S.DEVA JOHNSONP.VENGADESH

M.S.P.VELAYUTHA NADAR POLYTECHNIC COLLEGE

PAVOORCHATRAMEMERGING TREND ROBOTICS IN NEURAL NETWORK

Contents:

1. Abstract

2. Introduction

3. What is Robot?

4. Why it needed?

5. Quality

6. Laws of Robotics

7. Applications of Robotics.

Military Services

Car Production

Space Exploration

Underwater Exploration

Commercialized Agriculture

8. What is Neural Network?

9. Involvement of neural networks.

10. Involvement of neural networks.

11. Top 5 Emerging Technologies In 2015

Robotics 2.0

Neuromorphic engineering

Intelligent nanobots

3D printing

12. Conclusion

13. References

ABSTRACT

The purpose of this paper is to provide an overview of the research being done in neural

network approaches to robotics, outline the strengths and weaknesses of current

approaches, and predict future trends in this area.

INTRODUCTION

An important area of application of neural networks is in the field of robotics. Usually,

these

networks are designed to direct a manipulator, which is the most important form of the

industrial

robot, to grasp objects, based on sensor data. Another applications include the steering

and

path-planning of autonomous robot vehicles.

In robotics, the major task involves making movements dependent on sensor data. There

are four, related, problems to be distinguished:

WHAT IS ROBOT?

A robot is a mechanical or virtual artificial agent, usually

an electromechanical machine that is guided by a computer program or electronic

circuitry, and thus a type of an embedded system.

WHY IT NEEDED?

There are many different reasons for using a robot but the central reason for most

applications is to eliminate a human operator. The most obvious reason is:

o To save labor and reduce cost.

Other classes of applications concern the product:

o Human is bad for the product for example semiconductor handling.

Within this class are other reasons for using robots for example food

handling, pharmaceuticals, etc.

o Product is bad for the human for example radioactive product.

Within the above are other reasons for using robots for example robots can

be used to replace human operators where the dangers are:

1. Repetitive strain syndrome.

2. Working with machinery that is dangerous for example presses, winders.

3. Working with materials which might be harmful in the short or long term.

QUALITYwhile the main reason for using a robot is to save labor the biggest impact a robot has can

be on quality.

Applications where quality will be improved are:

1. gluing,

2. spraying (glue or paint),

3. trimming and de-burring,

4. Testing and gauging.

5. assembly

6. laboratory routines

LAWS OF ROBOTICS

The term robotics was coined in the 1940s by science fiction writer Isaac Asimov. In a

series of stories and novels, he imagined a world in which mechanical beings were

mankind's devoted helpmates. They were constrained to obey what have become

known as Asimov's Laws of Robotics:

1. A robot may not injure a human being, or, through inaction, allow a human being to

come to harm.

2. A robot must obey the orders given it by human beings except where such orders

would conflict with the First Law.

3. A robot must protect its own existence as long as such protection does not conflict

with the First or Second Law.

APPLICATIONS OF ROBOTICS.

Sometimes a human operator can do better than the robot in terms of quality or speed but

the robot will do the task consistently.

1. Military Services: Military robots are some of the

most high-tech and important robots used today. These

state-of-the-art machines save lives by performing extremely dangerous tasks

without endangering humans.

2. Car Production: Robots are used in the automobile

industry to assist in building cars. These high-powered

machines have mechanical arms with tools, wheels and

sensors that make them ideal for assembly line jobs.

3. Space Exploration: One of the most amazing areas of

robotics is the use of robots in space. These state-of-the-art

machines give astronauts the chance to explore space in the

most mind-boggling ways.

4. Underwater Exploration: Underwater robots have

radically changed the way we see the world from the ocean

floor. Underwater robots can dive longer and deeper than any

human, and they provide an up-close look at marine life.

5. Commercialized Agriculture: Farming has been performed by man since the

beginning of time, but throughout the years robots have

been introduced to the world of commercial agriculture.

