics circuit, ports,
sensors, effectors for its functioning. Although it seems a
very complicated design but it is not so. A sensor works
as an interface between the robot and environment. A
robot should contain both active and passive sensor.
In robots three types of sensor is used first record the
distance of the object second tells about the environment
by capturing the image and third one measure the
property of robot that how much efficiency has it work
the or to solve the problem. The effectors in robots help it
to manipulate or understand the environment and with the
help of effectors it can move and change its shape of body according to the environment. There is a concept known
as Degree of Freedom (DOF) with the help of it we test
the ability of robot to interact with the environment. We
count one degree of freedom for each move of robot and
its effectors. The DFOs define the kinematic state of a
robot.
An additional advantage of learning a robot from its
experience is that it can also learn from the experience of
its peers. A key feature is that, we are using two servers
one is the local server restricted to a robot only while
other is the global server which is shared globally with all
the robots. And both these servers will hold the
experiences of the robots.
Fig. (2) Chart showing the interaction of robot with the environment
2. What is Cloud Computing?
As a metaphor for the Internet, "the cloud" is a familiar
cliché, but when combined with "computing," the
meaning gets bigger and fuzzier. It has been envisioned as
the next generation architecture of IT Enterprise.
According to the IEEE Computer Society cloud
computing is “a paradigm in which information is
permanently stored in servers on the internet and cached
temporarily on clients that include desktop, entertainment
centers, notebooks, etc.” The Internet is commonly
visualized as clouds; hence the term “cloud computing”
for computation done through the Internet. Cloud
computing allows consumers and businesses to use
applications without installation and access their personal
files at any computer with internet access. The concept of
cloud computing dates back to the 1960s, when John
McCarthy opined that "computation may someday be
organized as a public utility." Cloud computing is a new
consumption and delivery model for IT services. The
concept of cloud computing represents a shift in thought,
in those end users need not know the details of a specific
technology. The service is fully managed by the provider.
Users can consume services at a rate that is set by their
particular needs. This on-demand service can be provided
at any time. The term "cloud" is used as a metaphor for
the Internet, based on the cloud drawing used in the past
to represent the telephone network, and later to depict the
Internet in computer network diagrams as an abstraction
of the underlying infrastructure it represents. Cloud
computing is a natural evolution of the widespread
adoption of virtualization, service-oriented architecture,
autonomic, and utility computing. It is popular for its pay-
as-you-go pricing model. Consumers of cloud services
may see increased reliability, even as costs decline due to
economies of scale and other production factors.
Fig. (1) Model of a cloud
3. RELATED WORK & PREVIOUS WORK
3.1 RoboEarth[2]
The RoboEarth project (i.e. World Wide Web for robots)
is implementing the global server for sharing the
experiences of robot. The objective of RoboEarth Project
is to enable robots from all over the world to share their
knowledge about actions, objects and the environment the
RoboEarth platform offers the ability to store reusable data in a generic and open format.
3.2 Optimization Learning Algorithms
Many algorithms have been developed for optimizing the
behavior of a machine. But here we are using
reinforcement learning algorithm for optimizing
performances of robots.
3.3 Reinforcement Learning
Reinforcement learning is the study of how animals and
the machines can learn to optimize their behavior in the
face of rewards and punishments. Reinforcement learning
algorithms have been developed that are closely related to methods of dynamic programming, which is a general
approach to optimal control. Reinforcement learning
phenomena have been observed in psychological studies
of animal behavior, and in neurobiological investigations
of neuro-modulation and addiction [3].
Reinforcement learning algorithm consist of
Set of Environment States E
Set of actions required A (Solution of a problem may
consists of sequence of actions)
Rules of transition between states
Rules that determine reward for the transition.
Rules that describe what the agent observes.[4]
4. CLOUD AND ROBOT
Cloud Computing Technology is discussing recent flare to
integrate in the world of robotics. Cloud Robot is the
result of the merger of these two technological advances.
