ce801: intelligent systems and roboticsorb.essex.ac.uk/ce/ce801/lecture notes/lecture 1.pdf · this...
TRANSCRIPT
Course Overview 2
Introduction to intelligent systems and robotics
Robot Sensors
Robot Actuators
Overview on Robot Control
Behaviour Based Robotics
Fuzzy Logic Control
Special thanks to Dr Martin Colley and Professor Gu where the Course material is based on the material he used and developed.
Learning Outcomes 4
This module gives an introduction to intelligent systems and robotics.
It goes on to consider the essential hardware for sensing and manipulating the real world, and their properties and characteristics.
The programming of intelligent systems and real-world robots are explored in the context of localisation and robot control and fuzzy logic systems.
Learning Outcomes 5
After completing this module, students will be expected to
be able to: Demonstrate an understanding of a range of intelligent systems and
robots
Explain the characteristics of a range of sensors and actuators
Explain the basic principles of robot localisation
Make use of the principles of robot control in controlling real-world devices
Have complete understanding of intelligent robot control using fuzzy logic systems
Perform programming of a robot
Grading 6
Assignment
1 Assignment: Worth 30% of your final mark: Out WK 4, In WK 11
Exam: 2 hours: Worth 70% of your final mark
Recommended Reading 7
BEKEY, G., Autonomous Robots, The MIT Press, 2005, ISBN-10: 0262025787, ISBN-13: 978-0262025782
MURPHY, R., Introduction to AI Robotics, The MIT Press, 2000, ISBN 0-262-13383-0
Robotics 8
Design, manufacture, control, and programming of robots
Use of robots to solve problems
Study of control processes, sensors, and algorithms used
in humans, animals, and machines
Application of control processes and algorithms to
designing robots
Intelligent Systems 9
Perform useful functions driven by desired goals and
current knowledge
Emulate biological and cognitive processes
Process information to achieve objectives
Learn by example or from experience
Adapt functions to a changing environment
Terminator II 10
Terminator: My CPU is a neural net processor, a learning computer. The more contact I have with humans, the more I learn.
Robotics History 11
A robot is a mechanical or virtual intelligent agent that can perform tasks automatically or with guidance
The word robot was introduced to the public by the Czech writer Karel Capek in his play R.U.R. (Rossum's Universal Robots), published in 1920. The play begins in a factory that makes artificial people called robots, though are creatures who can be mistaken for humans. They can plainly think for themselves, though they seem happy to serve.
The word robot comes from the word robota, meaning literally slave labour , and, figuratively, "labour" or "hard work" in modern Czech language.
Karel Čapek himself did not coin the word where the word was coined by his brother Josef Čapek,
The word robotics, used to describe this field of study, was coined by the science fiction writer Isaac Asimov. Asimov created the Three Laws of Robotics" which are a recurring theme in his books. These have since been used by many others to define laws used in fact and fiction. Introduced in his 1942 short story "Runaround" the Laws state the following:
A robot may not injure a human being or, through inaction, allow a human being to come to harm.
A robot must obey any orders given to it by human beings, except where such orders would conflict with the First Law.
A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.
Overview on Robotics History I 12
1921: The term robot was first used, in a play called RUR (Rossum’s Universal Robots) by the Czech writer Karel Capek.
1939: Elektro, humanoid in appearance, was shown in NY World’s Fair (the smoking robot).
1941: The word ‘robotics’ was first used by science fiction writer Isaac Asimov
1956: Formation of Unimation, the word’s first robot company. Built first Industrial robot, PUMA (Programmable Universal Machine
for Assembly) in 1961 for General Motors. 1970: Shakey the first mobile robot with the ability to reason and react
to its environment controlled by artificial intelligence was created by SRI International.
Overview of Robotics History II 13
1968: The first computer controlled walking machine created by Mcgee and Frank at the University of South Carolina.
1980: Quasi-dynamic walking was developed by Ichiro Kato, Waseda University,
1981: Arms in space “Canadarm” was first deployed aboard the Columbia to repair satellites, telescopes and shuttles by Jet Propulsions Laboratories (JPL)
1989: The Mobile Robots Group at MIT created Genghis, a walking robot. "Genghis gait
Overview of Robotics History III 14
1996: RoboTuna was created by David Barrett at MIT. The robot is used to study how fish swim
1996: Honda created P2, the first major step in creating their ASIMO. P2 was the first self-regulating, bipedal humanoid robot.
1997: NASA's PathFinder “Sojourner” landed on Mars. It is a robotic rover that sends images and data about Mars back to Earth,
1998: Dr. Cynthia created Kismet, a robotic creature that socially interacts with people.
Overview of Robotics History IV 15
1998: LEGO released their MINDSTORMS product
1998: Sony released the first Aibo dog.
2000: Honda released the ASIMO.
2007: Nao Robot
Early Robotics Control Paradigms: Sense-think-act paradigm
16
Developed in SRI in 1967
Sense-think-act paradigm Sense the world using vision, sonar range finder
Plan a sequence of actions that achieves specified goal (STRIPS)
Execute plan
Tasks: navigation around blocks and
Implemented in the Robot Shakey to go over bridges, rearranging blocks by pushing them
Behaviour Based Robotics 17
Robots should not plan their actions using a planner like STRIPS
Instead, intelligent behaviour should “emerge” from a set of robust behaviors
Behaviours are local-domain experts
No explicit models of the environment
Do something simple, but do it effectively
Space Robots 21
Mars Exploration Rover - A (Spirit) and Mars Exploration Rover – B (Opportunity)
Both had successful missions on Mars in starting in late 2004 (and are still both operational)
9 cameras
Remote human planning combing with local autonomy
Increased autonomy as mission has progressed
Robocup Challenge 22
The Robocup sets a target that by year 2050, a team of fully autonomous humanoid robot soccer players shall win the soccer game, comply with the official rule of the FIFA, against the winner of the most recent World Cup.”
Different leagues: Soccer Leagues
Small Size League Medium Size League Simulation League Standard League Humonid League
Robocup at Home Rescue League Logistics League
DARPA Grand Challenge 23
2005 Winner “Stanley” (Stanford University)
Completed 175miles desert course autonomously in 6 hours 54 minutes
Guided along rough “corridor” by GPS
Road-following and obstacle avoidance using laser range-finder and vision.
DARPA Grand Challenge II 24
2007 winner “BOSS” (Carnegie Mellon University)
Robots had to achieve extended missions in a mocked-up urban area, obeying California traffic laws and avoiding other vehicles
Much more sophisticated sensor suites than in desert challenge (lasers, cameras, radars) to achieve all-around awareness
Applications 25
Exploration (planetary, undersea, polar) Search and rescue (earthquake rescue, demining) Mining and heavy transport Military (unmanned aircraft, unmanned underwater
vehicles) Medical (helping the elderly, hospital delivery, surgical robots) Transport (autonomous cars) Domestic (Vacuum cleaning, Lawn mowing, …) Agricultural Museum Guide Entertainment