Like manufacturing jobs, robots have the ability to work

faster, longer and more efficiently than humans in agriculture.

WHAT IS NEURAL NETWORK?

An artificial neural network (ANN), usually called neural network (NN), is a

mathematical model or computational model that is inspired by the structure and/or

functional aspects of biological neural networks.

ADVANTAGE OF NEURAL

NETWORK:

They provide a straightforward

mapping between sensors and

motors

They are robust to noise (noisy

sensors and environments)

They can provide a biologically

plausible metaphor

ROBOTIC IN NEURAL NETWORK:

Deep Neural Networks (DNNs) are well known for doing amazing things, but why

are they not used more in robotics?

If you have a neural network that can recognize things, why not couple it up to a

robot's camera and let it control the robot? At the moment we have reached the

point where if you look around the labs and the different work

Neural Networks in Robotics is an integrated view of both the application of

artificial neural networks to robot control and the neuromuscular models from

which robots were created

. The behavior of biological systems provides both the inspiration and the

challenge for robotics. The goal is to build robots which can emulate the ability of

living organisms to integrate perceptual inputs smoothly with motor responses,

even in the presence of novel stimuli and changes in the environment

The ability of living systems to learn and to adapt provides the standard against

which robotic systems are judged. In order to emulate these abilities, a number of

investigators have attempted to create robot controllers which are modelled on

known processes in the brain and musculoskeletal system

Neural Networks in Robotics provides an indispensable reference to the work of

major researchers in the field. Similarly, since robotics is an outstanding

application area for artificial neural networks, Neural Networks in Robotics is

equally important to workers in connectionism and to students for sensor monitor

control in living systems.

TOP 5 EMERGING TECHNOLOGIES IN 2015

Emerging Technologies – Most of the global challenges of the 21st century are a direct

consequence of the most important technological innovations of the 20st century.

New technology is arriving

faster than ever and holds the

promise of solving many of the

world’s pressing challenges

such as food and water

security, energy sustainability

and personalised medicine.

Lighter, cheaper and flexible

electronics made from organic

materials have found endless practical applications and drugs are being delivered via

nanotechnology at the molecular level, at the moment just in medical labs.

However, outdated government regulations, inadequate existing funding models for

research and uninformed public opinion are the greatest challenges in effectively moving

emerging technologies from the research labs to people’s lives.

1. ROBOTICS 2.0

A new generation of robotics takes machines away from just automating the most

manual manufacturing assembly line tasks and orchestrates them to collaborate in

creating more advanced assemblies, subassemblies and complete products.

Collaborative robotics can accelerate time-to-market, improve production accuracy

and reduce rework. By using GPS technology that is commonly available in

smartphones, robots can

be used in precision

agriculture for weed

control and harvesting.

We’ve seen robots that

can walk like an ape and

run like a cheetah, robots

that can mix a perfect

martini, help the disabled,

or drive you to the store.

Robots could replace

soldiers on the battlefield.

In Japan, robots are being

tested in nursing roles: they help patients out of bed and support stroke victims in

regaining control of their limbs.

Artificial Intelligence, machine learning and computer vision are constantly

developing and perfecting new technologies that “enable the machine” to perceive and

respond to its ever changing environment. Emergent AI is the nascent field of how

systems can learn automatically by assimilating large volumes of information. An

example of this is how Watson system developed by IBM is now being deployed in

oncology to assist in diagnosis and personalised, evidence-based treatment options for

cancer patients.

1. NEUROMORPHIC ENGINEERING

Neuromorphic engineering, also known as neuromorphic computing started as a

concept developed by Carver Mead in the late 1980s, describing the use of very-large-

scale integration (VLSI) systems containing electronic analogue circuits to mimic

neurobiological architectures present in the nervous system.

A key aspect of

neuromorphic engineering

is understanding how the

morphology of individual

neurones, circuits and

overall architectures creates

desirable computations,

affects how information is represented, influences robustness to damage, incorporates

learning and development, adapts to local change (plasticity), and facilitates

evolutionary change. Neuromorphic Computing is next stage in machine learning.