Cloud Robot is different from all the robots that exist
today and said that the intelligence is extraordinary, even
unlimited because of a “Cloud Brain” consisting of
processor and unlimited data in the cloud (Internet). As
cloud computing has the role of the hardware devices in
the user getting smaller (transition from notebook to the
net book, tablet PCs and smart phones). Similarly, the
cloud is said in the future robots will become cheaper
manufacturing costs. Due to the needs of processors in the
brain that does not require sophisticated first of all data
processing is done centrally on the server cloud. Cloud
robot is simply consisting only of input and output
devices and the entire process focuses on the cloud. Best
of the cloud robot is able to communicate with other robots of clouds to humans, even with colleagues via the
Internet. Entering Cloud computing allows a robot to do
the job, even superior to human intelligence, known as
robot cloud. Several research groups are exploring the
idea of robots that rely on cloud-computing infrastructure
to access vast amounts of processing power and data. This
approach, which some are calling "cloud robotics," would
allow robots to offload compute-intensive tasks like
image processing and voice recognition and even
download new skills instantly, Matrix-style.
A researcher suggests that the future of robotics is in cloud-computing. This means that robots could offload
their more complex tasks to remote servers that could do
the heavy computations.
A cloud connected robot can:-
Perceive
Understand
Share
React
Fig. (3) Robot connected with cloud
5. PROPOSED APPROACH
To realize this whole scenario we will use two servers one
is local to a particular robot, while other is centralized
server which can be accessed by every robot which is
authorized to that server.
The purpose of making two servers is that the local server will handle or assist the robot to work in a particular
environment and with the particular objects and as soon
as the robot will continue to work in the same
environment it will gain experience of working in that
environment and hence it will work more intelligently
while the global server will keep the solution for all the
problems (tasks assigned to robots are referred as
problems) which are faced by all the robots present
globally, and these solutions will be generalized rather
than specialized e.g. a robot working in your garden and
trimming a plant, if we look at the optimal solution then
your robot will be trimming the plant according to the size
and shape of that particular plant. But the robot at the remote location working in another garden will have
slightly different environment (difference may be very
slight) and different specification of object of interaction
(i.e. in this case, shape & size of plant). So the solution of
first robot cannot be used by second robot directly. Hence
the solution of first robot will be considered as
generalized one at the global server and the robot at
remote location will use this solution after applying few
optimization algorithms and making slight changes in the
environment variables, and specifications of object of
interaction etc as per its requirement.
5.1 Local Server (Local Database)
The scope of creating a local database is that every robot
is having a different environment to work and they deal
with different-different objects. As the robot will deal
with the objects in its surroundings, it will gain
experience of dealing with these objects by optimizing the
solution on the basis of its environment, object of
interactions and saving this solution in its local database.
So the local database will act as memory of a robot to let
it work more intelligently in a particular environment e.g.
a robot working in a hospital will have experiences about
dealing with the objects present in that hospital, these experiences will get collected in the local database and as
the time passes the robot will have good intelligence to
handle every object (of interaction) in the hospital
expertly.
5.2 Cloud Server (Global Database)
The second database we are talking about is the global
database, it is the idea through which we will share the
learning (experience) of one robot with the other robot. It
is just like the learning of human being who learnt
everything by his ideas and experiences and sharing his
experiences with each other. In broader context it is about sharing the knowledge of robot with each other to get
their task completed.
It will be implemented in the following ways. When any
problem comes or a task is assigned to a robot, first the
robot will check for the solution of that problem in its
local database if it does not exist there, it means robot is
novice to that problem then it will look at the global
server for the solution if the solution exist on the global
server then it will download it from there and use
reinforcement learning to optimize the solution according
to its own environment. But if it does not exist on the
global server then the robot will apply its own learning to
find the solution of the given problem and save this
solution at both the server i.e. local server as well as
global server.
5.3.1 Problem Characteristics & variables for
global database –
Global problem Id (GPID) – Identification of the problem globally corresponding to
the problem statement.
