06-04-2010, 11:29 PM
[attachment=3075]
[attachment=3076]
Fundamental Idea: Robot Pose
2D world (floor plan)
3 DOF
Major Issues with Autonomy
Movement
Inaccuracy
How do we Solve Localization? Represent beliefs as a probability density
Markov assumption
Pose distribution at time t conditioned on:
pose dist. at time t-1
movement at time t-1
sensor readings at time t
Discretize the density by
sampling
Localization Foundation
At every time step t:
UPDATE each sampleâ„¢s new location based on movement
RESAMPLE the pose distribution based on sensor readings
Algorithms
Markov localization (simplest)
Kalman filters (historically most popular)
Monte Carlo localization / particle filters
Same: Sampled probability distribution
Basic update-resample loop
Different: Sampling techniques
Movement assumptions
Localizationâ„¢s Sidekick: Globalization
Credit to Dieter Fox for this demo
Problem Two: Mapping
Problem Two: Mapping
Given:
Simultaneous LocalizationAnd Mapping (SLAM)
Circular Error Problem
How do we Solve SLAM?
Credit to Sebastian Thrun for this demo
For the Interested
Robotics
Where AI meets the real world.
What is a Robot ?
A re-programmable, multifunctional manipulator designed to movematerial, parts, tools, or specialized devices
through various programmedmotions for the performance of a variety of tasks.
A robot must have the following essential characteristics:
Mobility: It possesses some form of mobility.
Programmability: implying computational or symbol- manipulative capabilities that a designer can combine as
desired (a robot is a computer). It can be programmed to accomplish a large variety of tasks. After being
programmed, it operates automatically.
Sensors: on or around the device that are able to sense the environment and give useful feedback to the device
Mechanical capability: enabling it to act on its environment rather than merely function as a data processing or
computational device (a robot is a machine); and
Flexibility: it can operate using a range of programs and manipulates and transport materials in a variety of
ways.
Isaac Asimov's Three Laws of Robotics
Law Zero A robot may not injure humanity, or, through inaction, allow humanity to come to harm.
First Law A robot may not injure a human being, or, through inaction, allow a human being to come to harm.
Second Law A robot must obey orders given it by human beings, except where such orders would conflict with the
First Law.
Third Law A robot must protect its own existence as long as such protection does not conflict with the First or
Second Law.
Construction & Working of the Robot
Mechanical platforms- the hardware base SensorsMotorsDriving mechanismsPower suppliesElectronic
ControlsMicrocontroller systemsLanguagesR/C ServosPneumaticsDriving High-Current Loads from LogicControllers
Sensors
Sensors are the parts that act like senses and can detect objects or things like heat and light and
convert the object information into symbols or in analog or digital form so that computers understand. And then
Robots react according to information provided by the sensory system
Vision Sensor
Camera
Frame grabber
Image processing unit
Motors
Driving mechanisms
Power supplies
Driving High-Current Loads from Logic
Microcontroller systems
Speed
Size
Memory
A robot system architecture
Artificial Intelligence
What is artificial intelligence?It is the science and engineering of making intelligent machines, especially
intelligent computer programs
Can a machine think?
Appling Robots
Future
Artificial neural networks
Robots which train themselves
Summary
Advantages
Disadvantages
Where gone Asimovâ„¢s law?
Acknowledgement
Thanks to all of my respected teachers for allowing me to represent an article on Robotics. I thank to
the Internet Faculty of our college for providing access to Internet for searching data. Thanks to my parents
for providing me a ËœPersonal Computerâ„¢.