IBM’s million “neurones” TrueNorth chip, revealed in prototype in August 2014, has

a power efficiency for certain tasks that is hundreds of times superior to conventional

CPU’s and comparable for the first time to the human cortex. The challenge here

remains creating code that can realise the potential of the TrueNorth chip, an area

IBM continues investing in today.

2. INTELLIGENT NANOBOTS

Again, Emergent AI and Computer Vision will provide drones with human like

capabilities allowing them to complete tasks too dangerous or remote for humans to do

like checking electric power lines or delivering medical supplies in an emergency for

example.

Autonomous drones will improve agricultural yields by collecting and processing vast

amounts of visual data from the air, allowing precise and efficient use of inputs such as

fertiliser and irrigation.

Ambulance drones that

can deliver vital medical

supplies and “on screen”

instructions. Drones with

mounted camera to

“learn” about

surroundings – with no

information about the

environment or the

objects within it- by

using reference points and different angles, it builds a 3D map of surroundings, with

additional sensors picking up barometric and ultrasonic data. Autopilot software then

uses all this data to navigate safely and even seek out specific objects. Autonomous.

Intelligent. Swarming. Nano Drones.

4) SPACE ROBOTICS

Valkyrie humanoid robot that will help astronauts on a journey to Mars. NASA Valkyrie Robots Prepare for Life on Mars

NASA needs help improving robot dexterity. Teams in the competition must program a virtual robot to complete a series of tasks in a simulation that includes periods of latency to represent communications delay from Earth to Mars. Each team’s R5 will be challenged with resolving the aftermath of a dust storm that has damaged a Martian habitat. This involves three objectives: aligning a communications dish, repairing a solar array, and fixing a habitat leak.

This technology could also benefit humankind on Earth, as they could operate under dangerous or extreme environments on our home planet.

“Precise and dexterous robotics, able to work with a communications delay, could be used in spaceflight and ground missions to Mars and elsewhere for hazardous and complicated tasks, which will be crucial to support our astronauts.

ROBOT TO PERFORM ACTIONS OF SERVICE DOGS

SResearchers at Georgia Tech have built a

biologically inspired robot to perform actions

of service dogs

Users issue verbal commands to robot, and indicate object with laser pointer.

Eg. Fetching items, or closing doors or drawers.

Worked with trainers of dogs

Conclusion

The paper presents our first results that we obtained making use of the proposed path

planning algorithm working with the neural network and sensor data. The simulation

examples of the generation of the collision free path for point robot and for two

dimensional robot show that designed strategy are acceptable for solution of this

problem. We played the role of the supervisor to learn the robot to make it’s way

intelligently toward its target and to avoid obstacles. In future we will implement this

technique for safe motion of our experimental mobile vehicle in indoor conditions. We

suppose to use this algorithm not only for the robot motion in known environment but for

unknown one, as well. It is necessary to test different parameters in neural network with

the aim of reaching the optimal time for finding the (shortest possible) safe path. As the

robot collects environment data currently along its path it can avoid not only the static

obstacles but also the dynamic ones. We feel that this technique will be suitable also for

the motion of mobile devices in complex environment

REFERENCES:

http://www.learnartificialneuralnetworks.com/robotcontrol.html

http://link.springer.com/article/10.1007/BF00368972

https://wtvox.com/robotics/top-5-emerging-technologies-in-2015/

http://www.i-programmer.info/news/105-artificial-intelligence/8619-a-robot-learns-to-

do-things-using-a-deep-neural-network.html

https://en.wikipedia.org/wiki/Neurorobotics

http://students.iitk.ac.in/eclub/assets/documentations/summer09/

NeuralNetworkRobot.pdf

http://www.neurosolutions.com/apps/files/Neural-Networks-in-Mobile-Robot-Motion.pdf