Problem Statement – Key for searching the problem.
Environment – Description about the working condition (i.e. hospital,
railway platform, library etc)
Global Environment Id attached to a
problem (GEID) –
Generated for different-different environments of the
same problem.
Description of Object of interaction – To which the robot is interacting, may be Door, rain, train
etc or it can be null.
5.3.2 Algorithms for global server The global server has two main tasks one is uploading the
solution received from the robot to its database and
second one is granting the permission for downloading
request made by robot. The algorithms are as follows-
Algorithm for Uploading
Step1 – Create a GPID for the problem and
GEID for the environment.
Step2 – Get the values of various variables like
problem statement and the environment
variables, object of interaction etc from the
robot.
Step3 – The global server will generalize this
solution by applying some algorithms.
Step4 – Save it at global server.
Step5 – Exit.
5.3.3 Algorithm for Downloading
Step1 – Check for the problem and environment
variables at the global server if the solution corresponding
to this problem – environment set exists there then
download the solution.
Step2 – Specialize this solution by making slight
changes in its variables as required and apply the
reinforcement learning algorithm for optimization
according to its own environment.
Step3 – Use the solution, initialize memory function
and save it at local database. Step4 – Exit.
5.3.4 Constraints/Protocols
Fuzzy logic and various matching algorithms may be used
for the match when the robot is looking for the solution at
the global server.
Only authorized Robots can access the global server.
5.3.5 Global Database Functionality Robots will have to register themselves once to get access to the Global database. A robot ID (RID) will be
generated at the time of registration that will be used to
identify robot while accessing the database. As soon as
the time passes the Global database will keep expanding
hence the robots will have a good store of knowledge.
6. Representation of how the Robots will use
Cloud Server (global database)
7. CONCLUSION & FUTURE WORK We have seen that how we can make robots more
intelligent to work in a particular environment by
enabling them to use their own experience to deal with the
objects present in their surrounding environments i.e. as
soon as the time passes the robot will have a good
experience of dealing with the objects present in their
surroundings. We have also seen that how a robot will use the experience of other robots to solve its own problem by
using the cloud server. In near future we can also work on
developing an intelligent agent for Robot – Human
interaction by having the similar approach that we have
seen in this paper.
8. References
[1] Hyde, Andrew Dean (Sept 28, 2010), “The
future of Artificial Intelligence”.
[2] Patterson, Dan W, (2007), “Introduction to
Artificial Intelligence & Expert Systems”,
Prentice-Hall India, New Delhi.
[3] Rich, Elaine, and Kevin Knight, (2006),
“Artificial Intelligence”, McGraw Hills Inc.
[4] Chun-Wang WEI, I-Chun HUNG, Ling LEE
& Nian-Shing CHEN April 2011 A joyful
classroom learning system with robot learning
companion for children to learn mathematics
multiplication.
[5] ICT Call 4 RoboEarth Project 2010-248942
Deliverable D6.1: Complete specification of the
RoboEarth platform December 1, 2010.
[6] Peter Dyan Gatsby, University College
London & Christopher JCH Watkins, University
of London: Reinforcement Learning.
[7] Wikipedia: Reinforcement Learning, 20th
November 2011 http://en.wikipedia.org/ wiki/
Reinforcement_learning.
[8] Prof. Hamid D. Taghirad “Robotics:
Evolution, Technology and Applications” K.n.
Toosi University of Technology.
[9] Introduction To AI Robotics, Robin R.
Murphy.
[10] Artificial Intelligence and Mobile Robots, D.
Kortenkamp, P.Bonasso, R.Murphy, editors, MIT
Press, 1998.
[10] Pratik, Rahul Abhishek, Payal Sinha. “Future
Aspect Of Artificial Intelligence”. ICWET-2012,
pp336.
[11] Pratik, Rahul Abhishek “The Relationship
Between Artificial Intelligence and Psychological
Theories”, Proceeding ICETM – Sept 2012