Transcript Robotics - Department of Computer Science

Robotics
Where AI meets Real World
Presentations on robotics
• Humanoid robots: An interaction
•
Discussion about the humanoid robots and their applications.
• Robotics
•
Robotics definition and types of robots.
• World of robots
•
History, applications and glimpse of robots in future.
Whats new ?
• Robotics is growing very fast.
•
Intelligence
•
Processing power.
• Self-reconfiguring modular robot (ModBots).
• Nano Robotics (Nanobots).
Intelligence in robots
• Can a Robot Lie ???
•
In an experiment performed in a Swiss laboratory, 10
robots with downward-facing sensors competed for
"food" - a light-colored ring on the floor. At the other end
of the space, a darker ring - "poison" - was placed. The
robots earned points for how much time they spent near
food as opposed to poison.
Robots Learn to Lie
!
• NASA trains its
Intelligence
in
Humanoid
robots
Humanoid robots for
space missions.
• Speech and facial
recognitions. (ASIMO)
•
A humanoid robot called asimo
has undergone various advance
development during past decade.
Now it can recognize speech and
face.
Robonaout R2
•
The dexterous robot not only looks like a
human but also is designed to work like one.
With human-like hands and arms, R2 is able
to use the same tools station crew members
use.
•
In the future, the greatest benefits of
humanoid robots in space may be as
assistants or stand-in for astronauts during
spacewalks or for tasks too difficult or
dangerous for humans.
•
For now, R2 is still a prototype and does not
have adequate protection needed to exist
outside the space station in the extreme
temperatures of space.
SC2010-E-017524 (11 Jan. 2010) --Chris Ihrke, senior project engineer
for General Motors, works with the
new dexterous humanoid robot
developed by NASA and General
Motors at Johnson Space Center.
ASIMO
• Charting a route.
• Recognizing moving objects.
• Distinguishing sounds.
• Recognizing faces and gestures.
ASIMO working in coordination
• Honda Develops
Intelligence
Technologies
Enabling Multiple
ASIMO Robots to
Work Together in
Coordination.
Technology behind ASIMO
• Network Integration
• Recognition
technology.
•
Recognition of moving
objects.
•
Recognition of postures
and gestures.
•
Environment
recognition.
•
Distinguishing sounds.
•
Facial Recognition.
• Integration with user’s network
system.
• Internet connectivity.
Processing Power
• To think faster.
• Processing the tasks through Artificial
neural networks.
• Speech and facial textures processing.
• Fast Image processing.
Self-reconfiguring modular robot
• Autonomous kinematic machines with
variable morphology.
• Self-reconfigurable mechanism utilizes two
types segment articulation
•
Lattice reconfiguration
•
Chain reconfiguration.
Architecture
• Lattice architectures:
•
Modules are connected in some regular, space filling 3 D
pattern.
•
Control and motion are executed in parallel.
•
Simple Computations.
• Chain architectures:
•
Modules are connected together in a string and tree topology.
Digital Clay
•
Roboticists at Xerox Parc in Palo Alto
have created modular intelligent
robotic system.
•
This system however does not use
actuators but instead relies on users
manipulating objects.
•
These modules have the ability to
sense each other and know if their are
other objects around them. They use
magnets to connect to each other.
Digital Clay..
• Self reproducing
• Healing
• Self- maintenance.
Video
Self-reconfiguring Robotics Projects
•
Self-reconfigurable modular robot that has been
developed by AIST and Tokyo-Tech since 1998.
•
Researchers at the Dartmouth
Robotics Laboratory have developed a
module capable of reconfiguring at a
large scale. This self-reconfiguring
robot consists of a set of identical
modules that can dynamically and
autonomously reconfigure in a variety
of shapes, to best fit the terrain,
environment, and task.
SuperBot
•
Researchers at the Polymorphic Robotics laboratory have designed
and manufactured a modular robot called the SuperBot. SuperBot is a
modular robot that consists of many reconfigurable modules that can
demonstrate multifunction and reconfiguration for running, climbing,
structuring, and many other activities in real environments.
