AD8705

AI&ROBOTICS

Prepared By,
Akileshwari R
M.E.,B.ED.,
 Course Objectives:
Course Objectives

 To study the Robot Locomotion and types of robots.

 To explore the kinematic models and constraints
 To Learn sensors of robots and image processing for robotics.
 To understand the methods for mobile robot Localization
 To study the Path planning and Navigation of Robots.
 ROBOT LOCOMOTION

Unit-1 ROBOT LOCOMOTION

Introduction to AI and Robotics – robot locomotion –

legged mobile robots –wheeled mobile robots –
aerial mobile robots.
 Introduction to AI and Robotics

• Artificial intelligence is a branch of computer science that

seeks to develop technology to simulate the workings of the
human brain.
• Combined with the field of robotics, AI has been used to
develop and innovate intelligent machines that can be used for
everything from manufacturing to assisting healthcare
providers.
 Introduction to AI and Robotics

TOP COMPANIES USING AI ROBOT TECHNOLOGY

 Miso Robotics
 Hanson Robotics
 Starship Technologies
 Neurala
 iRobot
 Skydio
 Boston Dynamics
 Introduction to AI and Robotics

• Applying artificial intelligence to robotics is all about

furthering innovation.
• These intelligent machines include self-driving cars,
autonomous drones, humanoid robots and autonomous farming
equipment with applications for a variety of industries from
retail and healthcare to agriculture and defense.
• They make use of sensors, computer vision technology,
machine learning and other AI technologies to perform
functions like navigating warehouses and sorting recyclables.
Introduction to AI and Robotics

Robotics is the intersection of

science, engineering and
technology that produces
machines, called robots, that
replicate or substitute for
human actions.
 Introduction to AI and Robotics

• A robot is a programmable machine that can

complete a task, while the term robotics
describes the field of study focused on
developing robots and automation.
• Each robot has a different level of autonomy.
These levels range from human-controlled bots
that carry out tasks to fully-autonomous bots
that perform tasks without any external
influences.
Introduction to AI and Robotics
 Introduction to AI and Robotics

• Robots are physical agents that perform tasks by

manipulating the physical world.
• To do so, they are equipped with effectors such as
legs, wheels, joints, and grippers.
• Effectors are designed to assert physical forces on
the environment.
 Introduction to AI and Robotics

• When they do this, a few things may happen: the robot’s

state might change (e.g., a car spins its wheels and makes
progress on the road as a result)
• The state of the environment might change(e.g., a robot
arm uses its gripper to push a mug across the counter)
• The state of the people around the robot might change
(e.g., an exoskeleton moves and that changes the
configuration of a person’s leg; or a mobile robot makes
progress toward the elevator doors, and a person notices
and is nice enough to move out of the way, or even push
the button for the robot).
 Introduction to AI and Robotics

• Robots are also equipped with sensors, which

enable them to perceive their environment.
• Present-day robotics employs a diverse set of
sensors, including cameras, radars, lasers, and
microphones to measure the state of the
environment and of the people around it; and
gyroscopes, strain and torque sensors, and
accelerometers to measure the robot’s own state.
 Introduction to AI and Robotics

• Robots operate in environments that are partially

observable and stochastic: cameras cannot see
around corners, and gears can slip.
• Moreover, the people acting in that same
environment are unpredictable, so the robot needs to
make predictions about them.
• Robots usually model their environment with a
continuous state space (the robot’s position has
continuous coordinates) and a continuous action
space (the amount of current a robot sends to its
motor is also measured in continuous units).
 Introduction to AI and Robotics

• Some robots operate in high dimensional

spaces: cars need to know the position,
orientation, and velocity of themselves and
the nearby agents; robot arms have six or
seven joints that can each be independently
moved; and robots that mimic the human
body have hundreds of joints.
 Introduction to AI and Robotics

• Robotic learning is constrained because the real

world stubbornly refuses to operate faster than
real time.
• In a simulated environment, it is possible to use
learning algorithms, Ex: the Q-learning algorithm
described in (Chapter 23) to learn in a few hours
from millions of trials.
• In a real environment, it might take years to run
these trials, and the robot cannot risk (and thus
cannot learn from) a trial that might cause harm.
 Introduction to AI and Robotics

• Thus, transferring what has been learned in simulation

to a real robot in the real world—the sim-to-real
problem—is an active area of research.
• Practical robotic systems need to embody prior
knowledge about the robot, the physical environment,
and the tasks to be performed so that the robot can
learn quickly and perform safely.
• Robotics brings together many of the concepts we have
seen in this book, including probabilistic state
estimation, perception, planning, unsupervised learning,
reinforcement learning, and game theory.
Introduction to AI and Robotics
 Introduction to AI and Robotics

Interesti ng one!!
https://www.youtube.com/watch?v=ERXG_yndO3E
 Introduction to AI and Robotics

ARE YOU READY TO BULID A

BOT?