•
Self Replicating.
How do they re-configure ?
• Deterministic reconfiguration:
•
Relies on units moving or being directly manipulated into their
target location during reconfiguration.
•
The exact location of each module/unit is always known.
• Stochastic reconfiguration
•
Relies on units moving around using statistical processes.
•
The exact location of each unit only known when it is connected
to the main structure, but it may take unknown paths to move
between locations
Self-reconfigure
• The units can do this in three ways
• They can move among each other.
• They can change their size.
• They can change a particular property,
like color.
Sandia Mini-Robots
•
At 1/4 cubic inch and weighing less
than an ounce, it is possibly the
smallest autonomous untethered
robot ever created.
•
Powered by three watch batteries,
it rides on track wheels and
consists of an 8K ROM processor,
temperature sensor, and two
motors that drive the wheels.
•
Enhancements being considered
include a miniature camera,
microphone, communication
device, and chemical micro-sensor.
Consequences
• Production is less complex because units are made in fewer
types.
• Development of solutions is basically software development.
• Reliability is revolutionized by the solutions’ ability to self-repair.
• Environmental impact is reduced by reassignment.
• Basic economics are transformed by reassignment.
• Productivity is increased by a better fit between tool and task.
Why Modular Robots ?
• Douglas Engelbart’s
presentation
of
NLS
(oN-Line System)
from 1968.
• “If you were supplied with a system, that is low
cost, environmentally friendly, virtually
unbreakable, and able to form a wide variety of
physical structures, that could perform many
tasks.What value could you derive from that?”
Video
NanoBots(NanoRobotics)
• This Is the Future of the Fight Against
Cancer.
• Nanorobotics is the technology of creating
machines or robots (nanobots) at or close to
the microscopic scale of a nanometers.
NanoBots..
• Nanorobots have potential applications in
the assembly and maintenance of
sophisticated systems.
• The future of Medicines.
• Nanomedicine.
• NanoRobotics in Action
NanoRobot Design
• For Molecular Manipulation nanorobot uses
actuators.
• Nanorobot navigation:
•
Uses plane surfaces (three fins total)
•
Propulsion by bi-directional propellers : two simultaneously
counter-rotating screw drives navigational acoustic sensors
Nanorobot Design..
The Road to Universal Robots
• Key to this evolution is a steady increase in
computer power, defined in terms of millions of
instructions per second, or MIPS.
Issues in Robot-Human interaction
• 7 principles for making interaction efficient.
•
Implicitly switch interfaces and autonomy modes,
•
Let the robot use natural human cues.
•
Manipulate the world instead of the robot,
•
Manipulate the relationship between the robot and the world,
•
Let people manipulate presented information,
•
Externalize memory, and
•
Help people manage attention.
Just in NEWS
•
The Lego robot solves [the] Rubik's Cube with a Motorola Droid as
a brain. A custom Android app on the handset uses the Droid's
camera to take pictures of each face. It then sends instructions via
Bluetooth to the Lego machine, which goes on to solve the Cube in
about 24 seconds.
Rise of Machines
• If robots do develop
consciousness, they may
also develop conscience,
and choose to be kind to
their human creators. In
the meantime, we may
want to remember where
the "off" button is. . .just
in case.
References
•
Dennis Hong: My seven species of robot | Video on TED.com
•
NASA trains humanoid robot for space station duty | TG Daily
•
Tech watch | Reuters.com
•
Ethical issues concerning robots and android humanoids technology. Links999.
•
Ethical Issues of Robots in Society Essay IEEE publication.
•
Robot Magazine - The latest hobby, science and consumer robotics, artificial intelligence
•
Robots Learn to Lie | LiveScience
•
Writing.Com: The Advancements of robotics.
•
http://www.schools.ash.org.au/mcpcompdept/ppts/Robotics.pdf
•
Microsoft PowerPoint - History of Robotics.ppt
•
http://www.site.uottawa.ca/~rabiel
?